| 4 23 5 15 3 82 5 67 14 19 19 14 19 13 11 13 13 13 3 10 12 1 13 13 2 4 6 12 12 13 1 6 6 6 1 4 4 1 2 4 1 3 2 1 6 1 5 6 12 40 39 3 12 4 7 2 1 9 5 7 13 2 15 4 6 8 4 7 13 42 42 4 15 28 1 17 29 2 26 27 12 17 27 2 12 3 45 26 26 11 11 11 11 14 14 14 14 14 13 13 12 1 11 13 2 5 4 4 6 6 1 5 5 5 5 1 1 1 1 2 2 2 2 10 10 1 1 4 2 7 6 6 6 1 1 1 6 6 1 1 8 6 10 6 10 10 10 15 1 1 12 4 4 4 4 1 23 11 4 8 11 24 24 5 1 1 1 1 3 6 12 2 2 9 1 3 10 6 19 19 24 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/userfaultfd.c * * Copyright (C) 2015 Red Hat, Inc. */ #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/userfaultfd_k.h> #include <linux/mmu_notifier.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include "internal.h" static __always_inline bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end) { /* Make sure that the dst range is fully within dst_vma. */ if (dst_end > dst_vma->vm_end) return false; /* * Check the vma is registered in uffd, this is required to * enforce the VM_MAYWRITE check done at uffd registration * time. */ if (!dst_vma->vm_userfaultfd_ctx.ctx) return false; return true; } static __always_inline struct vm_area_struct *find_vma_and_prepare_anon(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; mmap_assert_locked(mm); vma = vma_lookup(mm, addr); if (!vma) vma = ERR_PTR(-ENOENT); else if (!(vma->vm_flags & VM_SHARED) && unlikely(anon_vma_prepare(vma))) vma = ERR_PTR(-ENOMEM); return vma; } #ifdef CONFIG_PER_VMA_LOCK /* * uffd_lock_vma() - Lookup and lock vma corresponding to @address. * @mm: mm to search vma in. * @address: address that the vma should contain. * * Should be called without holding mmap_lock. * * Return: A locked vma containing @address, -ENOENT if no vma is found, or * -ENOMEM if anon_vma couldn't be allocated. */ static struct vm_area_struct *uffd_lock_vma(struct mm_struct *mm, unsigned long address) { struct vm_area_struct *vma; vma = lock_vma_under_rcu(mm, address); if (vma) { /* * We know we're going to need to use anon_vma, so check * that early. */ if (!(vma->vm_flags & VM_SHARED) && unlikely(!vma->anon_vma)) vma_end_read(vma); else return vma; } mmap_read_lock(mm); vma = find_vma_and_prepare_anon(mm, address); if (!IS_ERR(vma)) { /* * We cannot use vma_start_read() as it may fail due to * false locked (see comment in vma_start_read()). We * can avoid that by directly locking vm_lock under * mmap_lock, which guarantees that nobody can lock the * vma for write (vma_start_write()) under us. */ down_read(&vma->vm_lock->lock); } mmap_read_unlock(mm); return vma; } static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len) { struct vm_area_struct *dst_vma; dst_vma = uffd_lock_vma(dst_mm, dst_start); if (IS_ERR(dst_vma) || validate_dst_vma(dst_vma, dst_start + len)) return dst_vma; vma_end_read(dst_vma); return ERR_PTR(-ENOENT); } static void uffd_mfill_unlock(struct vm_area_struct *vma) { vma_end_read(vma); } #else static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len) { struct vm_area_struct *dst_vma; mmap_read_lock(dst_mm); dst_vma = find_vma_and_prepare_anon(dst_mm, dst_start); if (IS_ERR(dst_vma)) goto out_unlock; if (validate_dst_vma(dst_vma, dst_start + len)) return dst_vma; dst_vma = ERR_PTR(-ENOENT); out_unlock: mmap_read_unlock(dst_mm); return dst_vma; } static void uffd_mfill_unlock(struct vm_area_struct *vma) { mmap_read_unlock(vma->vm_mm); } #endif /* Check if dst_addr is outside of file's size. Must be called with ptl held. */ static bool mfill_file_over_size(struct vm_area_struct *dst_vma, unsigned long dst_addr) { struct inode *inode; pgoff_t offset, max_off; if (!dst_vma->vm_file) return false; inode = dst_vma->vm_file->f_inode; offset = linear_page_index(dst_vma, dst_addr); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); return offset >= max_off; } /* * Install PTEs, to map dst_addr (within dst_vma) to page. * * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem * and anon, and for both shared and private VMAs. */ int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, uffd_flags_t flags) { int ret; struct mm_struct *dst_mm = dst_vma->vm_mm; pte_t _dst_pte, *dst_pte; bool writable = dst_vma->vm_flags & VM_WRITE; bool vm_shared = dst_vma->vm_flags & VM_SHARED; spinlock_t *ptl; struct folio *folio = page_folio(page); bool page_in_cache = folio_mapping(folio); _dst_pte = mk_pte(page, dst_vma->vm_page_prot); _dst_pte = pte_mkdirty(_dst_pte); if (page_in_cache && !vm_shared) writable = false; if (writable) _dst_pte = pte_mkwrite(_dst_pte, dst_vma); if (flags & MFILL_ATOMIC_WP) _dst_pte = pte_mkuffd_wp(_dst_pte); ret = -EAGAIN; dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); if (!dst_pte) goto out; if (mfill_file_over_size(dst_vma, dst_addr)) { ret = -EFAULT; goto out_unlock; } ret = -EEXIST; /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ if (!pte_none_mostly(ptep_get(dst_pte))) goto out_unlock; if (page_in_cache) { /* Usually, cache pages are already added to LRU */ if (newly_allocated) folio_add_lru(folio); folio_add_file_rmap_pte(folio, page, dst_vma); } else { folio_add_new_anon_rmap(folio, dst_vma, dst_addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, dst_vma); } /* * Must happen after rmap, as mm_counter() checks mapping (via * PageAnon()), which is set by __page_set_anon_rmap(). */ inc_mm_counter(dst_mm, mm_counter(folio)); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); ret = 0; out_unlock: pte_unmap_unlock(dst_pte, ptl); out: return ret; } static int mfill_atomic_pte_copy(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) { void *kaddr; int ret; struct folio *folio; if (!*foliop) { ret = -ENOMEM; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, dst_vma, dst_addr, false); if (!folio) goto out; kaddr = kmap_local_folio(folio, 0); /* * The read mmap_lock is held here. Despite the * mmap_lock being read recursive a deadlock is still * possible if a writer has taken a lock. For example: * * process A thread 1 takes read lock on own mmap_lock * process A thread 2 calls mmap, blocks taking write lock * process B thread 1 takes page fault, read lock on own mmap lock * process B thread 2 calls mmap, blocks taking write lock * process A thread 1 blocks taking read lock on process B * process B thread 1 blocks taking read lock on process A * * Disable page faults to prevent potential deadlock * and retry the copy outside the mmap_lock. */ pagefault_disable(); ret = copy_from_user(kaddr, (const void __user *) src_addr, PAGE_SIZE); pagefault_enable(); kunmap_local(kaddr); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; *foliop = folio; /* don't free the page */ goto out; } flush_dcache_folio(folio); } else { folio = *foliop; *foliop = NULL; } /* * The memory barrier inside __folio_mark_uptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __folio_mark_uptodate(folio); ret = -ENOMEM; if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL)) goto out_release; ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, &folio->page, true, flags); if (ret) goto out_release; out: return ret; out_release: folio_put(folio); goto out; } static int mfill_atomic_pte_zeroed_folio(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) { struct folio *folio; int ret = -ENOMEM; folio = vma_alloc_zeroed_movable_folio(dst_vma, dst_addr); if (!folio) return ret; if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL)) goto out_put; /* * The memory barrier inside __folio_mark_uptodate makes sure that * zeroing out the folio become visible before mapping the page * using set_pte_at(). See do_anonymous_page(). */ __folio_mark_uptodate(folio); ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, &folio->page, true, 0); if (ret) goto out_put; return 0; out_put: folio_put(folio); return ret; } static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) { pte_t _dst_pte, *dst_pte; spinlock_t *ptl; int ret; if (mm_forbids_zeropage(dst_vma->vm_mm)) return mfill_atomic_pte_zeroed_folio(dst_pmd, dst_vma, dst_addr); _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); ret = -EAGAIN; dst_pte = pte_offset_map_lock(dst_vma->vm_mm, dst_pmd, dst_addr, &ptl); if (!dst_pte) goto out; if (mfill_file_over_size(dst_vma, dst_addr)) { ret = -EFAULT; goto out_unlock; } ret = -EEXIST; if (!pte_none(ptep_get(dst_pte))) goto out_unlock; set_pte_at(dst_vma->vm_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); ret = 0; out_unlock: pte_unmap_unlock(dst_pte, ptl); out: return ret; } /* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ static int mfill_atomic_pte_continue(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, uffd_flags_t flags) { struct inode *inode = file_inode(dst_vma->vm_file); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); struct folio *folio; struct page *page; int ret; ret = shmem_get_folio(inode, pgoff, &folio, SGP_NOALLOC); /* Our caller expects us to return -EFAULT if we failed to find folio */ if (ret == -ENOENT) ret = -EFAULT; if (ret) goto out; if (!folio) { ret = -EFAULT; goto out; } page = folio_file_page(folio, pgoff); if (PageHWPoison(page)) { ret = -EIO; goto out_release; } ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, page, false, flags); if (ret) goto out_release; folio_unlock(folio); ret = 0; out: return ret; out_release: folio_unlock(folio); folio_put(folio); goto out; } /* Handles UFFDIO_POISON for all non-hugetlb VMAs. */ static int mfill_atomic_pte_poison(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, uffd_flags_t flags) { int ret; struct mm_struct *dst_mm = dst_vma->vm_mm; pte_t _dst_pte, *dst_pte; spinlock_t *ptl; _dst_pte = make_pte_marker(PTE_MARKER_POISONED); ret = -EAGAIN; dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); if (!dst_pte) goto out; if (mfill_file_over_size(dst_vma, dst_addr)) { ret = -EFAULT; goto out_unlock; } ret = -EEXIST; /* Refuse to overwrite any PTE, even a PTE marker (e.g. UFFD WP). */ if (!pte_none(ptep_get(dst_pte))) goto out_unlock; set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); ret = 0; out_unlock: pte_unmap_unlock(dst_pte, ptl); out: return ret; } static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, address); if (!pud) return NULL; /* * Note that we didn't run this because the pmd was * missing, the *pmd may be already established and in * turn it may also be a trans_huge_pmd. */ return pmd_alloc(mm, pud, address); } #ifdef CONFIG_HUGETLB_PAGE /* * mfill_atomic processing for HUGETLB vmas. Note that this routine is * called with either vma-lock or mmap_lock held, it will release the lock * before returning. */ static __always_inline ssize_t mfill_atomic_hugetlb( struct userfaultfd_ctx *ctx, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; ssize_t err; pte_t *dst_pte; unsigned long src_addr, dst_addr; long copied; struct folio *folio; unsigned long vma_hpagesize; pgoff_t idx; u32 hash; struct address_space *mapping; /* * There is no default zero huge page for all huge page sizes as * supported by hugetlb. A PMD_SIZE huge pages may exist as used * by THP. Since we can not reliably insert a zero page, this * feature is not supported. */ if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) { up_read(&ctx->map_changing_lock); uffd_mfill_unlock(dst_vma); return -EINVAL; } src_addr = src_start; dst_addr = dst_start; copied = 0; folio = NULL; vma_hpagesize = vma_kernel_pagesize(dst_vma); /* * Validate alignment based on huge page size */ err = -EINVAL; if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1)) goto out_unlock; retry: /* * On routine entry dst_vma is set. If we had to drop mmap_lock and * retry, dst_vma will be set to NULL and we must lookup again. */ if (!dst_vma) { dst_vma = uffd_mfill_lock(dst_mm, dst_start, len); if (IS_ERR(dst_vma)) { err = PTR_ERR(dst_vma); goto out; } err = -ENOENT; if (!is_vm_hugetlb_page(dst_vma)) goto out_unlock_vma; err = -EINVAL; if (vma_hpagesize != vma_kernel_pagesize(dst_vma)) goto out_unlock_vma; /* * If memory mappings are changing because of non-cooperative * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ down_read(&ctx->map_changing_lock); err = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out_unlock; } while (src_addr < src_start + len) { BUG_ON(dst_addr >= dst_start + len); /* * Serialize via vma_lock and hugetlb_fault_mutex. * vma_lock ensures the dst_pte remains valid even * in the case of shared pmds. fault mutex prevents * races with other faulting threads. */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(dst_vma); err = -ENOMEM; dst_pte = huge_pte_alloc(dst_mm, dst_vma, dst_addr, vma_hpagesize); if (!dst_pte) { hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; } if (!uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE) && !huge_pte_none_mostly(huge_ptep_get(dst_mm, dst_addr, dst_pte))) { err = -EEXIST; hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; } err = hugetlb_mfill_atomic_pte(dst_pte, dst_vma, dst_addr, src_addr, flags, &folio); hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); cond_resched(); if (unlikely(err == -ENOENT)) { up_read(&ctx->map_changing_lock); uffd_mfill_unlock(dst_vma); BUG_ON(!folio); err = copy_folio_from_user(folio, (const void __user *)src_addr, true); if (unlikely(err)) { err = -EFAULT; goto out; } dst_vma = NULL; goto retry; } else BUG_ON(folio); if (!err) { dst_addr += vma_hpagesize; src_addr += vma_hpagesize; copied += vma_hpagesize; if (fatal_signal_pending(current)) err = -EINTR; } if (err) break; } out_unlock: up_read(&ctx->map_changing_lock); out_unlock_vma: uffd_mfill_unlock(dst_vma); out: if (folio) folio_put(folio); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); return copied ? copied : err; } #else /* !CONFIG_HUGETLB_PAGE */ /* fail at build time if gcc attempts to use this */ extern ssize_t mfill_atomic_hugetlb(struct userfaultfd_ctx *ctx, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ static __always_inline ssize_t 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) { ssize_t err; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE)) { return mfill_atomic_pte_continue(dst_pmd, dst_vma, dst_addr, flags); } else if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { return mfill_atomic_pte_poison(dst_pmd, dst_vma, dst_addr, flags); } /* * The normal page fault path for a shmem will invoke the * fault, fill the hole in the file and COW it right away. The * result generates plain anonymous memory. So when we are * asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll * generate anonymous memory directly without actually filling * the hole. For the MAP_PRIVATE case the robustness check * only happens in the pagetable (to verify it's still none) * and not in the radix tree. */ if (!(dst_vma->vm_flags & VM_SHARED)) { if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) err = mfill_atomic_pte_copy(dst_pmd, dst_vma, dst_addr, src_addr, flags, foliop); else err = mfill_atomic_pte_zeropage(dst_pmd, dst_vma, dst_addr); } else { err = shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, src_addr, flags, foliop); } return err; } static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, uffd_flags_t flags) { struct mm_struct *dst_mm = ctx->mm; struct vm_area_struct *dst_vma; ssize_t err; pmd_t *dst_pmd; unsigned long src_addr, dst_addr; long copied; struct folio *folio; /* * Sanitize the command parameters: */ BUG_ON(dst_start & ~PAGE_MASK); BUG_ON(len & ~PAGE_MASK); /* Does the address range wrap, or is the span zero-sized? */ BUG_ON(src_start + len <= src_start); BUG_ON(dst_start + len <= dst_start); src_addr = src_start; dst_addr = dst_start; copied = 0; folio = NULL; retry: /* * Make sure the vma is not shared, that the dst range is * both valid and fully within a single existing vma. */ dst_vma = uffd_mfill_lock(dst_mm, dst_start, len); if (IS_ERR(dst_vma)) { err = PTR_ERR(dst_vma); goto out; } /* * If memory mappings are changing because of non-cooperative * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ down_read(&ctx->map_changing_lock); err = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out_unlock; err = -EINVAL; /* * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but * it will overwrite vm_ops, so vma_is_anonymous must return false. */ if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) && dst_vma->vm_flags & VM_SHARED)) goto out_unlock; /* * validate 'mode' now that we know the dst_vma: don't allow * a wrprotect copy if the userfaultfd didn't register as WP. */ if ((flags & MFILL_ATOMIC_WP) && !(dst_vma->vm_flags & VM_UFFD_WP)) goto out_unlock; /* * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) return mfill_atomic_hugetlb(ctx, dst_vma, dst_start, src_start, len, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; if (!vma_is_shmem(dst_vma) && uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE)) goto out_unlock; while (src_addr < src_start + len) { pmd_t dst_pmdval; BUG_ON(dst_addr >= dst_start + len); dst_pmd = mm_alloc_pmd(dst_mm, dst_addr); if (unlikely(!dst_pmd)) { err = -ENOMEM; break; } dst_pmdval = pmdp_get_lockless(dst_pmd); /* * If the dst_pmd is mapped as THP don't * override it and just be strict. */ if (unlikely(pmd_trans_huge(dst_pmdval))) { err = -EEXIST; break; } if (unlikely(pmd_none(dst_pmdval)) && unlikely(__pte_alloc(dst_mm, dst_pmd))) { err = -ENOMEM; break; } /* If an huge pmd materialized from under us fail */ if (unlikely(pmd_trans_huge(*dst_pmd))) { err = -EFAULT; break; } BUG_ON(pmd_none(*dst_pmd)); BUG_ON(pmd_trans_huge(*dst_pmd)); err = mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, src_addr, flags, &folio); cond_resched(); if (unlikely(err == -ENOENT)) { void *kaddr; up_read(&ctx->map_changing_lock); uffd_mfill_unlock(dst_vma); BUG_ON(!folio); kaddr = kmap_local_folio(folio, 0); err = copy_from_user(kaddr, (const void __user *) src_addr, PAGE_SIZE); kunmap_local(kaddr); if (unlikely(err)) { err = -EFAULT; goto out; } flush_dcache_folio(folio); goto retry; } else BUG_ON(folio); if (!err) { dst_addr += PAGE_SIZE; src_addr += PAGE_SIZE; copied += PAGE_SIZE; if (fatal_signal_pending(current)) err = -EINTR; } if (err) break; } out_unlock: up_read(&ctx->map_changing_lock); uffd_mfill_unlock(dst_vma); out: if (folio) folio_put(folio); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); return copied ? copied : err; } ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, uffd_flags_t flags) { return mfill_atomic(ctx, dst_start, src_start, len, uffd_flags_set_mode(flags, MFILL_ATOMIC_COPY)); } ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len) { return mfill_atomic(ctx, start, 0, len, uffd_flags_set_mode(0, MFILL_ATOMIC_ZEROPAGE)); } ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len, uffd_flags_t flags) { /* * A caller might reasonably assume that UFFDIO_CONTINUE contains an * smp_wmb() to ensure that any writes to the about-to-be-mapped page by * the thread doing the UFFDIO_CONTINUE are guaranteed to be visible to * subsequent loads from the page through the newly mapped address range. */ smp_wmb(); return mfill_atomic(ctx, start, 0, len, uffd_flags_set_mode(flags, MFILL_ATOMIC_CONTINUE)); } ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len, uffd_flags_t flags) { return mfill_atomic(ctx, start, 0, len, uffd_flags_set_mode(flags, MFILL_ATOMIC_POISON)); } long uffd_wp_range(struct vm_area_struct *dst_vma, unsigned long start, unsigned long len, bool enable_wp) { unsigned int mm_cp_flags; struct mmu_gather tlb; long ret; VM_WARN_ONCE(start < dst_vma->vm_start || start + len > dst_vma->vm_end, "The address range exceeds VMA boundary.\n"); if (enable_wp) mm_cp_flags = MM_CP_UFFD_WP; else mm_cp_flags = MM_CP_UFFD_WP_RESOLVE; /* * vma->vm_page_prot already reflects that uffd-wp is enabled for this * VMA (see userfaultfd_set_vm_flags()) and that all PTEs are supposed * to be write-protected as default whenever protection changes. * Try upgrading write permissions manually. */ if (!enable_wp && vma_wants_manual_pte_write_upgrade(dst_vma)) mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE; tlb_gather_mmu(&tlb, dst_vma->vm_mm); ret = change_protection(&tlb, dst_vma, start, start + len, mm_cp_flags); tlb_finish_mmu(&tlb); return ret; } int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len, bool enable_wp) { struct mm_struct *dst_mm = ctx->mm; unsigned long end = start + len; unsigned long _start, _end; struct vm_area_struct *dst_vma; unsigned long page_mask; long err; VMA_ITERATOR(vmi, dst_mm, start); /* * Sanitize the command parameters: */ BUG_ON(start & ~PAGE_MASK); BUG_ON(len & ~PAGE_MASK); /* Does the address range wrap, or is the span zero-sized? */ BUG_ON(start + len <= start); mmap_read_lock(dst_mm); /* * If memory mappings are changing because of non-cooperative * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ down_read(&ctx->map_changing_lock); err = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out_unlock; err = -ENOENT; for_each_vma_range(vmi, dst_vma, end) { if (!userfaultfd_wp(dst_vma)) { err = -ENOENT; break; } if (is_vm_hugetlb_page(dst_vma)) { err = -EINVAL; page_mask = vma_kernel_pagesize(dst_vma) - 1; if ((start & page_mask) || (len & page_mask)) break; } _start = max(dst_vma->vm_start, start); _end = min(dst_vma->vm_end, end); err = uffd_wp_range(dst_vma, _start, _end - _start, enable_wp); /* Return 0 on success, <0 on failures */ if (err < 0) break; err = 0; } out_unlock: up_read(&ctx->map_changing_lock); mmap_read_unlock(dst_mm); return err; } void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2) __acquires(ptl1) __acquires(ptl2) { if (ptl1 > ptl2) swap(ptl1, ptl2); /* lock in virtual address order to avoid lock inversion */ spin_lock(ptl1); if (ptl1 != ptl2) spin_lock_nested(ptl2, SINGLE_DEPTH_NESTING); else __acquire(ptl2); } void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2) __releases(ptl1) __releases(ptl2) { spin_unlock(ptl1); if (ptl1 != ptl2) spin_unlock(ptl2); else __release(ptl2); } static int move_present_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, pte_t orig_dst_pte, pte_t orig_src_pte, spinlock_t *dst_ptl, spinlock_t *src_ptl, struct folio *src_folio) { int err = 0; double_pt_lock(dst_ptl, src_ptl); if (!pte_same(ptep_get(src_pte), orig_src_pte) || !pte_same(ptep_get(dst_pte), orig_dst_pte)) { err = -EAGAIN; goto out; } if (folio_test_large(src_folio) || folio_maybe_dma_pinned(src_folio) || !PageAnonExclusive(&src_folio->page)) { err = -EBUSY; goto out; } orig_src_pte = ptep_clear_flush(src_vma, src_addr, src_pte); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { set_pte_at(mm, src_addr, src_pte, orig_src_pte); err = -EBUSY; goto out; } folio_move_anon_rmap(src_folio, dst_vma); src_folio->index = linear_page_index(dst_vma, dst_addr); orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma); set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte); out: double_pt_unlock(dst_ptl, src_ptl); return err; } static int move_swap_pte(struct mm_struct *mm, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, pte_t orig_dst_pte, pte_t orig_src_pte, spinlock_t *dst_ptl, spinlock_t *src_ptl) { if (!pte_swp_exclusive(orig_src_pte)) return -EBUSY; double_pt_lock(dst_ptl, src_ptl); if (!pte_same(ptep_get(src_pte), orig_src_pte) || !pte_same(ptep_get(dst_pte), orig_dst_pte)) { double_pt_unlock(dst_ptl, src_ptl); return -EAGAIN; } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); double_pt_unlock(dst_ptl, src_ptl); return 0; } static int move_zeropage_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr, pte_t *dst_pte, pte_t *src_pte, pte_t orig_dst_pte, pte_t orig_src_pte, spinlock_t *dst_ptl, spinlock_t *src_ptl) { pte_t zero_pte; double_pt_lock(dst_ptl, src_ptl); if (!pte_same(ptep_get(src_pte), orig_src_pte) || !pte_same(ptep_get(dst_pte), orig_dst_pte)) { double_pt_unlock(dst_ptl, src_ptl); return -EAGAIN; } zero_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); ptep_clear_flush(src_vma, src_addr, src_pte); set_pte_at(mm, dst_addr, dst_pte, zero_pte); double_pt_unlock(dst_ptl, src_ptl); return 0; } /* * The mmap_lock for reading is held by the caller. Just move the page * from src_pmd to dst_pmd if possible, and return true if succeeded * in moving the page. */ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr, __u64 mode) { swp_entry_t entry; pte_t orig_src_pte, orig_dst_pte; pte_t src_folio_pte; spinlock_t *src_ptl, *dst_ptl; pte_t *src_pte = NULL; pte_t *dst_pte = NULL; struct folio *src_folio = NULL; struct anon_vma *src_anon_vma = NULL; struct mmu_notifier_range range; int err = 0; flush_cache_range(src_vma, src_addr, src_addr + PAGE_SIZE); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr, src_addr + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); retry: dst_pte = pte_offset_map_nolock(mm, dst_pmd, dst_addr, &dst_ptl); /* Retry if a huge pmd materialized from under us */ if (unlikely(!dst_pte)) { err = -EAGAIN; goto out; } src_pte = pte_offset_map_nolock(mm, src_pmd, src_addr, &src_ptl); /* * We held the mmap_lock for reading so MADV_DONTNEED * can zap transparent huge pages under us, or the * transparent huge page fault can establish new * transparent huge pages under us. */ if (unlikely(!src_pte)) { err = -EAGAIN; goto out; } /* Sanity checks before the operation */ if (WARN_ON_ONCE(pmd_none(*dst_pmd)) || WARN_ON_ONCE(pmd_none(*src_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*dst_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*src_pmd))) { err = -EINVAL; goto out; } spin_lock(dst_ptl); orig_dst_pte = ptep_get(dst_pte); spin_unlock(dst_ptl); if (!pte_none(orig_dst_pte)) { err = -EEXIST; goto out; } spin_lock(src_ptl); orig_src_pte = ptep_get(src_pte); spin_unlock(src_ptl); if (pte_none(orig_src_pte)) { if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) err = -ENOENT; else /* nothing to do to move a hole */ err = 0; goto out; } /* If PTE changed after we locked the folio them start over */ if (src_folio && unlikely(!pte_same(src_folio_pte, orig_src_pte))) { err = -EAGAIN; goto out; } if (pte_present(orig_src_pte)) { if (is_zero_pfn(pte_pfn(orig_src_pte))) { err = move_zeropage_pte(mm, dst_vma, src_vma, dst_addr, src_addr, dst_pte, src_pte, orig_dst_pte, orig_src_pte, dst_ptl, src_ptl); goto out; } /* * Pin and lock both source folio and anon_vma. Since we are in * RCU read section, we can't block, so on contention have to * unmap the ptes, obtain the lock and retry. */ if (!src_folio) { struct folio *folio; /* * Pin the page while holding the lock to be sure the * page isn't freed under us */ spin_lock(src_ptl); if (!pte_same(orig_src_pte, ptep_get(src_pte))) { spin_unlock(src_ptl); err = -EAGAIN; goto out; } folio = vm_normal_folio(src_vma, src_addr, orig_src_pte); if (!folio || !PageAnonExclusive(&folio->page)) { spin_unlock(src_ptl); err = -EBUSY; goto out; } folio_get(folio); src_folio = folio; src_folio_pte = orig_src_pte; spin_unlock(src_ptl); if (!folio_trylock(src_folio)) { pte_unmap(&orig_src_pte); pte_unmap(&orig_dst_pte); src_pte = dst_pte = NULL; /* now we can block and wait */ folio_lock(src_folio); goto retry; } if (WARN_ON_ONCE(!folio_test_anon(src_folio))) { err = -EBUSY; goto out; } } /* at this point we have src_folio locked */ if (folio_test_large(src_folio)) { /* split_folio() can block */ pte_unmap(&orig_src_pte); pte_unmap(&orig_dst_pte); src_pte = dst_pte = NULL; err = split_folio(src_folio); if (err) goto out; /* have to reacquire the folio after it got split */ folio_unlock(src_folio); folio_put(src_folio); src_folio = NULL; goto retry; } if (!src_anon_vma) { /* * folio_referenced walks the anon_vma chain * without the folio lock. Serialize against it with * the anon_vma lock, the folio lock is not enough. */ src_anon_vma = folio_get_anon_vma(src_folio); if (!src_anon_vma) { /* page was unmapped from under us */ err = -EAGAIN; goto out; } if (!anon_vma_trylock_write(src_anon_vma)) { pte_unmap(&orig_src_pte); pte_unmap(&orig_dst_pte); src_pte = dst_pte = NULL; /* now we can block and wait */ anon_vma_lock_write(src_anon_vma); goto retry; } } err = move_present_pte(mm, dst_vma, src_vma, dst_addr, src_addr, dst_pte, src_pte, orig_dst_pte, orig_src_pte, dst_ptl, src_ptl, src_folio); } else { entry = pte_to_swp_entry(orig_src_pte); if (non_swap_entry(entry)) { if (is_migration_entry(entry)) { pte_unmap(&orig_src_pte); pte_unmap(&orig_dst_pte); src_pte = dst_pte = NULL; migration_entry_wait(mm, src_pmd, src_addr); err = -EAGAIN; } else err = -EFAULT; goto out; } err = move_swap_pte(mm, dst_addr, src_addr, dst_pte, src_pte, orig_dst_pte, orig_src_pte, dst_ptl, src_ptl); } out: if (src_anon_vma) { anon_vma_unlock_write(src_anon_vma); put_anon_vma(src_anon_vma); } if (src_folio) { folio_unlock(src_folio); folio_put(src_folio); } if (dst_pte) pte_unmap(dst_pte); if (src_pte) pte_unmap(src_pte); mmu_notifier_invalidate_range_end(&range); return err; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline bool move_splits_huge_pmd(unsigned long dst_addr, unsigned long src_addr, unsigned long src_end) { return (src_addr & ~HPAGE_PMD_MASK) || (dst_addr & ~HPAGE_PMD_MASK) || src_end - src_addr < HPAGE_PMD_SIZE; } #else static inline bool move_splits_huge_pmd(unsigned long dst_addr, unsigned long src_addr, unsigned long src_end) { /* This is unreachable anyway, just to avoid warnings when HPAGE_PMD_SIZE==0 */ return false; } #endif static inline bool vma_move_compatible(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_PFNMAP | VM_IO | VM_HUGETLB | VM_MIXEDMAP | VM_SHADOW_STACK)); } static int validate_move_areas(struct userfaultfd_ctx *ctx, struct vm_area_struct *src_vma, struct vm_area_struct *dst_vma) { /* Only allow moving if both have the same access and protection */ if ((src_vma->vm_flags & VM_ACCESS_FLAGS) != (dst_vma->vm_flags & VM_ACCESS_FLAGS) || pgprot_val(src_vma->vm_page_prot) != pgprot_val(dst_vma->vm_page_prot)) return -EINVAL; /* Only allow moving if both are mlocked or both aren't */ if ((src_vma->vm_flags & VM_LOCKED) != (dst_vma->vm_flags & VM_LOCKED)) return -EINVAL; /* * For now, we keep it simple and only move between writable VMAs. * Access flags are equal, therefore cheching only the source is enough. */ if (!(src_vma->vm_flags & VM_WRITE)) return -EINVAL; /* Check if vma flags indicate content which can be moved */ if (!vma_move_compatible(src_vma) || !vma_move_compatible(dst_vma)) return -EINVAL; /* Ensure dst_vma is registered in uffd we are operating on */ if (!dst_vma->vm_userfaultfd_ctx.ctx || dst_vma->vm_userfaultfd_ctx.ctx != ctx) return -EINVAL; /* Only allow moving across anonymous vmas */ if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma)) return -EINVAL; return 0; } static __always_inline int find_vmas_mm_locked(struct mm_struct *mm, unsigned long dst_start, unsigned long src_start, struct vm_area_struct **dst_vmap, struct vm_area_struct **src_vmap) { struct vm_area_struct *vma; mmap_assert_locked(mm); vma = find_vma_and_prepare_anon(mm, dst_start); if (IS_ERR(vma)) return PTR_ERR(vma); *dst_vmap = vma; /* Skip finding src_vma if src_start is in dst_vma */ if (src_start >= vma->vm_start && src_start < vma->vm_end) goto out_success; vma = vma_lookup(mm, src_start); if (!vma) return -ENOENT; out_success: *src_vmap = vma; return 0; } #ifdef CONFIG_PER_VMA_LOCK static int uffd_move_lock(struct mm_struct *mm, unsigned long dst_start, unsigned long src_start, struct vm_area_struct **dst_vmap, struct vm_area_struct **src_vmap) { struct vm_area_struct *vma; int err; vma = uffd_lock_vma(mm, dst_start); if (IS_ERR(vma)) return PTR_ERR(vma); *dst_vmap = vma; /* * Skip finding src_vma if src_start is in dst_vma. This also ensures * that we don't lock the same vma twice. */ if (src_start >= vma->vm_start && src_start < vma->vm_end) { *src_vmap = vma; return 0; } /* * Using uffd_lock_vma() to get src_vma can lead to following deadlock: * * Thread1 Thread2 * ------- ------- * vma_start_read(dst_vma) * mmap_write_lock(mm) * vma_start_write(src_vma) * vma_start_read(src_vma) * mmap_read_lock(mm) * vma_start_write(dst_vma) */ *src_vmap = lock_vma_under_rcu(mm, src_start); if (likely(*src_vmap)) return 0; /* Undo any locking and retry in mmap_lock critical section */ vma_end_read(*dst_vmap); mmap_read_lock(mm); err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap); if (!err) { /* * See comment in uffd_lock_vma() as to why not using * vma_start_read() here. */ down_read(&(*dst_vmap)->vm_lock->lock); if (*dst_vmap != *src_vmap) down_read_nested(&(*src_vmap)->vm_lock->lock, SINGLE_DEPTH_NESTING); } mmap_read_unlock(mm); return err; } static void uffd_move_unlock(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { vma_end_read(src_vma); if (src_vma != dst_vma) vma_end_read(dst_vma); } #else static int uffd_move_lock(struct mm_struct *mm, unsigned long dst_start, unsigned long src_start, struct vm_area_struct **dst_vmap, struct vm_area_struct **src_vmap) { int err; mmap_read_lock(mm); err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap); if (err) mmap_read_unlock(mm); return err; } static void uffd_move_unlock(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { mmap_assert_locked(src_vma->vm_mm); mmap_read_unlock(dst_vma->vm_mm); } #endif /** * move_pages - move arbitrary anonymous pages of an existing vma * @ctx: pointer to the userfaultfd context * @dst_start: start of the destination virtual memory range * @src_start: start of the source virtual memory range * @len: length of the virtual memory range * @mode: flags from uffdio_move.mode * * It will either use the mmap_lock in read mode or per-vma locks * * move_pages() remaps arbitrary anonymous pages atomically in zero * copy. It only works on non shared anonymous pages because those can * be relocated without generating non linear anon_vmas in the rmap * code. * * It provides a zero copy mechanism to handle userspace page faults. * The source vma pages should have mapcount == 1, which can be * enforced by using madvise(MADV_DONTFORK) on src vma. * * The thread receiving the page during the userland page fault * will receive the faulting page in the source vma through the network, * storage or any other I/O device (MADV_DONTFORK in the source vma * avoids move_pages() to fail with -EBUSY if the process forks before * move_pages() is called), then it will call move_pages() to map the * page in the faulting address in the destination vma. * * This userfaultfd command works purely via pagetables, so it's the * most efficient way to move physical non shared anonymous pages * across different virtual addresses. Unlike mremap()/mmap()/munmap() * it does not create any new vmas. The mapping in the destination * address is atomic. * * It only works if the vma protection bits are identical from the * source and destination vma. * * It can remap non shared anonymous pages within the same vma too. * * If the source virtual memory range has any unmapped holes, or if * the destination virtual memory range is not a whole unmapped hole, * move_pages() will fail respectively with -ENOENT or -EEXIST. This * provides a very strict behavior to avoid any chance of memory * corruption going unnoticed if there are userland race conditions. * Only one thread should resolve the userland page fault at any given * time for any given faulting address. This means that if two threads * try to both call move_pages() on the same destination address at the * same time, the second thread will get an explicit error from this * command. * * The command retval will return "len" is successful. The command * however can be interrupted by fatal signals or errors. If * interrupted it will return the number of bytes successfully * remapped before the interruption if any, or the negative error if * none. It will never return zero. Either it will return an error or * an amount of bytes successfully moved. If the retval reports a * "short" remap, the move_pages() command should be repeated by * userland with src+retval, dst+reval, len-retval if it wants to know * about the error that interrupted it. * * The UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES flag can be specified to * prevent -ENOENT errors to materialize if there are holes in the * source virtual range that is being remapped. The holes will be * accounted as successfully remapped in the retval of the * command. This is mostly useful to remap hugepage naturally aligned * virtual regions without knowing if there are transparent hugepage * in the regions or not, but preventing the risk of having to split * the hugepmd during the remap. * * If there's any rmap walk that is taking the anon_vma locks without * first obtaining the folio lock (the only current instance is * folio_referenced), they will have to verify if the folio->mapping * has changed after taking the anon_vma lock. If it changed they * should release the lock and retry obtaining a new anon_vma, because * it means the anon_vma was changed by move_pages() before the lock * could be obtained. This is the only additional complexity added to * the rmap code to provide this anonymous page remapping functionality. */ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, __u64 mode) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *src_vma, *dst_vma; unsigned long src_addr, dst_addr; pmd_t *src_pmd, *dst_pmd; long err = -EINVAL; ssize_t moved = 0; /* Sanitize the command parameters. */ if (WARN_ON_ONCE(src_start & ~PAGE_MASK) || WARN_ON_ONCE(dst_start & ~PAGE_MASK) || WARN_ON_ONCE(len & ~PAGE_MASK)) goto out; /* Does the address range wrap, or is the span zero-sized? */ if (WARN_ON_ONCE(src_start + len <= src_start) || WARN_ON_ONCE(dst_start + len <= dst_start)) goto out; err = uffd_move_lock(mm, dst_start, src_start, &dst_vma, &src_vma); if (err) goto out; /* Re-check after taking map_changing_lock */ err = -EAGAIN; down_read(&ctx->map_changing_lock); if (likely(atomic_read(&ctx->mmap_changing))) goto out_unlock; /* * Make sure the vma is not shared, that the src and dst remap * ranges are both valid and fully within a single existing * vma. */ err = -EINVAL; if (src_vma->vm_flags & VM_SHARED) goto out_unlock; if (src_start + len > src_vma->vm_end) goto out_unlock; if (dst_vma->vm_flags & VM_SHARED) goto out_unlock; if (dst_start + len > dst_vma->vm_end) goto out_unlock; err = validate_move_areas(ctx, src_vma, dst_vma); if (err) goto out_unlock; for (src_addr = src_start, dst_addr = dst_start; src_addr < src_start + len;) { spinlock_t *ptl; pmd_t dst_pmdval; unsigned long step_size; /* * Below works because anonymous area would not have a * transparent huge PUD. If file-backed support is added, * that case would need to be handled here. */ src_pmd = mm_find_pmd(mm, src_addr); if (unlikely(!src_pmd)) { if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) { err = -ENOENT; break; } src_pmd = mm_alloc_pmd(mm, src_addr); if (unlikely(!src_pmd)) { err = -ENOMEM; break; } } dst_pmd = mm_alloc_pmd(mm, dst_addr); if (unlikely(!dst_pmd)) { err = -ENOMEM; break; } dst_pmdval = pmdp_get_lockless(dst_pmd); /* * If the dst_pmd is mapped as THP don't override it and just * be strict. If dst_pmd changes into TPH after this check, the * move_pages_huge_pmd() will detect the change and retry * while move_pages_pte() will detect the change and fail. */ if (unlikely(pmd_trans_huge(dst_pmdval))) { err = -EEXIST; break; } ptl = pmd_trans_huge_lock(src_pmd, src_vma); if (ptl) { if (pmd_devmap(*src_pmd)) { spin_unlock(ptl); err = -ENOENT; break; } /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { struct folio *folio = pmd_folio(*src_pmd); if (!folio || (!is_huge_zero_folio(folio) && !PageAnonExclusive(&folio->page))) { spin_unlock(ptl); err = -EBUSY; break; } spin_unlock(ptl); split_huge_pmd(src_vma, src_pmd, src_addr); /* The folio will be split by move_pages_pte() */ continue; } err = move_pages_huge_pmd(mm, dst_pmd, src_pmd, dst_pmdval, dst_vma, src_vma, dst_addr, src_addr); step_size = HPAGE_PMD_SIZE; } else { if (pmd_none(*src_pmd)) { if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) { err = -ENOENT; break; } if (unlikely(__pte_alloc(mm, src_pmd))) { err = -ENOMEM; break; } } if (unlikely(pte_alloc(mm, dst_pmd))) { err = -ENOMEM; break; } err = move_pages_pte(mm, dst_pmd, src_pmd, dst_vma, src_vma, dst_addr, src_addr, mode); step_size = PAGE_SIZE; } cond_resched(); if (fatal_signal_pending(current)) { /* Do not override an error */ if (!err || err == -EAGAIN) err = -EINTR; break; } if (err) { if (err == -EAGAIN) continue; break; } /* Proceed to the next page */ dst_addr += step_size; src_addr += step_size; moved += step_size; } out_unlock: up_read(&ctx->map_changing_lock); uffd_move_unlock(dst_vma, src_vma); out: VM_WARN_ON(moved < 0); VM_WARN_ON(err > 0); VM_WARN_ON(!moved && !err); return moved ? moved : err; } |
| 139 145 133 131 5 152 47 19 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * vivid-core.h - core datastructures * * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #ifndef _VIVID_CORE_H_ #define _VIVID_CORE_H_ #include <linux/fb.h> #include <linux/workqueue.h> #include <media/cec.h> #include <media/videobuf2-v4l2.h> #include <media/v4l2-device.h> #include <media/v4l2-dev.h> #include <media/v4l2-ctrls.h> #include <media/tpg/v4l2-tpg.h> #include "vivid-rds-gen.h" #include "vivid-vbi-gen.h" #define dprintk(dev, level, fmt, arg...) \ v4l2_dbg(level, vivid_debug, &dev->v4l2_dev, fmt, ## arg) /* The maximum number of inputs */ #define MAX_INPUTS 16 /* The maximum number of outputs */ #define MAX_OUTPUTS 16 /* The maximum up or down scaling factor is 4 */ #define MAX_ZOOM 4 /* The maximum image width/height are set to 4K DMT */ #define MAX_WIDTH 4096 #define MAX_HEIGHT 2160 /* The minimum image width/height */ #define MIN_WIDTH 16 #define MIN_HEIGHT MIN_WIDTH /* Pixel Array control divider */ #define PIXEL_ARRAY_DIV MIN_WIDTH /* The data_offset of plane 0 for the multiplanar formats */ #define PLANE0_DATA_OFFSET 128 /* The supported TV frequency range in MHz */ #define MIN_TV_FREQ (44U * 16U) #define MAX_TV_FREQ (958U * 16U) /* The number of samples returned in every SDR buffer */ #define SDR_CAP_SAMPLES_PER_BUF 0x4000 /* used by the threads to know when to resync internal counters */ #define JIFFIES_PER_DAY (3600U * 24U * HZ) #define JIFFIES_RESYNC (JIFFIES_PER_DAY * (0xf0000000U / JIFFIES_PER_DAY)) /* * Maximum number of HDMI inputs allowed by vivid, due to limitations * of the Physical Address in the EDID and used by CEC we stop at 15 * inputs and outputs. */ #define MAX_HDMI_INPUTS 15 #define MAX_HDMI_OUTPUTS 15 /* Maximum number of S-Video inputs allowed by vivid */ #define MAX_SVID_INPUTS 16 /* The maximum number of items in a menu control */ #define MAX_MENU_ITEMS BITS_PER_LONG_LONG /* Number of fixed menu items in the 'Connected To' menu controls */ #define FIXED_MENU_ITEMS 2 /* The maximum number of vivid devices */ #define VIVID_MAX_DEVS CONFIG_VIDEO_VIVID_MAX_DEVS extern const struct v4l2_rect vivid_min_rect; extern const struct v4l2_rect vivid_max_rect; extern unsigned vivid_debug; /* * NULL-terminated string array for the HDMI 'Connected To' menu controls * with the list of possible HDMI outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_hdmi_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all HDMI outputs that are in use */ extern u64 hdmi_to_output_menu_skip_mask; /* * Bitmask of which vivid instances need to update any connected * HDMI outputs. */ extern u64 hdmi_input_update_outputs_mask; /* * Spinlock for access to hdmi_to_output_menu_skip_mask and * hdmi_input_update_outputs_mask. */ extern spinlock_t hdmi_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the HDMI menu skip mask * changes. */ extern struct workqueue_struct *update_hdmi_ctrls_workqueue; /* * The HDMI menu control value (index in the menu list) maps to an HDMI * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_hdmi_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_hdmi_to_output_index[MAX_MENU_ITEMS]; /* * NULL-terminated string array for the S-Video 'Connected To' menu controls * with the list of possible S-Video outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_svid_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all S-Video outputs that are in use */ extern u64 svid_to_output_menu_skip_mask; /* Spinlock for access to svid_to_output_menu_skip_mask */ extern spinlock_t svid_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the S-Video menu skip mask * changes. */ extern struct workqueue_struct *update_svid_ctrls_workqueue; /* * The S-Video menu control value (index in the menu list) maps to an S-Video * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_svid_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_svid_to_output_index[MAX_MENU_ITEMS]; extern struct vivid_dev *vivid_devs[VIVID_MAX_DEVS]; extern unsigned int n_devs; struct vivid_fmt { u32 fourcc; /* v4l2 format id */ enum tgp_color_enc color_enc; bool can_do_overlay; u8 vdownsampling[TPG_MAX_PLANES]; u32 alpha_mask; u8 planes; u8 buffers; u32 data_offset[TPG_MAX_PLANES]; u32 bit_depth[TPG_MAX_PLANES]; }; extern struct vivid_fmt vivid_formats[]; /* buffer for one video frame */ struct vivid_buffer { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; }; enum vivid_input { WEBCAM, TV, SVID, HDMI, }; enum vivid_signal_mode { CURRENT_DV_TIMINGS, CURRENT_STD = CURRENT_DV_TIMINGS, NO_SIGNAL, NO_LOCK, OUT_OF_RANGE, SELECTED_DV_TIMINGS, SELECTED_STD = SELECTED_DV_TIMINGS, CYCLE_DV_TIMINGS, CYCLE_STD = CYCLE_DV_TIMINGS, CUSTOM_DV_TIMINGS, }; enum vivid_colorspace { VIVID_CS_170M, VIVID_CS_709, VIVID_CS_SRGB, VIVID_CS_OPRGB, VIVID_CS_2020, VIVID_CS_DCI_P3, VIVID_CS_240M, VIVID_CS_SYS_M, VIVID_CS_SYS_BG, }; #define VIVID_INVALID_SIGNAL(mode) \ ((mode) == NO_SIGNAL || (mode) == NO_LOCK || (mode) == OUT_OF_RANGE) struct vivid_cec_xfer { struct cec_adapter *adap; u8 msg[CEC_MAX_MSG_SIZE]; u32 len; u32 sft; }; struct vivid_dev { u8 inst; struct v4l2_device v4l2_dev; #ifdef CONFIG_MEDIA_CONTROLLER struct media_device mdev; struct media_pad vid_cap_pad; struct media_pad vid_out_pad; struct media_pad vbi_cap_pad; struct media_pad vbi_out_pad; struct media_pad sdr_cap_pad; struct media_pad meta_cap_pad; struct media_pad meta_out_pad; struct media_pad touch_cap_pad; #endif struct v4l2_ctrl_handler ctrl_hdl_user_gen; struct v4l2_ctrl_handler ctrl_hdl_user_vid; struct v4l2_ctrl_handler ctrl_hdl_user_aud; struct v4l2_ctrl_handler ctrl_hdl_streaming; struct v4l2_ctrl_handler ctrl_hdl_sdtv_cap; struct v4l2_ctrl_handler ctrl_hdl_loop_cap; struct v4l2_ctrl_handler ctrl_hdl_fb; struct video_device vid_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_cap; struct video_device vid_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_out; struct video_device vbi_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_cap; struct video_device vbi_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_out; struct video_device radio_rx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_rx; struct video_device radio_tx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_tx; struct video_device sdr_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_sdr_cap; struct video_device meta_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_cap; struct video_device meta_out_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_out; struct video_device touch_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_touch_cap; spinlock_t slock; struct mutex mutex; struct work_struct update_hdmi_ctrl_work; struct work_struct update_svid_ctrl_work; /* capabilities */ u32 vid_cap_caps; u32 vid_out_caps; u32 vbi_cap_caps; u32 vbi_out_caps; u32 sdr_cap_caps; u32 radio_rx_caps; u32 radio_tx_caps; u32 meta_cap_caps; u32 meta_out_caps; u32 touch_cap_caps; /* supported features */ bool multiplanar; u8 num_inputs; u8 num_hdmi_inputs; u8 num_svid_inputs; u8 input_type[MAX_INPUTS]; u8 input_name_counter[MAX_INPUTS]; u8 num_outputs; u8 num_hdmi_outputs; u8 output_type[MAX_OUTPUTS]; u8 output_name_counter[MAX_OUTPUTS]; bool has_audio_inputs; bool has_audio_outputs; bool has_vid_cap; bool has_vid_out; bool has_vbi_cap; bool has_raw_vbi_cap; bool has_sliced_vbi_cap; bool has_vbi_out; bool has_raw_vbi_out; bool has_sliced_vbi_out; bool has_radio_rx; bool has_radio_tx; bool has_sdr_cap; bool has_fb; bool has_meta_cap; bool has_meta_out; bool has_tv_tuner; bool has_touch_cap; /* Output index (0-MAX_OUTPUTS) to vivid instance of connected input */ struct vivid_dev *output_to_input_instance[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to input index (0-MAX_INPUTS) of connected input */ u8 output_to_input_index[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to HDMI or S-Video output index (0-MAX_HDMI/SVID_OUTPUTS) */ u8 output_to_iface_index[MAX_OUTPUTS]; /* ctrl_hdmi_to_output or ctrl_svid_to_output control value for each input */ s32 input_is_connected_to_output[MAX_INPUTS]; /* HDMI index (0-MAX_HDMI_OUTPUTS) to output index (0-MAX_OUTPUTS) */ u8 hdmi_index_to_output_index[MAX_HDMI_OUTPUTS]; /* HDMI index (0-MAX_HDMI_INPUTS) to input index (0-MAX_INPUTS) */ u8 hdmi_index_to_input_index[MAX_HDMI_INPUTS]; /* S-Video index (0-MAX_SVID_INPUTS) to input index (0-MAX_INPUTS) */ u8 svid_index_to_input_index[MAX_SVID_INPUTS]; /* controls */ struct v4l2_ctrl *brightness; struct v4l2_ctrl *contrast; struct v4l2_ctrl *saturation; struct v4l2_ctrl *hue; struct { /* autogain/gain cluster */ struct v4l2_ctrl *autogain; struct v4l2_ctrl *gain; }; struct v4l2_ctrl *volume; struct v4l2_ctrl *mute; struct v4l2_ctrl *alpha; struct v4l2_ctrl *button; struct v4l2_ctrl *boolean; struct v4l2_ctrl *int32; struct v4l2_ctrl *int64; struct v4l2_ctrl *menu; struct v4l2_ctrl *string; struct v4l2_ctrl *bitmask; struct v4l2_ctrl *int_menu; struct v4l2_ctrl *ro_int32; struct v4l2_ctrl *pixel_array; struct v4l2_ctrl *test_pattern; struct v4l2_ctrl *colorspace; struct v4l2_ctrl *rgb_range_cap; struct v4l2_ctrl *real_rgb_range_cap; struct { /* std_signal_mode/standard cluster */ struct v4l2_ctrl *ctrl_std_signal_mode; struct v4l2_ctrl *ctrl_standard; }; struct { /* dv_timings_signal_mode/timings cluster */ struct v4l2_ctrl *ctrl_dv_timings_signal_mode; struct v4l2_ctrl *ctrl_dv_timings; }; struct v4l2_ctrl *ctrl_has_crop_cap; struct v4l2_ctrl *ctrl_has_compose_cap; struct v4l2_ctrl *ctrl_has_scaler_cap; struct v4l2_ctrl *ctrl_has_crop_out; struct v4l2_ctrl *ctrl_has_compose_out; struct v4l2_ctrl *ctrl_has_scaler_out; struct v4l2_ctrl *ctrl_tx_mode; struct v4l2_ctrl *ctrl_tx_rgb_range; struct v4l2_ctrl *ctrl_tx_edid_present; struct v4l2_ctrl *ctrl_tx_hotplug; struct v4l2_ctrl *ctrl_tx_rxsense; struct v4l2_ctrl *ctrl_rx_power_present; struct v4l2_ctrl *radio_tx_rds_pi; struct v4l2_ctrl *radio_tx_rds_pty; struct v4l2_ctrl *radio_tx_rds_mono_stereo; struct v4l2_ctrl *radio_tx_rds_art_head; struct v4l2_ctrl *radio_tx_rds_compressed; struct v4l2_ctrl *radio_tx_rds_dyn_pty; struct v4l2_ctrl *radio_tx_rds_ta; struct v4l2_ctrl *radio_tx_rds_tp; struct v4l2_ctrl *radio_tx_rds_ms; struct v4l2_ctrl *radio_tx_rds_psname; struct v4l2_ctrl *radio_tx_rds_radiotext; struct v4l2_ctrl *radio_rx_rds_pty; struct v4l2_ctrl *radio_rx_rds_ta; struct v4l2_ctrl *radio_rx_rds_tp; struct v4l2_ctrl *radio_rx_rds_ms; struct v4l2_ctrl *radio_rx_rds_psname; struct v4l2_ctrl *radio_rx_rds_radiotext; struct v4l2_ctrl *ctrl_hdmi_to_output[MAX_HDMI_INPUTS]; char ctrl_hdmi_to_output_names[MAX_HDMI_INPUTS][32]; struct v4l2_ctrl *ctrl_svid_to_output[MAX_SVID_INPUTS]; char ctrl_svid_to_output_names[MAX_SVID_INPUTS][32]; unsigned input_brightness[MAX_INPUTS]; unsigned osd_mode; unsigned button_pressed; bool sensor_hflip; bool sensor_vflip; bool hflip; bool vflip; bool vbi_cap_interlaced; bool loop_video; bool reduced_fps; /* Framebuffer */ unsigned long video_pbase; void *video_vbase; u32 video_buffer_size; int display_width; int display_height; int display_byte_stride; int bits_per_pixel; int bytes_per_pixel; struct fb_info fb_info; struct fb_var_screeninfo fb_defined; struct fb_fix_screeninfo fb_fix; /* Error injection */ bool disconnect_error; bool queue_setup_error; bool buf_prepare_error; bool start_streaming_error; bool dqbuf_error; bool req_validate_error; bool seq_wrap; u64 time_wrap; u64 time_wrap_offset; unsigned perc_dropped_buffers; enum vivid_signal_mode std_signal_mode[MAX_INPUTS]; unsigned int query_std_last[MAX_INPUTS]; v4l2_std_id query_std[MAX_INPUTS]; enum tpg_video_aspect std_aspect_ratio[MAX_INPUTS]; enum vivid_signal_mode dv_timings_signal_mode[MAX_INPUTS]; char **query_dv_timings_qmenu; char *query_dv_timings_qmenu_strings; unsigned query_dv_timings_size; unsigned int query_dv_timings_last[MAX_INPUTS]; unsigned int query_dv_timings[MAX_INPUTS]; enum tpg_video_aspect dv_timings_aspect_ratio[MAX_INPUTS]; /* Input */ unsigned input; v4l2_std_id std_cap[MAX_INPUTS]; struct v4l2_dv_timings dv_timings_cap[MAX_INPUTS]; int dv_timings_cap_sel[MAX_INPUTS]; u32 service_set_cap; struct vivid_vbi_gen_data vbi_gen; u8 *edid; unsigned edid_blocks; unsigned edid_max_blocks; unsigned webcam_size_idx; unsigned webcam_ival_idx; unsigned tv_freq; unsigned tv_audmode; unsigned tv_field_cap; unsigned tv_audio_input; u32 power_present; /* Output */ unsigned output; v4l2_std_id std_out; struct v4l2_dv_timings dv_timings_out; u32 colorspace_out; u32 ycbcr_enc_out; u32 hsv_enc_out; u32 quantization_out; u32 xfer_func_out; u32 service_set_out; unsigned bytesperline_out[TPG_MAX_PLANES]; unsigned tv_field_out; unsigned tv_audio_output; bool vbi_out_have_wss; u8 vbi_out_wss[2]; bool vbi_out_have_cc[2]; u8 vbi_out_cc[2][2]; bool dvi_d_out; u8 *scaled_line; u8 *blended_line; unsigned cur_scaled_line; /* Output Overlay */ void *fb_vbase_out; bool overlay_out_enabled; int overlay_out_top, overlay_out_left; unsigned fbuf_out_flags; u32 chromakey_out; u8 global_alpha_out; /* video capture */ struct tpg_data tpg; unsigned ms_vid_cap; bool must_blank[VIDEO_MAX_FRAME]; const struct vivid_fmt *fmt_cap; struct v4l2_fract timeperframe_vid_cap; enum v4l2_field field_cap; struct v4l2_rect src_rect; struct v4l2_rect fmt_cap_rect; struct v4l2_rect crop_cap; struct v4l2_rect compose_cap; struct v4l2_rect crop_bounds_cap; struct vb2_queue vb_vid_cap_q; struct list_head vid_cap_active; struct vb2_queue vb_vbi_cap_q; struct list_head vbi_cap_active; struct vb2_queue vb_meta_cap_q; struct list_head meta_cap_active; struct vb2_queue vb_touch_cap_q; struct list_head touch_cap_active; /* thread for generating video capture stream */ struct task_struct *kthread_vid_cap; unsigned long jiffies_vid_cap; u64 cap_stream_start; u64 cap_frame_period; u64 cap_frame_eof_offset; u32 cap_seq_offset; u32 cap_seq_count; bool cap_seq_resync; u32 vid_cap_seq_start; u32 vid_cap_seq_count; bool vid_cap_streaming; u32 vbi_cap_seq_start; u32 vbi_cap_seq_count; bool vbi_cap_streaming; u32 meta_cap_seq_start; u32 meta_cap_seq_count; bool meta_cap_streaming; /* Touch capture */ struct task_struct *kthread_touch_cap; unsigned long jiffies_touch_cap; u64 touch_cap_stream_start; u32 touch_cap_seq_offset; bool touch_cap_seq_resync; u32 touch_cap_seq_start; u32 touch_cap_seq_count; u32 touch_cap_with_seq_wrap_count; bool touch_cap_streaming; struct v4l2_fract timeperframe_tch_cap; struct v4l2_pix_format tch_format; int tch_pat_random; /* video output */ const struct vivid_fmt *fmt_out; struct v4l2_fract timeperframe_vid_out; enum v4l2_field field_out; struct v4l2_rect sink_rect; struct v4l2_rect fmt_out_rect; struct v4l2_rect crop_out; struct v4l2_rect compose_out; struct v4l2_rect compose_bounds_out; struct vb2_queue vb_vid_out_q; struct list_head vid_out_active; struct vb2_queue vb_vbi_out_q; struct list_head vbi_out_active; struct vb2_queue vb_meta_out_q; struct list_head meta_out_active; /* video loop precalculated rectangles */ /* * Intersection between what the output side composes and the capture side * crops. I.e., what actually needs to be copied from the output buffer to * the capture buffer. */ struct v4l2_rect loop_vid_copy; /* The part of the output buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_out; /* The part of the capture buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_cap; /* * The intersection of the framebuffer, the overlay output window and * loop_vid_copy. I.e., the part of the framebuffer that actually should be * blended with the compose_out rectangle. This uses the framebuffer origin. */ struct v4l2_rect loop_fb_copy; /* The same as loop_fb_copy but with compose_out origin. */ struct v4l2_rect loop_vid_overlay; /* * The part of the capture buffer that (after scaling) corresponds * to loop_vid_overlay. */ struct v4l2_rect loop_vid_overlay_cap; /* thread for generating video output stream */ struct task_struct *kthread_vid_out; unsigned long jiffies_vid_out; u32 out_seq_offset; u32 out_seq_count; bool out_seq_resync; u32 vid_out_seq_start; u32 vid_out_seq_count; bool vid_out_streaming; u32 vbi_out_seq_start; u32 vbi_out_seq_count; bool vbi_out_streaming; bool stream_sliced_vbi_out; u32 meta_out_seq_start; u32 meta_out_seq_count; bool meta_out_streaming; /* SDR capture */ struct vb2_queue vb_sdr_cap_q; struct list_head sdr_cap_active; u32 sdr_pixelformat; /* v4l2 format id */ unsigned sdr_buffersize; unsigned sdr_adc_freq; unsigned sdr_fm_freq; unsigned sdr_fm_deviation; int sdr_fixp_src_phase; int sdr_fixp_mod_phase; bool tstamp_src_is_soe; bool has_crop_cap; bool has_compose_cap; bool has_scaler_cap; bool has_crop_out; bool has_compose_out; bool has_scaler_out; /* thread for generating SDR stream */ struct task_struct *kthread_sdr_cap; unsigned long jiffies_sdr_cap; u32 sdr_cap_seq_offset; u32 sdr_cap_seq_start; u32 sdr_cap_seq_count; u32 sdr_cap_with_seq_wrap_count; bool sdr_cap_seq_resync; /* RDS generator */ struct vivid_rds_gen rds_gen; /* Radio receiver */ unsigned radio_rx_freq; unsigned radio_rx_audmode; int radio_rx_sig_qual; unsigned radio_rx_hw_seek_mode; bool radio_rx_hw_seek_prog_lim; bool radio_rx_rds_controls; bool radio_rx_rds_enabled; unsigned radio_rx_rds_use_alternates; unsigned radio_rx_rds_last_block; struct v4l2_fh *radio_rx_rds_owner; /* Radio transmitter */ unsigned radio_tx_freq; unsigned radio_tx_subchans; bool radio_tx_rds_controls; unsigned radio_tx_rds_last_block; struct v4l2_fh *radio_tx_rds_owner; /* Shared between radio receiver and transmitter */ bool radio_rds_loop; ktime_t radio_rds_init_time; /* CEC */ struct cec_adapter *cec_rx_adap; struct cec_adapter *cec_tx_adap[MAX_HDMI_OUTPUTS]; struct task_struct *kthread_cec; wait_queue_head_t kthread_waitq_cec; struct vivid_cec_xfer xfers[MAX_OUTPUTS]; spinlock_t cec_xfers_slock; /* read and write cec messages */ u32 cec_sft; /* bus signal free time, in bit periods */ u8 last_initiator; /* CEC OSD String */ char osd[14]; unsigned long osd_jiffies; bool meta_pts; bool meta_scr; }; static inline bool vivid_is_webcam(const struct vivid_dev *dev) { return dev->input_type[dev->input] == WEBCAM; } static inline bool vivid_is_tv_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == TV; } static inline bool vivid_is_svid_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == SVID; } static inline bool vivid_is_hdmi_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == HDMI; } static inline bool vivid_is_sdtv_cap(const struct vivid_dev *dev) { return vivid_is_tv_cap(dev) || vivid_is_svid_cap(dev); } static inline bool vivid_is_svid_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == SVID; } static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == HDMI; } #endif |
| 37 1 36 37 37 31 37 69 37 37 37 37 37 37 37 3 3 3 37 46 46 11 11 11 12 12 11 1 11 8 1 9 46 44 45 1 44 46 46 553 557 558 558 1 555 558 45 534 538 535 1 497 499 499 45 45 36 1 31 31 36 68 45 43 42 43 11 32 62 45 45 67 68 68 67 67 68 68 68 65 36 68 38 5 6 1 68 1 1 1 30 36 66 34 1 28 1 28 1 1 1 1 51 24 1 65 2 34 60 60 59 59 1 1 1 66 52 6 6 46 45 45 45 46 45 60 17 27 1 60 1 59 60 19 45 8 44 45 44 45 45 50 50 62 63 63 63 63 37 759 759 763 35 35 34 33 34 34 34 34 34 35 28 13 38 15 32 32 6 20 28 24 2 37 36 37 37 26 27 12 27 11 27 26 49 26 26 23 23 23 23 23 23 23 22 23 88 87 26 26 26 26 26 26 2 26 26 26 26 26 26 26 4 25 28 37 8 8 8 35 35 35 35 5 5 5 5 5 5 5 5 5 5 26 26 26 26 25 1 26 26 26 26 26 26 26 33 32 32 33 26 33 29 32 32 32 12 12 12 12 12 8 8 5 5 8 5 12 12 26 26 26 26 1 26 26 26 26 1 26 26 26 1 26 26 12 4 26 26 26 26 26 26 26 26 25 26 26 5 37 37 26 36 37 26 37 37 34 36 35 25 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 37 37 37 37 37 37 31 31 31 31 31 31 31 27 24 11 24 31 31 26 31 31 18 18 31 12 20 31 29 26 37 37 37 37 37 37 37 37 37 37 2 2 2 2 2 37 37 37 37 16 10 10 37 37 37 31 36 3 3 36 1 36 36 36 36 36 37 37 37 37 37 37 37 37 37 37 36 36 4 37 37 4 37 37 34 4 32 34 3 34 34 34 34 37 37 37 37 37 16 35 34 34 2 1 34 1 35 34 35 35 35 37 37 37 22 6 33 21 37 37 37 37 37 37 26 37 37 37 36 36 37 37 19 33 6 37 37 37 37 37 37 26 37 37 37 36 37 36 37 37 37 37 37 1 7 37 37 37 37 37 2 2 2 2 2 2 37 37 3 32 34 37 11 37 37 37 7 35 36 36 37 31 37 37 37 36 37 17 37 31 37 31 31 31 31 31 28 11 8 37 37 36 17 37 37 37 37 37 37 36 37 37 37 31 31 56 56 261 603 75 607 1476 1476 249 1329 1402 138 965 608 56 608 6 5 6 6 6 5 5 4 4 4 5 5 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/migrate.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/memory-tiers.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include <linux/sched/sysctl.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; #ifdef CONFIG_MEMCG /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */ int *proactive_swappiness; #endif /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; /* Not allow cache_trim_mode to be turned on as part of reclaim? */ unsigned int no_cache_trim_mode:1; /* Has cache_trim_mode failed at least once? */ unsigned int cache_trim_mode_failed:1; /* Proactive reclaim invoked by userspace through memory.reclaim */ unsigned int proactive:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; /* Shared cgroup tree walk failed, rescan the whole tree */ unsigned int memcg_full_walk:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file folios on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ if ((_folio)->lru.prev != _base) { \ struct folio *prev; \ \ prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* * From 0 .. MAX_SWAPPINESS. Higher means more swappy. */ int vm_swappiness = 60; #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /* * Returns true for reclaim on the root cgroup. This is true for direct * allocator reclaim and reclaim through cgroup interfaces on the root cgroup. */ static bool root_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup); } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { if (sc->proactive && sc->proactive_swappiness) return *sc->proactive_swappiness; return mem_cgroup_swappiness(memcg); } #else static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool root_reclaim(struct scan_control *sc) { return true; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) { return READ_ONCE(vm_swappiness); } #endif static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } /* * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to * scan_control->nr_reclaimed. */ static void flush_reclaim_state(struct scan_control *sc) { /* * Currently, reclaim_state->reclaimed includes three types of pages * freed outside of vmscan: * (1) Slab pages. * (2) Clean file pages from pruned inodes (on highmem systems). * (3) XFS freed buffer pages. * * For all of these cases, we cannot universally link the pages to a * single memcg. For example, a memcg-aware shrinker can free one object * charged to the target memcg, causing an entire page to be freed. * If we count the entire page as reclaimed from the memcg, we end up * overestimating the reclaimed amount (potentially under-reclaiming). * * Only count such pages for global reclaim to prevent under-reclaiming * from the target memcg; preventing unnecessary retries during memcg * charging and false positives from proactive reclaim. * * For uncommon cases where the freed pages were actually mostly * charged to the target memcg, we end up underestimating the reclaimed * amount. This should be fine. The freed pages will be uncharged * anyway, even if they are not counted here properly, and we will be * able to make forward progress in charging (which is usually in a * retry loop). * * We can go one step further, and report the uncharged objcg pages in * memcg reclaim, to make reporting more accurate and reduce * underestimation, but it's probably not worth the complexity for now. */ if (current->reclaim_state && root_reclaim(sc)) { sc->nr_reclaimed += current->reclaim_state->reclaimed; current->reclaim_state->reclaimed = 0; } } static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) return false; if (sc && sc->no_demotion) return false; if (next_demotion_node(nid) == NUMA_NO_NODE) return false; return true; } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, int nid, struct scan_control *sc) { if (memcg == NULL) { /* * For non-memcg reclaim, is there * space in any swap device? */ if (get_nr_swap_pages() > 0) return true; } else { /* Is the memcg below its swap limit? */ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) return true; } /* * The page can not be swapped. * * Can it be reclaimed from this node via demotion? */ return can_demote(nid, sc); } /* * This misses isolated folios which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; for (zid = 0; zid <= zone_idx; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) continue; if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; struct mem_cgroup *memcg = NULL; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); return freed; } void drop_slab(void) { int nid; int shift = 0; unsigned long freed; do { freed = 0; for_each_online_node(nid) { if (fatal_signal_pending(current)) return; freed += drop_slab_node(nid); } } while ((freed >> shift++) > 1); } static int reclaimer_offset(void) { BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD); BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != PGSCAN_DIRECT - PGSCAN_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD); if (current_is_kswapd()) return 0; if (current_is_khugepaged()) return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD; return PGSTEAL_DIRECT - PGSTEAL_KSWAPD; } static inline int is_page_cache_freeable(struct folio *folio) { /* * A freeable page cache folio is referenced only by the caller * that isolated the folio, the page cache and optional filesystem * private data at folio->private. */ return folio_ref_count(folio) - folio_test_private(folio) == 1 + folio_nr_pages(folio); } /* * We detected a synchronous write error writing a folio out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the folio and once * that folio is locked, the mapping is pinned. * * We're allowed to run sleeping folio_lock() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct folio *folio, int error) { folio_lock(folio); if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); folio_unlock(folio); } static bool skip_throttle_noprogress(pg_data_t *pgdat) { int reclaimable = 0, write_pending = 0; int i; /* * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; /* * If there are a lot of dirty/writeback folios then do not * throttle as throttling will occur when the folios cycle * towards the end of the LRU if still under writeback. */ for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; reclaimable += zone_reclaimable_pages(zone); write_pending += zone_page_state_snapshot(zone, NR_ZONE_WRITE_PENDING); } if (2 * write_pending <= reclaimable) return true; return false; } void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long timeout, ret; DEFINE_WAIT(wait); /* * Do not throttle user workers, kthreads other than kswapd or * workqueues. They may be required for reclaim to make * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && current->flags & (PF_USER_WORKER|PF_KTHREAD)) { cond_resched(); return; } /* * These figures are pulled out of thin air. * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many * parallel reclaimers which is a short-lived event so the timeout is * short. Failing to make progress or waiting on writeback are * potentially long-lived events so use a longer timeout. This is shaky * logic as a failure to make progress could be due to anything from * writeback to a slow device to excessive referenced folios at the tail * of the inactive LRU. */ switch(reason) { case VMSCAN_THROTTLE_WRITEBACK: timeout = HZ/10; if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } break; case VMSCAN_THROTTLE_CONGESTED: fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: if (skip_throttle_noprogress(pgdat)) { cond_resched(); return; } timeout = 1; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; break; default: WARN_ON_ONCE(1); timeout = HZ; break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), reason); } /* * Account for folios written if tasks are throttled waiting on dirty * folios to clean. If enough folios have been cleaned since throttling * started then wakeup the throttled tasks. */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled) { unsigned long nr_written; node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); /* * This is an inaccurate read as the per-cpu deltas may not * be synchronised. However, given that the system is * writeback throttled, it is not worth taking the penalty * of getting an accurate count. At worst, the throttle * timeout guarantees forward progress. */ nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - READ_ONCE(pgdat->nr_reclaim_start); if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); } /* possible outcome of pageout() */ typedef enum { /* failed to write folio out, folio is locked */ PAGE_KEEP, /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_folio_list() for each dirty folio. * Calls ->writepage(). */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug) { /* * If the folio is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this folio's queue, we can perform writeback even if that * will block. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned folios can have * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (folio_clear_dirty_for_io(folio)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, .swap_plug = plug, }; folio_set_reclaim(folio); res = mapping->a_ops->writepage(&folio->page, &wbc); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { folio_clear_reclaim(folio); return PAGE_ACTIVATE; } if (!folio_test_writeback(folio)) { /* synchronous write or broken a_ops? */ folio_clear_reclaim(folio); } trace_mm_vmscan_write_folio(folio); node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the folio is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { int refcount; void *shadow = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(mapping != folio_mapping(folio)); if (!folio_test_swapcache(folio)) spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); /* * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has * a ref to the folio, it may be possible that they dirty it then * drop the reference. So if the dirty flag is tested before the * refcount here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !folio_test_dirty(folio) [good] * folio_set_dirty(folio); * folio_put(folio); * !refcount(folio) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the folio->flags * load is not satisfied before that of folio->_refcount. * * Note that if the dirty flag is always set via folio_mark_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + folio_nr_pages(folio); if (!folio_ref_freeze(folio, refcount)) goto cannot_free; /* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */ if (unlikely(folio_test_dirty(folio))) { folio_ref_unfreeze(folio, refcount); goto cannot_free; } if (folio_test_swapcache(folio)) { swp_entry_t swap = folio->swap; if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); __delete_from_swap_cache(folio, swap, shadow); mem_cgroup_swapout(folio, swap); xa_unlock_irq(&mapping->i_pages); put_swap_folio(folio, swap); } else { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache folios found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(folio, target_memcg); __filemap_remove_folio(folio, shadow); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); if (free_folio) free_folio(folio); } return 1; cannot_free: xa_unlock_irq(&mapping->i_pages); if (!folio_test_swapcache(folio)) spin_unlock(&mapping->host->i_lock); return 0; } /** * remove_mapping() - Attempt to remove a folio from its mapping. * @mapping: The address space. * @folio: The folio to remove. * * If the folio is dirty, under writeback or if someone else has a ref * on it, removal will fail. * Return: The number of pages removed from the mapping. 0 if the folio * could not be removed. * Context: The caller should have a single refcount on the folio and * hold its lock. */ long remove_mapping(struct address_space *mapping, struct folio *folio) { if (__remove_mapping(mapping, folio, false, NULL)) { /* * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ folio_ref_unfreeze(folio, 1); return folio_nr_pages(folio); } return 0; } /** * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. * @folio: Folio to be returned to an LRU list. * * Add previously isolated @folio to appropriate LRU list. * The folio may still be unevictable for other reasons. * * Context: lru_lock must not be held, interrupts must be enabled. */ void folio_putback_lru(struct folio *folio) { folio_add_lru(folio); folio_put(folio); /* drop ref from isolate */ } enum folio_references { FOLIOREF_RECLAIM, FOLIOREF_RECLAIM_CLEAN, FOLIOREF_KEEP, FOLIOREF_ACTIVATE, }; static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { int referenced_ptes, referenced_folio; unsigned long vm_flags; referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); referenced_folio = folio_test_clear_referenced(folio); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. * Let the folio, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) return FOLIOREF_ACTIVATE; /* rmap lock contention: rotate */ if (referenced_ptes == -1) return FOLIOREF_KEEP; if (referenced_ptes) { /* * All mapped folios start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file/anon folio is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated folios as well * so that recently deactivated but used folios are * quickly recovered. */ folio_set_referenced(folio); if (referenced_folio || referenced_ptes > 1) return FOLIOREF_ACTIVATE; /* * Activate file-backed executable folios after first usage. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return FOLIOREF_ACTIVATE; return FOLIOREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ if (referenced_folio && folio_is_file_lru(folio)) return FOLIOREF_RECLAIM_CLEAN; return FOLIOREF_RECLAIM; } /* Check if a folio is dirty or under writeback */ static void folio_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous folios are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them. * MADV_FREE anonymous folios are put into inactive file list too. * They could be mistakenly treated as file lru. So further anon * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } /* By default assume that the folio flags are accurate */ *dirty = folio_test_dirty(folio); *writeback = folio_test_writeback(folio); /* Verify dirty/writeback state if the filesystem supports it */ if (!folio_test_private(folio)) return; mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } struct folio *alloc_migrate_folio(struct folio *src, unsigned long private) { struct folio *dst; nodemask_t *allowed_mask; struct migration_target_control *mtc; mtc = (struct migration_target_control *)private; allowed_mask = mtc->nmask; /* * make sure we allocate from the target node first also trying to * demote or reclaim pages from the target node via kswapd if we are * low on free memory on target node. If we don't do this and if * we have free memory on the slower(lower) memtier, we would start * allocating pages from slower(lower) memory tiers without even forcing * a demotion of cold pages from the target memtier. This can result * in the kernel placing hot pages in slower(lower) memory tiers. */ mtc->nmask = NULL; mtc->gfp_mask |= __GFP_THISNODE; dst = alloc_migration_target(src, (unsigned long)mtc); if (dst) return dst; mtc->gfp_mask &= ~__GFP_THISNODE; mtc->nmask = allowed_mask; return alloc_migration_target(src, (unsigned long)mtc); } /* * Take folios on @demote_folios and attempt to demote them to another node. * Folios which are not demoted are left on @demote_folios. */ static unsigned int demote_folio_list(struct list_head *demote_folios, struct pglist_data *pgdat) { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; nodemask_t allowed_mask; struct migration_target_control mtc = { /* * Allocate from 'node', or fail quickly and quietly. * When this happens, 'page' will likely just be discarded * instead of migrated. */ .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, .nmask = &allowed_mask, .reason = MR_DEMOTION, }; if (list_empty(demote_folios)) return 0; if (target_nid == NUMA_NO_NODE) return 0; node_get_allowed_targets(pgdat, &allowed_mask); /* Demotion ignores all cpuset and mempolicy settings */ migrate_pages(demote_folios, alloc_migrate_folio, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded); return nr_succeeded; } static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) { if (gfp_mask & __GFP_FS) return true; if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) return false; /* * We can "enter_fs" for swap-cache with only __GFP_IO * providing this isn't SWP_FS_OPS. * ->flags can be updated non-atomicially (scan_swap_map_slots), * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* * shrink_folio_list() returns the number of reclaimed pages */ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; folio_batch_init(&free_folios); memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc); retry: while (!list_empty(folio_list)) { struct address_space *mapping; struct folio *folio; enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(folio_list); list_del(&folio->lru); if (!folio_trylock(folio)) goto keep; VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); /* Account the number of base pages */ sc->nr_scanned += nr_pages; if (unlikely(!folio_evictable(folio))) goto activate_locked; if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; /* folio_update_gen() tried to promote this page? */ if (lru_gen_enabled() && !ignore_references && folio_mapped(folio) && folio_test_referenced(folio)) goto keep_locked; /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty += nr_pages; if (dirty && !writeback) stat->nr_unqueued_dirty += nr_pages; /* * Treat this folio as congested if folios are cycling * through the LRU so quickly that the folios marked * for immediate reclaim are making it to the end of * the LRU a second time. */ if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number * of folios under writeback and this folio has both * the writeback and reclaim flags set, then it * indicates that folios are being queued for I/O but * are being recycled through the LRU before the I/O * can complete. Waiting on the folio itself risks an * indefinite stall if it is impossible to writeback * the folio due to I/O error or disconnected storage * so instead note that the LRU is being scanned too * quickly and the caller can stall after the folio * list has been processed. * * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the folio for immediate * reclaim and continue scanning. * * Require may_enter_fs() because we would wait on fs, which * may not have submitted I/O yet. And the loop driver might * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a folio that already has the * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the folios to get them out of * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (folio_test_writeback(folio)) { /* Case 1 above */ if (current_is_kswapd() && folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !folio_test_reclaim(folio) || !may_enter_fs(folio, sc->gfp_mask)) { /* * This is slightly racy - * folio_end_writeback() might have * just cleared the reclaim flag, then * setting the reclaim flag here ends up * interpreted as the readahead flag - but * that does not matter enough to care. * What we do want is for this folio to * have the reclaim flag set next time * memcg reclaim reaches the tests above, * so it will then wait for writeback to * avoid OOM; and it's also appropriate * in global reclaim. */ folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { folio_unlock(folio); folio_wait_writeback(folio); /* then go back and try same folio again */ list_add_tail(&folio->lru, folio_list); continue; } } if (!ignore_references) references = folio_check_references(folio, sc); switch (references) { case FOLIOREF_ACTIVATE: goto activate_locked; case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case FOLIOREF_RECLAIM: case FOLIOREF_RECLAIM_CLEAN: ; /* try to reclaim the folio below */ } /* * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && (thp_migration_supported() || !folio_test_large(folio))) { list_add(&folio->lru, &demote_folios); folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree folio could be freed directly */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ if (!can_split_folio(folio, NULL)) goto activate_locked; /* * Split partially mapped folios right away. * We can free the unmapped pages without IO. */ if (data_race(!list_empty(&folio->_deferred_list)) && split_folio_to_list(folio, folio_list)) goto activate_locked; } if (!add_to_swap(folio)) { int __maybe_unused order = folio_order(folio); if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (nr_pages >= HPAGE_PMD_NR) { count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; } } } else if (folio_test_swapbacked(folio) && folio_test_large(folio)) { /* Split shmem folio */ if (split_folio_to_list(folio, folio_list)) goto keep_locked; } /* * If the folio was split above, the tail pages will make * their own pass through this function and be accounted * then. */ if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = folio_test_swapbacked(folio); if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; /* * Without TTU_SYNC, try_to_unmap will only begin to * hold PTL from the first present PTE within a large * folio. Some initial PTEs might be skipped due to * races with parallel PTE writes in which PTEs can be * cleared temporarily before being written new present * values. This will lead to a large folio is still * mapped while some subpages have been partially * unmapped after try_to_unmap; TTU_SYNC helps * try_to_unmap acquire PTL from the first PTE, * eliminating the influence of temporary PTE values. */ if (folio_test_large(folio)) flags |= TTU_SYNC; try_to_unmap(folio, flags); if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } /* * Folio is unmapped now so it cannot be newly pinned anymore. * No point in trying to reclaim folio if it is pinned. * Furthermore we don't want to reclaim underlying fs metadata * if the folio is pinned and thus potentially modified by the * pinning process as that may upset the filesystem. */ if (folio_maybe_dma_pinned(folio)) goto activate_locked; mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only * write folios when we've encountered many * dirty folios, and when we've already scanned * the rest of the LRU for clean folios and see * the same dirty folios again (with the reclaim * flag set). */ if (folio_is_file_lru(folio) && (!current_is_kswapd() || !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principle to folio_deactivate() * except we already have the folio isolated * and know it's dirty */ node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, nr_pages); folio_set_reclaim(folio); goto activate_locked; } if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Folio is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(folio, mapping, &plug)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) goto keep; if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the folio. */ if (!folio_trylock(folio)) goto keep; if (folio_test_dirty(folio) || folio_test_writeback(folio)) goto keep_locked; mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: ; /* try to free the folio below */ } } /* * If the folio has buffers, try to free the buffer * mappings associated with this folio. If we succeed * we try to free the folio as well. * * We do this even if the folio is dirty. * filemap_release_folio() does not perform I/O, but it * is possible for a folio to have the dirty flag set, * but it is actually clean (all its buffers are clean). * This happens if the buffers were written out directly, * with submit_bh(). ext3 will do this, as well as * the blockdev mapping. filemap_release_folio() will * discover that cleanness and will drop the buffers * and mark the folio clean - it can be freed. * * Rarely, folios can have buffers and no ->mapping. * These are the folios which were not successfully * invalidated in truncate_cleanup_folio(). We try to * drop those buffers here and if that worked, and the * folio is no longer mapped into process address space * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { folio_unlock(folio); if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed += nr_pages; continue; } } } if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* * The folio has only one reference left, which is * from the isolation. After the caller puts the * folio back on the lru and drops the reference, the * folio will be freed anyway. It doesn't matter * which lru it goes on. So we don't bother checking * the dirty flag here. */ count_vm_events(PGLAZYFREED, nr_pages); count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; folio_unlock(folio); free_it: /* * Folio may get swapped out as a whole, need to account * all pages in it. */ nr_reclaimed += nr_pages; folio_undo_large_rmappable(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); } continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (folio_test_swapcache(folio) && (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio))) folio_free_swap(folio); VM_BUG_ON_FOLIO(folio_test_active(folio), folio); if (!folio_test_mlocked(folio)) { int type = folio_is_file_lru(folio); folio_set_active(folio); stat->nr_activate[type] += nr_pages; count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: folio_unlock(folio); keep: list_add(&folio->lru, &ret_folios); VM_BUG_ON_FOLIO(folio_test_lru(folio) || folio_test_unevictable(folio), folio); } /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ nr_reclaimed += demote_folio_list(&demote_folios, pgdat); /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ list_splice_init(&demote_folios, folio_list); /* * goto retry to reclaim the undemoted folios in folio_list if * desired. * * Reclaiming directly from top tier nodes is not often desired * due to it breaking the LRU ordering: in general memory * should be reclaimed from lower tier nodes and demoted from * top tier nodes. * * However, disabling reclaim from top tier nodes entirely * would cause ooms in edge scenarios where lower tier memory * is unreclaimable for whatever reason, eg memory being * mlocked or too hot to reclaim. We can disable reclaim * from top tier nodes in proactive reclaim though as that is * not real memory pressure. */ if (!sc->proactive) { do_demote_pass = false; goto retry; } } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); free_unref_folios(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); if (plug) swap_write_unplug(plug); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio, *next; LIST_HEAD(clean_folios); unsigned int noreclaim_flag; list_for_each_entry_safe(folio, next, folio_list, lru) { if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && !folio_test_dirty(folio) && !__folio_test_movable(folio) && !folio_test_unevictable(folio)) { folio_clear_active(folio); list_move(&folio->lru, &clean_folios); } } /* * We should be safe here since we are only dealing with file pages and * we are not kswapd and therefore cannot write dirty file pages. But * call memalloc_noreclaim_save() anyway, just in case these conditions * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true); memalloc_noreclaim_restore(noreclaim_flag); list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } #ifdef CONFIG_CMA /* * It is waste of effort to scan and reclaim CMA pages if it is not available * for current allocation context. Kswapd can not be enrolled as it can not * distinguish this scenario by using sc->gfp_mask = GFP_KERNEL */ static bool skip_cma(struct folio *folio, struct scan_control *sc) { return !current_is_kswapd() && gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE && folio_migratetype(folio) == MIGRATE_CMA; } #else static bool skip_cma(struct folio *folio, struct scan_control *sc) { return false; } #endif /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Lru_lock must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; LIST_HEAD(folios_skipped); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; struct folio *folio; folio = lru_to_folio(src); prefetchw_prev_lru_folio(folio, src, flags); nr_pages = folio_nr_pages(folio); total_scan += nr_pages; if (folio_zonenum(folio) > sc->reclaim_idx || skip_cma(folio, sc)) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; goto move; } /* * Do not count skipped folios because that makes the function * return with no isolated folios if the LRU mostly contains * ineligible folios. This causes the VM to not reclaim any * folios, triggering a premature OOM. * Account all pages in a folio. */ scan += nr_pages; if (!folio_test_lru(folio)) goto move; if (!sc->may_unmap && folio_mapped(folio)) goto move; /* * Be careful not to clear the lru flag until after we're * sure the folio is not being freed elsewhere -- the * folio release code relies on it. */ if (unlikely(!folio_try_get(folio))) goto move; if (!folio_test_clear_lru(folio)) { /* Another thread is already isolating this folio */ folio_put(folio); goto move; } nr_taken += nr_pages; nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: list_move(&folio->lru, move_to); } /* * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ if (!list_empty(&folios_skipped)) { int zid; list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * folio_isolate_lru() - Try to isolate a folio from its LRU list. * @folio: Folio to isolate from its LRU list. * * Isolate a @folio from an LRU list and adjust the vmstat statistic * corresponding to whatever LRU list the folio was on. * * The folio will have its LRU flag cleared. If it was found on the * active list, it will have the Active flag set. If it was found on the * unevictable list, it will have the Unevictable flag set. These flags * may need to be cleared by the caller before letting the page go. * * Context: * * (1) Must be called with an elevated refcount on the folio. This is a * fundamental difference from isolate_lru_folios() (which is called * without a stable reference). * (2) The lru_lock must not be held. * (3) Interrupts must be enabled. * * Return: true if the folio was removed from an LRU list. * false if the folio was not on an LRU list. */ bool folio_isolate_lru(struct folio *folio) { bool ret = false; VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; folio_get(folio); lruvec = folio_lruvec_lock_irq(folio); lruvec_del_folio(lruvec, folio); unlock_page_lruvec_irq(lruvec); ret = true; } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static bool too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; bool too_many; if (current_is_kswapd()) return false; if (!writeback_throttling_sane(sc)) return false; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if (gfp_has_io_fs(sc->gfp_mask)) inactive >>= 3; too_many = isolated > inactive; /* Wake up tasks throttled due to too_many_isolated. */ if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /* * move_folios_to_lru() moves folios from private @list to appropriate LRU list. * * Returns the number of pages moved to the given lruvec. */ static unsigned int move_folios_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; struct folio_batch free_folios; folio_batch_init(&free_folios); while (!list_empty(list)) { struct folio *folio = lru_to_folio(list); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_folios_to_lru #1 release_pages * if (!folio_put_testzero()) * if (folio_put_testzero()) * !lru //skip lru_lock * folio_set_lru() * list_add(&folio->lru,) * list_add(&folio->lru,) */ folio_set_lru(folio); if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); folio_undo_large_rmappable(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } continue; } /* * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); lruvec_add_folio(lruvec, folio); nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } if (free_folios.nr) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); free_unref_folios(&free_folios); spin_lock_irq(&lruvec->lru_lock); } return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services a backing * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(folio_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ stalled = true; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false); spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&lruvec->lru_lock); lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed); /* * If dirty folios are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty folios to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty folios grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); /* * For cgroupv1 dirty throttling is achieved by waking up * the kernel flusher here and later waiting on folios * which are in writeback to finish (see shrink_folio_list()). * * Flusher may not be able to issue writeback quickly * enough for cgroupv1 writeback throttling to work * on a large system. */ if (!writeback_throttling_sane(sc)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } /* * shrink_active_list() moves folios from the active LRU to the inactive LRU. * * We move them the other way if the folio is referenced by one or more * processes. * * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if * the folios are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each folio. It's impossible to balance * this, so instead we remove the folios from the LRU while processing them. * It is safe to rely on the active flag against the non-LRU folios in here * because nobody will play with that bit on a non-LRU folio. * * The downside is that we have to touch folio->_refcount against each folio. * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; bool file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { struct folio *folio; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { if (folio_needs_release(folio) && folio_trylock(folio)) { filemap_release_folio(folio, 0); folio_unlock(folio); } } /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; } } folio_clear_active(folio); /* we are de-activating */ folio_set_workingset(folio); list_add(&folio->lru, &l_inactive); } /* * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_folios_to_lru(lruvec, &l_active); nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&lruvec->lru_lock); if (nr_rotated) lru_note_cost(lruvec, file, 0, nr_rotated); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { struct reclaim_stat dummy_stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .no_demotion = 1, }; nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, true); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } return nr_reclaimed; } unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); do { struct folio *folio = lru_to_folio(folio_list); if (nid == folio_nid(folio)) { folio_clear_active(folio); list_move(&folio->lru, &node_folio_list); continue; } nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); nid = folio_nid(lru_to_folio(folio_list)); } while (!list_empty(folio_list)); nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * folio has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* * Flush the memory cgroup stats, so that we read accurate per-memcg * lruvec stats for heuristics. */ mem_cgroup_flush_stats(sc->target_mem_cgroup); /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&target_lruvec->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&target_lruvec->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[WORKINGSET_ANON] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[WORKINGSET_FILE] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE) && !sc->no_cache_trim_mode) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } } /* * Determine how aggressively the anon and file LRU lists should be * scanned. * * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = sc_swappiness(sc, memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; unsigned long ap, fp; enum lru_list lru; /* If we have no swap space, do not bother scanning anon folios. */ if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (MAX_SWAPPINESS - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; denominator = ap + fp; out: for_each_evictable_lru(lru) { bool file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } /* * Anonymous LRU management is a waste if there is * ultimately no way to reclaim the memory. */ static bool can_age_anon_pages(struct pglist_data *pgdat, struct scan_control *sc) { /* Aging the anon LRU is valuable if swap is present: */ if (total_swap_pages > 0) return true; /* Also valuable if anon pages can be demoted: */ return can_demote(pgdat->node_id, sc); } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_likely(&lru_gen_caps[cap]) #else DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap]) #endif static bool should_walk_mmu(void) { return arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK); } static bool should_clear_pmd_young(void) { return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG); } /****************************************************************************** * shorthand helpers ******************************************************************************/ #define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) #define DEFINE_MIN_SEQ(lruvec) \ unsigned long min_seq[ANON_AND_FILE] = { \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) #define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) #define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); #ifdef CONFIG_MEMCG if (memcg) { struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; /* see the comment in mem_cgroup_lruvec() */ if (!lruvec->pgdat) lruvec->pgdat = pgdat; return lruvec; } #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &pgdat->__lruvec; } static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); if (!sc->may_swap) return 0; if (!can_demote(pgdat->node_id, sc) && mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; return sc_swappiness(sc, memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) { return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; } static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { /* see the comment on lru_gen_folio */ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; } /****************************************************************************** * Bloom filters ******************************************************************************/ /* * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of * bits in a bitmap, k is the number of hash functions and n is the number of * inserted items. * * Page table walkers use one of the two filters to reduce their search space. * To get rid of non-leaf entries that no longer have enough leaf entries, the * aging uses the double-buffering technique to flip to the other filter each * time it produces a new generation. For non-leaf entries that have enough * leaf entries, the aging carries them over to the next generation in * walk_pmd_range(); the eviction also report them when walking the rmap * in lru_gen_look_around(). * * For future optimizations: * 1. It's not necessary to keep both filters all the time. The spare one can be * freed after the RCU grace period and reallocated if needed again. * 2. And when reallocating, it's worth scaling its size according to the number * of inserted entries in the other filter, to reduce the memory overhead on * small systems and false positives on large systems. * 3. Jenkins' hash function is an alternative to Knuth's. */ #define BLOOM_FILTER_SHIFT 15 static inline int filter_gen_from_seq(unsigned long seq) { return seq % NR_BLOOM_FILTERS; } static void get_item_key(void *item, int *key) { u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2); BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32)); key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1); key[1] = hash >> BLOOM_FILTER_SHIFT; } static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return true; get_item_key(item, key); return test_bit(key[0], filter) && test_bit(key[1], filter); } static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return; get_item_key(item, key); if (!test_bit(key[0], filter)) set_bit(key[0], filter); if (!test_bit(key[1], filter)) set_bit(key[1], filter); } static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq) { unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = mm_state->filters[gen]; if (filter) { bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT)); return; } filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); WRITE_ONCE(mm_state->filters[gen], filter); } /****************************************************************************** * mm_struct list ******************************************************************************/ #ifdef CONFIG_LRU_GEN_WALKS_MMU static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { static struct lru_gen_mm_list mm_list = { .fifo = LIST_HEAD_INIT(mm_list.fifo), .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock), }; #ifdef CONFIG_MEMCG if (memcg) return &memcg->mm_list; #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &mm_list; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return &lruvec->mm_state; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { int key; struct mm_struct *mm; struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) return NULL; clear_bit(key, &mm->lru_gen.bitmap); return mmget_not_zero(mm) ? mm : NULL; } void lru_gen_add_mm(struct mm_struct *mm) { int nid; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list)); #ifdef CONFIG_MEMCG VM_WARN_ON_ONCE(mm->lru_gen.memcg); mm->lru_gen.memcg = memcg; #endif spin_lock(&mm_list->lock); for_each_node_state(nid, N_MEMORY) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* the first addition since the last iteration */ if (mm_state->tail == &mm_list->fifo) mm_state->tail = &mm->lru_gen.list; } list_add_tail(&mm->lru_gen.list, &mm_list->fifo); spin_unlock(&mm_list->lock); } void lru_gen_del_mm(struct mm_struct *mm) { int nid; struct lru_gen_mm_list *mm_list; struct mem_cgroup *memcg = NULL; if (list_empty(&mm->lru_gen.list)) return; #ifdef CONFIG_MEMCG memcg = mm->lru_gen.memcg; #endif mm_list = get_mm_list(memcg); spin_lock(&mm_list->lock); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* where the current iteration continues after */ if (mm_state->head == &mm->lru_gen.list) mm_state->head = mm_state->head->prev; /* where the last iteration ended before */ if (mm_state->tail == &mm->lru_gen.list) mm_state->tail = mm_state->tail->next; } list_del_init(&mm->lru_gen.list); spin_unlock(&mm_list->lock); #ifdef CONFIG_MEMCG mem_cgroup_put(mm->lru_gen.memcg); mm->lru_gen.memcg = NULL; #endif } #ifdef CONFIG_MEMCG void lru_gen_migrate_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; struct task_struct *task = rcu_dereference_protected(mm->owner, true); VM_WARN_ON_ONCE(task->mm != mm); lockdep_assert_held(&task->alloc_lock); /* for mm_update_next_owner() */ if (mem_cgroup_disabled()) return; /* migration can happen before addition */ if (!mm->lru_gen.memcg) return; rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); lru_gen_add_mm(mm); } #endif #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { return NULL; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return NULL; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { return NULL; } #endif static void reset_mm_stats(struct lru_gen_mm_walk *walk, bool last) { int i; int hist; struct lruvec *lruvec = walk->lruvec; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); hist = lru_hist_from_seq(walk->seq); for (i = 0; i < NR_MM_STATS; i++) { WRITE_ONCE(mm_state->stats[hist][i], mm_state->stats[hist][i] + walk->mm_stats[i]); walk->mm_stats[i] = 0; } if (NR_HIST_GENS > 1 && last) { hist = lru_hist_from_seq(walk->seq + 1); for (i = 0; i < NR_MM_STATS; i++) WRITE_ONCE(mm_state->stats[hist][i], 0); } } static bool iterate_mm_list(struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; bool last = false; struct mm_struct *mm = NULL; struct lruvec *lruvec = walk->lruvec; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* * mm_state->seq is incremented after each iteration of mm_list. There * are three interesting cases for this page table walker: * 1. It tries to start a new iteration with a stale max_seq: there is * nothing left to do. * 2. It started the next iteration: it needs to reset the Bloom filter * so that a fresh set of PTE tables can be recorded. * 3. It ended the current iteration: it needs to reset the mm stats * counters and tell its caller to increment max_seq. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->seq); if (walk->seq <= mm_state->seq) goto done; if (!mm_state->head) mm_state->head = &mm_list->fifo; if (mm_state->head == &mm_list->fifo) first = true; do { mm_state->head = mm_state->head->next; if (mm_state->head == &mm_list->fifo) { WRITE_ONCE(mm_state->seq, mm_state->seq + 1); last = true; break; } /* force scan for those added after the last iteration */ if (!mm_state->tail || mm_state->tail == mm_state->head) { mm_state->tail = mm_state->head->next; walk->force_scan = true; } } while (!(mm = get_next_mm(walk))); done: if (*iter || last) reset_mm_stats(walk, last); spin_unlock(&mm_list->lock); if (mm && first) reset_bloom_filter(mm_state, walk->seq + 1); if (*iter) mmput_async(*iter); *iter = mm; return last; } static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long seq) { bool success = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < seq); if (seq > mm_state->seq) { mm_state->head = NULL; mm_state->tail = NULL; WRITE_ONCE(mm_state->seq, mm_state->seq + 1); success = true; } spin_unlock(&mm_list->lock); return success; } /****************************************************************************** * PID controller ******************************************************************************/ /* * A feedback loop based on Proportional-Integral-Derivative (PID) controller. * * The P term is refaulted/(evicted+protected) from a tier in the generation * currently being evicted; the I term is the exponential moving average of the * P term over the generations previously evicted, using the smoothing factor * 1/2; the D term isn't supported. * * The setpoint (SP) is always the first tier of one type; the process variable * (PV) is either any tier of the other type or any other tier of the same * type. * * The error is the difference between the SP and the PV; the correction is to * turn off protection when SP>PV or turn on protection when SP<PV. * * For future optimizations: * 1. The D term may discount the other two terms over time so that long-lived * generations can resist stale information. */ struct ctrl_pos { unsigned long refaulted; unsigned long total; int gain; }; static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->refaulted = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); pos->total = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) pos->total += lrugen->protected[hist][type][tier - 1]; pos->gain = gain; } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; lockdep_assert_held(&lruvec->lru_lock); if (!carryover && !clear) return; hist = lru_hist_from_seq(seq); for (tier = 0; tier < MAX_NR_TIERS; tier++) { if (carryover) { unsigned long sum; sum = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) sum += lrugen->protected[hist][type][tier - 1]; WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); if (tier) WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0); } } } static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) { /* * Return true if the PV has a limited number of refaults or a lower * refaulted/total than the SP. */ return pv->refaulted < MIN_LRU_BATCH || pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <= (sp->refaulted + 1) * pv->total * pv->gain; } /****************************************************************************** * the aging ******************************************************************************/ /* promote pages accessed through page tables */ static int folio_update_gen(struct folio *folio, int gen) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(!rcu_read_lock_held()); do { /* lru_gen_del_folio() has isolated this page? */ if (!(old_flags & LRU_GEN_MASK)) { /* for shrink_folio_list() */ new_flags = old_flags | BIT(PG_referenced); continue; } new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (gen + 1UL) << LRU_GEN_PGOFF; } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; /* folio_update_gen() has promoted this page? */ if (new_gen >= 0 && new_gen != old_gen) return new_gen; new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) new_flags |= BIT(PG_reclaim); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); lru_gen_update_size(lruvec, folio, old_gen, new_gen); return new_gen; } static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS); walk->batched++; walk->nr_pages[old_gen][type][zone] -= delta; walk->nr_pages[new_gen][type][zone] += delta; } static void reset_batch_size(struct lru_gen_mm_walk *walk) { int gen, type, zone; struct lruvec *lruvec = walk->lruvec; struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; for_each_gen_type_zone(gen, type, zone) { enum lru_list lru = type * LRU_INACTIVE_FILE; int delta = walk->nr_pages[gen][type][zone]; if (!delta) continue; walk->nr_pages[gen][type][zone] = 0; WRITE_ONCE(lrugen->nr_pages[gen][type][zone], lrugen->nr_pages[gen][type][zone] + delta); if (lru_gen_is_active(lruvec, gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); } } static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args) { struct address_space *mapping; struct vm_area_struct *vma = args->vma; struct lru_gen_mm_walk *walk = args->private; if (!vma_is_accessible(vma)) return true; if (is_vm_hugetlb_page(vma)) return true; if (!vma_has_recency(vma)) return true; if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) return true; if (vma == get_gate_vma(vma->vm_mm)) return true; if (vma_is_anonymous(vma)) return !walk->can_swap; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; mapping = vma->vm_file->f_mapping; if (mapping_unevictable(mapping)) return true; if (shmem_mapping(mapping)) return !walk->can_swap; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; } /* * Some userspace memory allocators map many single-page VMAs. Instead of * returning back to the PGD table for each of such VMAs, finish an entire PMD * table to reduce zigzags and improve cache performance. */ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args, unsigned long *vm_start, unsigned long *vm_end) { unsigned long start = round_up(*vm_end, size); unsigned long end = (start | ~mask) + 1; VMA_ITERATOR(vmi, args->mm, start); VM_WARN_ON_ONCE(mask & size); VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask)); for_each_vma(vmi, args->vma) { if (end && end <= args->vma->vm_start) return false; if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) continue; *vm_start = max(start, args->vma->vm_start); *vm_end = min(end - 1, args->vma->vm_end - 1) + 1; return true; } return false; } static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pte_pfn(pte); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pte_present(pte) || is_zero_pfn(pfn)) return -1; if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pmd_pfn(pmd); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) return -1; if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, struct pglist_data *pgdat, bool can_swap) { struct folio *folio; /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return NULL; folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg_rcu(folio) != memcg) return NULL; /* file VMAs can contain anon pages from COW */ if (!folio_is_file_lru(folio) && !can_swap) return NULL; return folio; } static bool suitable_to_scan(int total, int young) { int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); /* suitable if the average number of young PTEs per cacheline is >=1 */ return young * n >= total; } static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); pte = pte_offset_map_nolock(args->mm, pmd, start & PMD_MASK, &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { pte_unmap(pte); return false; } arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; struct folio *folio; pte_t ptent = ptep_get(pte + i); total++; walk->mm_stats[MM_LEAF_TOTAL]++; pfn = get_pte_pfn(ptent, args->vma, addr); if (pfn == -1) continue; if (!pte_young(ptent)) { walk->mm_stats[MM_LEAF_OLD]++; continue; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; walk->mm_stats[MM_LEAF_YOUNG]++; if (pte_dirty(ptent) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); } if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte, ptl); return suitable_to_scan(total, young); } static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *first) { int i; pmd_t *pmd; spinlock_t *ptl; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ if (*first == -1) { *first = addr; bitmap_zero(bitmap, MIN_LRU_BATCH); return; } i = addr == -1 ? 0 : pmd_index(addr) - pmd_index(*first); if (i && i <= MIN_LRU_BATCH) { __set_bit(i - 1, bitmap); return; } pmd = pmd_offset(pud, *first); ptl = pmd_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) goto done; arch_enter_lazy_mmu_mode(); do { unsigned long pfn; struct folio *folio; /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; pfn = get_pmd_pfn(pmd[i], vma, addr); if (pfn == -1) goto next; if (!pmd_trans_huge(pmd[i])) { if (should_clear_pmd_young()) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: *first = -1; } static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pmd_t *pmd; unsigned long next; unsigned long addr; struct vm_area_struct *vma; DECLARE_BITMAP(bitmap, MIN_LRU_BATCH); unsigned long first = -1; struct lru_gen_mm_walk *walk = args->private; struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* * Finish an entire PMD in two passes: the first only reaches to PTE * tables to avoid taking the PMD lock; the second, if necessary, takes * the PMD lock to clear the accessed bit in PMD entries. */ pmd = pmd_offset(pud, start & PUD_MASK); restart: /* walk_pte_range() may call get_next_vma() */ vma = args->vma; for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { pmd_t val = pmdp_get_lockless(pmd + i); next = pmd_addr_end(addr, end); if (!pmd_present(val) || is_huge_zero_pmd(val)) { walk->mm_stats[MM_LEAF_TOTAL]++; continue; } if (pmd_trans_huge(val)) { unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); walk->mm_stats[MM_LEAF_TOTAL]++; if (!pmd_young(val)) { walk->mm_stats[MM_LEAF_OLD]++; continue; } /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } walk->mm_stats[MM_NONLEAF_TOTAL]++; if (should_clear_pmd_young()) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); } if (!walk->force_scan && !test_bloom_filter(mm_state, walk->seq, pmd + i)) continue; walk->mm_stats[MM_NONLEAF_FOUND]++; if (!walk_pte_range(&val, addr, next, args)) continue; walk->mm_stats[MM_NONLEAF_ADDED]++; /* carry over to the next generation */ update_bloom_filter(mm_state, walk->seq + 1, pmd + i); } walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first); if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) goto restart; } static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pud_t *pud; unsigned long addr; unsigned long next; struct lru_gen_mm_walk *walk = args->private; VM_WARN_ON_ONCE(p4d_leaf(*p4d)); pud = pud_offset(p4d, start & P4D_MASK); restart: for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { pud_t val = READ_ONCE(pud[i]); next = pud_addr_end(addr, end); if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) continue; walk_pmd_range(&val, addr, next, args); if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; } } if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) goto restart; end = round_up(end, P4D_SIZE); done: if (!end || !args->vma) return 1; walk->next_addr = max(end, args->vma->vm_start); return -EAGAIN; } static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) { static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; int err; struct lruvec *lruvec = walk->lruvec; struct mem_cgroup *memcg = lruvec_memcg(lruvec); walk->next_addr = FIRST_USER_ADDRESS; do { DEFINE_MAX_SEQ(lruvec); err = -EBUSY; /* another thread might have called inc_max_seq() */ if (walk->seq != max_seq) break; /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) break; /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); mmap_read_unlock(mm); } mem_cgroup_unlock_pages(); if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(walk); spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while (err == -EAGAIN); } static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; if (pgdat && current_is_kswapd()) { VM_WARN_ON_ONCE(walk); walk = &pgdat->mm_walk; } else if (!walk && force_alloc) { VM_WARN_ON_ONCE(current_is_kswapd()); walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); } current->reclaim_state->mm_walk = walk; return walk; } static void clear_mm_walk(void) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); current->reclaim_state->mm_walk = NULL; if (!current_is_kswapd()) kfree(walk); } static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); if (type == LRU_GEN_ANON && !can_swap) goto done; /* prevent cold/hot inversion if force_scan is true */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); if (!--remaining) return false; } } done: reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); return true; } static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) { int gen, type, zone; bool success = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ for (type = !can_swap; type < ANON_AND_FILE; type++) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } min_seq[type]++; } next: ; } /* see the comment on lru_gen_folio */ if (can_swap) { min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); } for (type = !can_swap; type < ANON_AND_FILE; type++) { if (min_seq[type] == lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); success = true; } return success; } static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, bool can_swap, bool force_scan) { bool success; int prev, next; int type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; restart: if (seq < READ_ONCE(lrugen->max_seq)) return false; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); success = seq == lrugen->max_seq; if (!success) goto unlock; for (type = ANON_AND_FILE - 1; type >= 0; type--) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap)); if (inc_min_seq(lruvec, type, can_swap)) continue; spin_unlock_irq(&lruvec->lru_lock); cond_resched(); goto restart; } /* * Update the active/inactive LRU sizes for compatibility. Both sides of * the current max_seq need to be covered, since max_seq+1 can overlap * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do * overlap, cold/hot inversion happens. */ prev = lru_gen_from_seq(lrugen->max_seq - 1); next = lru_gen_from_seq(lrugen->max_seq + 1); for (type = 0; type < ANON_AND_FILE; type++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { enum lru_list lru = type * LRU_INACTIVE_FILE; long delta = lrugen->nr_pages[prev][type][zone] - lrugen->nr_pages[next][type][zone]; if (!delta) continue; __update_lru_size(lruvec, lru, zone, delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); } } for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); unlock: spin_unlock_irq(&lruvec->lru_lock); return success; } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq, bool can_swap, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq)); if (!mm_state) return inc_max_seq(lruvec, seq, can_swap, force_scan); /* see the comment in iterate_mm_list() */ if (seq <= READ_ONCE(mm_state->seq)) return false; /* * If the hardware doesn't automatically set the accessed bit, fallback * to lru_gen_look_around(), which only clears the accessed bit in a * handful of PTEs. Spreading the work out over a period of time usually * is less efficient, but it avoids bursty page faults. */ if (!should_walk_mmu()) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk = set_mm_walk(NULL, true); if (!walk) { success = iterate_mm_list_nowalk(lruvec, seq); goto done; } walk->lruvec = lruvec; walk->seq = seq; walk->can_swap = can_swap; walk->force_scan = force_scan; do { success = iterate_mm_list(walk, &mm); if (mm) walk_mm(mm, walk); } while (mm); done: if (success) { success = inc_max_seq(lruvec, seq, can_swap, force_scan); WARN_ON_ONCE(!success); } return success; } /****************************************************************************** * working set protection ******************************************************************************/ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) { int priority; unsigned long reclaimable; if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* * Determine the initial priority based on * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); /* * The estimation is based on LRU pages only, so cap it to prevent * overshoots of shrinker objects by large margins. */ sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); } static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; unsigned long total = 0; bool can_swap = get_swappiness(lruvec, sc); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); for (type = !can_swap; type < ANON_AND_FILE; type++) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } /* whether the size is big enough to be helpful */ return mem_cgroup_online(memcg) ? (total >> sc->priority) : total; } static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) { int gen; unsigned long birth; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); if (mem_cgroup_below_min(NULL, memcg)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; /* see the comment on lru_gen_folio */ gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); return time_is_before_jiffies(birth + min_ttl); } /* to protect the working set of the last N jiffies */ static unsigned long lru_gen_min_ttl __read_mostly; static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); bool reclaimable = !min_ttl; VM_WARN_ON_ONCE(!current_is_kswapd()); set_initial_priority(pgdat, sc); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); mem_cgroup_calculate_protection(NULL, memcg); if (!reclaimable) reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* * The main goal is to OOM kill if every generation from all memcgs is * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ if (!reclaimable && mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; out_of_memory(&oc); mutex_unlock(&oom_lock); } } /****************************************************************************** * rmap/PT walk feedback ******************************************************************************/ /* * This function exploits spatial locality when shrink_folio_list() walks the * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If * the scan was done cacheline efficiently, it adds the PMD entry pointing to * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; int young = 0; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); bool can_swap = !folio_is_file_lru(folio); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); DEFINE_MAX_SEQ(lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); if (spin_is_contended(pvmw->ptl)) return; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) return; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; else if (end - addr < MIN_LRU_BATCH * PAGE_SIZE / 2) start = end - MIN_LRU_BATCH * PAGE_SIZE; else { start = addr - MIN_LRU_BATCH * PAGE_SIZE / 2; end = addr + MIN_LRU_BATCH * PAGE_SIZE / 2; } } /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) return; arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; pte_t ptent = ptep_get(pte + i); pfn = get_pte_pfn(ptent, vma, addr); if (pfn == -1) continue; if (!pte_young(ptent)) continue; folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; if (pte_dirty(ptent) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); if (walk) { old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); continue; } old_gen = folio_lru_gen(folio); if (old_gen < 0) folio_set_referenced(folio); else if (old_gen != new_gen) folio_activate(folio); } arch_leave_lazy_mmu_mode(); mem_cgroup_unlock_pages(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); } /****************************************************************************** * memcg LRU ******************************************************************************/ /* see the comment on MEMCG_NR_GENS */ enum { MEMCG_LRU_NOP, MEMCG_LRU_HEAD, MEMCG_LRU_TAIL, MEMCG_LRU_OLD, MEMCG_LRU_YOUNG, }; static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) { int seg; int old, new; unsigned long flags; int bin = get_random_u32_below(MEMCG_NR_BINS); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irqsave(&pgdat->memcg_lru.lock, flags); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); seg = 0; new = old = lruvec->lrugen.gen; /* see the comment on MEMCG_NR_GENS */ if (op == MEMCG_LRU_HEAD) seg = MEMCG_LRU_HEAD; else if (op == MEMCG_LRU_TAIL) seg = MEMCG_LRU_TAIL; else if (op == MEMCG_LRU_OLD) new = get_memcg_gen(pgdat->memcg_lru.seq); else if (op == MEMCG_LRU_YOUNG) new = get_memcg_gen(pgdat->memcg_lru.seq + 1); else VM_WARN_ON_ONCE(true); WRITE_ONCE(lruvec->lrugen.seg, seg); WRITE_ONCE(lruvec->lrugen.gen, new); hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); else hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags); } #ifdef CONFIG_MEMCG void lru_gen_online_memcg(struct mem_cgroup *memcg) { int gen; int nid; int bin = get_random_u32_below(MEMCG_NR_BINS); for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); gen = get_memcg_gen(pgdat->memcg_lru.seq); lruvec->lrugen.gen = gen; hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_offline_memcg(struct mem_cgroup *memcg) { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); } } void lru_gen_release_memcg(struct mem_cgroup *memcg) { int gen; int nid; for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); if (hlist_nulls_unhashed(&lruvec->lrugen.list)) goto unlock; gen = lruvec->lrugen.gen; hlist_nulls_del_init_rcu(&lruvec->lrugen.list); pgdat->memcg_lru.nr_memcgs[gen]--; if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); unlock: spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); } #endif /* CONFIG_MEMCG */ /****************************************************************************** * the eviction ******************************************************************************/ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc, int tier_idx) { bool success; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); int tier = lru_tier_from_refs(refs); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); /* unevictable */ if (!folio_evictable(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, delta); return true; } /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* protected */ if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); WRITE_ONCE(lrugen->protected[hist][type][tier - 1], lrugen->protected[hist][type][tier - 1] + delta); return true; } /* ineligible */ if (zone > sc->reclaim_idx || skip_cma(folio, sc)) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* waiting for writeback */ if (folio_test_locked(folio) || folio_test_writeback(folio) || (type == LRU_GEN_FILE && folio_test_dirty(folio))) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } return false; } static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc) { bool success; /* swap constrained */ if (!(sc->gfp_mask & __GFP_IO) && (folio_test_dirty(folio) || (folio_test_anon(folio) && !folio_test_swapcache(folio)))) return false; /* raced with release_pages() */ if (!folio_try_get(folio)) return false; /* raced with another isolation */ if (!folio_test_clear_lru(folio)) { folio_put(folio); return false; } /* see the comment on MAX_NR_TIERS */ if (!folio_test_referenced(folio)) set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); folio_clear_referenced(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); return true; } static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { int i; int gen; enum vm_event_item item; int sorted = 0; int scanned = 0; int isolated = 0; int skipped = 0; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); if (get_nr_gens(lruvec, type) == MIN_NR_GENS) return 0; gen = lru_gen_from_seq(lrugen->min_seq[type]); for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); int skipped_zone = 0; int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); scanned += delta; if (sort_folio(lruvec, folio, sc, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); isolated += delta; } else { list_move(&folio->lru, &moved); skipped_zone += delta; } if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) break; } if (skipped_zone) { list_splice(&moved, head); __count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone); skipped += skipped_zone; } if (!remaining || isolated >= MIN_LRU_BATCH) break; } item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); } __count_memcg_events(memcg, item, isolated); __count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. */ return isolated || !remaining ? scanned : 0; } static int get_tier_idx(struct lruvec *lruvec, int type) { int tier; struct ctrl_pos sp, pv; /* * To leave a margin for fluctuations, use a larger gain factor (1:2). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ read_ctrl_pos(lruvec, type, 0, 1, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, 2, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } return tier - 1; } static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx) { int type, tier; struct ctrl_pos sp, pv; int gain[ANON_AND_FILE] = { swappiness, MAX_SWAPPINESS - swappiness }; /* * Compare the first tier of anon with that of file to determine which * type to scan. Also need to compare other tiers of the selected type * with the first tier of the other type to determine the last tier (of * the selected type) to evict. */ read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp); read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv); type = positive_ctrl_err(&sp, &pv); read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, gain[type], &pv); if (!positive_ctrl_err(&sp, &pv)) break; } *tier_idx = tier - 1; return type; } static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; int type; int scanned; int tier = -1; DEFINE_MIN_SEQ(lruvec); /* * Try to make the obvious choice first, and if anon and file are both * available from the same generation, * 1. Interpret swappiness 1 as file first and MAX_SWAPPINESS as anon * first. * 2. If !__GFP_IO, file first since clean pagecache is more likely to * exist than clean swapcache. */ if (!swappiness) type = LRU_GEN_FILE; else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE]) type = LRU_GEN_ANON; else if (swappiness == 1) type = LRU_GEN_FILE; else if (swappiness == MAX_SWAPPINESS) type = LRU_GEN_ANON; else if (!(sc->gfp_mask & __GFP_IO)) type = LRU_GEN_FILE; else type = get_type_to_scan(lruvec, swappiness, &tier); for (i = !swappiness; i < ANON_AND_FILE; i++) { if (tier < 0) tier = get_tier_idx(lruvec, type); scanned = scan_folios(lruvec, sc, type, tier, list); if (scanned) break; type = !type; tier = -1; } *type_scanned = type; return scanned; } static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { int type; int scanned; int reclaimed; LIST_HEAD(list); LIST_HEAD(clean); struct folio *folio; struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irq(&lruvec->lru_lock); scanned = isolate_folios(lruvec, sc, swappiness, &type, &list); scanned += try_to_inc_min_seq(lruvec, swappiness); if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); if (list_empty(&list)) return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } if (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ if (folio_test_workingset(folio)) folio_set_referenced(folio); continue; } if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) || folio_mapped(folio) || folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_writeback(folio)) { /* don't add rejected folios to the oldest generation */ set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, BIT(PG_active)); continue; } /* retry folios that may have missed folio_rotate_reclaimable() */ list_move(&folio->lru, &clean); } spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &list); walk = current->reclaim_state->mm_walk; if (walk && walk->batched) { walk->lruvec = lruvec; reset_batch_size(walk); } item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); __count_memcg_events(memcg, item, reclaimed); __count_vm_events(PGSTEAL_ANON + type, reclaimed); spin_unlock_irq(&lruvec->lru_lock); list_splice_init(&clean, &list); if (!list_empty(&list)) { skip_retry = true; goto retry; } return scanned; } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, bool can_swap, unsigned long *nr_to_scan) { int gen, type, zone; unsigned long old = 0; unsigned long young = 0; unsigned long total = 0; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); /* whether this lruvec is completely out of cold folios */ if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) { *nr_to_scan = 0; return true; } for (type = !can_swap; type < ANON_AND_FILE; type++) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { unsigned long size = 0; gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); total += size; if (seq == max_seq) young += size; else if (seq + MIN_NR_GENS == max_seq) old += size; } } *nr_to_scan = total; /* * The aging tries to be lazy to reduce the overhead, while the eviction * stalls when the number of generations reaches MIN_NR_GENS. Hence, the * ideal number of generations is MIN_NR_GENS+1. */ if (min_seq[!can_swap] + MIN_NR_GENS < max_seq) return false; /* * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1) * of the total number of pages for each generation. A reasonable range * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The * aging cares about the upper bound of hot pages, while the eviction * cares about the lower bound of cold pages. */ if (young * MIN_NR_GENS > total) return true; if (old * (MIN_NR_GENS + 2) < total) return true; return false; } /* * For future optimizations: * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap) { bool success; unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) return -1; success = should_run_aging(lruvec, max_seq, can_swap, &nr_to_scan); /* try to scrape all its memory if this memcg was deleted */ if (nr_to_scan && !mem_cgroup_online(memcg)) return nr_to_scan; /* try to get away with not aging at the default priority */ if (!success || sc->priority == DEF_PRIORITY) return nr_to_scan >> sc->priority; /* stop scanning this lruvec as it's low on cold folios */ return try_to_inc_max_seq(lruvec, max_seq, can_swap, false) ? -1 : 0; } static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { int i; enum zone_watermarks mark; /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) return false; if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) return true; /* check the order to exclude compaction-induced reclaim */ if (!current_is_kswapd() || sc->order) return false; mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? WMARK_PROMO : WMARK_HIGH; for (i = 0; i <= sc->reclaim_idx; i++) { struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) return false; } /* kswapd should abort if all eligible zones are safe */ return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; int swappiness = get_swappiness(lruvec, sc); while (true) { int delta; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); if (nr_to_scan <= 0) break; delta = evict_folios(lruvec, sc, swappiness); if (!delta) break; scanned += delta; if (scanned >= nr_to_scan) break; if (should_abort_scan(lruvec, sc)) break; cond_resched(); } /* whether this lruvec should be rotated */ return nr_to_scan < 0; } static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) { bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); /* lru_gen_age_node() called mem_cgroup_calculate_protection() */ if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); } success = try_to_shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); flush_reclaim_state(sc); if (success && mem_cgroup_online(memcg)) return MEMCG_LRU_YOUNG; if (!success && lruvec_is_sizable(lruvec, sc)) return 0; /* one retry if offlined or too small */ return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) { int op; int gen; int bin; int first_bin; struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct hlist_nulls_node *pos; gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; rcu_read_lock(); hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) { if (op) { lru_gen_rotate_memcg(lruvec, op); op = 0; } mem_cgroup_put(memcg); memcg = NULL; if (gen != READ_ONCE(lrugen->gen)) continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); if (!mem_cgroup_tryget(memcg)) { lru_gen_release_memcg(memcg); memcg = NULL; continue; } rcu_read_unlock(); op = shrink_one(lruvec, sc); rcu_read_lock(); if (should_abort_scan(lruvec, sc)) break; } rcu_read_unlock(); if (op) lru_gen_rotate_memcg(lruvec, op); mem_cgroup_put(memcg); if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ if (gen != get_nulls_value(pos)) goto restart; /* try the rest of the bins of the current generation */ bin = get_memcg_bin(bin + 1); if (bin != first_bin) goto restart; } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { struct blk_plug plug; VM_WARN_ON_ONCE(root_reclaim(sc)); VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap); lru_add_drain(); blk_start_plug(&plug); set_mm_walk(NULL, sc->proactive); if (try_to_shrink_lruvec(lruvec, sc)) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG); clear_mm_walk(); blk_finish_plug(&plug); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { struct blk_plug plug; unsigned long reclaimed = sc->nr_reclaimed; VM_WARN_ON_ONCE(!root_reclaim(sc)); /* * Unmapped clean folios are already prioritized. Scanning for more of * them is likely futile and can cause high reclaim latency when there * is a large number of memcgs. */ if (!sc->may_writepage || !sc->may_unmap) goto done; lru_add_drain(); blk_start_plug(&plug); set_mm_walk(pgdat, sc->proactive); set_initial_priority(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed = 0; if (mem_cgroup_disabled()) shrink_one(&pgdat->__lruvec, sc); else shrink_many(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed += reclaimed; clear_mm_walk(); blk_finish_plug(&plug); done: /* kswapd should never fail */ pgdat->kswapd_failures = 0; } /****************************************************************************** * state change ******************************************************************************/ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; for_each_evictable_lru(lru) { if (!list_empty(&lruvec->lists[lru])) return false; } } else { int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } return true; } static bool fill_evictable(struct lruvec *lruvec) { enum lru_list lru; int remaining = MAX_LRU_BATCH; for_each_evictable_lru(lru) { int type = is_file_lru(lru); bool active = is_active_lru(lru); struct list_head *head = &lruvec->lists[lru]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); lruvec_del_folio(lruvec, folio); success = lru_gen_add_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); if (!--remaining) return false; } } return true; } static bool drain_evictable(struct lruvec *lruvec) { int gen, type, zone; int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); success = lru_gen_del_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); lruvec_add_folio(lruvec, folio); if (!--remaining) return false; } } return true; } static void lru_gen_change_state(bool enabled) { static DEFINE_MUTEX(state_mutex); struct mem_cgroup *memcg; cgroup_lock(); cpus_read_lock(); get_online_mems(); mutex_lock(&state_mutex); if (enabled == lru_gen_enabled()) goto unlock; if (enabled) static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); else static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); VM_WARN_ON_ONCE(!state_is_valid(lruvec)); lruvec->lrugen.enabled = enabled; while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); unlock: mutex_unlock(&state_mutex); put_online_mems(); cpus_read_unlock(); cgroup_unlock(); } /****************************************************************************** * sysfs interface ******************************************************************************/ static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned int msecs; if (kstrtouint(buf, 0, &msecs)) return -EINVAL; WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); return len; } static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms); static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; if (get_cap(LRU_GEN_CORE)) caps |= BIT(LRU_GEN_CORE); if (should_walk_mmu()) caps |= BIT(LRU_GEN_MM_WALK); if (should_clear_pmd_young()) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return sysfs_emit(buf, "0x%04x\n", caps); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; unsigned int caps; if (tolower(*buf) == 'n') caps = 0; else if (tolower(*buf) == 'y') caps = -1; else if (kstrtouint(buf, 0, &caps)) return -EINVAL; for (i = 0; i < NR_LRU_GEN_CAPS; i++) { bool enabled = caps & BIT(i); if (i == LRU_GEN_CORE) lru_gen_change_state(enabled); else if (enabled) static_branch_enable(&lru_gen_caps[i]); else static_branch_disable(&lru_gen_caps[i]); } return len; } static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; static const struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; /****************************************************************************** * debugfs interface ******************************************************************************/ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg; loff_t nr_to_skip = *pos; m->private = kvmalloc(PATH_MAX, GFP_KERNEL); if (!m->private) return ERR_PTR(-ENOMEM); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node_state(nid, N_MEMORY) { if (!nr_to_skip--) return get_lruvec(memcg, nid); } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); return NULL; } static void lru_gen_seq_stop(struct seq_file *m, void *v) { if (!IS_ERR_OR_NULL(v)) mem_cgroup_iter_break(NULL, lruvec_memcg(v)); kvfree(m->private); m->private = NULL; } static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) { int nid = lruvec_pgdat(v)->node_id; struct mem_cgroup *memcg = lruvec_memcg(v); ++*pos; nid = next_memory_node(nid); if (nid == MAX_NUMNODES) { memcg = mem_cgroup_iter(NULL, memcg, NULL); if (!memcg) return NULL; nid = first_memory_node; } return get_lruvec(memcg, nid); } static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, unsigned long seq) { int i; int type, tier; int hist = lru_hist_from_seq(seq); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { const char *s = " "; unsigned long n[3] = {}; if (seq == max_seq) { s = "RT "; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]); } for (i = 0; i < 3; i++) seq_printf(m, " %10lu%c", n[i], s[i]); } seq_putc(m, '\n'); } if (!mm_state) return; seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { const char *s = " "; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { s = "LOYNFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { s = "loynfa"; n = READ_ONCE(mm_state->stats[hist][i]); } seq_printf(m, " %10lu%c", n, s[i]); } seq_putc(m, '\n'); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static int lru_gen_seq_show(struct seq_file *m, void *v) { unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (nid == first_memory_node) { const char *path = memcg ? m->private : ""; #ifdef CONFIG_MEMCG if (memcg) cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); #endif seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); } seq_printf(m, " node %5d\n", nid); if (!full) seq = min_seq[LRU_GEN_ANON]; else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else seq = 0; for (; seq <= max_seq; seq++) { int type, zone; int gen = lru_gen_from_seq(seq); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); for (type = 0; type < ANON_AND_FILE; type++) { unsigned long size = 0; char mark = full && seq < min_seq[type] ? 'x' : ' '; for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); seq_printf(m, " %10lu%c", size, mark); } seq_putc(m, '\n'); if (full) lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); } return 0; } static const struct seq_operations lru_gen_seq_ops = { .start = lru_gen_seq_start, .stop = lru_gen_seq_stop, .next = lru_gen_seq_next, .show = lru_gen_seq_show, }; static int run_aging(struct lruvec *lruvec, unsigned long seq, bool can_swap, bool force_scan) { DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (seq < max_seq) return 0; if (seq > max_seq) return -EINVAL; if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq) return -ERANGE; try_to_inc_max_seq(lruvec, max_seq, can_swap, force_scan); return 0; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long nr_to_reclaim) { DEFINE_MAX_SEQ(lruvec); if (seq + MIN_NR_GENS > max_seq) return -EINVAL; sc->nr_reclaimed = 0; while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); if (seq < min_seq[!swappiness]) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) return 0; if (!evict_folios(lruvec, sc, swappiness)) return 0; cond_resched(); } return -EINTR; } static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long opt) { struct lruvec *lruvec; int err = -EINVAL; struct mem_cgroup *memcg = NULL; if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) return -EINVAL; if (!mem_cgroup_disabled()) { rcu_read_lock(); memcg = mem_cgroup_from_id(memcg_id); if (!mem_cgroup_tryget(memcg)) memcg = NULL; rcu_read_unlock(); if (!memcg) return -EINVAL; } if (memcg_id != mem_cgroup_id(memcg)) goto done; lruvec = get_lruvec(memcg, nid); if (swappiness < MIN_SWAPPINESS) swappiness = get_swappiness(lruvec, sc); else if (swappiness > MAX_SWAPPINESS) goto done; switch (cmd) { case '+': err = run_aging(lruvec, seq, swappiness, opt); break; case '-': err = run_eviction(lruvec, seq, sc, swappiness, opt); break; } done: mem_cgroup_put(memcg); return err; } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, size_t len, loff_t *pos) { void *buf; char *cur, *next; unsigned int flags; struct blk_plug plug; int err = -EINVAL; struct scan_control sc = { .may_writepage = true, .may_unmap = true, .may_swap = true, .reclaim_idx = MAX_NR_ZONES - 1, .gfp_mask = GFP_KERNEL, }; buf = kvmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, src, len)) { kvfree(buf); return -EFAULT; } set_task_reclaim_state(current, &sc.reclaim_state); flags = memalloc_noreclaim_save(); blk_start_plug(&plug); if (!set_mm_walk(NULL, true)) { err = -ENOMEM; goto done; } next = buf; next[len] = '\0'; while ((cur = strsep(&next, ",;\n"))) { int n; int end; char cmd; unsigned int memcg_id; unsigned int nid; unsigned long seq; unsigned int swappiness = -1; unsigned long opt = -1; cur = skip_spaces(cur); if (!*cur) continue; n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid, &seq, &end, &swappiness, &end, &opt, &end); if (n < 4 || cur[end]) { err = -EINVAL; break; } err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); if (err) break; } done: clear_mm_walk(); blk_finish_plug(&plug); memalloc_noreclaim_restore(flags); set_task_reclaim_state(current, NULL); kvfree(buf); return err ? : len; } static int lru_gen_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &lru_gen_seq_ops); } static const struct file_operations lru_gen_rw_fops = { .open = lru_gen_seq_open, .read = seq_read, .write = lru_gen_seq_write, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations lru_gen_ro_fops = { .open = lru_gen_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; /****************************************************************************** * initialization ******************************************************************************/ void lru_gen_init_pgdat(struct pglist_data *pgdat) { int i, j; spin_lock_init(&pgdat->memcg_lru.lock); for (i = 0; i < MEMCG_NR_GENS; i++) { for (j = 0; j < MEMCG_NR_BINS; j++) INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i); } } void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); for (i = 0; i <= MIN_NR_GENS + 1; i++) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); if (mm_state) mm_state->seq = MIN_NR_GENS; } #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg) { struct lru_gen_mm_list *mm_list = get_mm_list(memcg); if (!mm_list) return; INIT_LIST_HEAD(&mm_list->fifo); spin_lock_init(&mm_list->lock); } void lru_gen_exit_memcg(struct mem_cgroup *memcg) { int i; int nid; struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo)); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); lruvec->lrugen.list.next = LIST_POISON1; if (!mm_state) continue; for (i = 0; i < NR_BLOOM_FILTERS; i++) { bitmap_free(mm_state->filters[i]); mm_state->filters[i] = NULL; } } } #endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) { BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); return 0; }; late_initcall(init_lru_gen); #else /* !CONFIG_LRU_GEN */ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; if (lru_gen_enabled() && !root_reclaim(sc)) { lru_gen_shrink_lruvec(lruvec, sc); return; } get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (gfp_compaction_allowed(sc->gfp_mask) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return false; if (compaction_suitable(zone, sc->order, sc->reclaim_idx)) return false; } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup_reclaim_cookie reclaim = { .pgdat = pgdat, }; struct mem_cgroup_reclaim_cookie *partial = &reclaim; struct mem_cgroup *memcg; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree, using an iterator state that * persists across invocations. This strikes a balance between * fairness and allocation latency. * * For kswapd, reliable forward progress is more important * than a quick return to idle. Always do full walks. */ if (current_is_kswapd() || sc->memcg_full_walk) partial = NULL; memcg = mem_cgroup_iter(target_memcg, NULL, partial); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(target_memcg, memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(target_memcg, memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); /* If partial walks are allowed, bail once goal is reached */ if (partial && sc->nr_reclaimed >= sc->nr_to_reclaim) { mem_cgroup_iter_break(target_memcg, memcg); break; } } while ((memcg = mem_cgroup_iter(target_memcg, memcg, partial))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed; struct lruvec *target_lruvec; bool reclaimable = false; if (lru_gen_enabled() && root_reclaim(sc)) { lru_gen_shrink_node(pgdat, sc); return; } target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; prepare_scan_control(pgdat, sc); shrink_node_memcgs(pgdat, sc); flush_reclaim_state(sc); nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed; /* Record the subtree's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, nr_node_reclaimed); if (nr_node_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so forcibly stall * until some pages complete writeback. */ if (sc->nr.immediate) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* * Tag a node/memcg as congested if all the dirty pages were marked * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in reclaim_throttle(). */ if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) { if (cgroup_reclaim(sc) && writeback_throttling_sane(sc)) set_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags); if (current_is_kswapd()) set_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags); } /* * Stall direct reclaim for IO completions if the lruvec is * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && (test_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags) || test_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags))) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; else if (sc->cache_trim_mode) sc->cache_trim_mode_failed = 1; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; if (!gfp_compaction_allowed(sc->gfp_mask)) return false; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return true; /* Compaction cannot yet proceed. Do reclaim. */ if (!compaction_suitable(zone, sc->order, sc->reclaim_idx)) return false; /* * Compaction is already possible, but it takes time to run and there * are potentially other callers using the pages just freed. So proceed * with reclaim to make a buffer of free pages available to give * compaction a reasonable chance of completing and allocating the page. * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone) + compact_gap(sc->order); return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) { /* * If reclaim is making progress greater than 12% efficiency then * wake all the NOPROGRESS throttled tasks. */ if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; if (waitqueue_active(wqh)) wake_up(wqh); return; } /* * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages * under writeback and marked for immediate reclaim at the tail of the * LRU. */ if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } if (!first_pgdat) first_pgdat = zone->zone_pgdat; /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } if (first_pgdat) consider_reclaim_throttle(first_pgdat, sc); /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[WORKINGSET_ANON] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[WORKINGSET_FILE] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { if (!sc->proactive) vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * In most cases, direct reclaimers can do partial walks * through the cgroup tree to meet the reclaim goal while * keeping latency low. Since the iterator state is shared * among all direct reclaim invocations (to retain fairness * among cgroups), though, high concurrency can result in * individual threads not seeing enough cgroups to make * meaningful forward progress. Avoid false OOMs in this case. */ if (!sc->memcg_full_walk) { sc->priority = initial_priority; sc->memcg_full_walk = 1; goto retry; } /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone)) continue; if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state_snapshot(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); else /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_PAGE_ORDER >= S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options, int *swappiness) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .proactive_swappiness = swappiness, .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (lru_gen_enabled()) { lru_gen_age_node(pgdat, sc); return; } if (!can_age_anon_pages(pgdat, sc)) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) mark = wmark_pages(zone, WMARK_PROMO); else mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_NODE_CONGESTED, &lruvec->flags); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; unsigned long nr_reclaimed = sc->nr_reclaimed; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; /* account for progress from mm_account_reclaimed_pages() */ return max(sc->nr_scanned, sc->nr_reclaimed - nr_reclaimed) >= sc->nr_to_reclaim; } /* Page allocator PCP high watermark is lowered if reclaim is active. */ static inline void update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) { int i; struct zone *zone; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (active) set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); else clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); } } static inline void set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, true); } static inline void clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, false); } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; bool was_frozen; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging, to give pages a chance to be * referenced before reclaiming. All pages are rotated * regardless of classzone as this is about consistent aging. */ kswapd_age_node(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = memcg1_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(_THIS_IP_); ret = kthread_freezable_should_stop(&was_frozen); __fs_reclaim_acquire(_THIS_IP_); if (was_frozen || ret) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); /* * Restart only if it went through the priority loop all the way, * but cache_trim_mode didn't work. */ if (!sc.nr_reclaimed && sc.priority < 1 && !sc.no_cache_trim_mode && sc.cache_trim_mode_failed) { sc.no_cache_trim_mode = 1; goto restart; } if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: clear_reclaim_active(pgdat, highest_zoneidx); /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool was_frozen; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); if (kthread_freezable_should_stop(&was_frozen)) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (was_frozen) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. */ void __meminit kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); pgdat_kswapd_lock(pgdat); if (!pgdat->kswapd) { pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ pr_err("Failed to start kswapd on node %d，ret=%ld\n", nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); pgdat->kswapd = NULL; } } pgdat_kswapd_unlock(pgdat); } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void __meminit kswapd_stop(int nid) { pg_data_t *pgdat = NODE_DATA(nid); struct task_struct *kswapd; pgdat_kswapd_lock(pgdat); kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); pgdat->kswapd = NULL; } pgdat_kswapd_unlock(pgdat); } static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); psi_memstall_enter(&pflags); delayacct_freepages_start(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP */ noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); delayacct_freepages_end(); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (!ret) count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list * @fbatch: Batch of lru folios to check. * * Checks folios for evictability, if an evictable folio is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru folios. */ void check_move_unevictable_folios(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < fbatch->nr; i++) { struct folio *folio = fbatch->folios[i]; int nr_pages = folio_nr_pages(folio); pgscanned += nr_pages; /* block memcg migration while the folio moves between lrus */ if (!folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_evictable(folio) && folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); pgrescued += nr_pages; } folio_set_lru(folio); } if (lruvec) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); unlock_page_lruvec_irq(lruvec); } else if (pgscanned) { count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } EXPORT_SYMBOL_GPL(check_move_unevictable_folios); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * A 'generic' spinlock implementation that is based on MCS locks. For an * architecture that's looking for a 'generic' spinlock, please first consider * ticket-lock.h and only come looking here when you've considered all the * constraints below and can show your hardware does actually perform better * with qspinlock. * * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no * weaker than RCtso if you're power), where regular code only expects atomic_t * to be RCpc. * * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set * of atomic operations to behave well together, please audit them carefully to * ensure they all have forward progress. Many atomic operations may default to * cmpxchg() loops which will not have good forward progress properties on * LL/SC architectures. * * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) * do. Carefully read the patches that introduced * queued_fetch_set_pending_acquire(). * * qspinlock also heavily relies on mixed size atomic operations, in specific * it requires architectures to have xchg16; something which many LL/SC * architectures need to implement as a 32bit and+or in order to satisfy the * forward progress guarantees mentioned above. * * Further reading on mixed size atomics that might be relevant: * * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !lock.val.counter; } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { int val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { int val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 13 1 1 2 2 1 1 2 15 15 15 5 4 6 11 4 1 10 2 3 6 7 1 1 4 1 14 14 9 2 2 15 10 10 7 1 6 7 7 6 2 4 1 1 9 2 1 1 1 1 3 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 Red Hat, Inc. */ #include "fuse_i.h" #include <linux/uio.h> #include <linux/compat.h> #include <linux/fileattr.h> #include <linux/fsverity.h> static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args, struct fuse_ioctl_out *outarg) { ssize_t ret; args->out_args[0].size = sizeof(*outarg); args->out_args[0].value = outarg; ret = fuse_simple_request(fm, args); /* Translate ENOSYS, which shouldn't be returned from fs */ if (ret == -ENOSYS) ret = -ENOTTY; if (ret >= 0 && outarg->result == -ENOSYS) outarg->result = -ENOTTY; return ret; } /* * CUSE servers compiled on 32bit broke on 64bit kernels because the * ABI was defined to be 'struct iovec' which is different on 32bit * and 64bit. Fortunately we can determine which structure the server * used from the size of the reply. */ static int fuse_copy_ioctl_iovec_old(struct iovec *dst, void *src, size_t transferred, unsigned count, bool is_compat) { #ifdef CONFIG_COMPAT if (count * sizeof(struct compat_iovec) == transferred) { struct compat_iovec *ciov = src; unsigned i; /* * With this interface a 32bit server cannot support * non-compat (i.e. ones coming from 64bit apps) ioctl * requests */ if (!is_compat) return -EINVAL; for (i = 0; i < count; i++) { dst[i].iov_base = compat_ptr(ciov[i].iov_base); dst[i].iov_len = ciov[i].iov_len; } return 0; } #endif if (count * sizeof(struct iovec) != transferred) return -EIO; memcpy(dst, src, transferred); return 0; } /* Make sure iov_length() won't overflow */ static int fuse_verify_ioctl_iov(struct fuse_conn *fc, struct iovec *iov, size_t count) { size_t n; u32 max = fc->max_pages << PAGE_SHIFT; for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) return -ENOMEM; max -= iov->iov_len; } return 0; } static int fuse_copy_ioctl_iovec(struct fuse_conn *fc, struct iovec *dst, void *src, size_t transferred, unsigned count, bool is_compat) { unsigned i; struct fuse_ioctl_iovec *fiov = src; if (fc->minor < 16) { return fuse_copy_ioctl_iovec_old(dst, src, transferred, count, is_compat); } if (count * sizeof(struct fuse_ioctl_iovec) != transferred) return -EIO; for (i = 0; i < count; i++) { /* Did the server supply an inappropriate value? */ if (fiov[i].base != (unsigned long) fiov[i].base || fiov[i].len != (unsigned long) fiov[i].len) return -EIO; dst[i].iov_base = (void __user *) (unsigned long) fiov[i].base; dst[i].iov_len = (size_t) fiov[i].len; #ifdef CONFIG_COMPAT if (is_compat && (ptr_to_compat(dst[i].iov_base) != fiov[i].base || (compat_size_t) dst[i].iov_len != fiov[i].len)) return -EIO; #endif } return 0; } /* For fs-verity, determine iov lengths from input */ static int fuse_setup_measure_verity(unsigned long arg, struct iovec *iov) { __u16 digest_size; struct fsverity_digest __user *uarg = (void __user *)arg; if (copy_from_user(&digest_size, &uarg->digest_size, sizeof(digest_size))) return -EFAULT; if (digest_size > SIZE_MAX - sizeof(struct fsverity_digest)) return -EINVAL; iov->iov_len = sizeof(struct fsverity_digest) + digest_size; return 0; } static int fuse_setup_enable_verity(unsigned long arg, struct iovec *iov, unsigned int *in_iovs) { struct fsverity_enable_arg enable; struct fsverity_enable_arg __user *uarg = (void __user *)arg; const __u32 max_buffer_len = FUSE_MAX_MAX_PAGES * PAGE_SIZE; if (copy_from_user(&enable, uarg, sizeof(enable))) return -EFAULT; if (enable.salt_size > max_buffer_len || enable.sig_size > max_buffer_len) return -ENOMEM; if (enable.salt_size > 0) { iov++; (*in_iovs)++; iov->iov_base = u64_to_user_ptr(enable.salt_ptr); iov->iov_len = enable.salt_size; } if (enable.sig_size > 0) { iov++; (*in_iovs)++; iov->iov_base = u64_to_user_ptr(enable.sig_ptr); iov->iov_len = enable.sig_size; } return 0; } /* * For ioctls, there is no generic way to determine how much memory * needs to be read and/or written. Furthermore, ioctls are allowed * to dereference the passed pointer, so the parameter requires deep * copying but FUSE has no idea whatsoever about what to copy in or * out. * * This is solved by allowing FUSE server to retry ioctl with * necessary in/out iovecs. Let's assume the ioctl implementation * needs to read in the following structure. * * struct a { * char *buf; * size_t buflen; * } * * On the first callout to FUSE server, inarg->in_size and * inarg->out_size will be NULL; then, the server completes the ioctl * with FUSE_IOCTL_RETRY set in out->flags, out->in_iovs set to 1 and * the actual iov array to * * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) } } * * which tells FUSE to copy in the requested area and retry the ioctl. * On the second round, the server has access to the structure and * from that it can tell what to look for next, so on the invocation, * it sets FUSE_IOCTL_RETRY, out->in_iovs to 2 and iov array to * * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) }, * { .iov_base = a.buf, .iov_len = a.buflen } } * * FUSE will copy both struct a and the pointed buffer from the * process doing the ioctl and retry ioctl with both struct a and the * buffer. * * This time, FUSE server has everything it needs and completes ioctl * without FUSE_IOCTL_RETRY which finishes the ioctl call. * * Copying data out works the same way. * * Note that if FUSE_IOCTL_UNRESTRICTED is clear, the kernel * automatically initializes in and out iovs by decoding @cmd with * _IOC_* macros and the server is not allowed to request RETRY. This * limits ioctl data transfers to well-formed ioctls and is the forced * behavior for all FUSE servers. */ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, unsigned int flags) { struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; struct fuse_ioctl_in inarg = { .fh = ff->fh, .cmd = cmd, .arg = arg, .flags = flags }; struct fuse_ioctl_out outarg; struct iovec *iov_page = NULL; struct iovec *in_iov = NULL, *out_iov = NULL; unsigned int in_iovs = 0, out_iovs = 0, max_pages; size_t in_size, out_size, c; ssize_t transferred; int err, i; struct iov_iter ii; struct fuse_args_pages ap = {}; #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; #else if (flags & FUSE_IOCTL_COMPAT) { inarg.flags |= FUSE_IOCTL_32BIT; #ifdef CONFIG_X86_X32_ABI if (in_x32_syscall()) inarg.flags |= FUSE_IOCTL_COMPAT_X32; #endif } #endif /* assume all the iovs returned by client always fits in a page */ BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE); err = -ENOMEM; ap.pages = fuse_pages_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.descs); iov_page = (struct iovec *) __get_free_page(GFP_KERNEL); if (!ap.pages || !iov_page) goto out; fuse_page_descs_length_init(ap.descs, 0, fm->fc->max_pages); /* * If restricted, initialize IO parameters as encoded in @cmd. * RETRY from server is not allowed. */ if (!(flags & FUSE_IOCTL_UNRESTRICTED)) { struct iovec *iov = iov_page; iov->iov_base = (void __user *)arg; iov->iov_len = _IOC_SIZE(cmd); if (_IOC_DIR(cmd) & _IOC_WRITE) { in_iov = iov; in_iovs = 1; } if (_IOC_DIR(cmd) & _IOC_READ) { out_iov = iov; out_iovs = 1; } err = 0; switch (cmd) { case FS_IOC_MEASURE_VERITY: err = fuse_setup_measure_verity(arg, iov); break; case FS_IOC_ENABLE_VERITY: err = fuse_setup_enable_verity(arg, iov, &in_iovs); break; } if (err) goto out; } retry: inarg.in_size = in_size = iov_length(in_iov, in_iovs); inarg.out_size = out_size = iov_length(out_iov, out_iovs); /* * Out data can be used either for actual out data or iovs, * make sure there always is at least one page. */ out_size = max_t(size_t, out_size, PAGE_SIZE); max_pages = DIV_ROUND_UP(max(in_size, out_size), PAGE_SIZE); /* make sure there are enough buffer pages and init request with them */ err = -ENOMEM; if (max_pages > fm->fc->max_pages) goto out; while (ap.num_pages < max_pages) { ap.pages[ap.num_pages] = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); if (!ap.pages[ap.num_pages]) goto out; ap.num_pages++; } /* okay, let's send it to the client */ ap.args.opcode = FUSE_IOCTL; ap.args.nodeid = ff->nodeid; ap.args.in_numargs = 1; ap.args.in_args[0].size = sizeof(inarg); ap.args.in_args[0].value = &inarg; if (in_size) { ap.args.in_numargs++; ap.args.in_args[1].size = in_size; ap.args.in_pages = true; err = -EFAULT; iov_iter_init(&ii, ITER_SOURCE, in_iov, in_iovs, in_size); for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) { c = copy_page_from_iter(ap.pages[i], 0, PAGE_SIZE, &ii); if (c != PAGE_SIZE && iov_iter_count(&ii)) goto out; } } ap.args.out_numargs = 2; ap.args.out_args[1].size = out_size; ap.args.out_pages = true; ap.args.out_argvar = true; transferred = fuse_send_ioctl(fm, &ap.args, &outarg); err = transferred; if (transferred < 0) goto out; /* did it ask for retry? */ if (outarg.flags & FUSE_IOCTL_RETRY) { void *vaddr; /* no retry if in restricted mode */ err = -EIO; if (!(flags & FUSE_IOCTL_UNRESTRICTED)) goto out; in_iovs = outarg.in_iovs; out_iovs = outarg.out_iovs; /* * Make sure things are in boundary, separate checks * are to protect against overflow. */ err = -ENOMEM; if (in_iovs > FUSE_IOCTL_MAX_IOV || out_iovs > FUSE_IOCTL_MAX_IOV || in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV) goto out; vaddr = kmap_local_page(ap.pages[0]); err = fuse_copy_ioctl_iovec(fm->fc, iov_page, vaddr, transferred, in_iovs + out_iovs, (flags & FUSE_IOCTL_COMPAT) != 0); kunmap_local(vaddr); if (err) goto out; in_iov = iov_page; out_iov = in_iov + in_iovs; err = fuse_verify_ioctl_iov(fm->fc, in_iov, in_iovs); if (err) goto out; err = fuse_verify_ioctl_iov(fm->fc, out_iov, out_iovs); if (err) goto out; goto retry; } err = -EIO; if (transferred > inarg.out_size) goto out; err = -EFAULT; iov_iter_init(&ii, ITER_DEST, out_iov, out_iovs, transferred); for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_pages); i++) { c = copy_page_to_iter(ap.pages[i], 0, PAGE_SIZE, &ii); if (c != PAGE_SIZE && iov_iter_count(&ii)) goto out; } err = 0; out: free_page((unsigned long) iov_page); while (ap.num_pages) __free_page(ap.pages[--ap.num_pages]); kfree(ap.pages); return err ? err : outarg.result; } EXPORT_SYMBOL_GPL(fuse_do_ioctl); long fuse_ioctl_common(struct file *file, unsigned int cmd, unsigned long arg, unsigned int flags) { struct inode *inode = file_inode(file); struct fuse_conn *fc = get_fuse_conn(inode); if (!fuse_allow_current_process(fc)) return -EACCES; if (fuse_is_bad(inode)) return -EIO; return fuse_do_ioctl(file, cmd, arg, flags); } long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return fuse_ioctl_common(file, cmd, arg, 0); } long fuse_file_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return fuse_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT); } static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff, unsigned int cmd, void *ptr, size_t size) { struct fuse_mount *fm = ff->fm; struct fuse_ioctl_in inarg; struct fuse_ioctl_out outarg; FUSE_ARGS(args); int err; memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; inarg.cmd = cmd; #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; #endif if (S_ISDIR(inode->i_mode)) inarg.flags |= FUSE_IOCTL_DIR; if (_IOC_DIR(cmd) & _IOC_READ) inarg.out_size = size; if (_IOC_DIR(cmd) & _IOC_WRITE) inarg.in_size = size; args.opcode = FUSE_IOCTL; args.nodeid = ff->nodeid; args.in_numargs = 2; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.in_args[1].size = inarg.in_size; args.in_args[1].value = ptr; args.out_numargs = 2; args.out_args[1].size = inarg.out_size; args.out_args[1].value = ptr; err = fuse_send_ioctl(fm, &args, &outarg); if (!err) { if (outarg.result < 0) err = outarg.result; else if (outarg.flags & FUSE_IOCTL_RETRY) err = -EIO; } return err; } static struct fuse_file *fuse_priv_ioctl_prepare(struct inode *inode) { struct fuse_mount *fm = get_fuse_mount(inode); bool isdir = S_ISDIR(inode->i_mode); if (!fuse_allow_current_process(fm->fc)) return ERR_PTR(-EACCES); if (fuse_is_bad(inode)) return ERR_PTR(-EIO); if (!S_ISREG(inode->i_mode) && !isdir) return ERR_PTR(-ENOTTY); return fuse_file_open(fm, get_node_id(inode), O_RDONLY, isdir); } static void fuse_priv_ioctl_cleanup(struct inode *inode, struct fuse_file *ff) { fuse_file_release(inode, ff, O_RDONLY, NULL, S_ISDIR(inode->i_mode)); } int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fuse_file *ff; unsigned int flags; struct fsxattr xfa; int err; ff = fuse_priv_ioctl_prepare(inode); if (IS_ERR(ff)) return PTR_ERR(ff); if (fa->flags_valid) { err = fuse_priv_ioctl(inode, ff, FS_IOC_GETFLAGS, &flags, sizeof(flags)); if (err) goto cleanup; fileattr_fill_flags(fa, flags); } else { err = fuse_priv_ioctl(inode, ff, FS_IOC_FSGETXATTR, &xfa, sizeof(xfa)); if (err) goto cleanup; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; } cleanup: fuse_priv_ioctl_cleanup(inode, ff); return err; } int fuse_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fuse_file *ff; unsigned int flags = fa->flags; struct fsxattr xfa; int err; ff = fuse_priv_ioctl_prepare(inode); if (IS_ERR(ff)) return PTR_ERR(ff); if (fa->flags_valid) { err = fuse_priv_ioctl(inode, ff, FS_IOC_SETFLAGS, &flags, sizeof(flags)); if (err) goto cleanup; } else { memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; err = fuse_priv_ioctl(inode, ff, FS_IOC_FSSETXATTR, &xfa, sizeof(xfa)); } cleanup: fuse_priv_ioctl_cleanup(inode, ff); return err; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM exceptions #if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGE_FAULT_H #include <linux/tracepoint.h> #include <asm/trace/common.h> extern int trace_pagefault_reg(void); extern void trace_pagefault_unreg(void); DECLARE_EVENT_CLASS(x86_exceptions, TP_PROTO(unsigned long address, struct pt_regs *regs, unsigned long error_code), TP_ARGS(address, regs, error_code), TP_STRUCT__entry( __field( unsigned long, address ) __field( unsigned long, ip ) __field( unsigned long, error_code ) ), TP_fast_assign( __entry->address = address; __entry->ip = regs->ip; __entry->error_code = error_code; ), TP_printk("address=%ps ip=%ps error_code=0x%lx", (void *)__entry->address, (void *)__entry->ip, __entry->error_code) ); #define DEFINE_PAGE_FAULT_EVENT(name) \ DEFINE_EVENT_FN(x86_exceptions, name, \ TP_PROTO(unsigned long address, struct pt_regs *regs, \ unsigned long error_code), \ TP_ARGS(address, regs, error_code), \ trace_pagefault_reg, trace_pagefault_unreg); DEFINE_PAGE_FAULT_EVENT(page_fault_user); DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); #undef TRACE_INCLUDE_PATH #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE exceptions #endif /* _TRACE_PAGE_FAULT_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 106 106 11 120 122 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * 9P Client Definitions * * Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net> */ #ifndef NET_9P_CLIENT_H #define NET_9P_CLIENT_H #include <linux/utsname.h> #include <linux/idr.h> #include <linux/tracepoint-defs.h> /* Number of requests per row */ #define P9_ROW_MAXTAG 255 /** enum p9_proto_versions - 9P protocol versions * @p9_proto_legacy: 9P Legacy mode, pre-9P2000.u * @p9_proto_2000u: 9P2000.u extension * @p9_proto_2000L: 9P2000.L extension */ enum p9_proto_versions { p9_proto_legacy, p9_proto_2000u, p9_proto_2000L, }; /** * enum p9_trans_status - different states of underlying transports * @Connected: transport is connected and healthy * @Disconnected: transport has been disconnected * @Hung: transport is connected by wedged * * This enumeration details the various states a transport * instatiation can be in. */ enum p9_trans_status { Connected, BeginDisconnect, Disconnected, Hung, }; /** * enum p9_req_status_t - status of a request * @REQ_STATUS_ALLOC: request has been allocated but not sent * @REQ_STATUS_UNSENT: request waiting to be sent * @REQ_STATUS_SENT: request sent to server * @REQ_STATUS_RCVD: response received from server * @REQ_STATUS_FLSHD: request has been flushed * @REQ_STATUS_ERROR: request encountered an error on the client side */ enum p9_req_status_t { REQ_STATUS_ALLOC, REQ_STATUS_UNSENT, REQ_STATUS_SENT, REQ_STATUS_RCVD, REQ_STATUS_FLSHD, REQ_STATUS_ERROR, }; /** * struct p9_req_t - request slots * @status: status of this request slot * @t_err: transport error * @wq: wait_queue for the client to block on for this request * @tc: the request fcall structure * @rc: the response fcall structure * @req_list: link for higher level objects to chain requests */ struct p9_req_t { int status; int t_err; refcount_t refcount; wait_queue_head_t wq; struct p9_fcall tc; struct p9_fcall rc; struct list_head req_list; }; /** * struct p9_client - per client instance state * @lock: protect @fids and @reqs * @msize: maximum data size negotiated by protocol * @proto_version: 9P protocol version to use * @trans_mod: module API instantiated with this client * @status: connection state * @trans: tranport instance state and API * @fids: All active FID handles * @reqs: All active requests. * @name: node name used as client id * * The client structure is used to keep track of various per-client * state that has been instantiated. */ struct p9_client { spinlock_t lock; unsigned int msize; unsigned char proto_version; struct p9_trans_module *trans_mod; enum p9_trans_status status; void *trans; struct kmem_cache *fcall_cache; union { struct { int rfd; int wfd; } fd; struct { u16 port; bool privport; } tcp; } trans_opts; struct idr fids; struct idr reqs; char name[__NEW_UTS_LEN + 1]; }; /** * struct p9_fid - file system entity handle * @clnt: back pointer to instantiating &p9_client * @fid: numeric identifier for this handle * @mode: current mode of this fid (enum?) * @qid: the &p9_qid server identifier this handle points to * @iounit: the server reported maximum transaction size for this file * @uid: the numeric uid of the local user who owns this handle * @rdir: readdir accounting structure (allocated on demand) * @dlist: per-dentry fid tracking * * TODO: This needs lots of explanation. */ enum fid_source { FID_FROM_OTHER, FID_FROM_INODE, FID_FROM_DENTRY, }; struct p9_fid { struct p9_client *clnt; u32 fid; refcount_t count; int mode; struct p9_qid qid; u32 iounit; kuid_t uid; void *rdir; struct hlist_node dlist; /* list of all fids attached to a dentry */ struct hlist_node ilist; }; /** * struct p9_dirent - directory entry structure * @qid: The p9 server qid for this dirent * @d_off: offset to the next dirent * @d_type: type of file * @d_name: file name */ struct p9_dirent { struct p9_qid qid; u64 d_off; unsigned char d_type; char d_name[256]; }; struct iov_iter; int p9_show_client_options(struct seq_file *m, struct p9_client *clnt); int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name); int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name, struct p9_fid *newdirfid, const char *new_name); struct p9_client *p9_client_create(const char *dev_name, char *options); void p9_client_destroy(struct p9_client *clnt); void p9_client_disconnect(struct p9_client *clnt); void p9_client_begin_disconnect(struct p9_client *clnt); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, const char *uname, kuid_t n_uname, const char *aname); struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, const unsigned char * const *wnames, int clone); int p9_client_open(struct p9_fid *fid, int mode); int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode, char *extension); int p9_client_link(struct p9_fid *fid, struct p9_fid *oldfid, const char *newname); int p9_client_symlink(struct p9_fid *fid, const char *name, const char *symname, kgid_t gid, struct p9_qid *qid); int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode, kgid_t gid, struct p9_qid *qid); int p9_client_clunk(struct p9_fid *fid); int p9_client_fsync(struct p9_fid *fid, int datasync); int p9_client_remove(struct p9_fid *fid); int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags); int p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err); int p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err); int p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err); struct netfs_io_subrequest; void p9_client_write_subreq(struct netfs_io_subrequest *subreq); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset); int p9dirent_read(struct p9_client *clnt, char *buf, int len, struct p9_dirent *dirent); struct p9_wstat *p9_client_stat(struct p9_fid *fid); int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst); int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *attr); struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, u64 request_mask); int p9_client_mknod_dotl(struct p9_fid *oldfid, const char *name, int mode, dev_t rdev, kgid_t gid, struct p9_qid *qid); int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode, kgid_t gid, struct p9_qid *qid); int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status); int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *fl); void p9_fcall_fini(struct p9_fcall *fc); struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag); static inline void p9_req_get(struct p9_req_t *r) { refcount_inc(&r->refcount); } static inline int p9_req_try_get(struct p9_req_t *r) { return refcount_inc_not_zero(&r->refcount); } int p9_req_put(struct p9_client *c, struct p9_req_t *r); /* We cannot have the real tracepoints in header files, * use a wrapper function */ DECLARE_TRACEPOINT(9p_fid_ref); void do_trace_9p_fid_get(struct p9_fid *fid); void do_trace_9p_fid_put(struct p9_fid *fid); /* fid reference counting helpers: * - fids used for any length of time should always be referenced through * p9_fid_get(), and released with p9_fid_put() * - v9fs_fid_lookup() or similar will automatically call get for you * and also require a put * - the *_fid_add() helpers will stash the fid in the inode, * at which point it is the responsibility of evict_inode() * to call the put * - the last put will automatically send a clunk to the server */ static inline struct p9_fid *p9_fid_get(struct p9_fid *fid) { if (tracepoint_enabled(9p_fid_ref)) do_trace_9p_fid_get(fid); refcount_inc(&fid->count); return fid; } static inline int p9_fid_put(struct p9_fid *fid) { if (!fid || IS_ERR(fid)) return 0; if (tracepoint_enabled(9p_fid_ref)) do_trace_9p_fid_put(fid); if (!refcount_dec_and_test(&fid->count)) return 0; return p9_client_clunk(fid); } void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status); int p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag, int rewind); int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st); void p9stat_free(struct p9_wstat *stbuf); int p9_is_proto_dotu(struct p9_client *clnt); int p9_is_proto_dotl(struct p9_client *clnt); struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, const char *attr_name, u64 *attr_size); int p9_client_xattrcreate(struct p9_fid *fid, const char *name, u64 attr_size, int flags); int p9_client_readlink(struct p9_fid *fid, char **target); int p9_client_init(void); void p9_client_exit(void); #endif /* NET_9P_CLIENT_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "btree_cache.h" #include "btree_iter.h" #include "btree_key_cache.h" #include "btree_locking.h" #include "btree_update.h" #include "errcode.h" #include "error.h" #include "journal.h" #include "journal_reclaim.h" #include "trace.h" #include <linux/sched/mm.h> static inline bool btree_uses_pcpu_readers(enum btree_id id) { return id == BTREE_ID_subvolumes; } static struct kmem_cache *bch2_key_cache; static int bch2_btree_key_cache_cmp_fn(struct rhashtable_compare_arg *arg, const void *obj) { const struct bkey_cached *ck = obj; const struct bkey_cached_key *key = arg->key; return ck->key.btree_id != key->btree_id || !bpos_eq(ck->key.pos, key->pos); } static const struct rhashtable_params bch2_btree_key_cache_params = { .head_offset = offsetof(struct bkey_cached, hash), .key_offset = offsetof(struct bkey_cached, key), .key_len = sizeof(struct bkey_cached_key), .obj_cmpfn = bch2_btree_key_cache_cmp_fn, .automatic_shrinking = true, }; static inline void btree_path_cached_set(struct btree_trans *trans, struct btree_path *path, struct bkey_cached *ck, enum btree_node_locked_type lock_held) { path->l[0].lock_seq = six_lock_seq(&ck->c.lock); path->l[0].b = (void *) ck; mark_btree_node_locked(trans, path, 0, lock_held); } __flatten inline struct bkey_cached * bch2_btree_key_cache_find(struct bch_fs *c, enum btree_id btree_id, struct bpos pos) { struct bkey_cached_key key = { .btree_id = btree_id, .pos = pos, }; return rhashtable_lookup_fast(&c->btree_key_cache.table, &key, bch2_btree_key_cache_params); } static bool bkey_cached_lock_for_evict(struct bkey_cached *ck) { if (!six_trylock_intent(&ck->c.lock)) return false; if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { six_unlock_intent(&ck->c.lock); return false; } if (!six_trylock_write(&ck->c.lock)) { six_unlock_intent(&ck->c.lock); return false; } return true; } static void bkey_cached_evict(struct btree_key_cache *c, struct bkey_cached *ck) { BUG_ON(rhashtable_remove_fast(&c->table, &ck->hash, bch2_btree_key_cache_params)); memset(&ck->key, ~0, sizeof(ck->key)); atomic_long_dec(&c->nr_keys); } static void bkey_cached_free(struct btree_key_cache *bc, struct bkey_cached *ck) { struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache); BUG_ON(test_bit(BKEY_CACHED_DIRTY, &ck->flags)); ck->btree_trans_barrier_seq = start_poll_synchronize_srcu(&c->btree_trans_barrier); if (ck->c.lock.readers) { list_move_tail(&ck->list, &bc->freed_pcpu); bc->nr_freed_pcpu++; } else { list_move_tail(&ck->list, &bc->freed_nonpcpu); bc->nr_freed_nonpcpu++; } atomic_long_inc(&bc->nr_freed); kfree(ck->k); ck->k = NULL; ck->u64s = 0; six_unlock_write(&ck->c.lock); six_unlock_intent(&ck->c.lock); } #ifdef __KERNEL__ static void __bkey_cached_move_to_freelist_ordered(struct btree_key_cache *bc, struct bkey_cached *ck) { struct bkey_cached *pos; bc->nr_freed_nonpcpu++; list_for_each_entry_reverse(pos, &bc->freed_nonpcpu, list) { if (ULONG_CMP_GE(ck->btree_trans_barrier_seq, pos->btree_trans_barrier_seq)) { list_move(&ck->list, &pos->list); return; } } list_move(&ck->list, &bc->freed_nonpcpu); } #endif static void bkey_cached_move_to_freelist(struct btree_key_cache *bc, struct bkey_cached *ck) { BUG_ON(test_bit(BKEY_CACHED_DIRTY, &ck->flags)); if (!ck->c.lock.readers) { #ifdef __KERNEL__ struct btree_key_cache_freelist *f; bool freed = false; preempt_disable(); f = this_cpu_ptr(bc->pcpu_freed); if (f->nr < ARRAY_SIZE(f->objs)) { f->objs[f->nr++] = ck; freed = true; } preempt_enable(); if (!freed) { mutex_lock(&bc->lock); preempt_disable(); f = this_cpu_ptr(bc->pcpu_freed); while (f->nr > ARRAY_SIZE(f->objs) / 2) { struct bkey_cached *ck2 = f->objs[--f->nr]; __bkey_cached_move_to_freelist_ordered(bc, ck2); } preempt_enable(); __bkey_cached_move_to_freelist_ordered(bc, ck); mutex_unlock(&bc->lock); } #else mutex_lock(&bc->lock); list_move_tail(&ck->list, &bc->freed_nonpcpu); bc->nr_freed_nonpcpu++; mutex_unlock(&bc->lock); #endif } else { mutex_lock(&bc->lock); list_move_tail(&ck->list, &bc->freed_pcpu); bc->nr_freed_pcpu++; mutex_unlock(&bc->lock); } } static void bkey_cached_free_fast(struct btree_key_cache *bc, struct bkey_cached *ck) { struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache); ck->btree_trans_barrier_seq = start_poll_synchronize_srcu(&c->btree_trans_barrier); list_del_init(&ck->list); atomic_long_inc(&bc->nr_freed); kfree(ck->k); ck->k = NULL; ck->u64s = 0; bkey_cached_move_to_freelist(bc, ck); six_unlock_write(&ck->c.lock); six_unlock_intent(&ck->c.lock); } static struct bkey_cached *__bkey_cached_alloc(unsigned key_u64s, gfp_t gfp) { struct bkey_cached *ck = kmem_cache_zalloc(bch2_key_cache, gfp); if (unlikely(!ck)) return NULL; ck->k = kmalloc(key_u64s * sizeof(u64), gfp); if (unlikely(!ck->k)) { kmem_cache_free(bch2_key_cache, ck); return NULL; } ck->u64s = key_u64s; return ck; } static struct bkey_cached * bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, unsigned key_u64s) { struct bch_fs *c = trans->c; struct btree_key_cache *bc = &c->btree_key_cache; struct bkey_cached *ck = NULL; bool pcpu_readers = btree_uses_pcpu_readers(path->btree_id); int ret; if (!pcpu_readers) { #ifdef __KERNEL__ struct btree_key_cache_freelist *f; preempt_disable(); f = this_cpu_ptr(bc->pcpu_freed); if (f->nr) ck = f->objs[--f->nr]; preempt_enable(); if (!ck) { mutex_lock(&bc->lock); preempt_disable(); f = this_cpu_ptr(bc->pcpu_freed); while (!list_empty(&bc->freed_nonpcpu) && f->nr < ARRAY_SIZE(f->objs) / 2) { ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list); list_del_init(&ck->list); bc->nr_freed_nonpcpu--; f->objs[f->nr++] = ck; } ck = f->nr ? f->objs[--f->nr] : NULL; preempt_enable(); mutex_unlock(&bc->lock); } #else mutex_lock(&bc->lock); if (!list_empty(&bc->freed_nonpcpu)) { ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list); list_del_init(&ck->list); bc->nr_freed_nonpcpu--; } mutex_unlock(&bc->lock); #endif } else { mutex_lock(&bc->lock); if (!list_empty(&bc->freed_pcpu)) { ck = list_last_entry(&bc->freed_pcpu, struct bkey_cached, list); list_del_init(&ck->list); bc->nr_freed_pcpu--; } mutex_unlock(&bc->lock); } if (ck) { ret = btree_node_lock_nopath(trans, &ck->c, SIX_LOCK_intent, _THIS_IP_); if (unlikely(ret)) { bkey_cached_move_to_freelist(bc, ck); return ERR_PTR(ret); } btree_path_cached_set(trans, path, ck, BTREE_NODE_INTENT_LOCKED); ret = bch2_btree_node_lock_write(trans, path, &ck->c); if (unlikely(ret)) { btree_node_unlock(trans, path, 0); bkey_cached_move_to_freelist(bc, ck); return ERR_PTR(ret); } return ck; } ck = allocate_dropping_locks(trans, ret, __bkey_cached_alloc(key_u64s, _gfp)); if (ret) { if (ck) kfree(ck->k); kmem_cache_free(bch2_key_cache, ck); return ERR_PTR(ret); } if (!ck) return NULL; INIT_LIST_HEAD(&ck->list); bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0); ck->c.cached = true; BUG_ON(!six_trylock_intent(&ck->c.lock)); BUG_ON(!six_trylock_write(&ck->c.lock)); return ck; } static struct bkey_cached * bkey_cached_reuse(struct btree_key_cache *c) { struct bucket_table *tbl; struct rhash_head *pos; struct bkey_cached *ck; unsigned i; mutex_lock(&c->lock); rcu_read_lock(); tbl = rht_dereference_rcu(c->table.tbl, &c->table); for (i = 0; i < tbl->size; i++) rht_for_each_entry_rcu(ck, pos, tbl, i, hash) { if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) && bkey_cached_lock_for_evict(ck)) { bkey_cached_evict(c, ck); goto out; } } ck = NULL; out: rcu_read_unlock(); mutex_unlock(&c->lock); return ck; } static int btree_key_cache_create(struct btree_trans *trans, struct btree_path *path, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct btree_key_cache *bc = &c->btree_key_cache; /* * bch2_varint_decode can read past the end of the buffer by at * most 7 bytes (it won't be used): */ unsigned key_u64s = k.k->u64s + 1; /* * Allocate some extra space so that the transaction commit path is less * likely to have to reallocate, since that requires a transaction * restart: */ key_u64s = min(256U, (key_u64s * 3) / 2); key_u64s = roundup_pow_of_two(key_u64s); struct bkey_cached *ck = bkey_cached_alloc(trans, path, key_u64s); int ret = PTR_ERR_OR_ZERO(ck); if (ret) return ret; if (unlikely(!ck)) { ck = bkey_cached_reuse(bc); if (unlikely(!ck)) { bch_err(c, "error allocating memory for key cache item, btree %s", bch2_btree_id_str(path->btree_id)); return -BCH_ERR_ENOMEM_btree_key_cache_create; } } ck->c.level = 0; ck->c.btree_id = path->btree_id; ck->key.btree_id = path->btree_id; ck->key.pos = path->pos; ck->flags = 1U << BKEY_CACHED_ACCESSED; if (unlikely(key_u64s > ck->u64s)) { mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED); struct bkey_i *new_k = allocate_dropping_locks(trans, ret, kmalloc(key_u64s * sizeof(u64), _gfp)); if (unlikely(!new_k)) { bch_err(trans->c, "error allocating memory for key cache key, btree %s u64s %u", bch2_btree_id_str(ck->key.btree_id), key_u64s); ret = -BCH_ERR_ENOMEM_btree_key_cache_fill; } else if (ret) { kfree(new_k); goto err; } kfree(ck->k); ck->k = new_k; ck->u64s = key_u64s; } bkey_reassemble(ck->k, k); ret = rhashtable_lookup_insert_fast(&bc->table, &ck->hash, bch2_btree_key_cache_params); if (unlikely(ret)) /* raced with another fill? */ goto err; atomic_long_inc(&bc->nr_keys); six_unlock_write(&ck->c.lock); enum six_lock_type lock_want = __btree_lock_want(path, 0); if (lock_want == SIX_LOCK_read) six_lock_downgrade(&ck->c.lock); btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want); path->uptodate = BTREE_ITER_UPTODATE; return 0; err: bkey_cached_free_fast(bc, ck); mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED); return ret; } static noinline int btree_key_cache_fill(struct btree_trans *trans, struct btree_path *ck_path, unsigned flags) { if (flags & BTREE_ITER_cached_nofill) { ck_path->uptodate = BTREE_ITER_UPTODATE; return 0; } struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret; bch2_trans_iter_init(trans, &iter, ck_path->btree_id, ck_path->pos, BTREE_ITER_key_cache_fill| BTREE_ITER_cached_nofill); iter.flags &= ~BTREE_ITER_with_journal; k = bch2_btree_iter_peek_slot(&iter); ret = bkey_err(k); if (ret) goto err; /* Recheck after btree lookup, before allocating: */ ret = bch2_btree_key_cache_find(c, ck_path->btree_id, ck_path->pos) ? -EEXIST : 0; if (unlikely(ret)) goto out; ret = btree_key_cache_create(trans, ck_path, k); if (ret) goto err; out: /* We're not likely to need this iterator again: */ bch2_set_btree_iter_dontneed(&iter); err: bch2_trans_iter_exit(trans, &iter); return ret; } static inline int btree_path_traverse_cached_fast(struct btree_trans *trans, struct btree_path *path) { struct bch_fs *c = trans->c; struct bkey_cached *ck; retry: ck = bch2_btree_key_cache_find(c, path->btree_id, path->pos); if (!ck) return -ENOENT; enum six_lock_type lock_want = __btree_lock_want(path, 0); int ret = btree_node_lock(trans, path, (void *) ck, 0, lock_want, _THIS_IP_); if (ret) return ret; if (ck->key.btree_id != path->btree_id || !bpos_eq(ck->key.pos, path->pos)) { six_unlock_type(&ck->c.lock, lock_want); goto retry; } if (!test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) set_bit(BKEY_CACHED_ACCESSED, &ck->flags); btree_path_cached_set(trans, path, ck, (enum btree_node_locked_type) lock_want); path->uptodate = BTREE_ITER_UPTODATE; return 0; } int bch2_btree_path_traverse_cached(struct btree_trans *trans, struct btree_path *path, unsigned flags) { EBUG_ON(path->level); path->l[1].b = NULL; int ret; do { ret = btree_path_traverse_cached_fast(trans, path); if (unlikely(ret == -ENOENT)) ret = btree_key_cache_fill(trans, path, flags); } while (ret == -EEXIST); if (unlikely(ret)) { path->uptodate = BTREE_ITER_NEED_TRAVERSE; if (!bch2_err_matches(ret, BCH_ERR_transaction_restart)) { btree_node_unlock(trans, path, 0); path->l[0].b = ERR_PTR(ret); } } return ret; } static int btree_key_cache_flush_pos(struct btree_trans *trans, struct bkey_cached_key key, u64 journal_seq, unsigned commit_flags, bool evict) { struct bch_fs *c = trans->c; struct journal *j = &c->journal; struct btree_iter c_iter, b_iter; struct bkey_cached *ck = NULL; int ret; bch2_trans_iter_init(trans, &b_iter, key.btree_id, key.pos, BTREE_ITER_slots| BTREE_ITER_intent| BTREE_ITER_all_snapshots); bch2_trans_iter_init(trans, &c_iter, key.btree_id, key.pos, BTREE_ITER_cached| BTREE_ITER_intent); b_iter.flags &= ~BTREE_ITER_with_key_cache; ret = bch2_btree_iter_traverse(&c_iter); if (ret) goto out; ck = (void *) btree_iter_path(trans, &c_iter)->l[0].b; if (!ck) goto out; if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { if (evict) goto evict; goto out; } if (journal_seq && ck->journal.seq != journal_seq) goto out; trans->journal_res.seq = ck->journal.seq; /* * If we're at the end of the journal, we really want to free up space * in the journal right away - we don't want to pin that old journal * sequence number with a new btree node write, we want to re-journal * the update */ if (ck->journal.seq == journal_last_seq(j)) commit_flags |= BCH_WATERMARK_reclaim; if (ck->journal.seq != journal_last_seq(j) || !test_bit(JOURNAL_space_low, &c->journal.flags)) commit_flags |= BCH_TRANS_COMMIT_no_journal_res; ret = bch2_btree_iter_traverse(&b_iter) ?: bch2_trans_update(trans, &b_iter, ck->k, BTREE_UPDATE_key_cache_reclaim| BTREE_UPDATE_internal_snapshot_node| BTREE_TRIGGER_norun) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_enospc| commit_flags); bch2_fs_fatal_err_on(ret && !bch2_err_matches(ret, BCH_ERR_transaction_restart) && !bch2_err_matches(ret, BCH_ERR_journal_reclaim_would_deadlock) && !bch2_journal_error(j), c, "flushing key cache: %s", bch2_err_str(ret)); if (ret) goto out; bch2_journal_pin_drop(j, &ck->journal); struct btree_path *path = btree_iter_path(trans, &c_iter); BUG_ON(!btree_node_locked(path, 0)); if (!evict) { if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { clear_bit(BKEY_CACHED_DIRTY, &ck->flags); atomic_long_dec(&c->btree_key_cache.nr_dirty); } } else { struct btree_path *path2; unsigned i; evict: trans_for_each_path(trans, path2, i) if (path2 != path) __bch2_btree_path_unlock(trans, path2); bch2_btree_node_lock_write_nofail(trans, path, &ck->c); if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { clear_bit(BKEY_CACHED_DIRTY, &ck->flags); atomic_long_dec(&c->btree_key_cache.nr_dirty); } mark_btree_node_locked_noreset(path, 0, BTREE_NODE_UNLOCKED); bkey_cached_evict(&c->btree_key_cache, ck); bkey_cached_free_fast(&c->btree_key_cache, ck); } out: bch2_trans_iter_exit(trans, &b_iter); bch2_trans_iter_exit(trans, &c_iter); return ret; } int bch2_btree_key_cache_journal_flush(struct journal *j, struct journal_entry_pin *pin, u64 seq) { struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bkey_cached *ck = container_of(pin, struct bkey_cached, journal); struct bkey_cached_key key; struct btree_trans *trans = bch2_trans_get(c); int srcu_idx = srcu_read_lock(&c->btree_trans_barrier); int ret = 0; btree_node_lock_nopath_nofail(trans, &ck->c, SIX_LOCK_read); key = ck->key; if (ck->journal.seq != seq || !test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { six_unlock_read(&ck->c.lock); goto unlock; } if (ck->seq != seq) { bch2_journal_pin_update(&c->journal, ck->seq, &ck->journal, bch2_btree_key_cache_journal_flush); six_unlock_read(&ck->c.lock); goto unlock; } six_unlock_read(&ck->c.lock); ret = lockrestart_do(trans, btree_key_cache_flush_pos(trans, key, seq, BCH_TRANS_COMMIT_journal_reclaim, false)); unlock: srcu_read_unlock(&c->btree_trans_barrier, srcu_idx); bch2_trans_put(trans); return ret; } bool bch2_btree_insert_key_cached(struct btree_trans *trans, unsigned flags, struct btree_insert_entry *insert_entry) { struct bch_fs *c = trans->c; struct bkey_cached *ck = (void *) (trans->paths + insert_entry->path)->l[0].b; struct bkey_i *insert = insert_entry->k; bool kick_reclaim = false; BUG_ON(insert->k.u64s > ck->u64s); bkey_copy(ck->k, insert); if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags)); set_bit(BKEY_CACHED_DIRTY, &ck->flags); atomic_long_inc(&c->btree_key_cache.nr_dirty); if (bch2_nr_btree_keys_need_flush(c)) kick_reclaim = true; } /* * To minimize lock contention, we only add the journal pin here and * defer pin updates to the flush callback via ->seq. Be careful not to * update ->seq on nojournal commits because we don't want to update the * pin to a seq that doesn't include journal updates on disk. Otherwise * we risk losing the update after a crash. * * The only exception is if the pin is not active in the first place. We * have to add the pin because journal reclaim drives key cache * flushing. The flush callback will not proceed unless ->seq matches * the latest pin, so make sure it starts with a consistent value. */ if (!(insert_entry->flags & BTREE_UPDATE_nojournal) || !journal_pin_active(&ck->journal)) { ck->seq = trans->journal_res.seq; } bch2_journal_pin_add(&c->journal, trans->journal_res.seq, &ck->journal, bch2_btree_key_cache_journal_flush); if (kick_reclaim) journal_reclaim_kick(&c->journal); return true; } void bch2_btree_key_cache_drop(struct btree_trans *trans, struct btree_path *path) { struct bch_fs *c = trans->c; struct btree_key_cache *bc = &c->btree_key_cache; struct bkey_cached *ck = (void *) path->l[0].b; /* * We just did an update to the btree, bypassing the key cache: the key * cache key is now stale and must be dropped, even if dirty: */ if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { clear_bit(BKEY_CACHED_DIRTY, &ck->flags); atomic_long_dec(&c->btree_key_cache.nr_dirty); bch2_journal_pin_drop(&c->journal, &ck->journal); } bkey_cached_evict(bc, ck); bkey_cached_free_fast(bc, ck); mark_btree_node_locked(trans, path, 0, BTREE_NODE_UNLOCKED); btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); path->should_be_locked = false; } static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { struct bch_fs *c = shrink->private_data; struct btree_key_cache *bc = &c->btree_key_cache; struct bucket_table *tbl; struct bkey_cached *ck, *t; size_t scanned = 0, freed = 0, nr = sc->nr_to_scan; unsigned start, flags; int srcu_idx; mutex_lock(&bc->lock); bc->requested_to_free += sc->nr_to_scan; srcu_idx = srcu_read_lock(&c->btree_trans_barrier); flags = memalloc_nofs_save(); /* * Newest freed entries are at the end of the list - once we hit one * that's too new to be freed, we can bail out: */ list_for_each_entry_safe(ck, t, &bc->freed_nonpcpu, list) { if (!poll_state_synchronize_srcu(&c->btree_trans_barrier, ck->btree_trans_barrier_seq)) break; list_del(&ck->list); six_lock_exit(&ck->c.lock); kmem_cache_free(bch2_key_cache, ck); atomic_long_dec(&bc->nr_freed); bc->nr_freed_nonpcpu--; bc->freed++; } list_for_each_entry_safe(ck, t, &bc->freed_pcpu, list) { if (!poll_state_synchronize_srcu(&c->btree_trans_barrier, ck->btree_trans_barrier_seq)) break; list_del(&ck->list); six_lock_exit(&ck->c.lock); kmem_cache_free(bch2_key_cache, ck); atomic_long_dec(&bc->nr_freed); bc->nr_freed_pcpu--; bc->freed++; } rcu_read_lock(); tbl = rht_dereference_rcu(bc->table.tbl, &bc->table); /* * Scanning is expensive while a rehash is in progress - most elements * will be on the new hashtable, if it's in progress * * A rehash could still start while we're scanning - that's ok, we'll * still see most elements. */ if (unlikely(tbl->nest)) { rcu_read_unlock(); srcu_read_unlock(&c->btree_trans_barrier, srcu_idx); return SHRINK_STOP; } if (bc->shrink_iter >= tbl->size) bc->shrink_iter = 0; start = bc->shrink_iter; do { struct rhash_head *pos, *next; pos = rht_ptr_rcu(&tbl->buckets[bc->shrink_iter]); while (!rht_is_a_nulls(pos)) { next = rht_dereference_bucket_rcu(pos->next, tbl, bc->shrink_iter); ck = container_of(pos, struct bkey_cached, hash); if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { bc->skipped_dirty++; } else if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) { clear_bit(BKEY_CACHED_ACCESSED, &ck->flags); bc->skipped_accessed++; } else if (!bkey_cached_lock_for_evict(ck)) { bc->skipped_lock_fail++; } else { bkey_cached_evict(bc, ck); bkey_cached_free(bc, ck); bc->moved_to_freelist++; freed++; } scanned++; if (scanned >= nr) break; pos = next; } bc->shrink_iter++; if (bc->shrink_iter >= tbl->size) bc->shrink_iter = 0; } while (scanned < nr && bc->shrink_iter != start); rcu_read_unlock(); memalloc_nofs_restore(flags); srcu_read_unlock(&c->btree_trans_barrier, srcu_idx); mutex_unlock(&bc->lock); return freed; } static unsigned long bch2_btree_key_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct bch_fs *c = shrink->private_data; struct btree_key_cache *bc = &c->btree_key_cache; long nr = atomic_long_read(&bc->nr_keys) - atomic_long_read(&bc->nr_dirty); /* * Avoid hammering our shrinker too much if it's nearly empty - the * shrinker code doesn't take into account how big our cache is, if it's * mostly empty but the system is under memory pressure it causes nasty * lock contention: */ nr -= 128; return max(0L, nr); } void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc) { struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache); struct bucket_table *tbl; struct bkey_cached *ck, *n; struct rhash_head *pos; LIST_HEAD(items); unsigned i; #ifdef __KERNEL__ int cpu; #endif shrinker_free(bc->shrink); mutex_lock(&bc->lock); /* * The loop is needed to guard against racing with rehash: */ while (atomic_long_read(&bc->nr_keys)) { rcu_read_lock(); tbl = rht_dereference_rcu(bc->table.tbl, &bc->table); if (tbl) { if (tbl->nest) { /* wait for in progress rehash */ rcu_read_unlock(); mutex_lock(&bc->table.mutex); mutex_unlock(&bc->table.mutex); rcu_read_lock(); continue; } for (i = 0; i < tbl->size; i++) while (pos = rht_ptr_rcu(&tbl->buckets[i]), !rht_is_a_nulls(pos)) { ck = container_of(pos, struct bkey_cached, hash); bkey_cached_evict(bc, ck); list_add(&ck->list, &items); } } rcu_read_unlock(); } #ifdef __KERNEL__ if (bc->pcpu_freed) { for_each_possible_cpu(cpu) { struct btree_key_cache_freelist *f = per_cpu_ptr(bc->pcpu_freed, cpu); for (i = 0; i < f->nr; i++) { ck = f->objs[i]; list_add(&ck->list, &items); } } } #endif BUG_ON(list_count_nodes(&bc->freed_pcpu) != bc->nr_freed_pcpu); BUG_ON(list_count_nodes(&bc->freed_nonpcpu) != bc->nr_freed_nonpcpu); list_splice(&bc->freed_pcpu, &items); list_splice(&bc->freed_nonpcpu, &items); mutex_unlock(&bc->lock); list_for_each_entry_safe(ck, n, &items, list) { cond_resched(); list_del(&ck->list); kfree(ck->k); six_lock_exit(&ck->c.lock); kmem_cache_free(bch2_key_cache, ck); } if (atomic_long_read(&bc->nr_dirty) && !bch2_journal_error(&c->journal) && test_bit(BCH_FS_was_rw, &c->flags)) panic("btree key cache shutdown error: nr_dirty nonzero (%li)\n", atomic_long_read(&bc->nr_dirty)); if (atomic_long_read(&bc->nr_keys)) panic("btree key cache shutdown error: nr_keys nonzero (%li)\n", atomic_long_read(&bc->nr_keys)); if (bc->table_init_done) rhashtable_destroy(&bc->table); free_percpu(bc->pcpu_freed); } void bch2_fs_btree_key_cache_init_early(struct btree_key_cache *c) { mutex_init(&c->lock); INIT_LIST_HEAD(&c->freed_pcpu); INIT_LIST_HEAD(&c->freed_nonpcpu); } int bch2_fs_btree_key_cache_init(struct btree_key_cache *bc) { struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache); struct shrinker *shrink; #ifdef __KERNEL__ bc->pcpu_freed = alloc_percpu(struct btree_key_cache_freelist); if (!bc->pcpu_freed) return -BCH_ERR_ENOMEM_fs_btree_cache_init; #endif if (rhashtable_init(&bc->table, &bch2_btree_key_cache_params)) return -BCH_ERR_ENOMEM_fs_btree_cache_init; bc->table_init_done = true; shrink = shrinker_alloc(0, "%s-btree_key_cache", c->name); if (!shrink) return -BCH_ERR_ENOMEM_fs_btree_cache_init; bc->shrink = shrink; shrink->count_objects = bch2_btree_key_cache_count; shrink->scan_objects = bch2_btree_key_cache_scan; shrink->batch = 1 << 14; shrink->seeks = 0; shrink->private_data = c; shrinker_register(shrink); return 0; } void bch2_btree_key_cache_to_text(struct printbuf *out, struct btree_key_cache *bc) { struct bch_fs *c = container_of(bc, struct bch_fs, btree_key_cache); printbuf_tabstop_push(out, 24); printbuf_tabstop_push(out, 12); unsigned flags = memalloc_nofs_save(); mutex_lock(&bc->lock); prt_printf(out, "keys:\t%lu\r\n", atomic_long_read(&bc->nr_keys)); prt_printf(out, "dirty:\t%lu\r\n", atomic_long_read(&bc->nr_dirty)); prt_printf(out, "freelist:\t%lu\r\n", atomic_long_read(&bc->nr_freed)); prt_printf(out, "nonpcpu freelist:\t%zu\r\n", bc->nr_freed_nonpcpu); prt_printf(out, "pcpu freelist:\t%zu\r\n", bc->nr_freed_pcpu); prt_printf(out, "\nshrinker:\n"); prt_printf(out, "requested_to_free:\t%lu\r\n", bc->requested_to_free); prt_printf(out, "freed:\t%lu\r\n", bc->freed); prt_printf(out, "moved_to_freelist:\t%lu\r\n", bc->moved_to_freelist); prt_printf(out, "skipped_dirty:\t%lu\r\n", bc->skipped_dirty); prt_printf(out, "skipped_accessed:\t%lu\r\n", bc->skipped_accessed); prt_printf(out, "skipped_lock_fail:\t%lu\r\n", bc->skipped_lock_fail); prt_printf(out, "srcu seq:\t%lu\r\n", get_state_synchronize_srcu(&c->btree_trans_barrier)); struct bkey_cached *ck; unsigned iter = 0; list_for_each_entry(ck, &bc->freed_nonpcpu, list) { prt_printf(out, "freed_nonpcpu:\t%lu\r\n", ck->btree_trans_barrier_seq); if (++iter > 10) break; } iter = 0; list_for_each_entry(ck, &bc->freed_pcpu, list) { prt_printf(out, "freed_pcpu:\t%lu\r\n", ck->btree_trans_barrier_seq); if (++iter > 10) break; } mutex_unlock(&bc->lock); memalloc_flags_restore(flags); } void bch2_btree_key_cache_exit(void) { kmem_cache_destroy(bch2_key_cache); } int __init bch2_btree_key_cache_init(void) { bch2_key_cache = KMEM_CACHE(bkey_cached, SLAB_RECLAIM_ACCOUNT); if (!bch2_key_cache) return -ENOMEM; return 0; } |
| 923 115 917 298 922 923 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 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * This is an implementation of the BLAKE2s hash and PRF functions. * * Information: https://blake2.net/ * */ #include <crypto/internal/blake2s.h> #include <linux/types.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bug.h> static inline void blake2s_set_lastblock(struct blake2s_state *state) { state->f[0] = -1; } void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) { const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; if (unlikely(!inlen)) return; if (inlen > fill) { memcpy(state->buf + state->buflen, in, fill); blake2s_compress(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); state->buflen = 0; in += fill; inlen -= fill; } if (inlen > BLAKE2S_BLOCK_SIZE) { const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); blake2s_compress(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); } memcpy(state->buf + state->buflen, in, inlen); state->buflen += inlen; } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_state *state, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); blake2s_set_lastblock(state); memset(state->buf + state->buflen, 0, BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ blake2s_compress(state, state->buf, 1, state->buflen); cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); memcpy(out, state->h, state->outlen); memzero_explicit(state, sizeof(*state)); } EXPORT_SYMBOL(blake2s_final); static int __init blake2s_mod_init(void) { if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && WARN_ON(!blake2s_selftest())) return -ENODEV; return 0; } module_init(blake2s_mod_init); MODULE_DESCRIPTION("BLAKE2s hash function"); MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); |
| 25 2 27 27 1439 1443 1405 27 27 16 16 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/ip.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <net/netns/generic.h> #include <net/route.h> #include <net/ip.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter_ipv4.h> #include <net/netfilter/ipv4/nf_defrag_ipv4.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif #include <net/netfilter/nf_conntrack_zones.h> static DEFINE_MUTEX(defrag4_mutex); static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, u_int32_t user) { int err; local_bh_disable(); err = ip_defrag(net, skb, user); local_bh_enable(); if (!err) skb->ignore_df = 1; return err; } static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, struct sk_buff *skb) { u16 zone_id = NF_CT_DEFAULT_ZONE_ID; #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (skb_nfct(skb)) { enum ip_conntrack_info ctinfo; const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); } #endif if (nf_bridge_in_prerouting(skb)) return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id; if (hooknum == NF_INET_PRE_ROUTING) return IP_DEFRAG_CONNTRACK_IN + zone_id; else return IP_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv4_conntrack_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct sock *sk = skb->sk; if (sk && sk_fullsock(sk) && (sk->sk_family == PF_INET) && inet_test_bit(NODEFRAG, sk)) return NF_ACCEPT; #if IS_ENABLED(CONFIG_NF_CONNTRACK) #if !IS_ENABLED(CONFIG_NF_NAT) /* Previously seen (loopback)? Ignore. Do this before fragment check. */ if (skb_nfct(skb) && !nf_ct_is_template((struct nf_conn *)skb_nfct(skb))) return NF_ACCEPT; #endif if (skb->_nfct == IP_CT_UNTRACKED) return NF_ACCEPT; #endif /* Gather fragments. */ if (ip_is_fragment(ip_hdr(skb))) { enum ip_defrag_users user = nf_ct_defrag_user(state->hook, skb); if (nf_ct_ipv4_gather_frags(state->net, skb, user)) return NF_STOLEN; } return NF_ACCEPT; } static const struct nf_hook_ops ipv4_defrag_ops[] = { { .hook = ipv4_conntrack_defrag, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv4_conntrack_defrag, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_CONNTRACK_DEFRAG, }, }; static void __net_exit defrag4_net_exit(struct net *net) { if (net->nf.defrag_ipv4_users) { nf_unregister_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); net->nf.defrag_ipv4_users = 0; } } static const struct nf_defrag_hook defrag_hook = { .owner = THIS_MODULE, .enable = nf_defrag_ipv4_enable, .disable = nf_defrag_ipv4_disable, }; static struct pernet_operations defrag4_net_ops = { .exit = defrag4_net_exit, }; static int __init nf_defrag_init(void) { int err; err = register_pernet_subsys(&defrag4_net_ops); if (err) return err; rcu_assign_pointer(nf_defrag_v4_hook, &defrag_hook); return err; } static void __exit nf_defrag_fini(void) { rcu_assign_pointer(nf_defrag_v4_hook, NULL); unregister_pernet_subsys(&defrag4_net_ops); } int nf_defrag_ipv4_enable(struct net *net) { int err = 0; mutex_lock(&defrag4_mutex); if (net->nf.defrag_ipv4_users == UINT_MAX) { err = -EOVERFLOW; goto out_unlock; } if (net->nf.defrag_ipv4_users) { net->nf.defrag_ipv4_users++; goto out_unlock; } err = nf_register_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); if (err == 0) net->nf.defrag_ipv4_users = 1; out_unlock: mutex_unlock(&defrag4_mutex); return err; } EXPORT_SYMBOL_GPL(nf_defrag_ipv4_enable); void nf_defrag_ipv4_disable(struct net *net) { mutex_lock(&defrag4_mutex); if (net->nf.defrag_ipv4_users) { net->nf.defrag_ipv4_users--; if (net->nf.defrag_ipv4_users == 0) nf_unregister_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); } mutex_unlock(&defrag4_mutex); } EXPORT_SYMBOL_GPL(nf_defrag_ipv4_disable); module_init(nf_defrag_init); module_exit(nf_defrag_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv4 defragmentation support"); |
| 7 7 6 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Universal Host Controller Interface driver for USB. * * Maintainer: Alan Stern <stern@rowland.harvard.edu> * * (C) Copyright 1999 Linus Torvalds * (C) Copyright 1999-2002 Johannes Erdfelt, johannes@erdfelt.com * (C) Copyright 1999 Randy Dunlap * (C) Copyright 1999 Georg Acher, acher@in.tum.de * (C) Copyright 1999 Deti Fliegl, deti@fliegl.de * (C) Copyright 1999 Thomas Sailer, sailer@ife.ee.ethz.ch * (C) Copyright 1999 Roman Weissgaerber, weissg@vienna.at * (C) Copyright 2000 Yggdrasil Computing, Inc. (port of new PCI interface * support from usb-ohci.c by Adam Richter, adam@yggdrasil.com). * (C) Copyright 1999 Gregory P. Smith (from usb-ohci.c) * (C) Copyright 2004-2007 Alan Stern, stern@rowland.harvard.edu */ /* * Technically, updating td->status here is a race, but it's not really a * problem. The worst that can happen is that we set the IOC bit again * generating a spurious interrupt. We could fix this by creating another * QH and leaving the IOC bit always set, but then we would have to play * games with the FSBR code to make sure we get the correct order in all * the cases. I don't think it's worth the effort */ static void uhci_set_next_interrupt(struct uhci_hcd *uhci) { if (uhci->is_stopped) mod_timer(&uhci_to_hcd(uhci)->rh_timer, jiffies); uhci->term_td->status |= cpu_to_hc32(uhci, TD_CTRL_IOC); } static inline void uhci_clear_next_interrupt(struct uhci_hcd *uhci) { uhci->term_td->status &= ~cpu_to_hc32(uhci, TD_CTRL_IOC); } /* * Full-Speed Bandwidth Reclamation (FSBR). * We turn on FSBR whenever a queue that wants it is advancing, * and leave it on for a short time thereafter. */ static void uhci_fsbr_on(struct uhci_hcd *uhci) { struct uhci_qh *lqh; /* The terminating skeleton QH always points back to the first * FSBR QH. Make the last async QH point to the terminating * skeleton QH. */ uhci->fsbr_is_on = 1; lqh = list_entry(uhci->skel_async_qh->node.prev, struct uhci_qh, node); lqh->link = LINK_TO_QH(uhci, uhci->skel_term_qh); } static void uhci_fsbr_off(struct uhci_hcd *uhci) { struct uhci_qh *lqh; /* Remove the link from the last async QH to the terminating * skeleton QH. */ uhci->fsbr_is_on = 0; lqh = list_entry(uhci->skel_async_qh->node.prev, struct uhci_qh, node); lqh->link = UHCI_PTR_TERM(uhci); } static void uhci_add_fsbr(struct uhci_hcd *uhci, struct urb *urb) { struct urb_priv *urbp = urb->hcpriv; urbp->fsbr = 1; } static void uhci_urbp_wants_fsbr(struct uhci_hcd *uhci, struct urb_priv *urbp) { if (urbp->fsbr) { uhci->fsbr_is_wanted = 1; if (!uhci->fsbr_is_on) uhci_fsbr_on(uhci); else if (uhci->fsbr_expiring) { uhci->fsbr_expiring = 0; del_timer(&uhci->fsbr_timer); } } } static void uhci_fsbr_timeout(struct timer_list *t) { struct uhci_hcd *uhci = from_timer(uhci, t, fsbr_timer); unsigned long flags; spin_lock_irqsave(&uhci->lock, flags); if (uhci->fsbr_expiring) { uhci->fsbr_expiring = 0; uhci_fsbr_off(uhci); } spin_unlock_irqrestore(&uhci->lock, flags); } static struct uhci_td *uhci_alloc_td(struct uhci_hcd *uhci) { dma_addr_t dma_handle; struct uhci_td *td; td = dma_pool_alloc(uhci->td_pool, GFP_ATOMIC, &dma_handle); if (!td) return NULL; td->dma_handle = dma_handle; td->frame = -1; INIT_LIST_HEAD(&td->list); INIT_LIST_HEAD(&td->fl_list); return td; } static void uhci_free_td(struct uhci_hcd *uhci, struct uhci_td *td) { if (!list_empty(&td->list)) dev_WARN(uhci_dev(uhci), "td %p still in list!\n", td); if (!list_empty(&td->fl_list)) dev_WARN(uhci_dev(uhci), "td %p still in fl_list!\n", td); dma_pool_free(uhci->td_pool, td, td->dma_handle); } static inline void uhci_fill_td(struct uhci_hcd *uhci, struct uhci_td *td, u32 status, u32 token, u32 buffer) { td->status = cpu_to_hc32(uhci, status); td->token = cpu_to_hc32(uhci, token); td->buffer = cpu_to_hc32(uhci, buffer); } static void uhci_add_td_to_urbp(struct uhci_td *td, struct urb_priv *urbp) { list_add_tail(&td->list, &urbp->td_list); } static void uhci_remove_td_from_urbp(struct uhci_td *td) { list_del_init(&td->list); } /* * We insert Isochronous URBs directly into the frame list at the beginning */ static inline void uhci_insert_td_in_frame_list(struct uhci_hcd *uhci, struct uhci_td *td, unsigned framenum) { framenum &= (UHCI_NUMFRAMES - 1); td->frame = framenum; /* Is there a TD already mapped there? */ if (uhci->frame_cpu[framenum]) { struct uhci_td *ftd, *ltd; ftd = uhci->frame_cpu[framenum]; ltd = list_entry(ftd->fl_list.prev, struct uhci_td, fl_list); list_add_tail(&td->fl_list, &ftd->fl_list); td->link = ltd->link; wmb(); ltd->link = LINK_TO_TD(uhci, td); } else { td->link = uhci->frame[framenum]; wmb(); uhci->frame[framenum] = LINK_TO_TD(uhci, td); uhci->frame_cpu[framenum] = td; } } static inline void uhci_remove_td_from_frame_list(struct uhci_hcd *uhci, struct uhci_td *td) { /* If it's not inserted, don't remove it */ if (td->frame == -1) { WARN_ON(!list_empty(&td->fl_list)); return; } if (uhci->frame_cpu[td->frame] == td) { if (list_empty(&td->fl_list)) { uhci->frame[td->frame] = td->link; uhci->frame_cpu[td->frame] = NULL; } else { struct uhci_td *ntd; ntd = list_entry(td->fl_list.next, struct uhci_td, fl_list); uhci->frame[td->frame] = LINK_TO_TD(uhci, ntd); uhci->frame_cpu[td->frame] = ntd; } } else { struct uhci_td *ptd; ptd = list_entry(td->fl_list.prev, struct uhci_td, fl_list); ptd->link = td->link; } list_del_init(&td->fl_list); td->frame = -1; } static inline void uhci_remove_tds_from_frame(struct uhci_hcd *uhci, unsigned int framenum) { struct uhci_td *ftd, *ltd; framenum &= (UHCI_NUMFRAMES - 1); ftd = uhci->frame_cpu[framenum]; if (ftd) { ltd = list_entry(ftd->fl_list.prev, struct uhci_td, fl_list); uhci->frame[framenum] = ltd->link; uhci->frame_cpu[framenum] = NULL; while (!list_empty(&ftd->fl_list)) list_del_init(ftd->fl_list.prev); } } /* * Remove all the TDs for an Isochronous URB from the frame list */ static void uhci_unlink_isochronous_tds(struct uhci_hcd *uhci, struct urb *urb) { struct urb_priv *urbp = (struct urb_priv *) urb->hcpriv; struct uhci_td *td; list_for_each_entry(td, &urbp->td_list, list) uhci_remove_td_from_frame_list(uhci, td); } static struct uhci_qh *uhci_alloc_qh(struct uhci_hcd *uhci, struct usb_device *udev, struct usb_host_endpoint *hep) { dma_addr_t dma_handle; struct uhci_qh *qh; qh = dma_pool_zalloc(uhci->qh_pool, GFP_ATOMIC, &dma_handle); if (!qh) return NULL; qh->dma_handle = dma_handle; qh->element = UHCI_PTR_TERM(uhci); qh->link = UHCI_PTR_TERM(uhci); INIT_LIST_HEAD(&qh->queue); INIT_LIST_HEAD(&qh->node); if (udev) { /* Normal QH */ qh->type = usb_endpoint_type(&hep->desc); if (qh->type != USB_ENDPOINT_XFER_ISOC) { qh->dummy_td = uhci_alloc_td(uhci); if (!qh->dummy_td) { dma_pool_free(uhci->qh_pool, qh, dma_handle); return NULL; } } qh->state = QH_STATE_IDLE; qh->hep = hep; qh->udev = udev; hep->hcpriv = qh; if (qh->type == USB_ENDPOINT_XFER_INT || qh->type == USB_ENDPOINT_XFER_ISOC) qh->load = usb_calc_bus_time(udev->speed, usb_endpoint_dir_in(&hep->desc), qh->type == USB_ENDPOINT_XFER_ISOC, usb_endpoint_maxp(&hep->desc)) / 1000 + 1; } else { /* Skeleton QH */ qh->state = QH_STATE_ACTIVE; qh->type = -1; } return qh; } static void uhci_free_qh(struct uhci_hcd *uhci, struct uhci_qh *qh) { WARN_ON(qh->state != QH_STATE_IDLE && qh->udev); if (!list_empty(&qh->queue)) dev_WARN(uhci_dev(uhci), "qh %p list not empty!\n", qh); list_del(&qh->node); if (qh->udev) { qh->hep->hcpriv = NULL; if (qh->dummy_td) uhci_free_td(uhci, qh->dummy_td); } dma_pool_free(uhci->qh_pool, qh, qh->dma_handle); } /* * When a queue is stopped and a dequeued URB is given back, adjust * the previous TD link (if the URB isn't first on the queue) or * save its toggle value (if it is first and is currently executing). * * Returns 0 if the URB should not yet be given back, 1 otherwise. */ static int uhci_cleanup_queue(struct uhci_hcd *uhci, struct uhci_qh *qh, struct urb *urb) { struct urb_priv *urbp = urb->hcpriv; struct uhci_td *td; int ret = 1; /* Isochronous pipes don't use toggles and their TD link pointers * get adjusted during uhci_urb_dequeue(). But since their queues * cannot truly be stopped, we have to watch out for dequeues * occurring after the nominal unlink frame. */ if (qh->type == USB_ENDPOINT_XFER_ISOC) { ret = (uhci->frame_number + uhci->is_stopped != qh->unlink_frame); goto done; } /* If the URB isn't first on its queue, adjust the link pointer * of the last TD in the previous URB. The toggle doesn't need * to be saved since this URB can't be executing yet. */ if (qh->queue.next != &urbp->node) { struct urb_priv *purbp; struct uhci_td *ptd; purbp = list_entry(urbp->node.prev, struct urb_priv, node); WARN_ON(list_empty(&purbp->td_list)); ptd = list_entry(purbp->td_list.prev, struct uhci_td, list); td = list_entry(urbp->td_list.prev, struct uhci_td, list); ptd->link = td->link; goto done; } /* If the QH element pointer is UHCI_PTR_TERM then then currently * executing URB has already been unlinked, so this one isn't it. */ if (qh_element(qh) == UHCI_PTR_TERM(uhci)) goto done; qh->element = UHCI_PTR_TERM(uhci); /* Control pipes don't have to worry about toggles */ if (qh->type == USB_ENDPOINT_XFER_CONTROL) goto done; /* Save the next toggle value */ WARN_ON(list_empty(&urbp->td_list)); td = list_entry(urbp->td_list.next, struct uhci_td, list); qh->needs_fixup = 1; qh->initial_toggle = uhci_toggle(td_token(uhci, td)); done: return ret; } /* * Fix up the data toggles for URBs in a queue, when one of them * terminates early (short transfer, error, or dequeued). */ static void uhci_fixup_toggles(struct uhci_hcd *uhci, struct uhci_qh *qh, int skip_first) { struct urb_priv *urbp = NULL; struct uhci_td *td; unsigned int toggle = qh->initial_toggle; unsigned int pipe; /* Fixups for a short transfer start with the second URB in the * queue (the short URB is the first). */ if (skip_first) urbp = list_entry(qh->queue.next, struct urb_priv, node); /* When starting with the first URB, if the QH element pointer is * still valid then we know the URB's toggles are okay. */ else if (qh_element(qh) != UHCI_PTR_TERM(uhci)) toggle = 2; /* Fix up the toggle for the URBs in the queue. Normally this * loop won't run more than once: When an error or short transfer * occurs, the queue usually gets emptied. */ urbp = list_prepare_entry(urbp, &qh->queue, node); list_for_each_entry_continue(urbp, &qh->queue, node) { /* If the first TD has the right toggle value, we don't * need to change any toggles in this URB */ td = list_entry(urbp->td_list.next, struct uhci_td, list); if (toggle > 1 || uhci_toggle(td_token(uhci, td)) == toggle) { td = list_entry(urbp->td_list.prev, struct uhci_td, list); toggle = uhci_toggle(td_token(uhci, td)) ^ 1; /* Otherwise all the toggles in the URB have to be switched */ } else { list_for_each_entry(td, &urbp->td_list, list) { td->token ^= cpu_to_hc32(uhci, TD_TOKEN_TOGGLE); toggle ^= 1; } } } wmb(); pipe = list_entry(qh->queue.next, struct urb_priv, node)->urb->pipe; usb_settoggle(qh->udev, usb_pipeendpoint(pipe), usb_pipeout(pipe), toggle); qh->needs_fixup = 0; } /* * Link an Isochronous QH into its skeleton's list */ static inline void link_iso(struct uhci_hcd *uhci, struct uhci_qh *qh) { list_add_tail(&qh->node, &uhci->skel_iso_qh->node); /* Isochronous QHs aren't linked by the hardware */ } /* * Link a high-period interrupt QH into the schedule at the end of its * skeleton's list */ static void link_interrupt(struct uhci_hcd *uhci, struct uhci_qh *qh) { struct uhci_qh *pqh; list_add_tail(&qh->node, &uhci->skelqh[qh->skel]->node); pqh = list_entry(qh->node.prev, struct uhci_qh, node); qh->link = pqh->link; wmb(); pqh->link = LINK_TO_QH(uhci, qh); } /* * Link a period-1 interrupt or async QH into the schedule at the * correct spot in the async skeleton's list, and update the FSBR link */ static void link_async(struct uhci_hcd *uhci, struct uhci_qh *qh) { struct uhci_qh *pqh; __hc32 link_to_new_qh; /* Find the predecessor QH for our new one and insert it in the list. * The list of QHs is expected to be short, so linear search won't * take too long. */ list_for_each_entry_reverse(pqh, &uhci->skel_async_qh->node, node) { if (pqh->skel <= qh->skel) break; } list_add(&qh->node, &pqh->node); /* Link it into the schedule */ qh->link = pqh->link; wmb(); link_to_new_qh = LINK_TO_QH(uhci, qh); pqh->link = link_to_new_qh; /* If this is now the first FSBR QH, link the terminating skeleton * QH to it. */ if (pqh->skel < SKEL_FSBR && qh->skel >= SKEL_FSBR) uhci->skel_term_qh->link = link_to_new_qh; } /* * Put a QH on the schedule in both hardware and software */ static void uhci_activate_qh(struct uhci_hcd *uhci, struct uhci_qh *qh) { WARN_ON(list_empty(&qh->queue)); /* Set the element pointer if it isn't set already. * This isn't needed for Isochronous queues, but it doesn't hurt. */ if (qh_element(qh) == UHCI_PTR_TERM(uhci)) { struct urb_priv *urbp = list_entry(qh->queue.next, struct urb_priv, node); struct uhci_td *td = list_entry(urbp->td_list.next, struct uhci_td, list); qh->element = LINK_TO_TD(uhci, td); } /* Treat the queue as if it has just advanced */ qh->wait_expired = 0; qh->advance_jiffies = jiffies; if (qh->state == QH_STATE_ACTIVE) return; qh->state = QH_STATE_ACTIVE; /* Move the QH from its old list to the correct spot in the appropriate * skeleton's list */ if (qh == uhci->next_qh) uhci->next_qh = list_entry(qh->node.next, struct uhci_qh, node); list_del(&qh->node); if (qh->skel == SKEL_ISO) link_iso(uhci, qh); else if (qh->skel < SKEL_ASYNC) link_interrupt(uhci, qh); else link_async(uhci, qh); } /* * Unlink a high-period interrupt QH from the schedule */ static void unlink_interrupt(struct uhci_hcd *uhci, struct uhci_qh *qh) { struct uhci_qh *pqh; pqh = list_entry(qh->node.prev, struct uhci_qh, node); pqh->link = qh->link; mb(); } /* * Unlink a period-1 interrupt or async QH from the schedule */ static void unlink_async(struct uhci_hcd *uhci, struct uhci_qh *qh) { struct uhci_qh *pqh; __hc32 link_to_next_qh = qh->link; pqh = list_entry(qh->node.prev, struct uhci_qh, node); pqh->link = link_to_next_qh; /* If this was the old first FSBR QH, link the terminating skeleton * QH to the next (new first FSBR) QH. */ if (pqh->skel < SKEL_FSBR && qh->skel >= SKEL_FSBR) uhci->skel_term_qh->link = link_to_next_qh; mb(); } /* * Take a QH off the hardware schedule */ static void uhci_unlink_qh(struct uhci_hcd *uhci, struct uhci_qh *qh) { if (qh->state == QH_STATE_UNLINKING) return; WARN_ON(qh->state != QH_STATE_ACTIVE || !qh->udev); qh->state = QH_STATE_UNLINKING; /* Unlink the QH from the schedule and record when we did it */ if (qh->skel == SKEL_ISO) ; else if (qh->skel < SKEL_ASYNC) unlink_interrupt(uhci, qh); else unlink_async(uhci, qh); uhci_get_current_frame_number(uhci); qh->unlink_frame = uhci->frame_number; /* Force an interrupt so we know when the QH is fully unlinked */ if (list_empty(&uhci->skel_unlink_qh->node) || uhci->is_stopped) uhci_set_next_interrupt(uhci); /* Move the QH from its old list to the end of the unlinking list */ if (qh == uhci->next_qh) uhci->next_qh = list_entry(qh->node.next, struct uhci_qh, node); list_move_tail(&qh->node, &uhci->skel_unlink_qh->node); } /* * When we and the controller are through with a QH, it becomes IDLE. * This happens when a QH has been off the schedule (on the unlinking * list) for more than one frame, or when an error occurs while adding * the first URB onto a new QH. */ static void uhci_make_qh_idle(struct uhci_hcd *uhci, struct uhci_qh *qh) { WARN_ON(qh->state == QH_STATE_ACTIVE); if (qh == uhci->next_qh) uhci->next_qh = list_entry(qh->node.next, struct uhci_qh, node); list_move(&qh->node, &uhci->idle_qh_list); qh->state = QH_STATE_IDLE; /* Now that the QH is idle, its post_td isn't being used */ if (qh->post_td) { uhci_free_td(uhci, qh->post_td); qh->post_td = NULL; } /* If anyone is waiting for a QH to become idle, wake them up */ if (uhci->num_waiting) wake_up_all(&uhci->waitqh); } /* * Find the highest existing bandwidth load for a given phase and period. */ static int uhci_highest_load(struct uhci_hcd *uhci, int phase, int period) { int highest_load = uhci->load[phase]; for (phase += period; phase < MAX_PHASE; phase += period) highest_load = max_t(int, highest_load, uhci->load[phase]); return highest_load; } /* * Set qh->phase to the optimal phase for a periodic transfer and * check whether the bandwidth requirement is acceptable. */ static int uhci_check_bandwidth(struct uhci_hcd *uhci, struct uhci_qh *qh) { int minimax_load; /* Find the optimal phase (unless it is already set) and get * its load value. */ if (qh->phase >= 0) minimax_load = uhci_highest_load(uhci, qh->phase, qh->period); else { int phase, load; int max_phase = min_t(int, MAX_PHASE, qh->period); qh->phase = 0; minimax_load = uhci_highest_load(uhci, qh->phase, qh->period); for (phase = 1; phase < max_phase; ++phase) { load = uhci_highest_load(uhci, phase, qh->period); if (load < minimax_load) { minimax_load = load; qh->phase = phase; } } } /* Maximum allowable periodic bandwidth is 90%, or 900 us per frame */ if (minimax_load + qh->load > 900) { dev_dbg(uhci_dev(uhci), "bandwidth allocation failed: " "period %d, phase %d, %d + %d us\n", qh->period, qh->phase, minimax_load, qh->load); return -ENOSPC; } return 0; } /* * Reserve a periodic QH's bandwidth in the schedule */ static void uhci_reserve_bandwidth(struct uhci_hcd *uhci, struct uhci_qh *qh) { int i; int load = qh->load; char *p = "??"; for (i = qh->phase; i < MAX_PHASE; i += qh->period) { uhci->load[i] += load; uhci->total_load += load; } uhci_to_hcd(uhci)->self.bandwidth_allocated = uhci->total_load / MAX_PHASE; switch (qh->type) { case USB_ENDPOINT_XFER_INT: ++uhci_to_hcd(uhci)->self.bandwidth_int_reqs; p = "INT"; break; case USB_ENDPOINT_XFER_ISOC: ++uhci_to_hcd(uhci)->self.bandwidth_isoc_reqs; p = "ISO"; break; } qh->bandwidth_reserved = 1; dev_dbg(uhci_dev(uhci), "%s dev %d ep%02x-%s, period %d, phase %d, %d us\n", "reserve", qh->udev->devnum, qh->hep->desc.bEndpointAddress, p, qh->period, qh->phase, load); } /* * Release a periodic QH's bandwidth reservation */ static void uhci_release_bandwidth(struct uhci_hcd *uhci, struct uhci_qh *qh) { int i; int load = qh->load; char *p = "??"; for (i = qh->phase; i < MAX_PHASE; i += qh->period) { uhci->load[i] -= load; uhci->total_load -= load; } uhci_to_hcd(uhci)->self.bandwidth_allocated = uhci->total_load / MAX_PHASE; switch (qh->type) { case USB_ENDPOINT_XFER_INT: --uhci_to_hcd(uhci)->self.bandwidth_int_reqs; p = "INT"; break; case USB_ENDPOINT_XFER_ISOC: --uhci_to_hcd(uhci)->self.bandwidth_isoc_reqs; p = "ISO"; break; } qh->bandwidth_reserved = 0; dev_dbg(uhci_dev(uhci), "%s dev %d ep%02x-%s, period %d, phase %d, %d us\n", "release", qh->udev->devnum, qh->hep->desc.bEndpointAddress, p, qh->period, qh->phase, load); } static inline struct urb_priv *uhci_alloc_urb_priv(struct uhci_hcd *uhci, struct urb *urb) { struct urb_priv *urbp; urbp = kmem_cache_zalloc(uhci_up_cachep, GFP_ATOMIC); if (!urbp) return NULL; urbp->urb = urb; urb->hcpriv = urbp; INIT_LIST_HEAD(&urbp->node); INIT_LIST_HEAD(&urbp->td_list); return urbp; } static void uhci_free_urb_priv(struct uhci_hcd *uhci, struct urb_priv *urbp) { struct uhci_td *td, *tmp; if (!list_empty(&urbp->node)) dev_WARN(uhci_dev(uhci), "urb %p still on QH's list!\n", urbp->urb); list_for_each_entry_safe(td, tmp, &urbp->td_list, list) { uhci_remove_td_from_urbp(td); uhci_free_td(uhci, td); } kmem_cache_free(uhci_up_cachep, urbp); } /* * Map status to standard result codes * * <status> is (td_status(uhci, td) & 0xF60000), a.k.a. * uhci_status_bits(td_status(uhci, td)). * Note: <status> does not include the TD_CTRL_NAK bit. * <dir_out> is True for output TDs and False for input TDs. */ static int uhci_map_status(int status, int dir_out) { if (!status) return 0; if (status & TD_CTRL_BITSTUFF) /* Bitstuff error */ return -EPROTO; if (status & TD_CTRL_CRCTIMEO) { /* CRC/Timeout */ if (dir_out) return -EPROTO; else return -EILSEQ; } if (status & TD_CTRL_BABBLE) /* Babble */ return -EOVERFLOW; if (status & TD_CTRL_DBUFERR) /* Buffer error */ return -ENOSR; if (status & TD_CTRL_STALLED) /* Stalled */ return -EPIPE; return 0; } /* * Control transfers */ static int uhci_submit_control(struct uhci_hcd *uhci, struct urb *urb, struct uhci_qh *qh) { struct uhci_td *td; unsigned long destination, status; int maxsze = usb_endpoint_maxp(&qh->hep->desc); int len = urb->transfer_buffer_length; dma_addr_t data = urb->transfer_dma; __hc32 *plink; struct urb_priv *urbp = urb->hcpriv; int skel; /* The "pipe" thing contains the destination in bits 8--18 */ destination = (urb->pipe & PIPE_DEVEP_MASK) | USB_PID_SETUP; /* 3 errors, dummy TD remains inactive */ status = uhci_maxerr(3); if (urb->dev->speed == USB_SPEED_LOW) status |= TD_CTRL_LS; /* * Build the TD for the control request setup packet */ td = qh->dummy_td; uhci_add_td_to_urbp(td, urbp); uhci_fill_td(uhci, td, status, destination | uhci_explen(8), urb->setup_dma); plink = &td->link; status |= TD_CTRL_ACTIVE; /* * If direction is "send", change the packet ID from SETUP (0x2D) * to OUT (0xE1). Else change it from SETUP to IN (0x69) and * set Short Packet Detect (SPD) for all data packets. * * 0-length transfers always get treated as "send". */ if (usb_pipeout(urb->pipe) || len == 0) destination ^= (USB_PID_SETUP ^ USB_PID_OUT); else { destination ^= (USB_PID_SETUP ^ USB_PID_IN); status |= TD_CTRL_SPD; } /* * Build the DATA TDs */ while (len > 0) { int pktsze = maxsze; if (len <= pktsze) { /* The last data packet */ pktsze = len; status &= ~TD_CTRL_SPD; } td = uhci_alloc_td(uhci); if (!td) goto nomem; *plink = LINK_TO_TD(uhci, td); /* Alternate Data0/1 (start with Data1) */ destination ^= TD_TOKEN_TOGGLE; uhci_add_td_to_urbp(td, urbp); uhci_fill_td(uhci, td, status, destination | uhci_explen(pktsze), data); plink = &td->link; data += pktsze; len -= pktsze; } /* * Build the final TD for control status */ td = uhci_alloc_td(uhci); if (!td) goto nomem; *plink = LINK_TO_TD(uhci, td); /* Change direction for the status transaction */ destination ^= (USB_PID_IN ^ USB_PID_OUT); destination |= TD_TOKEN_TOGGLE; /* End in Data1 */ uhci_add_td_to_urbp(td, urbp); uhci_fill_td(uhci, td, status | TD_CTRL_IOC, destination | uhci_explen(0), 0); plink = &td->link; /* * Build the new dummy TD and activate the old one */ td = uhci_alloc_td(uhci); if (!td) goto nomem; *plink = LINK_TO_TD(uhci, td); uhci_fill_td(uhci, td, 0, USB_PID_OUT | uhci_explen(0), 0); wmb(); qh->dummy_td->status |= cpu_to_hc32(uhci, TD_CTRL_ACTIVE); qh->dummy_td = td; /* Low-speed transfers get a different queue, and won't hog the bus. * Also, some devices enumerate better without FSBR; the easiest way * to do that is to put URBs on the low-speed queue while the device * isn't in the CONFIGURED state. */ if (urb->dev->speed == USB_SPEED_LOW || urb->dev->state != USB_STATE_CONFIGURED) skel = SKEL_LS_CONTROL; else { skel = SKEL_FS_CONTROL; uhci_add_fsbr(uhci, urb); } if (qh->state != QH_STATE_ACTIVE) qh->skel = skel; return 0; nomem: /* Remove the dummy TD from the td_list so it doesn't get freed */ uhci_remove_td_from_urbp(qh->dummy_td); return -ENOMEM; } /* * Common submit for bulk and interrupt */ static int uhci_submit_common(struct uhci_hcd *uhci, struct urb *urb, struct uhci_qh *qh) { struct uhci_td *td; unsigned long destination, status; int maxsze = usb_endpoint_maxp(&qh->hep->desc); int len = urb->transfer_buffer_length; int this_sg_len; dma_addr_t data; __hc32 *plink; struct urb_priv *urbp = urb->hcpriv; unsigned int toggle; struct scatterlist *sg; int i; if (len < 0) return -EINVAL; /* The "pipe" thing contains the destination in bits 8--18 */ destination = (urb->pipe & PIPE_DEVEP_MASK) | usb_packetid(urb->pipe); toggle = usb_gettoggle(urb->dev, usb_pipeendpoint(urb->pipe), usb_pipeout(urb->pipe)); /* 3 errors, dummy TD remains inactive */ status = uhci_maxerr(3); if (urb->dev->speed == USB_SPEED_LOW) status |= TD_CTRL_LS; if (usb_pipein(urb->pipe)) status |= TD_CTRL_SPD; i = urb->num_mapped_sgs; if (len > 0 && i > 0) { sg = urb->sg; data = sg_dma_address(sg); /* urb->transfer_buffer_length may be smaller than the * size of the scatterlist (or vice versa) */ this_sg_len = min_t(int, sg_dma_len(sg), len); } else { sg = NULL; data = urb->transfer_dma; this_sg_len = len; } /* * Build the DATA TDs */ plink = NULL; td = qh->dummy_td; for (;;) { /* Allow zero length packets */ int pktsze = maxsze; if (len <= pktsze) { /* The last packet */ pktsze = len; if (!(urb->transfer_flags & URB_SHORT_NOT_OK)) status &= ~TD_CTRL_SPD; } if (plink) { td = uhci_alloc_td(uhci); if (!td) goto nomem; *plink = LINK_TO_TD(uhci, td); } uhci_add_td_to_urbp(td, urbp); uhci_fill_td(uhci, td, status, destination | uhci_explen(pktsze) | (toggle << TD_TOKEN_TOGGLE_SHIFT), data); plink = &td->link; status |= TD_CTRL_ACTIVE; toggle ^= 1; data += pktsze; this_sg_len -= pktsze; len -= maxsze; if (this_sg_len <= 0) { if (--i <= 0 || len <= 0) break; sg = sg_next(sg); data = sg_dma_address(sg); this_sg_len = min_t(int, sg_dma_len(sg), len); } } /* * URB_ZERO_PACKET means adding a 0-length packet, if direction * is OUT and the transfer_length was an exact multiple of maxsze, * hence (len = transfer_length - N * maxsze) == 0 * however, if transfer_length == 0, the zero packet was already * prepared above. */ if ((urb->transfer_flags & URB_ZERO_PACKET) && usb_pipeout(urb->pipe) && len == 0 && urb->transfer_buffer_length > 0) { td = uhci_alloc_td(uhci); if (!td) goto nomem; *plink = LINK_TO_TD(uhci, td); uhci_add_td_to_urbp(td, urbp); uhci_fill_td(uhci, td, status, destination | uhci_explen(0) | (toggle << TD_TOKEN_TOGGLE_SHIFT), data); plink = &td->link; toggle ^= 1; } /* Set the interrupt-on-completion flag on the last packet. * A more-or-less typical 4 KB URB (= size of one memory page) * will require about 3 ms to transfer; that's a little on the * fast side but not enough to justify delaying an interrupt * more than 2 or 3 URBs, so we will ignore the URB_NO_INTERRUPT * flag setting. */ td->status |= cpu_to_hc32(uhci, TD_CTRL_IOC); /* * Build the new dummy TD and activate the old one */ td = uhci_alloc_td(uhci); if (!td) goto nomem; *plink = LINK_TO_TD(uhci, td); uhci_fill_td(uhci, td, 0, USB_PID_OUT | uhci_explen(0), 0); wmb(); qh->dummy_td->status |= cpu_to_hc32(uhci, TD_CTRL_ACTIVE); qh->dummy_td = td; usb_settoggle(urb->dev, usb_pipeendpoint(urb->pipe), usb_pipeout(urb->pipe), toggle); return 0; nomem: /* Remove the dummy TD from the td_list so it doesn't get freed */ uhci_remove_td_from_urbp(qh->dummy_td); return -ENOMEM; } static int uhci_submit_bulk(struct uhci_hcd *uhci, struct urb *urb, struct uhci_qh *qh) { int ret; /* Can't have low-speed bulk transfers */ if (urb->dev->speed == USB_SPEED_LOW) return -EINVAL; if (qh->state != QH_STATE_ACTIVE) qh->skel = SKEL_BULK; ret = uhci_submit_common(uhci, urb, qh); if (ret == 0) uhci_add_fsbr(uhci, urb); return ret; } static int uhci_submit_interrupt(struct uhci_hcd *uhci, struct urb *urb, struct uhci_qh *qh) { int ret; /* USB 1.1 interrupt transfers only involve one packet per interval. * Drivers can submit URBs of any length, but longer ones will need * multiple intervals to complete. */ if (!qh->bandwidth_reserved) { int exponent; /* Figure out which power-of-two queue to use */ for (exponent = 7; exponent >= 0; --exponent) { if ((1 << exponent) <= urb->interval) break; } if (exponent < 0) return -EINVAL; /* If the slot is full, try a lower period */ do { qh->period = 1 << exponent; qh->skel = SKEL_INDEX(exponent); /* For now, interrupt phase is fixed by the layout * of the QH lists. */ qh->phase = (qh->period / 2) & (MAX_PHASE - 1); ret = uhci_check_bandwidth(uhci, qh); } while (ret != 0 && --exponent >= 0); if (ret) return ret; } else if (qh->period > urb->interval) return -EINVAL; /* Can't decrease the period */ ret = uhci_submit_common(uhci, urb, qh); if (ret == 0) { urb->interval = qh->period; if (!qh->bandwidth_reserved) uhci_reserve_bandwidth(uhci, qh); } return ret; } /* * Fix up the data structures following a short transfer */ static int uhci_fixup_short_transfer(struct uhci_hcd *uhci, struct uhci_qh *qh, struct urb_priv *urbp) { struct uhci_td *td; struct list_head *tmp; int ret; td = list_entry(urbp->td_list.prev, struct uhci_td, list); if (qh->type == USB_ENDPOINT_XFER_CONTROL) { /* When a control transfer is short, we have to restart * the queue at the status stage transaction, which is * the last TD. */ WARN_ON(list_empty(&urbp->td_list)); qh->element = LINK_TO_TD(uhci, td); tmp = td->list.prev; ret = -EINPROGRESS; } else { /* When a bulk/interrupt transfer is short, we have to * fix up the toggles of the following URBs on the queue * before restarting the queue at the next URB. */ qh->initial_toggle = uhci_toggle(td_token(uhci, qh->post_td)) ^ 1; uhci_fixup_toggles(uhci, qh, 1); if (list_empty(&urbp->td_list)) td = qh->post_td; qh->element = td->link; tmp = urbp->td_list.prev; ret = 0; } /* Remove all the TDs we skipped over, from tmp back to the start */ while (tmp != &urbp->td_list) { td = list_entry(tmp, struct uhci_td, list); tmp = tmp->prev; uhci_remove_td_from_urbp(td); uhci_free_td(uhci, td); } return ret; } /* * Common result for control, bulk, and interrupt */ static int uhci_result_common(struct uhci_hcd *uhci, struct urb *urb) { struct urb_priv *urbp = urb->hcpriv; struct uhci_qh *qh = urbp->qh; struct uhci_td *td, *tmp; unsigned status; int ret = 0; list_for_each_entry_safe(td, tmp, &urbp->td_list, list) { unsigned int ctrlstat; int len; ctrlstat = td_status(uhci, td); status = uhci_status_bits(ctrlstat); if (status & TD_CTRL_ACTIVE) return -EINPROGRESS; len = uhci_actual_length(ctrlstat); urb->actual_length += len; if (status) { ret = uhci_map_status(status, uhci_packetout(td_token(uhci, td))); if ((debug == 1 && ret != -EPIPE) || debug > 1) { /* Some debugging code */ dev_dbg(&urb->dev->dev, "%s: failed with status %x\n", __func__, status); if (debug > 1 && errbuf) { /* Print the chain for debugging */ uhci_show_qh(uhci, urbp->qh, errbuf, ERRBUF_LEN - EXTRA_SPACE, 0); lprintk(errbuf); } } /* Did we receive a short packet? */ } else if (len < uhci_expected_length(td_token(uhci, td))) { /* For control transfers, go to the status TD if * this isn't already the last data TD */ if (qh->type == USB_ENDPOINT_XFER_CONTROL) { if (td->list.next != urbp->td_list.prev) ret = 1; } /* For bulk and interrupt, this may be an error */ else if (urb->transfer_flags & URB_SHORT_NOT_OK) ret = -EREMOTEIO; /* Fixup needed only if this isn't the URB's last TD */ else if (&td->list != urbp->td_list.prev) ret = 1; } uhci_remove_td_from_urbp(td); if (qh->post_td) uhci_free_td(uhci, qh->post_td); qh->post_td = td; if (ret != 0) goto err; } return ret; err: if (ret < 0) { /* Note that the queue has stopped and save * the next toggle value */ qh->element = UHCI_PTR_TERM(uhci); qh->is_stopped = 1; qh->needs_fixup = (qh->type != USB_ENDPOINT_XFER_CONTROL); qh->initial_toggle = uhci_toggle(td_token(uhci, td)) ^ (ret == -EREMOTEIO); } else /* Short packet received */ ret = uhci_fixup_short_transfer(uhci, qh, urbp); return ret; } /* * Isochronous transfers */ static int uhci_submit_isochronous(struct uhci_hcd *uhci, struct urb *urb, struct uhci_qh *qh) { struct uhci_td *td = NULL; /* Since urb->number_of_packets > 0 */ int i; unsigned frame, next; unsigned long destination, status; struct urb_priv *urbp = (struct urb_priv *) urb->hcpriv; /* Values must not be too big (could overflow below) */ if (urb->interval >= UHCI_NUMFRAMES || urb->number_of_packets >= UHCI_NUMFRAMES) return -EFBIG; uhci_get_current_frame_number(uhci); /* Check the period and figure out the starting frame number */ if (!qh->bandwidth_reserved) { qh->period = urb->interval; qh->phase = -1; /* Find the best phase */ i = uhci_check_bandwidth(uhci, qh); if (i) return i; /* Allow a little time to allocate the TDs */ next = uhci->frame_number + 10; frame = qh->phase; /* Round up to the first available slot */ frame += (next - frame + qh->period - 1) & -qh->period; } else if (qh->period != urb->interval) { return -EINVAL; /* Can't change the period */ } else { next = uhci->frame_number + 1; /* Find the next unused frame */ if (list_empty(&qh->queue)) { frame = qh->iso_frame; } else { struct urb *lurb; lurb = list_entry(qh->queue.prev, struct urb_priv, node)->urb; frame = lurb->start_frame + lurb->number_of_packets * lurb->interval; } /* Fell behind? */ if (!uhci_frame_before_eq(next, frame)) { /* USB_ISO_ASAP: Round up to the first available slot */ if (urb->transfer_flags & URB_ISO_ASAP) frame += (next - frame + qh->period - 1) & -qh->period; /* * Not ASAP: Use the next slot in the stream, * no matter what. */ else if (!uhci_frame_before_eq(next, frame + (urb->number_of_packets - 1) * qh->period)) dev_dbg(uhci_dev(uhci), "iso underrun %p (%u+%u < %u)\n", urb, frame, (urb->number_of_packets - 1) * qh->period, next); } } /* Make sure we won't have to go too far into the future */ if (uhci_frame_before_eq(uhci->last_iso_frame + UHCI_NUMFRAMES, frame + urb->number_of_packets * urb->interval)) return -EFBIG; urb->start_frame = frame; status = TD_CTRL_ACTIVE | TD_CTRL_IOS; destination = (urb->pipe & PIPE_DEVEP_MASK) | usb_packetid(urb->pipe); for (i = 0; i < urb->number_of_packets; i++) { td = uhci_alloc_td(uhci); if (!td) return -ENOMEM; uhci_add_td_to_urbp(td, urbp); uhci_fill_td(uhci, td, status, destination | uhci_explen(urb->iso_frame_desc[i].length), urb->transfer_dma + urb->iso_frame_desc[i].offset); } /* Set the interrupt-on-completion flag on the last packet. */ td->status |= cpu_to_hc32(uhci, TD_CTRL_IOC); /* Add the TDs to the frame list */ frame = urb->start_frame; list_for_each_entry(td, &urbp->td_list, list) { uhci_insert_td_in_frame_list(uhci, td, frame); frame += qh->period; } if (list_empty(&qh->queue)) { qh->iso_packet_desc = &urb->iso_frame_desc[0]; qh->iso_frame = urb->start_frame; } qh->skel = SKEL_ISO; if (!qh->bandwidth_reserved) uhci_reserve_bandwidth(uhci, qh); return 0; } static int uhci_result_isochronous(struct uhci_hcd *uhci, struct urb *urb) { struct uhci_td *td, *tmp; struct urb_priv *urbp = urb->hcpriv; struct uhci_qh *qh = urbp->qh; list_for_each_entry_safe(td, tmp, &urbp->td_list, list) { unsigned int ctrlstat; int status; int actlength; if (uhci_frame_before_eq(uhci->cur_iso_frame, qh->iso_frame)) return -EINPROGRESS; uhci_remove_tds_from_frame(uhci, qh->iso_frame); ctrlstat = td_status(uhci, td); if (ctrlstat & TD_CTRL_ACTIVE) { status = -EXDEV; /* TD was added too late? */ } else { status = uhci_map_status(uhci_status_bits(ctrlstat), usb_pipeout(urb->pipe)); actlength = uhci_actual_length(ctrlstat); urb->actual_length += actlength; qh->iso_packet_desc->actual_length = actlength; qh->iso_packet_desc->status = status; } if (status) urb->error_count++; uhci_remove_td_from_urbp(td); uhci_free_td(uhci, td); qh->iso_frame += qh->period; ++qh->iso_packet_desc; } return 0; } static int uhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flags) { int ret; struct uhci_hcd *uhci = hcd_to_uhci(hcd); unsigned long flags; struct urb_priv *urbp; struct uhci_qh *qh; spin_lock_irqsave(&uhci->lock, flags); ret = usb_hcd_link_urb_to_ep(hcd, urb); if (ret) goto done_not_linked; ret = -ENOMEM; urbp = uhci_alloc_urb_priv(uhci, urb); if (!urbp) goto done; if (urb->ep->hcpriv) qh = urb->ep->hcpriv; else { qh = uhci_alloc_qh(uhci, urb->dev, urb->ep); if (!qh) goto err_no_qh; } urbp->qh = qh; switch (qh->type) { case USB_ENDPOINT_XFER_CONTROL: ret = uhci_submit_control(uhci, urb, qh); break; case USB_ENDPOINT_XFER_BULK: ret = uhci_submit_bulk(uhci, urb, qh); break; case USB_ENDPOINT_XFER_INT: ret = uhci_submit_interrupt(uhci, urb, qh); break; case USB_ENDPOINT_XFER_ISOC: urb->error_count = 0; ret = uhci_submit_isochronous(uhci, urb, qh); break; } if (ret != 0) goto err_submit_failed; /* Add this URB to the QH */ list_add_tail(&urbp->node, &qh->queue); /* If the new URB is the first and only one on this QH then either * the QH is new and idle or else it's unlinked and waiting to * become idle, so we can activate it right away. But only if the * queue isn't stopped. */ if (qh->queue.next == &urbp->node && !qh->is_stopped) { uhci_activate_qh(uhci, qh); uhci_urbp_wants_fsbr(uhci, urbp); } goto done; err_submit_failed: if (qh->state == QH_STATE_IDLE) uhci_make_qh_idle(uhci, qh); /* Reclaim unused QH */ err_no_qh: uhci_free_urb_priv(uhci, urbp); done: if (ret) usb_hcd_unlink_urb_from_ep(hcd, urb); done_not_linked: spin_unlock_irqrestore(&uhci->lock, flags); return ret; } static int uhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) { struct uhci_hcd *uhci = hcd_to_uhci(hcd); unsigned long flags; struct uhci_qh *qh; int rc; spin_lock_irqsave(&uhci->lock, flags); rc = usb_hcd_check_unlink_urb(hcd, urb, status); if (rc) goto done; qh = ((struct urb_priv *) urb->hcpriv)->qh; /* Remove Isochronous TDs from the frame list ASAP */ if (qh->type == USB_ENDPOINT_XFER_ISOC) { uhci_unlink_isochronous_tds(uhci, urb); mb(); /* If the URB has already started, update the QH unlink time */ uhci_get_current_frame_number(uhci); if (uhci_frame_before_eq(urb->start_frame, uhci->frame_number)) qh->unlink_frame = uhci->frame_number; } uhci_unlink_qh(uhci, qh); done: spin_unlock_irqrestore(&uhci->lock, flags); return rc; } /* * Finish unlinking an URB and give it back */ static void uhci_giveback_urb(struct uhci_hcd *uhci, struct uhci_qh *qh, struct urb *urb, int status) __releases(uhci->lock) __acquires(uhci->lock) { struct urb_priv *urbp = (struct urb_priv *) urb->hcpriv; if (qh->type == USB_ENDPOINT_XFER_CONTROL) { /* Subtract off the length of the SETUP packet from * urb->actual_length. */ urb->actual_length -= min_t(u32, 8, urb->actual_length); } /* When giving back the first URB in an Isochronous queue, * reinitialize the QH's iso-related members for the next URB. */ else if (qh->type == USB_ENDPOINT_XFER_ISOC && urbp->node.prev == &qh->queue && urbp->node.next != &qh->queue) { struct urb *nurb = list_entry(urbp->node.next, struct urb_priv, node)->urb; qh->iso_packet_desc = &nurb->iso_frame_desc[0]; qh->iso_frame = nurb->start_frame; } /* Take the URB off the QH's queue. If the queue is now empty, * this is a perfect time for a toggle fixup. */ list_del_init(&urbp->node); if (list_empty(&qh->queue) && qh->needs_fixup) { usb_settoggle(urb->dev, usb_pipeendpoint(urb->pipe), usb_pipeout(urb->pipe), qh->initial_toggle); qh->needs_fixup = 0; } uhci_free_urb_priv(uhci, urbp); usb_hcd_unlink_urb_from_ep(uhci_to_hcd(uhci), urb); spin_unlock(&uhci->lock); usb_hcd_giveback_urb(uhci_to_hcd(uhci), urb, status); spin_lock(&uhci->lock); /* If the queue is now empty, we can unlink the QH and give up its * reserved bandwidth. */ if (list_empty(&qh->queue)) { uhci_unlink_qh(uhci, qh); if (qh->bandwidth_reserved) uhci_release_bandwidth(uhci, qh); } } /* * Scan the URBs in a QH's queue */ #define QH_FINISHED_UNLINKING(qh) \ (qh->state == QH_STATE_UNLINKING && \ uhci->frame_number + uhci->is_stopped != qh->unlink_frame) static void uhci_scan_qh(struct uhci_hcd *uhci, struct uhci_qh *qh) { struct urb_priv *urbp; struct urb *urb; int status; while (!list_empty(&qh->queue)) { urbp = list_entry(qh->queue.next, struct urb_priv, node); urb = urbp->urb; if (qh->type == USB_ENDPOINT_XFER_ISOC) status = uhci_result_isochronous(uhci, urb); else status = uhci_result_common(uhci, urb); if (status == -EINPROGRESS) break; /* Dequeued but completed URBs can't be given back unless * the QH is stopped or has finished unlinking. */ if (urb->unlinked) { if (QH_FINISHED_UNLINKING(qh)) qh->is_stopped = 1; else if (!qh->is_stopped) return; } uhci_giveback_urb(uhci, qh, urb, status); if (status < 0) break; } /* If the QH is neither stopped nor finished unlinking (normal case), * our work here is done. */ if (QH_FINISHED_UNLINKING(qh)) qh->is_stopped = 1; else if (!qh->is_stopped) return; /* Otherwise give back each of the dequeued URBs */ restart: list_for_each_entry(urbp, &qh->queue, node) { urb = urbp->urb; if (urb->unlinked) { /* Fix up the TD links and save the toggles for * non-Isochronous queues. For Isochronous queues, * test for too-recent dequeues. */ if (!uhci_cleanup_queue(uhci, qh, urb)) { qh->is_stopped = 0; return; } uhci_giveback_urb(uhci, qh, urb, 0); goto restart; } } qh->is_stopped = 0; /* There are no more dequeued URBs. If there are still URBs on the * queue, the QH can now be re-activated. */ if (!list_empty(&qh->queue)) { if (qh->needs_fixup) uhci_fixup_toggles(uhci, qh, 0); /* If the first URB on the queue wants FSBR but its time * limit has expired, set the next TD to interrupt on * completion before reactivating the QH. */ urbp = list_entry(qh->queue.next, struct urb_priv, node); if (urbp->fsbr && qh->wait_expired) { struct uhci_td *td = list_entry(urbp->td_list.next, struct uhci_td, list); td->status |= cpu_to_hc32(uhci, TD_CTRL_IOC); } uhci_activate_qh(uhci, qh); } /* The queue is empty. The QH can become idle if it is fully * unlinked. */ else if (QH_FINISHED_UNLINKING(qh)) uhci_make_qh_idle(uhci, qh); } /* * Check for queues that have made some forward progress. * Returns 0 if the queue is not Isochronous, is ACTIVE, and * has not advanced since last examined; 1 otherwise. * * Early Intel controllers have a bug which causes qh->element sometimes * not to advance when a TD completes successfully. The queue remains * stuck on the inactive completed TD. We detect such cases and advance * the element pointer by hand. */ static int uhci_advance_check(struct uhci_hcd *uhci, struct uhci_qh *qh) { struct urb_priv *urbp = NULL; struct uhci_td *td; int ret = 1; unsigned status; if (qh->type == USB_ENDPOINT_XFER_ISOC) goto done; /* Treat an UNLINKING queue as though it hasn't advanced. * This is okay because reactivation will treat it as though * it has advanced, and if it is going to become IDLE then * this doesn't matter anyway. Furthermore it's possible * for an UNLINKING queue not to have any URBs at all, or * for its first URB not to have any TDs (if it was dequeued * just as it completed). So it's not easy in any case to * test whether such queues have advanced. */ if (qh->state != QH_STATE_ACTIVE) { urbp = NULL; status = 0; } else { urbp = list_entry(qh->queue.next, struct urb_priv, node); td = list_entry(urbp->td_list.next, struct uhci_td, list); status = td_status(uhci, td); if (!(status & TD_CTRL_ACTIVE)) { /* We're okay, the queue has advanced */ qh->wait_expired = 0; qh->advance_jiffies = jiffies; goto done; } ret = uhci->is_stopped; } /* The queue hasn't advanced; check for timeout */ if (qh->wait_expired) goto done; if (time_after(jiffies, qh->advance_jiffies + QH_WAIT_TIMEOUT)) { /* Detect the Intel bug and work around it */ if (qh->post_td && qh_element(qh) == LINK_TO_TD(uhci, qh->post_td)) { qh->element = qh->post_td->link; qh->advance_jiffies = jiffies; ret = 1; goto done; } qh->wait_expired = 1; /* If the current URB wants FSBR, unlink it temporarily * so that we can safely set the next TD to interrupt on * completion. That way we'll know as soon as the queue * starts moving again. */ if (urbp && urbp->fsbr && !(status & TD_CTRL_IOC)) uhci_unlink_qh(uhci, qh); } else { /* Unmoving but not-yet-expired queues keep FSBR alive */ if (urbp) uhci_urbp_wants_fsbr(uhci, urbp); } done: return ret; } /* * Process events in the schedule, but only in one thread at a time */ static void uhci_scan_schedule(struct uhci_hcd *uhci) { int i; struct uhci_qh *qh; /* Don't allow re-entrant calls */ if (uhci->scan_in_progress) { uhci->need_rescan = 1; return; } uhci->scan_in_progress = 1; rescan: uhci->need_rescan = 0; uhci->fsbr_is_wanted = 0; uhci_clear_next_interrupt(uhci); uhci_get_current_frame_number(uhci); uhci->cur_iso_frame = uhci->frame_number; /* Go through all the QH queues and process the URBs in each one */ for (i = 0; i < UHCI_NUM_SKELQH - 1; ++i) { uhci->next_qh = list_entry(uhci->skelqh[i]->node.next, struct uhci_qh, node); while ((qh = uhci->next_qh) != uhci->skelqh[i]) { uhci->next_qh = list_entry(qh->node.next, struct uhci_qh, node); if (uhci_advance_check(uhci, qh)) { uhci_scan_qh(uhci, qh); if (qh->state == QH_STATE_ACTIVE) { uhci_urbp_wants_fsbr(uhci, list_entry(qh->queue.next, struct urb_priv, node)); } } } } uhci->last_iso_frame = uhci->cur_iso_frame; if (uhci->need_rescan) goto rescan; uhci->scan_in_progress = 0; if (uhci->fsbr_is_on && !uhci->fsbr_is_wanted && !uhci->fsbr_expiring) { uhci->fsbr_expiring = 1; mod_timer(&uhci->fsbr_timer, jiffies + FSBR_OFF_DELAY); } if (list_empty(&uhci->skel_unlink_qh->node)) uhci_clear_next_interrupt(uhci); else uhci_set_next_interrupt(uhci); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 9 9 9 9 106 107 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> struct nft_rbtree { struct rb_root root; rwlock_t lock; seqcount_rwlock_t count; unsigned long last_gc; }; struct nft_rbtree_elem { struct nft_elem_priv priv; struct rb_node node; struct nft_set_ext ext; }; static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe) { return nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) && (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END); } static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) { return !nft_rbtree_interval_end(rbe); } static int nft_rbtree_cmp(const struct nft_set *set, const struct nft_rbtree_elem *e1, const struct nft_rbtree_elem *e2) { return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext), set->klen); } static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) { return nft_set_elem_expired(&rbe->ext); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) { struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; int d; parent = rcu_dereference_raw(priv->root.rb_node); while (parent != NULL) { if (read_seqcount_retry(&priv->count, seq)) return false; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (interval && !nft_rbtree_cmp(set, rbe, interval) && nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; interval = rbe; } else if (d > 0) parent = rcu_dereference_raw(parent->rb_right); else { if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); continue; } if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { if (nft_set_is_anonymous(set)) return false; parent = rcu_dereference_raw(parent->rb_left); interval = NULL; continue; } *ext = &rbe->ext; return true; } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; } return false; } INDIRECT_CALLABLE_SCOPE bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); bool ret; ret = __nft_rbtree_lookup(net, set, key, ext, seq); if (ret || !read_seqcount_retry(&priv->count, seq)) return ret; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_lookup(net, set, key, ext, seq); read_unlock_bh(&priv->lock); return ret; } static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, const u32 *key, struct nft_rbtree_elem **elem, unsigned int seq, unsigned int flags, u8 genmask) { struct nft_rbtree_elem *rbe, *interval = NULL; struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent; const void *this; int d; parent = rcu_dereference_raw(priv->root.rb_node); while (parent != NULL) { if (read_seqcount_retry(&priv->count, seq)) return false; rbe = rb_entry(parent, struct nft_rbtree_elem, node); this = nft_set_ext_key(&rbe->ext); d = memcmp(this, key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (!(flags & NFT_SET_ELEM_INTERVAL_END)) interval = rbe; } else if (d > 0) { parent = rcu_dereference_raw(parent->rb_right); if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); continue; } if (nft_set_elem_expired(&rbe->ext)) return false; if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == (flags & NFT_SET_ELEM_INTERVAL_END)) { *elem = rbe; return true; } if (nft_rbtree_interval_end(rbe)) interval = NULL; parent = rcu_dereference_raw(parent->rb_left); } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_set_elem_expired(&interval->ext) && ((!nft_rbtree_interval_end(interval) && !(flags & NFT_SET_ELEM_INTERVAL_END)) || (nft_rbtree_interval_end(interval) && (flags & NFT_SET_ELEM_INTERVAL_END)))) { *elem = interval; return true; } return false; } static struct nft_elem_priv * nft_rbtree_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); struct nft_rbtree_elem *rbe = ERR_PTR(-ENOENT); const u32 *key = (const u32 *)&elem->key.val; u8 genmask = nft_genmask_cur(net); bool ret; ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); if (ret || !read_seqcount_retry(&priv->count, seq)) return &rbe->priv; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); read_unlock_bh(&priv->lock); if (!ret) return ERR_PTR(-ENOENT); return &rbe->priv; } static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { lockdep_assert_held_write(&priv->lock); nft_setelem_data_deactivate(net, set, &rbe->priv); rb_erase(&rbe->node, &priv->root); } static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; struct nft_trans_gc *gc; gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); if (!gc) return ERR_PTR(-ENOMEM); /* search for end interval coming before this element. * end intervals don't carry a timeout extension, they * are coupled with the interval start element. */ while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); } rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); nft_rbtree_gc_elem_remove(net, set, priv, rbe_prev); /* There is always room in this trans gc for this element, * memory allocation never actually happens, hence, the warning * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, * this is synchronous gc which never fails. */ gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe_prev); } nft_rbtree_gc_elem_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe); nft_trans_gc_queue_sync_done(gc); return rbe_prev; } static bool nft_rbtree_update_first(const struct nft_set *set, struct nft_rbtree_elem *rbe, struct rb_node *first) { struct nft_rbtree_elem *first_elem; first_elem = rb_entry(first, struct nft_rbtree_elem, node); /* this element is closest to where the new element is to be inserted: * update the first element for the node list path. */ if (nft_rbtree_cmp(set, rbe, first_elem) < 0) return true; return false; } static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); u64 tstamp = nft_net_tstamp(net); int d; /* Descend the tree to search for an existing element greater than the * key value to insert that is greater than the new element. This is the * first element to walk the ordered elements to find possible overlap. */ parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = nft_rbtree_cmp(set, rbe, new); if (d < 0) { p = &parent->rb_left; } else if (d > 0) { if (!first || nft_rbtree_update_first(set, rbe, first)) first = &rbe->node; p = &parent->rb_right; } else { if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; else p = &parent->rb_right; } } if (!first) first = rb_first(&priv->root); /* Detect overlap by going through the list of valid tree nodes. * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ for (node = first; node != NULL; node = next) { next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) continue; /* perform garbage collection to avoid bogus overlap reports * but skip new elements in this transaction. */ if (__nft_set_elem_expired(&rbe->ext, tstamp) && nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); if (removed_end == rbe_le || removed_end == rbe_ge) return -EAGAIN; continue; } d = nft_rbtree_cmp(set, rbe, new); if (d == 0) { /* Matching end element: no need to look for an * overlapping greater or equal element. */ if (nft_rbtree_interval_end(rbe)) { rbe_le = rbe; break; } /* first element that is greater or equal to key value. */ if (!rbe_ge) { rbe_ge = rbe; continue; } /* this is a closer more or equal element, update it. */ if (nft_rbtree_cmp(set, rbe_ge, new) != 0) { rbe_ge = rbe; continue; } /* element is equal to key value, make sure flags are * the same, an existing more or equal start element * must not be replaced by more or equal end element. */ if ((nft_rbtree_interval_start(new) && nft_rbtree_interval_start(rbe_ge)) || (nft_rbtree_interval_end(new) && nft_rbtree_interval_end(rbe_ge))) { rbe_ge = rbe; continue; } } else if (d > 0) { /* annotate element greater than the new element. */ rbe_ge = rbe; continue; } else if (d < 0) { /* annotate element less than the new element. */ rbe_le = rbe; break; } } /* - new start element matching existing start element: full overlap * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. */ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { *elem_priv = &rbe_ge->priv; return -EEXIST; } /* - new end element matching existing end element: full overlap * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. */ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { *elem_priv = &rbe_le->priv; return -EEXIST; } /* - new start element with existing closest, less or equal key value * being a start element: partial overlap, reported as -ENOTEMPTY. * Anonymous sets allow for two consecutive start element since they * are constant, skip them to avoid bogus overlap reports. */ if (!nft_set_is_anonymous(set) && rbe_le && nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) return -ENOTEMPTY; /* - new end element with existing closest, less or equal key value * being a end element: partial overlap, reported as -ENOTEMPTY. */ if (rbe_le && nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; /* - new end element with existing closest, greater or equal key value * being an end element: partial overlap, reported as -ENOTEMPTY */ if (rbe_ge && nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; /* Accepted element: pick insertion point depending on key value */ parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = nft_rbtree_cmp(set, rbe, new); if (d < 0) p = &parent->rb_left; else if (d > 0) p = &parent->rb_right; else if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; else p = &parent->rb_right; } rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; } static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem->priv); struct nft_rbtree *priv = nft_set_priv(set); int err; do { if (fatal_signal_pending(current)) return -EINTR; cond_resched(); write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); err = __nft_rbtree_insert(net, set, rbe, elem_priv); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } while (err == -EAGAIN); return err; } static void nft_rbtree_erase(struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); rb_erase(&rbe->node, &priv->root); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } static void nft_rbtree_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); struct nft_rbtree *priv = nft_set_priv(set); nft_rbtree_erase(priv, rbe); } static void nft_rbtree_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_clear(net, &rbe->ext); } static void nft_rbtree_flush(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &rbe->ext); } static struct nft_elem_priv * nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree_elem *rbe, *this = nft_elem_priv_cast(elem->priv); const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; u8 genmask = nft_genmask_next(net); u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = memcmp(nft_set_ext_key(&rbe->ext), &elem->key.val, set->klen); if (d < 0) parent = parent->rb_left; else if (d > 0) parent = parent->rb_right; else { if (nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(this)) { parent = parent->rb_left; continue; } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; } nft_rbtree_flush(net, set, &rbe->priv); return &rbe->priv; } } return NULL; } static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *node; read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); if (iter->count < iter->skip) goto cont; iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { read_unlock_bh(&priv->lock); return; } cont: iter->count++; } read_unlock_bh(&priv->lock); } static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { nft_setelem_data_deactivate(net, set, &rbe->priv); nft_rbtree_erase(priv, rbe); } static void nft_rbtree_gc(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; struct net *net = read_pnet(&set->net); u64 tstamp = nft_net_tstamp(net); struct rb_node *node, *next; struct nft_trans_gc *gc; set = nft_set_container_of(priv); net = read_pnet(&set->net); gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (!gc) return; for (node = rb_first(&priv->root); node ; node = next) { next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is * always visited before the start element. */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!__nft_set_elem_expired(&rbe->ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; /* end element needs to be removed first, it has * no timeout extension. */ if (rbe_end) { nft_rbtree_gc_remove(net, set, priv, rbe_end); nft_trans_gc_elem_add(gc, rbe_end); rbe_end = NULL; } gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; nft_rbtree_gc_remove(net, set, priv, rbe); nft_trans_gc_elem_add(gc, rbe); } try_later: if (gc) { gc = nft_trans_gc_catchall_sync(gc); nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; } } static u64 nft_rbtree_privsize(const struct nlattr * const nla[], const struct nft_set_desc *desc) { return sizeof(struct nft_rbtree); } static int nft_rbtree_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]) { struct nft_rbtree *priv = nft_set_priv(set); BUILD_BUG_ON(offsetof(struct nft_rbtree_elem, priv) != 0); rwlock_init(&priv->lock); seqcount_rwlock_init(&priv->count, &priv->lock); priv->root = RB_ROOT; return 0; } static void nft_rbtree_destroy(const struct nft_ctx *ctx, const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *node; while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); nf_tables_set_elem_destroy(ctx, set, &rbe->priv); } } static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { if (desc->field_count > 1) return false; if (desc->size) est->size = sizeof(struct nft_rbtree) + desc->size * sizeof(struct nft_rbtree_elem); else est->size = ~0; est->lookup = NFT_SET_CLASS_O_LOG_N; est->space = NFT_SET_CLASS_O_N; return true; } static void nft_rbtree_commit(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) nft_rbtree_gc(set); } static void nft_rbtree_gc_init(const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); priv->last_gc = jiffies; } const struct nft_set_type nft_set_rbtree_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { .privsize = nft_rbtree_privsize, .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, .init = nft_rbtree_init, .destroy = nft_rbtree_destroy, .insert = nft_rbtree_insert, .remove = nft_rbtree_remove, .deactivate = nft_rbtree_deactivate, .flush = nft_rbtree_flush, .activate = nft_rbtree_activate, .commit = nft_rbtree_commit, .gc_init = nft_rbtree_gc_init, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .get = nft_rbtree_get, }, }; |
| 12 2 11 3 1 3 2 3 7 4 1 2 6 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fs.h> #include <linux/types.h> #include "ctree.h" #include "disk-io.h" #include "btrfs_inode.h" #include "export.h" #include "accessors.h" #include "super.h" #define BTRFS_FID_SIZE_NON_CONNECTABLE (offsetof(struct btrfs_fid, \ parent_objectid) / 4) #define BTRFS_FID_SIZE_CONNECTABLE (offsetof(struct btrfs_fid, \ parent_root_objectid) / 4) #define BTRFS_FID_SIZE_CONNECTABLE_ROOT (sizeof(struct btrfs_fid) / 4) static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, struct inode *parent) { struct btrfs_fid *fid = (struct btrfs_fid *)fh; int len = *max_len; int type; if (parent && (len < BTRFS_FID_SIZE_CONNECTABLE)) { *max_len = BTRFS_FID_SIZE_CONNECTABLE; return FILEID_INVALID; } else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) { *max_len = BTRFS_FID_SIZE_NON_CONNECTABLE; return FILEID_INVALID; } len = BTRFS_FID_SIZE_NON_CONNECTABLE; type = FILEID_BTRFS_WITHOUT_PARENT; fid->objectid = btrfs_ino(BTRFS_I(inode)); fid->root_objectid = btrfs_root_id(BTRFS_I(inode)->root); fid->gen = inode->i_generation; if (parent) { u64 parent_root_id; fid->parent_objectid = btrfs_ino(BTRFS_I(parent)); fid->parent_gen = parent->i_generation; parent_root_id = btrfs_root_id(BTRFS_I(parent)->root); if (parent_root_id != fid->root_objectid) { fid->parent_root_objectid = parent_root_id; len = BTRFS_FID_SIZE_CONNECTABLE_ROOT; type = FILEID_BTRFS_WITH_PARENT_ROOT; } else { len = BTRFS_FID_SIZE_CONNECTABLE; type = FILEID_BTRFS_WITH_PARENT; } } *max_len = len; return type; } /* * Read dentry of inode with @objectid from filesystem root @root_objectid. * * @sb: the filesystem super block * @objectid: inode objectid * @root_objectid: object id of the subvolume root where to look up the inode * @generation: optional, if not zero, verify that the found inode * generation matches * * Return dentry alias for the inode, otherwise an error. In case the * generation does not match return ESTALE. */ struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, u64 root_objectid, u64 generation) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root; struct inode *inode; if (objectid < BTRFS_FIRST_FREE_OBJECTID) return ERR_PTR(-ESTALE); root = btrfs_get_fs_root(fs_info, root_objectid, true); if (IS_ERR(root)) return ERR_CAST(root); inode = btrfs_iget(objectid, root); btrfs_put_root(root); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation != 0 && generation != inode->i_generation) { iput(inode); return ERR_PTR(-ESTALE); } return d_obtain_alias(inode); } static struct dentry *btrfs_fh_to_parent(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct btrfs_fid *fid = (struct btrfs_fid *) fh; u64 objectid, root_objectid; u32 generation; if (fh_type == FILEID_BTRFS_WITH_PARENT) { if (fh_len < BTRFS_FID_SIZE_CONNECTABLE) return NULL; root_objectid = fid->root_objectid; } else if (fh_type == FILEID_BTRFS_WITH_PARENT_ROOT) { if (fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) return NULL; root_objectid = fid->parent_root_objectid; } else return NULL; objectid = fid->parent_objectid; generation = fid->parent_gen; return btrfs_get_dentry(sb, objectid, root_objectid, generation); } static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct btrfs_fid *fid = (struct btrfs_fid *) fh; u64 objectid, root_objectid; u32 generation; if ((fh_type != FILEID_BTRFS_WITH_PARENT || fh_len < BTRFS_FID_SIZE_CONNECTABLE) && (fh_type != FILEID_BTRFS_WITH_PARENT_ROOT || fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) && (fh_type != FILEID_BTRFS_WITHOUT_PARENT || fh_len < BTRFS_FID_SIZE_NON_CONNECTABLE)) return NULL; objectid = fid->objectid; root_objectid = fid->root_objectid; generation = fid->gen; return btrfs_get_dentry(sb, objectid, root_objectid, generation); } struct dentry *btrfs_get_parent(struct dentry *child) { struct inode *dir = d_inode(child); struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb); struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_root_ref *ref; struct btrfs_key key; struct btrfs_key found_key; int ret; path = btrfs_alloc_path(); if (!path) return ERR_PTR(-ENOMEM); if (btrfs_ino(BTRFS_I(dir)) == BTRFS_FIRST_FREE_OBJECTID) { key.objectid = btrfs_root_id(root); key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = (u64)-1; root = fs_info->tree_root; } else { key.objectid = btrfs_ino(BTRFS_I(dir)); key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; if (ret == 0) { /* * Key with offset of -1 found, there would have to exist an * inode with such number or a root with such id. */ ret = -EUCLEAN; goto fail; } if (path->slots[0] == 0) { ret = -ENOENT; goto fail; } path->slots[0]--; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid != key.objectid || found_key.type != key.type) { ret = -ENOENT; goto fail; } if (found_key.type == BTRFS_ROOT_BACKREF_KEY) { ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); key.objectid = btrfs_root_ref_dirid(leaf, ref); } else { key.objectid = found_key.offset; } btrfs_free_path(path); if (found_key.type == BTRFS_ROOT_BACKREF_KEY) { return btrfs_get_dentry(fs_info->sb, key.objectid, found_key.offset, 0); } return d_obtain_alias(btrfs_iget(key.objectid, root)); fail: btrfs_free_path(path); return ERR_PTR(ret); } static int btrfs_get_name(struct dentry *parent, char *name, struct dentry *child) { struct inode *inode = d_inode(child); struct inode *dir = d_inode(parent); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct btrfs_path *path; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_inode_ref *iref; struct btrfs_root_ref *rref; struct extent_buffer *leaf; unsigned long name_ptr; struct btrfs_key key; int name_len; int ret; u64 ino; if (!S_ISDIR(dir->i_mode)) return -EINVAL; ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) return -ENOMEM; if (ino == BTRFS_FIRST_FREE_OBJECTID) { key.objectid = btrfs_root_id(BTRFS_I(inode)->root); key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = (u64)-1; root = fs_info->tree_root; } else { key.objectid = ino; key.offset = btrfs_ino(BTRFS_I(dir)); key.type = BTRFS_INODE_REF_KEY; } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) { btrfs_free_path(path); return ret; } else if (ret > 0) { if (ino == BTRFS_FIRST_FREE_OBJECTID) { path->slots[0]--; } else { btrfs_free_path(path); return -ENOENT; } } leaf = path->nodes[0]; if (ino == BTRFS_FIRST_FREE_OBJECTID) { rref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); name_ptr = (unsigned long)(rref + 1); name_len = btrfs_root_ref_name_len(leaf, rref); } else { iref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_ref); name_ptr = (unsigned long)(iref + 1); name_len = btrfs_inode_ref_name_len(leaf, iref); } read_extent_buffer(leaf, name, name_ptr, name_len); btrfs_free_path(path); /* * have to add the null termination to make sure that reconnect_path * gets the right len for strlen */ name[name_len] = '\0'; return 0; } const struct export_operations btrfs_export_ops = { .encode_fh = btrfs_encode_fh, .fh_to_dentry = btrfs_fh_to_dentry, .fh_to_parent = btrfs_fh_to_parent, .get_parent = btrfs_get_parent, .get_name = btrfs_get_name, }; |
| 680 23 24 24 1 23 7 1 5 12 1 1 15 11 13 7 8 8 1 1 7 6 6 1 5 34 1 17 18 1 31 1 31 9 9 9 9 6 1 5 1 9 245 247 242 6 25 25 1 1 22 22 1 10 9 3 21 1 3 2 12 3 2 13 1 4 15 15 1 1 2 8 8 2 1 3 3 6 2 4 6 8 8 1 7 1 2 5 6 6 38 38 38 38 33 4 1 1 3 2 4 688 675 292 157 353 678 142 3 139 362 352 158 107 259 351 14 157 168 155 153 3 3 3 688 689 44 2 2 2 19 21 160 160 160 16 16 160 160 160 160 159 458 662 456 295 295 456 458 469 471 1 470 11 459 458 454 319 318 319 53 294 6 23 29 29 29 1 28 342 339 341 1 342 273 281 8 343 329 227 250 201 146 309 87 329 330 812 812 812 2 812 812 812 2 2 2 1 1 1 7 7 6 6 6 2 2 5 3 2 22 3 19 2 17 16 17 4 12 3 16 17 3 16 17 34 34 8 3 3 34 34 10 12 4 9 2 1 11 3 3 26 27 13 16 25 17 2 2 25 300 301 1 301 3 13 13 3 10 7 7 3 10 157 156 287 287 287 23 23 23 332 333 329 330 329 329 330 680 344 345 345 431 432 161 160 159 159 159 159 158 1106 1105 1102 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 3 1 3 3 3 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 3 2 3 3 3 3 6 6 6 6 | 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 | // 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_arp.h> #include <linux/route.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/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; /* * socket join on multicast group */ #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 int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); int err; ASSERT_RTNL(); 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; if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else dev = __dev_get_by_index(net, 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); 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 */ 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 *mc_lst; struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); ASSERT_RTNL(); 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)) { struct net_device *dev; *lnk = mc_lst->next; 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); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } return -EADDRNOTAVAIL; } EXPORT_SYMBOL(ipv6_sock_mc_drop); static struct inet6_dev *ip6_mc_find_dev_rtnl(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev = NULL; struct inet6_dev *idev = NULL; if (ifindex == 0) { struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else { dev = __dev_get_by_index(net, ifindex); } if (!dev) return NULL; idev = __in6_dev_get(dev); if (!idev) return NULL; if (idev->dead) return NULL; return idev; } void __ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); ASSERT_RTNL(); while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; 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); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); } } void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); if (!rcu_access_pointer(np->ipv6_mc_list)) return; rtnl_lock(); lock_sock(sk); __ipv6_sock_mc_close(sk); release_sock(sk); rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr) { struct in6_addr *source, *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; struct net *net = sock_net(sk); int i, j, rv; int leavegroup = 0; 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_dev_rtnl(net, group, pgsr->gsr_interface); if (!idev) return -ENODEV; err = -EADDRNOTAVAIL; mutex_lock(&idev->mc_lock); 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); 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) { const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); 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_dev_rtnl(net, group, gsf->gf_interface); if (!idev) return -ENODEV; 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; } mutex_lock(&idev->mc_lock); err = ip6_mc_add_src(idev, group, gsf->gf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { mutex_unlock(&idev->mc_lock); sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } mutex_unlock(&idev->mc_lock); } else { newpsl = NULL; mutex_lock(&idev->mc_lock); ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); } mutex_lock(&idev->mc_lock); 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); mutex_unlock(&idev->mc_lock); kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: 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; int i, count, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; /* changes to the ipv6_mc_list require the socket lock and * rtnl lock. We have the socket lock, so reading the list is safe. */ 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 = count < gsf->gf_numsrc ? 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; } /* called with mc_lock */ static void igmp6_group_added(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; 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); } /* called with mc_lock */ static void igmp6_group_dropped(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; 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 * called with mc_lock */ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ifmcaddr6 *pmc; /* 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(sizeof(*pmc), GFP_KERNEL); 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); } /* called with mc_lock */ 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; pmc_prev = NULL; for_each_mc_tomb(idev, pmc) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc->next); else rcu_assign_pointer(idev->mc_tomb, pmc->next); } if (pmc) { 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; } in6_dev_put(pmc->idev); ip6_mc_clear_src(pmc); kfree_rcu(pmc, rcu); } } /* called with mc_lock */ static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; 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) { struct sk_buff *skb; spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_query_lock); } static void mld_clear_report(struct inet6_dev *idev) { struct sk_buff *skb; spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_report_lock); } static void mca_get(struct ifmcaddr6 *mc) { refcount_inc(&mc->mca_refcnt); } static void ma_put(struct ifmcaddr6 *mc) { if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree_rcu(mc, rcu); } } /* called with mc_lock */ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; mc = kzalloc(sizeof(*mc), GFP_KERNEL); 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; } /* * 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 ifmcaddr6 *mc; struct inet6_dev *idev; ASSERT_RTNL(); /* we need to take a reference on idev */ idev = in6_dev_get(dev); if (!idev) return -EINVAL; if (idev->dead) { in6_dev_put(idev); return -ENODEV; } mutex_lock(&idev->mc_lock); 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); mca_get(mc); mld_del_delrec(idev, mc); igmp6_group_added(mc); mutex_unlock(&idev->mc_lock); ma_put(mc); 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; ASSERT_RTNL(); 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); 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; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (!idev) err = -ENODEV; else err = __ipv6_dev_mc_dec(idev, addr); 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) { for_each_mc_rcu(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, group)) break; } if (mc) { 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 = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != mc->mca_sfcount[MCAST_EXCLUDE]; else rv = mc->mca_sfcount[MCAST_EXCLUDE] != 0; } else rv = true; /* don't filter unspecified source */ } } rcu_read_unlock(); return rv; } /* called with mc_lock */ static void mld_gq_start_work(struct inet6_dev *idev) { unsigned long tv = get_random_u32_below(idev->mc_maxdelay); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_gq_stop_work(struct inet6_dev *idev) { idev->mc_gq_running = 0; if (cancel_delayed_work(&idev->mc_gq_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_ifc_stop_work(struct inet6_dev *idev) { idev->mc_ifc_count = 0; if (cancel_delayed_work(&idev->mc_ifc_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); 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) * called with mc_lock */ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) { unsigned long delay = resptime; /* 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 * called with mc_lock */ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; 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; } /* called with mc_lock */ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; 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; struct net *net = dev_net(dev); const struct in6_addr *saddr; struct in6_addr addr_buf; struct mld2_report *pmr; struct sk_buff *skb; unsigned int size; struct sock *sk; int err; sk = net->ipv6.igmp_sk; /* 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 = sock_alloc_send_skb(sk, size, 1, &err); if (!skb) return NULL; skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); 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); 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) /* called with mc_lock */ 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; 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; } /* called with mc_lock */ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) { struct sk_buff *skb = NULL; int type; 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 * called with mc_lock */ 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; } } } /* called with mc_lock */ 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) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; struct sk_buff *skb; struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; struct in6_addr addr_buf; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct flowi6 fl6; struct dst_entry *dst; 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; rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); rcu_read_unlock(); skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); if (!skb) { rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; } 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)); rcu_read_lock(); idev = __in6_dev_get(skb->dev); 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; } /* called with mc_lock */ static void mld_send_initial_cr(struct inet6_dev *idev) { struct sk_buff *skb; struct ifmcaddr6 *pmc; int type; 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); } /* called with mc_lock */ 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; 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; } psf->sf_count[sfmode]--; 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; } /* called with mc_lock */ 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; 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 * called with mc_lock */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; 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(sizeof(*psf), GFP_KERNEL); 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); } } psf->sf_count[sfmode]++; return 0; } /* called with mc_lock */ static void sf_markstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; 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; } } } /* called with mc_lock */ static int sf_setstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *dpsf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; int qrv = pmc->idev->mc_qrv; int new_in, rv; 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(sizeof(*dpsf), GFP_KERNEL); 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 * called with mc_lock */ 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; 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) pmc->mca_sfcount[sfmode]++; 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) pmc->mca_sfcount[sfmode]--; 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; } /* called with mc_lock */ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *nextpsf; 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; pmc->mca_sfcount[MCAST_EXCLUDE] = 1; } /* called with mc_lock */ static void igmp6_join_group(struct ifmcaddr6 *ma) { unsigned long delay; 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; } /* called with mc_lock */ static void igmp6_leave_group(struct ifmcaddr6 *ma) { 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); } /* called with mc_lock */ static void mld_ifc_event(struct inet6_dev *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; ASSERT_RTNL(); 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, psf->sf_count[MCAST_INCLUDE], 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); } |
| 12 14 172 46 16 96 7 11 14 7 9 8 8 8 1 9 2 9 9 7 7 7 7 7 7 7 1 7 7 7 57 57 57 57 47 4 7 3 47 46 47 46 40 4 41 7 41 79 80 81 80 81 11 11 11 11 191 191 188 2 2 136 133 138 138 65 28 28 19 28 5 22 28 25 25 25 23 1 7 16 23 23 23 23 25 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_trace.h" /* * Prototypes for internal functions. */ static void xfs_dir2_sf_addname_easy(xfs_da_args_t *args, xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t offset, int new_isize); static void xfs_dir2_sf_addname_hard(xfs_da_args_t *args, int objchange, int new_isize); static int xfs_dir2_sf_addname_pick(xfs_da_args_t *args, int objchange, xfs_dir2_sf_entry_t **sfepp, xfs_dir2_data_aoff_t *offsetp); #ifdef DEBUG static void xfs_dir2_sf_check(xfs_da_args_t *args); #else #define xfs_dir2_sf_check(args) #endif /* DEBUG */ static void xfs_dir2_sf_toino4(xfs_da_args_t *args); static void xfs_dir2_sf_toino8(xfs_da_args_t *args); int xfs_dir2_sf_entsize( struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, int len) { int count = len; count += sizeof(struct xfs_dir2_sf_entry); /* namelen + offset */ count += hdr->i8count ? XFS_INO64_SIZE : XFS_INO32_SIZE; /* ino # */ if (xfs_has_ftype(mp)) count += sizeof(uint8_t); return count; } struct xfs_dir2_sf_entry * xfs_dir2_sf_nextentry( struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, struct xfs_dir2_sf_entry *sfep) { return (void *)sfep + xfs_dir2_sf_entsize(mp, hdr, sfep->namelen); } /* * In short-form directory entries the inode numbers are stored at variable * offset behind the entry name. If the entry stores a filetype value, then it * sits between the name and the inode number. The actual inode numbers can * come in two formats as well, either 4 bytes or 8 bytes wide. */ xfs_ino_t xfs_dir2_sf_get_ino( struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, struct xfs_dir2_sf_entry *sfep) { uint8_t *from = sfep->name + sfep->namelen; if (xfs_has_ftype(mp)) from++; if (!hdr->i8count) return get_unaligned_be32(from); return get_unaligned_be64(from) & XFS_MAXINUMBER; } void xfs_dir2_sf_put_ino( struct xfs_mount *mp, struct xfs_dir2_sf_hdr *hdr, struct xfs_dir2_sf_entry *sfep, xfs_ino_t ino) { uint8_t *to = sfep->name + sfep->namelen; ASSERT(ino <= XFS_MAXINUMBER); if (xfs_has_ftype(mp)) to++; if (hdr->i8count) put_unaligned_be64(ino, to); else put_unaligned_be32(ino, to); } xfs_ino_t xfs_dir2_sf_get_parent_ino( struct xfs_dir2_sf_hdr *hdr) { if (!hdr->i8count) return get_unaligned_be32(hdr->parent); return get_unaligned_be64(hdr->parent) & XFS_MAXINUMBER; } void xfs_dir2_sf_put_parent_ino( struct xfs_dir2_sf_hdr *hdr, xfs_ino_t ino) { ASSERT(ino <= XFS_MAXINUMBER); if (hdr->i8count) put_unaligned_be64(ino, hdr->parent); else put_unaligned_be32(ino, hdr->parent); } /* * The file type field is stored at the end of the name for filetype enabled * shortform directories, or not at all otherwise. */ uint8_t xfs_dir2_sf_get_ftype( struct xfs_mount *mp, struct xfs_dir2_sf_entry *sfep) { if (xfs_has_ftype(mp)) { uint8_t ftype = sfep->name[sfep->namelen]; if (ftype < XFS_DIR3_FT_MAX) return ftype; } return XFS_DIR3_FT_UNKNOWN; } void xfs_dir2_sf_put_ftype( struct xfs_mount *mp, struct xfs_dir2_sf_entry *sfep, uint8_t ftype) { ASSERT(ftype < XFS_DIR3_FT_MAX); if (xfs_has_ftype(mp)) sfep->name[sfep->namelen] = ftype; } /* * Given a block directory (dp/block), calculate its size as a shortform (sf) * directory and a header for the sf directory, if it will fit it the * space currently present in the inode. If it won't fit, the output * size is too big (but not accurate). */ int /* size for sf form */ xfs_dir2_block_sfsize( xfs_inode_t *dp, /* incore inode pointer */ xfs_dir2_data_hdr_t *hdr, /* block directory data */ xfs_dir2_sf_hdr_t *sfhp) /* output: header for sf form */ { xfs_dir2_dataptr_t addr; /* data entry address */ xfs_dir2_leaf_entry_t *blp; /* leaf area of the block */ xfs_dir2_block_tail_t *btp; /* tail area of the block */ int count; /* shortform entry count */ xfs_dir2_data_entry_t *dep; /* data entry in the block */ int i; /* block entry index */ int i8count; /* count of big-inode entries */ int isdot; /* entry is "." */ int isdotdot; /* entry is ".." */ xfs_mount_t *mp; /* mount structure pointer */ int namelen; /* total name bytes */ xfs_ino_t parent = 0; /* parent inode number */ int size=0; /* total computed size */ int has_ftype; struct xfs_da_geometry *geo; mp = dp->i_mount; geo = mp->m_dir_geo; /* * if there is a filetype field, add the extra byte to the namelen * for each entry that we see. */ has_ftype = xfs_has_ftype(mp) ? 1 : 0; count = i8count = namelen = 0; btp = xfs_dir2_block_tail_p(geo, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Iterate over the block's data entries by using the leaf pointers. */ for (i = 0; i < be32_to_cpu(btp->count); i++) { if ((addr = be32_to_cpu(blp[i].address)) == XFS_DIR2_NULL_DATAPTR) continue; /* * Calculate the pointer to the entry at hand. */ dep = (xfs_dir2_data_entry_t *)((char *)hdr + xfs_dir2_dataptr_to_off(geo, addr)); /* * Detect . and .., so we can special-case them. * . is not included in sf directories. * .. is included by just the parent inode number. */ isdot = dep->namelen == 1 && dep->name[0] == '.'; isdotdot = dep->namelen == 2 && dep->name[0] == '.' && dep->name[1] == '.'; if (!isdot) i8count += be64_to_cpu(dep->inumber) > XFS_DIR2_MAX_SHORT_INUM; /* take into account the file type field */ if (!isdot && !isdotdot) { count++; namelen += dep->namelen + has_ftype; } else if (isdotdot) parent = be64_to_cpu(dep->inumber); /* * Calculate the new size, see if we should give up yet. */ size = xfs_dir2_sf_hdr_size(i8count) + /* header */ count * 3 * sizeof(u8) + /* namelen + offset */ namelen + /* name */ (i8count ? /* inumber */ count * XFS_INO64_SIZE : count * XFS_INO32_SIZE); if (size > xfs_inode_data_fork_size(dp)) return size; /* size value is a failure */ } /* * Create the output header, if it worked. */ sfhp->count = count; sfhp->i8count = i8count; xfs_dir2_sf_put_parent_ino(sfhp, parent); return size; } /* * Convert a block format directory to shortform. * Caller has already checked that it will fit, and built us a header. */ int /* error */ xfs_dir2_block_to_sf( struct xfs_da_args *args, /* operation arguments */ struct xfs_buf *bp, int size, /* shortform directory size */ struct xfs_dir2_sf_hdr *sfhp) /* shortform directory hdr */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; int error; /* error return value */ int logflags; /* inode logging flags */ struct xfs_dir2_sf_entry *sfep; /* shortform entry */ struct xfs_dir2_sf_hdr *sfp; /* shortform directory header */ unsigned int offset = args->geo->data_entry_offset; unsigned int end; trace_xfs_dir2_block_to_sf(args); /* * Allocate a temporary destination buffer the size of the inode to * format the data into. Once we have formatted the data, we can free * the block and copy the formatted data into the inode literal area. */ sfp = kmalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | __GFP_NOFAIL); memcpy(sfp, sfhp, xfs_dir2_sf_hdr_size(sfhp->i8count)); /* * Loop over the active and unused entries. Stop when we reach the * leaf/tail portion of the block. */ end = xfs_dir3_data_end_offset(args->geo, bp->b_addr); sfep = xfs_dir2_sf_firstentry(sfp); while (offset < end) { struct xfs_dir2_data_unused *dup = bp->b_addr + offset; struct xfs_dir2_data_entry *dep = bp->b_addr + offset; /* * If it's unused, just skip over it. */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { offset += be16_to_cpu(dup->length); continue; } /* * Skip . */ if (dep->namelen == 1 && dep->name[0] == '.') ASSERT(be64_to_cpu(dep->inumber) == dp->i_ino); /* * Skip .., but make sure the inode number is right. */ else if (dep->namelen == 2 && dep->name[0] == '.' && dep->name[1] == '.') ASSERT(be64_to_cpu(dep->inumber) == xfs_dir2_sf_get_parent_ino(sfp)); /* * Normal entry, copy it into shortform. */ else { sfep->namelen = dep->namelen; xfs_dir2_sf_put_offset(sfep, offset); memcpy(sfep->name, dep->name, dep->namelen); xfs_dir2_sf_put_ino(mp, sfp, sfep, be64_to_cpu(dep->inumber)); xfs_dir2_sf_put_ftype(mp, sfep, xfs_dir2_data_get_ftype(mp, dep)); sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); } offset += xfs_dir2_data_entsize(mp, dep->namelen); } ASSERT((char *)sfep - (char *)sfp == size); /* now we are done with the block, we can shrink the inode */ logflags = XFS_ILOG_CORE; error = xfs_dir2_shrink_inode(args, args->geo->datablk, bp); if (error) { ASSERT(error != -ENOSPC); goto out; } /* * The buffer is now unconditionally gone, whether * xfs_dir2_shrink_inode worked or not. * * Convert the inode to local format and copy the data in. */ ASSERT(dp->i_df.if_bytes == 0); xfs_init_local_fork(dp, XFS_DATA_FORK, sfp, size); dp->i_df.if_format = XFS_DINODE_FMT_LOCAL; dp->i_disk_size = size; logflags |= XFS_ILOG_DDATA; xfs_dir2_sf_check(args); out: xfs_trans_log_inode(args->trans, dp, logflags); kfree(sfp); return error; } /* * Add a name to a shortform directory. * There are two algorithms, "easy" and "hard" which we decide on * before changing anything. * Convert to block form if necessary, if the new entry won't fit. */ int /* error */ xfs_dir2_sf_addname( xfs_da_args_t *args) /* operation arguments */ { struct xfs_inode *dp = args->dp; struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int error; /* error return value */ int incr_isize; /* total change in size */ int new_isize; /* size after adding name */ int objchange; /* changing to 8-byte inodes */ xfs_dir2_data_aoff_t offset = 0; /* offset for new entry */ int pick; /* which algorithm to use */ xfs_dir2_sf_entry_t *sfep = NULL; /* shortform entry */ trace_xfs_dir2_sf_addname(args); ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT); ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == dp->i_disk_size); ASSERT(sfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Compute entry (and change in) size. */ incr_isize = xfs_dir2_sf_entsize(dp->i_mount, sfp, args->namelen); objchange = 0; /* * Do we have to change to 8 byte inodes? */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) { /* * Yes, adjust the inode size. old count + (parent + new) */ incr_isize += (sfp->count + 2) * XFS_INO64_DIFF; objchange = 1; } new_isize = (int)dp->i_disk_size + incr_isize; /* * Won't fit as shortform any more (due to size), * or the pick routine says it won't (due to offset values). */ if (new_isize > xfs_inode_data_fork_size(dp) || (pick = xfs_dir2_sf_addname_pick(args, objchange, &sfep, &offset)) == 0) { /* * Just checking or no space reservation, it doesn't fit. */ if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0) return -ENOSPC; /* * Convert to block form then add the name. */ error = xfs_dir2_sf_to_block(args); if (error) return error; return xfs_dir2_block_addname(args); } /* * Just checking, it fits. */ if (args->op_flags & XFS_DA_OP_JUSTCHECK) return 0; /* * Do it the easy way - just add it at the end. */ if (pick == 1) xfs_dir2_sf_addname_easy(args, sfep, offset, new_isize); /* * Do it the hard way - look for a place to insert the new entry. * Convert to 8 byte inode numbers first if necessary. */ else { ASSERT(pick == 2); if (objchange) xfs_dir2_sf_toino8(args); xfs_dir2_sf_addname_hard(args, objchange, new_isize); } xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); return 0; } /* * Add the new entry the "easy" way. * This is copying the old directory and adding the new entry at the end. * Since it's sorted by "offset" we need room after the last offset * that's already there, and then room to convert to a block directory. * This is already checked by the pick routine. */ static void xfs_dir2_sf_addname_easy( xfs_da_args_t *args, /* operation arguments */ xfs_dir2_sf_entry_t *sfep, /* pointer to new entry */ xfs_dir2_data_aoff_t offset, /* offset to use for new ent */ int new_isize) /* new directory size */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int byteoff = (int)((char *)sfep - (char *)sfp); /* * Grow the in-inode space. */ sfp = xfs_idata_realloc(dp, xfs_dir2_sf_entsize(mp, sfp, args->namelen), XFS_DATA_FORK); /* * Need to set up again due to realloc of the inode data. */ sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff); /* * Fill in the new entry. */ sfep->namelen = args->namelen; xfs_dir2_sf_put_offset(sfep, offset); memcpy(sfep->name, args->name, sfep->namelen); xfs_dir2_sf_put_ino(mp, sfp, sfep, args->inumber); xfs_dir2_sf_put_ftype(mp, sfep, args->filetype); /* * Update the header and inode. */ sfp->count++; if (args->inumber > XFS_DIR2_MAX_SHORT_INUM) sfp->i8count++; dp->i_disk_size = new_isize; xfs_dir2_sf_check(args); } /* * Add the new entry the "hard" way. * The caller has already converted to 8 byte inode numbers if necessary, * in which case we need to leave the i8count at 1. * Find a hole that the new entry will fit into, and copy * the first part of the entries, the new entry, and the last part of * the entries. */ /* ARGSUSED */ static void xfs_dir2_sf_addname_hard( xfs_da_args_t *args, /* operation arguments */ int objchange, /* changing inode number size */ int new_isize) /* new directory size */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; int add_datasize; /* data size need for new ent */ char *buf; /* buffer for old */ int eof; /* reached end of old dir */ int nbytes; /* temp for byte copies */ xfs_dir2_data_aoff_t new_offset; /* next offset value */ xfs_dir2_data_aoff_t offset; /* current offset value */ int old_isize; /* previous size */ xfs_dir2_sf_entry_t *oldsfep; /* entry in original dir */ xfs_dir2_sf_hdr_t *oldsfp; /* original shortform dir */ xfs_dir2_sf_entry_t *sfep; /* entry in new dir */ xfs_dir2_sf_hdr_t *sfp; /* new shortform dir */ /* * Copy the old directory to the stack buffer. */ old_isize = (int)dp->i_disk_size; buf = kmalloc(old_isize, GFP_KERNEL | __GFP_NOFAIL); oldsfp = (xfs_dir2_sf_hdr_t *)buf; memcpy(oldsfp, dp->i_df.if_data, old_isize); /* * Loop over the old directory finding the place we're going * to insert the new entry. * If it's going to end up at the end then oldsfep will point there. */ for (offset = args->geo->data_first_offset, oldsfep = xfs_dir2_sf_firstentry(oldsfp), add_datasize = xfs_dir2_data_entsize(mp, args->namelen), eof = (char *)oldsfep == &buf[old_isize]; !eof; offset = new_offset + xfs_dir2_data_entsize(mp, oldsfep->namelen), oldsfep = xfs_dir2_sf_nextentry(mp, oldsfp, oldsfep), eof = (char *)oldsfep == &buf[old_isize]) { new_offset = xfs_dir2_sf_get_offset(oldsfep); if (offset + add_datasize <= new_offset) break; } /* * Get rid of the old directory, then allocate space for * the new one. We do this so xfs_idata_realloc won't copy * the data. */ xfs_idata_realloc(dp, -old_isize, XFS_DATA_FORK); sfp = xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK); /* * Copy the first part of the directory, including the header. */ nbytes = (int)((char *)oldsfep - (char *)oldsfp); memcpy(sfp, oldsfp, nbytes); sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + nbytes); /* * Fill in the new entry, and update the header counts. */ sfep->namelen = args->namelen; xfs_dir2_sf_put_offset(sfep, offset); memcpy(sfep->name, args->name, sfep->namelen); xfs_dir2_sf_put_ino(mp, sfp, sfep, args->inumber); xfs_dir2_sf_put_ftype(mp, sfep, args->filetype); sfp->count++; if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && !objchange) sfp->i8count++; /* * If there's more left to copy, do that. */ if (!eof) { sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); memcpy(sfep, oldsfep, old_isize - nbytes); } kfree(buf); dp->i_disk_size = new_isize; xfs_dir2_sf_check(args); } /* * Decide if the new entry will fit at all. * If it will fit, pick between adding the new entry to the end (easy) * or somewhere else (hard). * Return 0 (won't fit), 1 (easy), 2 (hard). */ /*ARGSUSED*/ static int /* pick result */ xfs_dir2_sf_addname_pick( xfs_da_args_t *args, /* operation arguments */ int objchange, /* inode # size changes */ xfs_dir2_sf_entry_t **sfepp, /* out(1): new entry ptr */ xfs_dir2_data_aoff_t *offsetp) /* out(1): new offset */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; int holefit; /* found hole it will fit in */ int i; /* entry number */ xfs_dir2_data_aoff_t offset; /* data block offset */ xfs_dir2_sf_entry_t *sfep; /* shortform entry */ struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int size; /* entry's data size */ int used; /* data bytes used */ size = xfs_dir2_data_entsize(mp, args->namelen); offset = args->geo->data_first_offset; sfep = xfs_dir2_sf_firstentry(sfp); holefit = 0; /* * Loop over sf entries. * Keep track of data offset and whether we've seen a place * to insert the new entry. */ for (i = 0; i < sfp->count; i++) { if (!holefit) holefit = offset + size <= xfs_dir2_sf_get_offset(sfep); offset = xfs_dir2_sf_get_offset(sfep) + xfs_dir2_data_entsize(mp, sfep->namelen); sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); } /* * Calculate data bytes used excluding the new entry, if this * was a data block (block form directory). */ used = offset + (sfp->count + 3) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t); /* * If it won't fit in a block form then we can't insert it, * we'll go back, convert to block, then try the insert and convert * to leaf. */ if (used + (holefit ? 0 : size) > args->geo->blksize) return 0; /* * If changing the inode number size, do it the hard way. */ if (objchange) return 2; /* * If it won't fit at the end then do it the hard way (use the hole). */ if (used + size > args->geo->blksize) return 2; /* * Do it the easy way. */ *sfepp = sfep; *offsetp = offset; return 1; } #ifdef DEBUG /* * Check consistency of shortform directory, assert if bad. */ static void xfs_dir2_sf_check( xfs_da_args_t *args) /* operation arguments */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int i; /* entry number */ int i8count; /* number of big inode#s */ xfs_ino_t ino; /* entry inode number */ int offset; /* data offset */ xfs_dir2_sf_entry_t *sfep; /* shortform dir entry */ offset = args->geo->data_first_offset; ino = xfs_dir2_sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep)) { ASSERT(xfs_dir2_sf_get_offset(sfep) >= offset); ino = xfs_dir2_sf_get_ino(mp, sfp, sfep); i8count += ino > XFS_DIR2_MAX_SHORT_INUM; offset = xfs_dir2_sf_get_offset(sfep) + xfs_dir2_data_entsize(mp, sfep->namelen); ASSERT(xfs_dir2_sf_get_ftype(mp, sfep) < XFS_DIR3_FT_MAX); } ASSERT(i8count == sfp->i8count); ASSERT((char *)sfep - (char *)sfp == dp->i_disk_size); ASSERT(offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t) <= args->geo->blksize); } #endif /* DEBUG */ /* Verify the consistency of an inline directory. */ xfs_failaddr_t xfs_dir2_sf_verify( struct xfs_mount *mp, struct xfs_dir2_sf_hdr *sfp, int64_t size) { struct xfs_dir2_sf_entry *sfep; struct xfs_dir2_sf_entry *next_sfep; char *endp; xfs_ino_t ino; int i; int i8count; int offset; int error; uint8_t filetype; /* * Give up if the directory is way too short. */ if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) || size < xfs_dir2_sf_hdr_size(sfp->i8count)) return __this_address; endp = (char *)sfp + size; /* Check .. entry */ ino = xfs_dir2_sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; error = xfs_dir_ino_validate(mp, ino); if (error) return __this_address; offset = mp->m_dir_geo->data_first_offset; /* Check all reported entries */ sfep = xfs_dir2_sf_firstentry(sfp); for (i = 0; i < sfp->count; i++) { /* * struct xfs_dir2_sf_entry has a variable length. * Check the fixed-offset parts of the structure are * within the data buffer. */ if (((char *)sfep + sizeof(*sfep)) >= endp) return __this_address; /* Don't allow names with known bad length. */ if (sfep->namelen == 0) return __this_address; /* * Check that the variable-length part of the structure is * within the data buffer. The next entry starts after the * name component, so nextentry is an acceptable test. */ next_sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); if (endp < (char *)next_sfep) return __this_address; /* Check that the offsets always increase. */ if (xfs_dir2_sf_get_offset(sfep) < offset) return __this_address; /* Check the inode number. */ ino = xfs_dir2_sf_get_ino(mp, sfp, sfep); i8count += ino > XFS_DIR2_MAX_SHORT_INUM; error = xfs_dir_ino_validate(mp, ino); if (error) return __this_address; /* Check the file type. */ filetype = xfs_dir2_sf_get_ftype(mp, sfep); if (filetype >= XFS_DIR3_FT_MAX) return __this_address; offset = xfs_dir2_sf_get_offset(sfep) + xfs_dir2_data_entsize(mp, sfep->namelen); sfep = next_sfep; } if (i8count != sfp->i8count) return __this_address; if ((void *)sfep != (void *)endp) return __this_address; /* Make sure this whole thing ought to be in local format. */ if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize) return __this_address; return NULL; } /* * Create a new (shortform) directory. */ int /* error, always 0 */ xfs_dir2_sf_create( xfs_da_args_t *args, /* operation arguments */ xfs_ino_t pino) /* parent inode number */ { xfs_inode_t *dp; /* incore directory inode */ int i8count; /* parent inode is an 8-byte number */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ int size; /* directory size */ trace_xfs_dir2_sf_create(args); dp = args->dp; ASSERT(dp != NULL); ASSERT(dp->i_disk_size == 0); /* * If it's currently a zero-length extent file, * convert it to local format. */ if (dp->i_df.if_format == XFS_DINODE_FMT_EXTENTS) { dp->i_df.if_format = XFS_DINODE_FMT_LOCAL; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE); } ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_df.if_bytes == 0); i8count = pino > XFS_DIR2_MAX_SHORT_INUM; size = xfs_dir2_sf_hdr_size(i8count); /* * Make a buffer for the data and fill in the header. */ sfp = xfs_idata_realloc(dp, size, XFS_DATA_FORK); sfp->i8count = i8count; /* * Now can put in the inode number, since i8count is set. */ xfs_dir2_sf_put_parent_ino(sfp, pino); sfp->count = 0; dp->i_disk_size = size; xfs_dir2_sf_check(args); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); return 0; } /* * Lookup an entry in a shortform directory. * Returns EEXIST if found, ENOENT if not found. */ int /* error */ xfs_dir2_sf_lookup( xfs_da_args_t *args) /* operation arguments */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int i; /* entry index */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ enum xfs_dacmp cmp; /* comparison result */ xfs_dir2_sf_entry_t *ci_sfep; /* case-insens. entry */ trace_xfs_dir2_sf_lookup(args); xfs_dir2_sf_check(args); ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == dp->i_disk_size); ASSERT(sfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Special case for . */ if (args->namelen == 1 && args->name[0] == '.') { args->inumber = dp->i_ino; args->cmpresult = XFS_CMP_EXACT; args->filetype = XFS_DIR3_FT_DIR; return -EEXIST; } /* * Special case for .. */ if (args->namelen == 2 && args->name[0] == '.' && args->name[1] == '.') { args->inumber = xfs_dir2_sf_get_parent_ino(sfp); args->cmpresult = XFS_CMP_EXACT; args->filetype = XFS_DIR3_FT_DIR; return -EEXIST; } /* * Loop over all the entries trying to match ours. */ ci_sfep = NULL; for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep)) { /* * Compare name and if it's an exact match, return the inode * number. If it's the first case-insensitive match, store the * inode number and continue looking for an exact match. */ cmp = xfs_dir2_compname(args, sfep->name, sfep->namelen); if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { args->cmpresult = cmp; args->inumber = xfs_dir2_sf_get_ino(mp, sfp, sfep); args->filetype = xfs_dir2_sf_get_ftype(mp, sfep); if (cmp == XFS_CMP_EXACT) return -EEXIST; ci_sfep = sfep; } } ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); /* * Here, we can only be doing a lookup (not a rename or replace). * If a case-insensitive match was not found, return -ENOENT. */ if (!ci_sfep) return -ENOENT; /* otherwise process the CI match as required by the caller */ return xfs_dir_cilookup_result(args, ci_sfep->name, ci_sfep->namelen); } /* * Remove an entry from a shortform directory. */ int /* error */ xfs_dir2_sf_removename( xfs_da_args_t *args) { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int byteoff; /* offset of removed entry */ int entsize; /* this entry's size */ int i; /* shortform entry index */ int newsize; /* new inode size */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ trace_xfs_dir2_sf_removename(args); ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); oldsize = (int)dp->i_disk_size; ASSERT(oldsize >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == oldsize); ASSERT(sfp != NULL); ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Loop over the old directory entries. * Find the one we're deleting. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep)) { if (xfs_da_compname(args, sfep->name, sfep->namelen) == XFS_CMP_EXACT) { ASSERT(xfs_dir2_sf_get_ino(mp, sfp, sfep) == args->inumber); break; } } /* * Didn't find it. */ if (i == sfp->count) return -ENOENT; /* * Calculate sizes. */ byteoff = (int)((char *)sfep - (char *)sfp); entsize = xfs_dir2_sf_entsize(mp, sfp, args->namelen); newsize = oldsize - entsize; /* * Copy the part if any after the removed entry, sliding it down. */ if (byteoff + entsize < oldsize) memmove((char *)sfp + byteoff, (char *)sfp + byteoff + entsize, oldsize - (byteoff + entsize)); /* * Fix up the header and file size. */ sfp->count--; dp->i_disk_size = newsize; /* * Reallocate, making it smaller. */ sfp = xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK); /* * Are we changing inode number size? */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM) { if (sfp->i8count == 1) xfs_dir2_sf_toino4(args); else sfp->i8count--; } xfs_dir2_sf_check(args); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); return 0; } /* * Check whether the sf dir replace operation need more blocks. */ static bool xfs_dir2_sf_replace_needblock( struct xfs_inode *dp, xfs_ino_t inum) { struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int newsize; if (dp->i_df.if_format != XFS_DINODE_FMT_LOCAL) return false; newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF; return inum > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0 && newsize > xfs_inode_data_fork_size(dp); } /* * Replace the inode number of an entry in a shortform directory. */ int /* error */ xfs_dir2_sf_replace( xfs_da_args_t *args) /* operation arguments */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir2_sf_hdr *sfp = dp->i_df.if_data; int i; /* entry index */ xfs_ino_t ino=0; /* entry old inode number */ int i8elevated; /* sf_toino8 set i8count=1 */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ trace_xfs_dir2_sf_replace(args); ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL); ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent)); ASSERT(dp->i_df.if_bytes == dp->i_disk_size); ASSERT(sfp != NULL); ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * New inode number is large, and need to convert to 8-byte inodes. */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) { int error; /* error return value */ /* * Won't fit as shortform, convert to block then do replace. */ if (xfs_dir2_sf_replace_needblock(dp, args->inumber)) { error = xfs_dir2_sf_to_block(args); if (error) return error; return xfs_dir2_block_replace(args); } /* * Still fits, convert to 8-byte now. */ xfs_dir2_sf_toino8(args); i8elevated = 1; sfp = dp->i_df.if_data; } else i8elevated = 0; ASSERT(args->namelen != 1 || args->name[0] != '.'); /* * Replace ..'s entry. */ if (args->namelen == 2 && args->name[0] == '.' && args->name[1] == '.') { ino = xfs_dir2_sf_get_parent_ino(sfp); ASSERT(args->inumber != ino); xfs_dir2_sf_put_parent_ino(sfp, args->inumber); } /* * Normal entry, look for the name. */ else { for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep)) { if (xfs_da_compname(args, sfep->name, sfep->namelen) == XFS_CMP_EXACT) { ino = xfs_dir2_sf_get_ino(mp, sfp, sfep); ASSERT(args->inumber != ino); xfs_dir2_sf_put_ino(mp, sfp, sfep, args->inumber); xfs_dir2_sf_put_ftype(mp, sfep, args->filetype); break; } } /* * Didn't find it. */ if (i == sfp->count) { ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); if (i8elevated) xfs_dir2_sf_toino4(args); return -ENOENT; } } /* * See if the old number was large, the new number is small. */ if (ino > XFS_DIR2_MAX_SHORT_INUM && args->inumber <= XFS_DIR2_MAX_SHORT_INUM) { /* * And the old count was one, so need to convert to small. */ if (sfp->i8count == 1) xfs_dir2_sf_toino4(args); else sfp->i8count--; } /* * See if the old number was small, the new number is large. */ if (ino <= XFS_DIR2_MAX_SHORT_INUM && args->inumber > XFS_DIR2_MAX_SHORT_INUM) { /* * add to the i8count unless we just converted to 8-byte * inodes (which does an implied i8count = 1) */ ASSERT(sfp->i8count != 0); if (!i8elevated) sfp->i8count++; } xfs_dir2_sf_check(args); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_DDATA); return 0; } /* * Convert from 8-byte inode numbers to 4-byte inode numbers. * The last 8-byte inode number is gone, but the count is still 1. */ static void xfs_dir2_sf_toino4( xfs_da_args_t *args) /* operation arguments */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir2_sf_hdr *oldsfp = dp->i_df.if_data; char *buf; /* old dir's buffer */ int i; /* entry index */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ trace_xfs_dir2_sf_toino4(args); /* * Copy the old directory to the buffer. * Then nuke it from the inode, and add the new buffer to the inode. * Don't want xfs_idata_realloc copying the data here. */ oldsize = dp->i_df.if_bytes; buf = kmalloc(oldsize, GFP_KERNEL | __GFP_NOFAIL); ASSERT(oldsfp->i8count == 1); memcpy(buf, oldsfp, oldsize); /* * Compute the new inode size. */ newsize = oldsize - (oldsfp->count + 1) * XFS_INO64_DIFF; xfs_idata_realloc(dp, -oldsize, XFS_DATA_FORK); xfs_idata_realloc(dp, newsize, XFS_DATA_FORK); /* * Reset our pointers, the data has moved. */ oldsfp = (xfs_dir2_sf_hdr_t *)buf; sfp = dp->i_df.if_data; /* * Fill in the new header. */ sfp->count = oldsfp->count; sfp->i8count = 0; xfs_dir2_sf_put_parent_ino(sfp, xfs_dir2_sf_get_parent_ino(oldsfp)); /* * Copy the entries field by field. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp), oldsfep = xfs_dir2_sf_firstentry(oldsfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep), oldsfep = xfs_dir2_sf_nextentry(mp, oldsfp, oldsfep)) { sfep->namelen = oldsfep->namelen; memcpy(sfep->offset, oldsfep->offset, sizeof(sfep->offset)); memcpy(sfep->name, oldsfep->name, sfep->namelen); xfs_dir2_sf_put_ino(mp, sfp, sfep, xfs_dir2_sf_get_ino(mp, oldsfp, oldsfep)); xfs_dir2_sf_put_ftype(mp, sfep, xfs_dir2_sf_get_ftype(mp, oldsfep)); } /* * Clean up the inode. */ kfree(buf); dp->i_disk_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } /* * Convert existing entries from 4-byte inode numbers to 8-byte inode numbers. * The new entry w/ an 8-byte inode number is not there yet; we leave with * i8count set to 1, but no corresponding 8-byte entry. */ static void xfs_dir2_sf_toino8( xfs_da_args_t *args) /* operation arguments */ { struct xfs_inode *dp = args->dp; struct xfs_mount *mp = dp->i_mount; struct xfs_dir2_sf_hdr *oldsfp = dp->i_df.if_data; char *buf; /* old dir's buffer */ int i; /* entry index */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ trace_xfs_dir2_sf_toino8(args); /* * Copy the old directory to the buffer. * Then nuke it from the inode, and add the new buffer to the inode. * Don't want xfs_idata_realloc copying the data here. */ oldsize = dp->i_df.if_bytes; buf = kmalloc(oldsize, GFP_KERNEL | __GFP_NOFAIL); ASSERT(oldsfp->i8count == 0); memcpy(buf, oldsfp, oldsize); /* * Compute the new inode size (nb: entry count + 1 for parent) */ newsize = oldsize + (oldsfp->count + 1) * XFS_INO64_DIFF; xfs_idata_realloc(dp, -oldsize, XFS_DATA_FORK); xfs_idata_realloc(dp, newsize, XFS_DATA_FORK); /* * Reset our pointers, the data has moved. */ oldsfp = (xfs_dir2_sf_hdr_t *)buf; sfp = dp->i_df.if_data; /* * Fill in the new header. */ sfp->count = oldsfp->count; sfp->i8count = 1; xfs_dir2_sf_put_parent_ino(sfp, xfs_dir2_sf_get_parent_ino(oldsfp)); /* * Copy the entries field by field. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp), oldsfep = xfs_dir2_sf_firstentry(oldsfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep), oldsfep = xfs_dir2_sf_nextentry(mp, oldsfp, oldsfep)) { sfep->namelen = oldsfep->namelen; memcpy(sfep->offset, oldsfep->offset, sizeof(sfep->offset)); memcpy(sfep->name, oldsfep->name, sfep->namelen); xfs_dir2_sf_put_ino(mp, sfp, sfep, xfs_dir2_sf_get_ino(mp, oldsfp, oldsfep)); xfs_dir2_sf_put_ftype(mp, sfep, xfs_dir2_sf_get_ftype(mp, oldsfep)); } /* * Clean up the inode. */ kfree(buf); dp->i_disk_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } |
| 2 4 2 1 1 5 1 4 4 4 15 15 15 15 2 14 1 1 15 15 3 3 2 10 10 5 10 10 31 1 29 1 29 29 29 15 15 5 14 2 2 15 2 14 40 40 5 2 1 2 2 16 13 3 4 1 1 1 1 1 1 1 2 1 1 1 1 8 1 4 3 4 1 1 1 2 5 5 5 3 2 3 2 5 3 1 1 1 1 1 9 1 2 1 1 2 2 2 1 1 6 6 6 6 31 31 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware VMCI Driver * * Copyright (C) 2012 VMware, Inc. All rights reserved. */ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/slab.h> #include "vmci_queue_pair.h" #include "vmci_datagram.h" #include "vmci_doorbell.h" #include "vmci_context.h" #include "vmci_driver.h" #include "vmci_event.h" /* Use a wide upper bound for the maximum contexts. */ #define VMCI_MAX_CONTEXTS 2000 /* * List of current VMCI contexts. Contexts can be added by * vmci_ctx_create() and removed via vmci_ctx_destroy(). * These, along with context lookup, are protected by the * list structure's lock. */ static struct { struct list_head head; spinlock_t lock; /* Spinlock for context list operations */ } ctx_list = { .head = LIST_HEAD_INIT(ctx_list.head), .lock = __SPIN_LOCK_UNLOCKED(ctx_list.lock), }; /* Used by contexts that did not set up notify flag pointers */ static bool ctx_dummy_notify; static void ctx_signal_notify(struct vmci_ctx *context) { *context->notify = true; } static void ctx_clear_notify(struct vmci_ctx *context) { *context->notify = false; } /* * If nothing requires the attention of the guest, clears both * notify flag and call. */ static void ctx_clear_notify_call(struct vmci_ctx *context) { if (context->pending_datagrams == 0 && vmci_handle_arr_get_size(context->pending_doorbell_array) == 0) ctx_clear_notify(context); } /* * Sets the context's notify flag iff datagrams are pending for this * context. Called from vmci_setup_notify(). */ void vmci_ctx_check_signal_notify(struct vmci_ctx *context) { spin_lock(&context->lock); if (context->pending_datagrams) ctx_signal_notify(context); spin_unlock(&context->lock); } /* * Allocates and initializes a VMCI context. */ struct vmci_ctx *vmci_ctx_create(u32 cid, u32 priv_flags, uintptr_t event_hnd, int user_version, const struct cred *cred) { struct vmci_ctx *context; int error; if (cid == VMCI_INVALID_ID) { pr_devel("Invalid context ID for VMCI context\n"); error = -EINVAL; goto err_out; } if (priv_flags & ~VMCI_PRIVILEGE_ALL_FLAGS) { pr_devel("Invalid flag (flags=0x%x) for VMCI context\n", priv_flags); error = -EINVAL; goto err_out; } if (user_version == 0) { pr_devel("Invalid suer_version %d\n", user_version); error = -EINVAL; goto err_out; } context = kzalloc(sizeof(*context), GFP_KERNEL); if (!context) { pr_warn("Failed to allocate memory for VMCI context\n"); error = -ENOMEM; goto err_out; } kref_init(&context->kref); spin_lock_init(&context->lock); INIT_LIST_HEAD(&context->list_item); INIT_LIST_HEAD(&context->datagram_queue); INIT_LIST_HEAD(&context->notifier_list); /* Initialize host-specific VMCI context. */ init_waitqueue_head(&context->host_context.wait_queue); context->queue_pair_array = vmci_handle_arr_create(0, VMCI_MAX_GUEST_QP_COUNT); if (!context->queue_pair_array) { error = -ENOMEM; goto err_free_ctx; } context->doorbell_array = vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT); if (!context->doorbell_array) { error = -ENOMEM; goto err_free_qp_array; } context->pending_doorbell_array = vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT); if (!context->pending_doorbell_array) { error = -ENOMEM; goto err_free_db_array; } context->user_version = user_version; context->priv_flags = priv_flags; if (cred) context->cred = get_cred(cred); context->notify = &ctx_dummy_notify; context->notify_page = NULL; /* * If we collide with an existing context we generate a new * and use it instead. The VMX will determine if regeneration * is okay. Since there isn't 4B - 16 VMs running on a given * host, the below loop will terminate. */ spin_lock(&ctx_list.lock); while (vmci_ctx_exists(cid)) { /* We reserve the lowest 16 ids for fixed contexts. */ cid = max(cid, VMCI_RESERVED_CID_LIMIT - 1) + 1; if (cid == VMCI_INVALID_ID) cid = VMCI_RESERVED_CID_LIMIT; } context->cid = cid; list_add_tail_rcu(&context->list_item, &ctx_list.head); spin_unlock(&ctx_list.lock); return context; err_free_db_array: vmci_handle_arr_destroy(context->doorbell_array); err_free_qp_array: vmci_handle_arr_destroy(context->queue_pair_array); err_free_ctx: kfree(context); err_out: return ERR_PTR(error); } /* * Destroy VMCI context. */ void vmci_ctx_destroy(struct vmci_ctx *context) { spin_lock(&ctx_list.lock); list_del_rcu(&context->list_item); spin_unlock(&ctx_list.lock); synchronize_rcu(); vmci_ctx_put(context); } /* * Fire notification for all contexts interested in given cid. */ static int ctx_fire_notification(u32 context_id, u32 priv_flags) { u32 i, array_size; struct vmci_ctx *sub_ctx; struct vmci_handle_arr *subscriber_array; struct vmci_handle context_handle = vmci_make_handle(context_id, VMCI_EVENT_HANDLER); /* * We create an array to hold the subscribers we find when * scanning through all contexts. */ subscriber_array = vmci_handle_arr_create(0, VMCI_MAX_CONTEXTS); if (subscriber_array == NULL) return VMCI_ERROR_NO_MEM; /* * Scan all contexts to find who is interested in being * notified about given contextID. */ rcu_read_lock(); list_for_each_entry_rcu(sub_ctx, &ctx_list.head, list_item) { struct vmci_handle_list *node; /* * We only deliver notifications of the removal of * contexts, if the two contexts are allowed to * interact. */ if (vmci_deny_interaction(priv_flags, sub_ctx->priv_flags)) continue; list_for_each_entry_rcu(node, &sub_ctx->notifier_list, node) { if (!vmci_handle_is_equal(node->handle, context_handle)) continue; vmci_handle_arr_append_entry(&subscriber_array, vmci_make_handle(sub_ctx->cid, VMCI_EVENT_HANDLER)); } } rcu_read_unlock(); /* Fire event to all subscribers. */ array_size = vmci_handle_arr_get_size(subscriber_array); for (i = 0; i < array_size; i++) { int result; struct vmci_event_ctx ev; ev.msg.hdr.dst = vmci_handle_arr_get_entry(subscriber_array, i); ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, VMCI_CONTEXT_RESOURCE_ID); ev.msg.hdr.payload_size = sizeof(ev) - sizeof(ev.msg.hdr); ev.msg.event_data.event = VMCI_EVENT_CTX_REMOVED; ev.payload.context_id = context_id; result = vmci_datagram_dispatch(VMCI_HYPERVISOR_CONTEXT_ID, &ev.msg.hdr, false); if (result < VMCI_SUCCESS) { pr_devel("Failed to enqueue event datagram (type=%d) for context (ID=0x%x)\n", ev.msg.event_data.event, ev.msg.hdr.dst.context); /* We continue to enqueue on next subscriber. */ } } vmci_handle_arr_destroy(subscriber_array); return VMCI_SUCCESS; } /* * Returns the current number of pending datagrams. The call may * also serve as a synchronization point for the datagram queue, * as no enqueue operations can occur concurrently. */ int vmci_ctx_pending_datagrams(u32 cid, u32 *pending) { struct vmci_ctx *context; context = vmci_ctx_get(cid); if (context == NULL) return VMCI_ERROR_INVALID_ARGS; spin_lock(&context->lock); if (pending) *pending = context->pending_datagrams; spin_unlock(&context->lock); vmci_ctx_put(context); return VMCI_SUCCESS; } /* * Queues a VMCI datagram for the appropriate target VM context. */ int vmci_ctx_enqueue_datagram(u32 cid, struct vmci_datagram *dg) { struct vmci_datagram_queue_entry *dq_entry; struct vmci_ctx *context; struct vmci_handle dg_src; size_t vmci_dg_size; vmci_dg_size = VMCI_DG_SIZE(dg); if (vmci_dg_size > VMCI_MAX_DG_SIZE) { pr_devel("Datagram too large (bytes=%zu)\n", vmci_dg_size); return VMCI_ERROR_INVALID_ARGS; } /* Get the target VM's VMCI context. */ context = vmci_ctx_get(cid); if (!context) { pr_devel("Invalid context (ID=0x%x)\n", cid); return VMCI_ERROR_INVALID_ARGS; } /* Allocate guest call entry and add it to the target VM's queue. */ dq_entry = kmalloc(sizeof(*dq_entry), GFP_KERNEL); if (dq_entry == NULL) { pr_warn("Failed to allocate memory for datagram\n"); vmci_ctx_put(context); return VMCI_ERROR_NO_MEM; } dq_entry->dg = dg; dq_entry->dg_size = vmci_dg_size; dg_src = dg->src; INIT_LIST_HEAD(&dq_entry->list_item); spin_lock(&context->lock); /* * We put a higher limit on datagrams from the hypervisor. If * the pending datagram is not from hypervisor, then we check * if enqueueing it would exceed the * VMCI_MAX_DATAGRAM_QUEUE_SIZE limit on the destination. If * the pending datagram is from hypervisor, we allow it to be * queued at the destination side provided we don't reach the * VMCI_MAX_DATAGRAM_AND_EVENT_QUEUE_SIZE limit. */ if (context->datagram_queue_size + vmci_dg_size >= VMCI_MAX_DATAGRAM_QUEUE_SIZE && (!vmci_handle_is_equal(dg_src, vmci_make_handle (VMCI_HYPERVISOR_CONTEXT_ID, VMCI_CONTEXT_RESOURCE_ID)) || context->datagram_queue_size + vmci_dg_size >= VMCI_MAX_DATAGRAM_AND_EVENT_QUEUE_SIZE)) { spin_unlock(&context->lock); vmci_ctx_put(context); kfree(dq_entry); pr_devel("Context (ID=0x%x) receive queue is full\n", cid); return VMCI_ERROR_NO_RESOURCES; } list_add(&dq_entry->list_item, &context->datagram_queue); context->pending_datagrams++; context->datagram_queue_size += vmci_dg_size; ctx_signal_notify(context); wake_up(&context->host_context.wait_queue); spin_unlock(&context->lock); vmci_ctx_put(context); return vmci_dg_size; } /* * Verifies whether a context with the specified context ID exists. * FIXME: utility is dubious as no decisions can be reliably made * using this data as context can appear and disappear at any time. */ bool vmci_ctx_exists(u32 cid) { struct vmci_ctx *context; bool exists = false; rcu_read_lock(); list_for_each_entry_rcu(context, &ctx_list.head, list_item) { if (context->cid == cid) { exists = true; break; } } rcu_read_unlock(); return exists; } /* * Retrieves VMCI context corresponding to the given cid. */ struct vmci_ctx *vmci_ctx_get(u32 cid) { struct vmci_ctx *c, *context = NULL; if (cid == VMCI_INVALID_ID) return NULL; rcu_read_lock(); list_for_each_entry_rcu(c, &ctx_list.head, list_item) { if (c->cid == cid) { /* * The context owner drops its own reference to the * context only after removing it from the list and * waiting for RCU grace period to expire. This * means that we are not about to increase the * reference count of something that is in the * process of being destroyed. */ context = c; kref_get(&context->kref); break; } } rcu_read_unlock(); return context; } /* * Deallocates all parts of a context data structure. This * function doesn't lock the context, because it assumes that * the caller was holding the last reference to context. */ static void ctx_free_ctx(struct kref *kref) { struct vmci_ctx *context = container_of(kref, struct vmci_ctx, kref); struct vmci_datagram_queue_entry *dq_entry, *dq_entry_tmp; struct vmci_handle temp_handle; struct vmci_handle_list *notifier, *tmp; /* * Fire event to all contexts interested in knowing this * context is dying. */ ctx_fire_notification(context->cid, context->priv_flags); /* * Cleanup all queue pair resources attached to context. If * the VM dies without cleaning up, this code will make sure * that no resources are leaked. */ temp_handle = vmci_handle_arr_get_entry(context->queue_pair_array, 0); while (!vmci_handle_is_equal(temp_handle, VMCI_INVALID_HANDLE)) { if (vmci_qp_broker_detach(temp_handle, context) < VMCI_SUCCESS) { /* * When vmci_qp_broker_detach() succeeds it * removes the handle from the array. If * detach fails, we must remove the handle * ourselves. */ vmci_handle_arr_remove_entry(context->queue_pair_array, temp_handle); } temp_handle = vmci_handle_arr_get_entry(context->queue_pair_array, 0); } /* * It is fine to destroy this without locking the callQueue, as * this is the only thread having a reference to the context. */ list_for_each_entry_safe(dq_entry, dq_entry_tmp, &context->datagram_queue, list_item) { WARN_ON(dq_entry->dg_size != VMCI_DG_SIZE(dq_entry->dg)); list_del(&dq_entry->list_item); kfree(dq_entry->dg); kfree(dq_entry); } list_for_each_entry_safe(notifier, tmp, &context->notifier_list, node) { list_del(¬ifier->node); kfree(notifier); } vmci_handle_arr_destroy(context->queue_pair_array); vmci_handle_arr_destroy(context->doorbell_array); vmci_handle_arr_destroy(context->pending_doorbell_array); vmci_ctx_unset_notify(context); if (context->cred) put_cred(context->cred); kfree(context); } /* * Drops reference to VMCI context. If this is the last reference to * the context it will be deallocated. A context is created with * a reference count of one, and on destroy, it is removed from * the context list before its reference count is decremented. Thus, * if we reach zero, we are sure that nobody else are about to increment * it (they need the entry in the context list for that), and so there * is no need for locking. */ void vmci_ctx_put(struct vmci_ctx *context) { kref_put(&context->kref, ctx_free_ctx); } /* * Dequeues the next datagram and returns it to caller. * The caller passes in a pointer to the max size datagram * it can handle and the datagram is only unqueued if the * size is less than max_size. If larger max_size is set to * the size of the datagram to give the caller a chance to * set up a larger buffer for the guestcall. */ int vmci_ctx_dequeue_datagram(struct vmci_ctx *context, size_t *max_size, struct vmci_datagram **dg) { struct vmci_datagram_queue_entry *dq_entry; struct list_head *list_item; int rv; /* Dequeue the next datagram entry. */ spin_lock(&context->lock); if (context->pending_datagrams == 0) { ctx_clear_notify_call(context); spin_unlock(&context->lock); pr_devel("No datagrams pending\n"); return VMCI_ERROR_NO_MORE_DATAGRAMS; } list_item = context->datagram_queue.next; dq_entry = list_entry(list_item, struct vmci_datagram_queue_entry, list_item); /* Check size of caller's buffer. */ if (*max_size < dq_entry->dg_size) { *max_size = dq_entry->dg_size; spin_unlock(&context->lock); pr_devel("Caller's buffer should be at least (size=%u bytes)\n", (u32) *max_size); return VMCI_ERROR_NO_MEM; } list_del(list_item); context->pending_datagrams--; context->datagram_queue_size -= dq_entry->dg_size; if (context->pending_datagrams == 0) { ctx_clear_notify_call(context); rv = VMCI_SUCCESS; } else { /* * Return the size of the next datagram. */ struct vmci_datagram_queue_entry *next_entry; list_item = context->datagram_queue.next; next_entry = list_entry(list_item, struct vmci_datagram_queue_entry, list_item); /* * The following size_t -> int truncation is fine as * the maximum size of a (routable) datagram is 68KB. */ rv = (int)next_entry->dg_size; } spin_unlock(&context->lock); /* Caller must free datagram. */ *dg = dq_entry->dg; dq_entry->dg = NULL; kfree(dq_entry); return rv; } /* * Reverts actions set up by vmci_setup_notify(). Unmaps and unlocks the * page mapped/locked by vmci_setup_notify(). */ void vmci_ctx_unset_notify(struct vmci_ctx *context) { struct page *notify_page; spin_lock(&context->lock); notify_page = context->notify_page; context->notify = &ctx_dummy_notify; context->notify_page = NULL; spin_unlock(&context->lock); if (notify_page) { kunmap(notify_page); put_page(notify_page); } } /* * Add remote_cid to list of contexts current contexts wants * notifications from/about. */ int vmci_ctx_add_notification(u32 context_id, u32 remote_cid) { struct vmci_ctx *context; struct vmci_handle_list *notifier, *n; int result; bool exists = false; context = vmci_ctx_get(context_id); if (!context) return VMCI_ERROR_NOT_FOUND; if (VMCI_CONTEXT_IS_VM(context_id) && VMCI_CONTEXT_IS_VM(remote_cid)) { pr_devel("Context removed notifications for other VMs not supported (src=0x%x, remote=0x%x)\n", context_id, remote_cid); result = VMCI_ERROR_DST_UNREACHABLE; goto out; } if (context->priv_flags & VMCI_PRIVILEGE_FLAG_RESTRICTED) { result = VMCI_ERROR_NO_ACCESS; goto out; } notifier = kmalloc(sizeof(struct vmci_handle_list), GFP_KERNEL); if (!notifier) { result = VMCI_ERROR_NO_MEM; goto out; } INIT_LIST_HEAD(¬ifier->node); notifier->handle = vmci_make_handle(remote_cid, VMCI_EVENT_HANDLER); spin_lock(&context->lock); if (context->n_notifiers < VMCI_MAX_CONTEXTS) { list_for_each_entry(n, &context->notifier_list, node) { if (vmci_handle_is_equal(n->handle, notifier->handle)) { exists = true; break; } } if (exists) { kfree(notifier); result = VMCI_ERROR_ALREADY_EXISTS; } else { list_add_tail_rcu(¬ifier->node, &context->notifier_list); context->n_notifiers++; result = VMCI_SUCCESS; } } else { kfree(notifier); result = VMCI_ERROR_NO_MEM; } spin_unlock(&context->lock); out: vmci_ctx_put(context); return result; } /* * Remove remote_cid from current context's list of contexts it is * interested in getting notifications from/about. */ int vmci_ctx_remove_notification(u32 context_id, u32 remote_cid) { struct vmci_ctx *context; struct vmci_handle_list *notifier = NULL, *iter, *tmp; struct vmci_handle handle; context = vmci_ctx_get(context_id); if (!context) return VMCI_ERROR_NOT_FOUND; handle = vmci_make_handle(remote_cid, VMCI_EVENT_HANDLER); spin_lock(&context->lock); list_for_each_entry_safe(iter, tmp, &context->notifier_list, node) { if (vmci_handle_is_equal(iter->handle, handle)) { list_del_rcu(&iter->node); context->n_notifiers--; notifier = iter; break; } } spin_unlock(&context->lock); if (notifier) kvfree_rcu_mightsleep(notifier); vmci_ctx_put(context); return notifier ? VMCI_SUCCESS : VMCI_ERROR_NOT_FOUND; } static int vmci_ctx_get_chkpt_notifiers(struct vmci_ctx *context, u32 *buf_size, void **pbuf) { u32 *notifiers; size_t data_size; struct vmci_handle_list *entry; int i = 0; if (context->n_notifiers == 0) { *buf_size = 0; *pbuf = NULL; return VMCI_SUCCESS; } data_size = context->n_notifiers * sizeof(*notifiers); if (*buf_size < data_size) { *buf_size = data_size; return VMCI_ERROR_MORE_DATA; } notifiers = kmalloc(data_size, GFP_ATOMIC); /* FIXME: want GFP_KERNEL */ if (!notifiers) return VMCI_ERROR_NO_MEM; list_for_each_entry(entry, &context->notifier_list, node) notifiers[i++] = entry->handle.context; *buf_size = data_size; *pbuf = notifiers; return VMCI_SUCCESS; } static int vmci_ctx_get_chkpt_doorbells(struct vmci_ctx *context, u32 *buf_size, void **pbuf) { struct dbell_cpt_state *dbells; u32 i, n_doorbells; n_doorbells = vmci_handle_arr_get_size(context->doorbell_array); if (n_doorbells > 0) { size_t data_size = n_doorbells * sizeof(*dbells); if (*buf_size < data_size) { *buf_size = data_size; return VMCI_ERROR_MORE_DATA; } dbells = kzalloc(data_size, GFP_ATOMIC); if (!dbells) return VMCI_ERROR_NO_MEM; for (i = 0; i < n_doorbells; i++) dbells[i].handle = vmci_handle_arr_get_entry( context->doorbell_array, i); *buf_size = data_size; *pbuf = dbells; } else { *buf_size = 0; *pbuf = NULL; } return VMCI_SUCCESS; } /* * Get current context's checkpoint state of given type. */ int vmci_ctx_get_chkpt_state(u32 context_id, u32 cpt_type, u32 *buf_size, void **pbuf) { struct vmci_ctx *context; int result; context = vmci_ctx_get(context_id); if (!context) return VMCI_ERROR_NOT_FOUND; spin_lock(&context->lock); switch (cpt_type) { case VMCI_NOTIFICATION_CPT_STATE: result = vmci_ctx_get_chkpt_notifiers(context, buf_size, pbuf); break; case VMCI_WELLKNOWN_CPT_STATE: /* * For compatibility with VMX'en with VM to VM communication, we * always return zero wellknown handles. */ *buf_size = 0; *pbuf = NULL; result = VMCI_SUCCESS; break; case VMCI_DOORBELL_CPT_STATE: result = vmci_ctx_get_chkpt_doorbells(context, buf_size, pbuf); break; default: pr_devel("Invalid cpt state (type=%d)\n", cpt_type); result = VMCI_ERROR_INVALID_ARGS; break; } spin_unlock(&context->lock); vmci_ctx_put(context); return result; } /* * Set current context's checkpoint state of given type. */ int vmci_ctx_set_chkpt_state(u32 context_id, u32 cpt_type, u32 buf_size, void *cpt_buf) { u32 i; u32 current_id; int result = VMCI_SUCCESS; u32 num_ids = buf_size / sizeof(u32); if (cpt_type == VMCI_WELLKNOWN_CPT_STATE && num_ids > 0) { /* * We would end up here if VMX with VM to VM communication * attempts to restore a checkpoint with wellknown handles. */ pr_warn("Attempt to restore checkpoint with obsolete wellknown handles\n"); return VMCI_ERROR_OBSOLETE; } if (cpt_type != VMCI_NOTIFICATION_CPT_STATE) { pr_devel("Invalid cpt state (type=%d)\n", cpt_type); return VMCI_ERROR_INVALID_ARGS; } for (i = 0; i < num_ids && result == VMCI_SUCCESS; i++) { current_id = ((u32 *)cpt_buf)[i]; result = vmci_ctx_add_notification(context_id, current_id); if (result != VMCI_SUCCESS) break; } if (result != VMCI_SUCCESS) pr_devel("Failed to set cpt state (type=%d) (error=%d)\n", cpt_type, result); return result; } /* * Retrieves the specified context's pending notifications in the * form of a handle array. The handle arrays returned are the * actual data - not a copy and should not be modified by the * caller. They must be released using * vmci_ctx_rcv_notifications_release. */ int vmci_ctx_rcv_notifications_get(u32 context_id, struct vmci_handle_arr **db_handle_array, struct vmci_handle_arr **qp_handle_array) { struct vmci_ctx *context; int result = VMCI_SUCCESS; context = vmci_ctx_get(context_id); if (context == NULL) return VMCI_ERROR_NOT_FOUND; spin_lock(&context->lock); *db_handle_array = context->pending_doorbell_array; context->pending_doorbell_array = vmci_handle_arr_create(0, VMCI_MAX_GUEST_DOORBELL_COUNT); if (!context->pending_doorbell_array) { context->pending_doorbell_array = *db_handle_array; *db_handle_array = NULL; result = VMCI_ERROR_NO_MEM; } *qp_handle_array = NULL; spin_unlock(&context->lock); vmci_ctx_put(context); return result; } /* * Releases handle arrays with pending notifications previously * retrieved using vmci_ctx_rcv_notifications_get. If the * notifications were not successfully handed over to the guest, * success must be false. */ void vmci_ctx_rcv_notifications_release(u32 context_id, struct vmci_handle_arr *db_handle_array, struct vmci_handle_arr *qp_handle_array, bool success) { struct vmci_ctx *context = vmci_ctx_get(context_id); spin_lock(&context->lock); if (!success) { struct vmci_handle handle; /* * New notifications may have been added while we were not * holding the context lock, so we transfer any new pending * doorbell notifications to the old array, and reinstate the * old array. */ handle = vmci_handle_arr_remove_tail( context->pending_doorbell_array); while (!vmci_handle_is_invalid(handle)) { if (!vmci_handle_arr_has_entry(db_handle_array, handle)) { vmci_handle_arr_append_entry( &db_handle_array, handle); } handle = vmci_handle_arr_remove_tail( context->pending_doorbell_array); } vmci_handle_arr_destroy(context->pending_doorbell_array); context->pending_doorbell_array = db_handle_array; db_handle_array = NULL; } else { ctx_clear_notify_call(context); } spin_unlock(&context->lock); vmci_ctx_put(context); if (db_handle_array) vmci_handle_arr_destroy(db_handle_array); if (qp_handle_array) vmci_handle_arr_destroy(qp_handle_array); } /* * Registers that a new doorbell handle has been allocated by the * context. Only doorbell handles registered can be notified. */ int vmci_ctx_dbell_create(u32 context_id, struct vmci_handle handle) { struct vmci_ctx *context; int result; if (context_id == VMCI_INVALID_ID || vmci_handle_is_invalid(handle)) return VMCI_ERROR_INVALID_ARGS; context = vmci_ctx_get(context_id); if (context == NULL) return VMCI_ERROR_NOT_FOUND; spin_lock(&context->lock); if (!vmci_handle_arr_has_entry(context->doorbell_array, handle)) result = vmci_handle_arr_append_entry(&context->doorbell_array, handle); else result = VMCI_ERROR_DUPLICATE_ENTRY; spin_unlock(&context->lock); vmci_ctx_put(context); return result; } /* * Unregisters a doorbell handle that was previously registered * with vmci_ctx_dbell_create. */ int vmci_ctx_dbell_destroy(u32 context_id, struct vmci_handle handle) { struct vmci_ctx *context; struct vmci_handle removed_handle; if (context_id == VMCI_INVALID_ID || vmci_handle_is_invalid(handle)) return VMCI_ERROR_INVALID_ARGS; context = vmci_ctx_get(context_id); if (context == NULL) return VMCI_ERROR_NOT_FOUND; spin_lock(&context->lock); removed_handle = vmci_handle_arr_remove_entry(context->doorbell_array, handle); vmci_handle_arr_remove_entry(context->pending_doorbell_array, handle); spin_unlock(&context->lock); vmci_ctx_put(context); return vmci_handle_is_invalid(removed_handle) ? VMCI_ERROR_NOT_FOUND : VMCI_SUCCESS; } /* * Unregisters all doorbell handles that were previously * registered with vmci_ctx_dbell_create. */ int vmci_ctx_dbell_destroy_all(u32 context_id) { struct vmci_ctx *context; struct vmci_handle handle; if (context_id == VMCI_INVALID_ID) return VMCI_ERROR_INVALID_ARGS; context = vmci_ctx_get(context_id); if (context == NULL) return VMCI_ERROR_NOT_FOUND; spin_lock(&context->lock); do { struct vmci_handle_arr *arr = context->doorbell_array; handle = vmci_handle_arr_remove_tail(arr); } while (!vmci_handle_is_invalid(handle)); do { struct vmci_handle_arr *arr = context->pending_doorbell_array; handle = vmci_handle_arr_remove_tail(arr); } while (!vmci_handle_is_invalid(handle)); spin_unlock(&context->lock); vmci_ctx_put(context); return VMCI_SUCCESS; } /* * Registers a notification of a doorbell handle initiated by the * specified source context. The notification of doorbells are * subject to the same isolation rules as datagram delivery. To * allow host side senders of notifications a finer granularity * of sender rights than those assigned to the sending context * itself, the host context is required to specify a different * set of privilege flags that will override the privileges of * the source context. */ int vmci_ctx_notify_dbell(u32 src_cid, struct vmci_handle handle, u32 src_priv_flags) { struct vmci_ctx *dst_context; int result; if (vmci_handle_is_invalid(handle)) return VMCI_ERROR_INVALID_ARGS; /* Get the target VM's VMCI context. */ dst_context = vmci_ctx_get(handle.context); if (!dst_context) { pr_devel("Invalid context (ID=0x%x)\n", handle.context); return VMCI_ERROR_NOT_FOUND; } if (src_cid != handle.context) { u32 dst_priv_flags; if (VMCI_CONTEXT_IS_VM(src_cid) && VMCI_CONTEXT_IS_VM(handle.context)) { pr_devel("Doorbell notification from VM to VM not supported (src=0x%x, dst=0x%x)\n", src_cid, handle.context); result = VMCI_ERROR_DST_UNREACHABLE; goto out; } result = vmci_dbell_get_priv_flags(handle, &dst_priv_flags); if (result < VMCI_SUCCESS) { pr_warn("Failed to get privilege flags for destination (handle=0x%x:0x%x)\n", handle.context, handle.resource); goto out; } if (src_cid != VMCI_HOST_CONTEXT_ID || src_priv_flags == VMCI_NO_PRIVILEGE_FLAGS) { src_priv_flags = vmci_context_get_priv_flags(src_cid); } if (vmci_deny_interaction(src_priv_flags, dst_priv_flags)) { result = VMCI_ERROR_NO_ACCESS; goto out; } } if (handle.context == VMCI_HOST_CONTEXT_ID) { result = vmci_dbell_host_context_notify(src_cid, handle); } else { spin_lock(&dst_context->lock); if (!vmci_handle_arr_has_entry(dst_context->doorbell_array, handle)) { result = VMCI_ERROR_NOT_FOUND; } else { if (!vmci_handle_arr_has_entry( dst_context->pending_doorbell_array, handle)) { result = vmci_handle_arr_append_entry( &dst_context->pending_doorbell_array, handle); if (result == VMCI_SUCCESS) { ctx_signal_notify(dst_context); wake_up(&dst_context->host_context.wait_queue); } } else { result = VMCI_SUCCESS; } } spin_unlock(&dst_context->lock); } out: vmci_ctx_put(dst_context); return result; } bool vmci_ctx_supports_host_qp(struct vmci_ctx *context) { return context && context->user_version >= VMCI_VERSION_HOSTQP; } /* * Registers that a new queue pair handle has been allocated by * the context. */ int vmci_ctx_qp_create(struct vmci_ctx *context, struct vmci_handle handle) { int result; if (context == NULL || vmci_handle_is_invalid(handle)) return VMCI_ERROR_INVALID_ARGS; if (!vmci_handle_arr_has_entry(context->queue_pair_array, handle)) result = vmci_handle_arr_append_entry( &context->queue_pair_array, handle); else result = VMCI_ERROR_DUPLICATE_ENTRY; return result; } /* * Unregisters a queue pair handle that was previously registered * with vmci_ctx_qp_create. */ int vmci_ctx_qp_destroy(struct vmci_ctx *context, struct vmci_handle handle) { struct vmci_handle hndl; if (context == NULL || vmci_handle_is_invalid(handle)) return VMCI_ERROR_INVALID_ARGS; hndl = vmci_handle_arr_remove_entry(context->queue_pair_array, handle); return vmci_handle_is_invalid(hndl) ? VMCI_ERROR_NOT_FOUND : VMCI_SUCCESS; } /* * Determines whether a given queue pair handle is registered * with the given context. */ bool vmci_ctx_qp_exists(struct vmci_ctx *context, struct vmci_handle handle) { if (context == NULL || vmci_handle_is_invalid(handle)) return false; return vmci_handle_arr_has_entry(context->queue_pair_array, handle); } /* * vmci_context_get_priv_flags() - Retrieve privilege flags. * @context_id: The context ID of the VMCI context. * * Retrieves privilege flags of the given VMCI context ID. */ u32 vmci_context_get_priv_flags(u32 context_id) { if (vmci_host_code_active()) { u32 flags; struct vmci_ctx *context; context = vmci_ctx_get(context_id); if (!context) return VMCI_LEAST_PRIVILEGE_FLAGS; flags = context->priv_flags; vmci_ctx_put(context); return flags; } return VMCI_NO_PRIVILEGE_FLAGS; } EXPORT_SYMBOL_GPL(vmci_context_get_priv_flags); /* * vmci_is_context_owner() - Determimnes if user is the context owner * @context_id: The context ID of the VMCI context. * @uid: The host user id (real kernel value). * * Determines whether a given UID is the owner of given VMCI context. */ bool vmci_is_context_owner(u32 context_id, kuid_t uid) { bool is_owner = false; if (vmci_host_code_active()) { struct vmci_ctx *context = vmci_ctx_get(context_id); if (context) { if (context->cred) is_owner = uid_eq(context->cred->uid, uid); vmci_ctx_put(context); } } return is_owner; } EXPORT_SYMBOL_GPL(vmci_is_context_owner); |
| 5 1 3 1 2 2 2 2 2 4 3 3 3 3 3 6 6 4 1 3 3 3 3 3 3 1 2 3 3 1 2 1 1 1 1 1 26 26 2 2 2 2 2 2 4 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 | // SPDX-License-Identifier: GPL-2.0 /* * net/tipc/crypto.c: TIPC crypto for key handling & packet en/decryption * * Copyright (c) 2019, Ericsson AB * 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 names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * 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 <crypto/aead.h> #include <crypto/aes.h> #include <crypto/rng.h> #include "crypto.h" #include "msg.h" #include "bcast.h" #define TIPC_TX_GRACE_PERIOD msecs_to_jiffies(5000) /* 5s */ #define TIPC_TX_LASTING_TIME msecs_to_jiffies(10000) /* 10s */ #define TIPC_RX_ACTIVE_LIM msecs_to_jiffies(3000) /* 3s */ #define TIPC_RX_PASSIVE_LIM msecs_to_jiffies(15000) /* 15s */ #define TIPC_MAX_TFMS_DEF 10 #define TIPC_MAX_TFMS_LIM 1000 #define TIPC_REKEYING_INTV_DEF (60 * 24) /* default: 1 day */ /* * TIPC Key ids */ enum { KEY_MASTER = 0, KEY_MIN = KEY_MASTER, KEY_1 = 1, KEY_2, KEY_3, KEY_MAX = KEY_3, }; /* * TIPC Crypto statistics */ enum { STAT_OK, STAT_NOK, STAT_ASYNC, STAT_ASYNC_OK, STAT_ASYNC_NOK, STAT_BADKEYS, /* tx only */ STAT_BADMSGS = STAT_BADKEYS, /* rx only */ STAT_NOKEYS, STAT_SWITCHES, MAX_STATS, }; /* TIPC crypto statistics' header */ static const char *hstats[MAX_STATS] = {"ok", "nok", "async", "async_ok", "async_nok", "badmsgs", "nokeys", "switches"}; /* Max TFMs number per key */ int sysctl_tipc_max_tfms __read_mostly = TIPC_MAX_TFMS_DEF; /* Key exchange switch, default: on */ int sysctl_tipc_key_exchange_enabled __read_mostly = 1; /* * struct tipc_key - TIPC keys' status indicator * * 7 6 5 4 3 2 1 0 * +-----+-----+-----+-----+-----+-----+-----+-----+ * key: | (reserved)|passive idx| active idx|pending idx| * +-----+-----+-----+-----+-----+-----+-----+-----+ */ struct tipc_key { #define KEY_BITS (2) #define KEY_MASK ((1 << KEY_BITS) - 1) union { struct { #if defined(__LITTLE_ENDIAN_BITFIELD) u8 pending:2, active:2, passive:2, /* rx only */ reserved:2; #elif defined(__BIG_ENDIAN_BITFIELD) u8 reserved:2, passive:2, /* rx only */ active:2, pending:2; #else #error "Please fix <asm/byteorder.h>" #endif } __packed; u8 keys; }; }; /** * struct tipc_tfm - TIPC TFM structure to form a list of TFMs * @tfm: cipher handle/key * @list: linked list of TFMs */ struct tipc_tfm { struct crypto_aead *tfm; struct list_head list; }; /** * struct tipc_aead - TIPC AEAD key structure * @tfm_entry: per-cpu pointer to one entry in TFM list * @crypto: TIPC crypto owns this key * @cloned: reference to the source key in case cloning * @users: the number of the key users (TX/RX) * @salt: the key's SALT value * @authsize: authentication tag size (max = 16) * @mode: crypto mode is applied to the key * @hint: a hint for user key * @rcu: struct rcu_head * @key: the aead key * @gen: the key's generation * @seqno: the key seqno (cluster scope) * @refcnt: the key reference counter */ struct tipc_aead { #define TIPC_AEAD_HINT_LEN (5) struct tipc_tfm * __percpu *tfm_entry; struct tipc_crypto *crypto; struct tipc_aead *cloned; atomic_t users; u32 salt; u8 authsize; u8 mode; char hint[2 * TIPC_AEAD_HINT_LEN + 1]; struct rcu_head rcu; struct tipc_aead_key *key; u16 gen; atomic64_t seqno ____cacheline_aligned; refcount_t refcnt ____cacheline_aligned; } ____cacheline_aligned; /** * struct tipc_crypto_stats - TIPC Crypto statistics * @stat: array of crypto statistics */ struct tipc_crypto_stats { unsigned int stat[MAX_STATS]; }; /** * struct tipc_crypto - TIPC TX/RX crypto structure * @net: struct net * @node: TIPC node (RX) * @aead: array of pointers to AEAD keys for encryption/decryption * @peer_rx_active: replicated peer RX active key index * @key_gen: TX/RX key generation * @key: the key states * @skey_mode: session key's mode * @skey: received session key * @wq: common workqueue on TX crypto * @work: delayed work sched for TX/RX * @key_distr: key distributing state * @rekeying_intv: rekeying interval (in minutes) * @stats: the crypto statistics * @name: the crypto name * @sndnxt: the per-peer sndnxt (TX) * @timer1: general timer 1 (jiffies) * @timer2: general timer 2 (jiffies) * @working: the crypto is working or not * @key_master: flag indicates if master key exists * @legacy_user: flag indicates if a peer joins w/o master key (for bwd comp.) * @nokey: no key indication * @flags: combined flags field * @lock: tipc_key lock */ struct tipc_crypto { struct net *net; struct tipc_node *node; struct tipc_aead __rcu *aead[KEY_MAX + 1]; atomic_t peer_rx_active; u16 key_gen; struct tipc_key key; u8 skey_mode; struct tipc_aead_key *skey; struct workqueue_struct *wq; struct delayed_work work; #define KEY_DISTR_SCHED 1 #define KEY_DISTR_COMPL 2 atomic_t key_distr; u32 rekeying_intv; struct tipc_crypto_stats __percpu *stats; char name[48]; atomic64_t sndnxt ____cacheline_aligned; unsigned long timer1; unsigned long timer2; union { struct { u8 working:1; u8 key_master:1; u8 legacy_user:1; u8 nokey: 1; }; u8 flags; }; spinlock_t lock; /* crypto lock */ } ____cacheline_aligned; /* struct tipc_crypto_tx_ctx - TX context for callbacks */ struct tipc_crypto_tx_ctx { struct tipc_aead *aead; struct tipc_bearer *bearer; struct tipc_media_addr dst; }; /* struct tipc_crypto_rx_ctx - RX context for callbacks */ struct tipc_crypto_rx_ctx { struct tipc_aead *aead; struct tipc_bearer *bearer; }; static struct tipc_aead *tipc_aead_get(struct tipc_aead __rcu *aead); static inline void tipc_aead_put(struct tipc_aead *aead); static void tipc_aead_free(struct rcu_head *rp); static int tipc_aead_users(struct tipc_aead __rcu *aead); static void tipc_aead_users_inc(struct tipc_aead __rcu *aead, int lim); static void tipc_aead_users_dec(struct tipc_aead __rcu *aead, int lim); static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val); static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead); static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey, u8 mode); static int tipc_aead_clone(struct tipc_aead **dst, struct tipc_aead *src); static void *tipc_aead_mem_alloc(struct crypto_aead *tfm, unsigned int crypto_ctx_size, u8 **iv, struct aead_request **req, struct scatterlist **sg, int nsg); static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, struct tipc_bearer *b, struct tipc_media_addr *dst, struct tipc_node *__dnode); static void tipc_aead_encrypt_done(void *data, int err); static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, struct sk_buff *skb, struct tipc_bearer *b); static void tipc_aead_decrypt_done(void *data, int err); static inline int tipc_ehdr_size(struct tipc_ehdr *ehdr); static int tipc_ehdr_build(struct net *net, struct tipc_aead *aead, u8 tx_key, struct sk_buff *skb, struct tipc_crypto *__rx); static inline void tipc_crypto_key_set_state(struct tipc_crypto *c, u8 new_passive, u8 new_active, u8 new_pending); static int tipc_crypto_key_attach(struct tipc_crypto *c, struct tipc_aead *aead, u8 pos, bool master_key); static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending); static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx, struct tipc_crypto *rx, struct sk_buff *skb, u8 tx_key); static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb); static int tipc_crypto_key_revoke(struct net *net, u8 tx_key); static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb, struct tipc_bearer *b, struct tipc_media_addr *dst, struct tipc_node *__dnode, u8 type); static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, struct tipc_bearer *b, struct sk_buff **skb, int err); static void tipc_crypto_do_cmd(struct net *net, int cmd); static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf); static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new, char *buf); static int tipc_crypto_key_xmit(struct net *net, struct tipc_aead_key *skey, u16 gen, u8 mode, u32 dnode); static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr); static void tipc_crypto_work_tx(struct work_struct *work); static void tipc_crypto_work_rx(struct work_struct *work); static int tipc_aead_key_generate(struct tipc_aead_key *skey); #define is_tx(crypto) (!(crypto)->node) #define is_rx(crypto) (!is_tx(crypto)) #define key_next(cur) ((cur) % KEY_MAX + 1) #define tipc_aead_rcu_ptr(rcu_ptr, lock) \ rcu_dereference_protected((rcu_ptr), lockdep_is_held(lock)) #define tipc_aead_rcu_replace(rcu_ptr, ptr, lock) \ do { \ struct tipc_aead *__tmp = rcu_dereference_protected((rcu_ptr), \ lockdep_is_held(lock)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ tipc_aead_put(__tmp); \ } while (0) #define tipc_crypto_key_detach(rcu_ptr, lock) \ tipc_aead_rcu_replace((rcu_ptr), NULL, lock) /** * tipc_aead_key_validate - Validate a AEAD user key * @ukey: pointer to user key data * @info: netlink info pointer */ int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info) { int keylen; /* Check if algorithm exists */ if (unlikely(!crypto_has_alg(ukey->alg_name, 0, 0))) { GENL_SET_ERR_MSG(info, "unable to load the algorithm (module existed?)"); return -ENODEV; } /* Currently, we only support the "gcm(aes)" cipher algorithm */ if (strcmp(ukey->alg_name, "gcm(aes)")) { GENL_SET_ERR_MSG(info, "not supported yet the algorithm"); return -ENOTSUPP; } /* Check if key size is correct */ keylen = ukey->keylen - TIPC_AES_GCM_SALT_SIZE; if (unlikely(keylen != TIPC_AES_GCM_KEY_SIZE_128 && keylen != TIPC_AES_GCM_KEY_SIZE_192 && keylen != TIPC_AES_GCM_KEY_SIZE_256)) { GENL_SET_ERR_MSG(info, "incorrect key length (20, 28 or 36 octets?)"); return -EKEYREJECTED; } return 0; } /** * tipc_aead_key_generate - Generate new session key * @skey: input/output key with new content * * Return: 0 in case of success, otherwise < 0 */ static int tipc_aead_key_generate(struct tipc_aead_key *skey) { int rc = 0; /* Fill the key's content with a random value via RNG cipher */ rc = crypto_get_default_rng(); if (likely(!rc)) { rc = crypto_rng_get_bytes(crypto_default_rng, skey->key, skey->keylen); crypto_put_default_rng(); } return rc; } static struct tipc_aead *tipc_aead_get(struct tipc_aead __rcu *aead) { struct tipc_aead *tmp; rcu_read_lock(); tmp = rcu_dereference(aead); if (unlikely(!tmp || !refcount_inc_not_zero(&tmp->refcnt))) tmp = NULL; rcu_read_unlock(); return tmp; } static inline void tipc_aead_put(struct tipc_aead *aead) { if (aead && refcount_dec_and_test(&aead->refcnt)) call_rcu(&aead->rcu, tipc_aead_free); } /** * tipc_aead_free - Release AEAD key incl. all the TFMs in the list * @rp: rcu head pointer */ static void tipc_aead_free(struct rcu_head *rp) { struct tipc_aead *aead = container_of(rp, struct tipc_aead, rcu); struct tipc_tfm *tfm_entry, *head, *tmp; if (aead->cloned) { tipc_aead_put(aead->cloned); } else { head = *get_cpu_ptr(aead->tfm_entry); put_cpu_ptr(aead->tfm_entry); list_for_each_entry_safe(tfm_entry, tmp, &head->list, list) { crypto_free_aead(tfm_entry->tfm); list_del(&tfm_entry->list); kfree(tfm_entry); } /* Free the head */ crypto_free_aead(head->tfm); list_del(&head->list); kfree(head); } free_percpu(aead->tfm_entry); kfree_sensitive(aead->key); kfree(aead); } static int tipc_aead_users(struct tipc_aead __rcu *aead) { struct tipc_aead *tmp; int users = 0; rcu_read_lock(); tmp = rcu_dereference(aead); if (tmp) users = atomic_read(&tmp->users); rcu_read_unlock(); return users; } static void tipc_aead_users_inc(struct tipc_aead __rcu *aead, int lim) { struct tipc_aead *tmp; rcu_read_lock(); tmp = rcu_dereference(aead); if (tmp) atomic_add_unless(&tmp->users, 1, lim); rcu_read_unlock(); } static void tipc_aead_users_dec(struct tipc_aead __rcu *aead, int lim) { struct tipc_aead *tmp; rcu_read_lock(); tmp = rcu_dereference(aead); if (tmp) atomic_add_unless(&rcu_dereference(aead)->users, -1, lim); rcu_read_unlock(); } static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val) { struct tipc_aead *tmp; int cur; rcu_read_lock(); tmp = rcu_dereference(aead); if (tmp) { do { cur = atomic_read(&tmp->users); if (cur == val) break; } while (atomic_cmpxchg(&tmp->users, cur, val) != cur); } rcu_read_unlock(); } /** * tipc_aead_tfm_next - Move TFM entry to the next one in list and return it * @aead: the AEAD key pointer */ static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead) { struct tipc_tfm **tfm_entry; struct crypto_aead *tfm; tfm_entry = get_cpu_ptr(aead->tfm_entry); *tfm_entry = list_next_entry(*tfm_entry, list); tfm = (*tfm_entry)->tfm; put_cpu_ptr(tfm_entry); return tfm; } /** * tipc_aead_init - Initiate TIPC AEAD * @aead: returned new TIPC AEAD key handle pointer * @ukey: pointer to user key data * @mode: the key mode * * Allocate a (list of) new cipher transformation (TFM) with the specific user * key data if valid. The number of the allocated TFMs can be set via the sysfs * "net/tipc/max_tfms" first. * Also, all the other AEAD data are also initialized. * * Return: 0 if the initiation is successful, otherwise: < 0 */ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey, u8 mode) { struct tipc_tfm *tfm_entry, *head; struct crypto_aead *tfm; struct tipc_aead *tmp; int keylen, err, cpu; int tfm_cnt = 0; if (unlikely(*aead)) return -EEXIST; /* Allocate a new AEAD */ tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC); if (unlikely(!tmp)) return -ENOMEM; /* The key consists of two parts: [AES-KEY][SALT] */ keylen = ukey->keylen - TIPC_AES_GCM_SALT_SIZE; /* Allocate per-cpu TFM entry pointer */ tmp->tfm_entry = alloc_percpu(struct tipc_tfm *); if (!tmp->tfm_entry) { kfree_sensitive(tmp); return -ENOMEM; } /* Make a list of TFMs with the user key data */ do { tfm = crypto_alloc_aead(ukey->alg_name, 0, 0); if (IS_ERR(tfm)) { err = PTR_ERR(tfm); break; } if (unlikely(!tfm_cnt && crypto_aead_ivsize(tfm) != TIPC_AES_GCM_IV_SIZE)) { crypto_free_aead(tfm); err = -ENOTSUPP; break; } err = crypto_aead_setauthsize(tfm, TIPC_AES_GCM_TAG_SIZE); err |= crypto_aead_setkey(tfm, ukey->key, keylen); if (unlikely(err)) { crypto_free_aead(tfm); break; } tfm_entry = kmalloc(sizeof(*tfm_entry), GFP_KERNEL); if (unlikely(!tfm_entry)) { crypto_free_aead(tfm); err = -ENOMEM; break; } INIT_LIST_HEAD(&tfm_entry->list); tfm_entry->tfm = tfm; /* First entry? */ if (!tfm_cnt) { head = tfm_entry; for_each_possible_cpu(cpu) { *per_cpu_ptr(tmp->tfm_entry, cpu) = head; } } else { list_add_tail(&tfm_entry->list, &head->list); } } while (++tfm_cnt < sysctl_tipc_max_tfms); /* Not any TFM is allocated? */ if (!tfm_cnt) { free_percpu(tmp->tfm_entry); kfree_sensitive(tmp); return err; } /* Form a hex string of some last bytes as the key's hint */ bin2hex(tmp->hint, ukey->key + keylen - TIPC_AEAD_HINT_LEN, TIPC_AEAD_HINT_LEN); /* Initialize the other data */ tmp->mode = mode; tmp->cloned = NULL; tmp->authsize = TIPC_AES_GCM_TAG_SIZE; tmp->key = kmemdup(ukey, tipc_aead_key_size(ukey), GFP_KERNEL); if (!tmp->key) { tipc_aead_free(&tmp->rcu); return -ENOMEM; } memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE); atomic_set(&tmp->users, 0); atomic64_set(&tmp->seqno, 0); refcount_set(&tmp->refcnt, 1); *aead = tmp; return 0; } /** * tipc_aead_clone - Clone a TIPC AEAD key * @dst: dest key for the cloning * @src: source key to clone from * * Make a "copy" of the source AEAD key data to the dest, the TFMs list is * common for the keys. * A reference to the source is hold in the "cloned" pointer for the later * freeing purposes. * * Note: this must be done in cluster-key mode only! * Return: 0 in case of success, otherwise < 0 */ static int tipc_aead_clone(struct tipc_aead **dst, struct tipc_aead *src) { struct tipc_aead *aead; int cpu; if (!src) return -ENOKEY; if (src->mode != CLUSTER_KEY) return -EINVAL; if (unlikely(*dst)) return -EEXIST; aead = kzalloc(sizeof(*aead), GFP_ATOMIC); if (unlikely(!aead)) return -ENOMEM; aead->tfm_entry = alloc_percpu_gfp(struct tipc_tfm *, GFP_ATOMIC); if (unlikely(!aead->tfm_entry)) { kfree_sensitive(aead); return -ENOMEM; } for_each_possible_cpu(cpu) { *per_cpu_ptr(aead->tfm_entry, cpu) = *per_cpu_ptr(src->tfm_entry, cpu); } memcpy(aead->hint, src->hint, sizeof(src->hint)); aead->mode = src->mode; aead->salt = src->salt; aead->authsize = src->authsize; atomic_set(&aead->users, 0); atomic64_set(&aead->seqno, 0); refcount_set(&aead->refcnt, 1); WARN_ON(!refcount_inc_not_zero(&src->refcnt)); aead->cloned = src; *dst = aead; return 0; } /** * tipc_aead_mem_alloc - Allocate memory for AEAD request operations * @tfm: cipher handle to be registered with the request * @crypto_ctx_size: size of crypto context for callback * @iv: returned pointer to IV data * @req: returned pointer to AEAD request data * @sg: returned pointer to SG lists * @nsg: number of SG lists to be allocated * * Allocate memory to store the crypto context data, AEAD request, IV and SG * lists, the memory layout is as follows: * crypto_ctx || iv || aead_req || sg[] * * Return: the pointer to the memory areas in case of success, otherwise NULL */ static void *tipc_aead_mem_alloc(struct crypto_aead *tfm, unsigned int crypto_ctx_size, u8 **iv, struct aead_request **req, struct scatterlist **sg, int nsg) { unsigned int iv_size, req_size; unsigned int len; u8 *mem; iv_size = crypto_aead_ivsize(tfm); req_size = sizeof(**req) + crypto_aead_reqsize(tfm); len = crypto_ctx_size; len += iv_size; len += crypto_aead_alignmask(tfm) & ~(crypto_tfm_ctx_alignment() - 1); len = ALIGN(len, crypto_tfm_ctx_alignment()); len += req_size; len = ALIGN(len, __alignof__(struct scatterlist)); len += nsg * sizeof(**sg); mem = kmalloc(len, GFP_ATOMIC); if (!mem) return NULL; *iv = (u8 *)PTR_ALIGN(mem + crypto_ctx_size, crypto_aead_alignmask(tfm) + 1); *req = (struct aead_request *)PTR_ALIGN(*iv + iv_size, crypto_tfm_ctx_alignment()); *sg = (struct scatterlist *)PTR_ALIGN((u8 *)*req + req_size, __alignof__(struct scatterlist)); return (void *)mem; } /** * tipc_aead_encrypt - Encrypt a message * @aead: TIPC AEAD key for the message encryption * @skb: the input/output skb * @b: TIPC bearer where the message will be delivered after the encryption * @dst: the destination media address * @__dnode: TIPC dest node if "known" * * Return: * * 0 : if the encryption has completed * * -EINPROGRESS/-EBUSY : if a callback will be performed * * < 0 : the encryption has failed */ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, struct tipc_bearer *b, struct tipc_media_addr *dst, struct tipc_node *__dnode) { struct crypto_aead *tfm = tipc_aead_tfm_next(aead); struct tipc_crypto_tx_ctx *tx_ctx; struct aead_request *req; struct sk_buff *trailer; struct scatterlist *sg; struct tipc_ehdr *ehdr; int ehsz, len, tailen, nsg, rc; void *ctx; u32 salt; u8 *iv; /* Make sure message len at least 4-byte aligned */ len = ALIGN(skb->len, 4); tailen = len - skb->len + aead->authsize; /* Expand skb tail for authentication tag: * As for simplicity, we'd have made sure skb having enough tailroom * for authentication tag @skb allocation. Even when skb is nonlinear * but there is no frag_list, it should be still fine! * Otherwise, we must cow it to be a writable buffer with the tailroom. */ SKB_LINEAR_ASSERT(skb); if (tailen > skb_tailroom(skb)) { pr_debug("TX(): skb tailroom is not enough: %d, requires: %d\n", skb_tailroom(skb), tailen); } nsg = skb_cow_data(skb, tailen, &trailer); if (unlikely(nsg < 0)) { pr_err("TX: skb_cow_data() returned %d\n", nsg); return nsg; } pskb_put(skb, trailer, tailen); /* Allocate memory for the AEAD operation */ ctx = tipc_aead_mem_alloc(tfm, sizeof(*tx_ctx), &iv, &req, &sg, nsg); if (unlikely(!ctx)) return -ENOMEM; TIPC_SKB_CB(skb)->crypto_ctx = ctx; /* Map skb to the sg lists */ sg_init_table(sg, nsg); rc = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(rc < 0)) { pr_err("TX: skb_to_sgvec() returned %d, nsg %d!\n", rc, nsg); goto exit; } /* Prepare IV: [SALT (4 octets)][SEQNO (8 octets)] * In case we're in cluster-key mode, SALT is varied by xor-ing with * the source address (or w0 of id), otherwise with the dest address * if dest is known. */ ehdr = (struct tipc_ehdr *)skb->data; salt = aead->salt; if (aead->mode == CLUSTER_KEY) salt ^= __be32_to_cpu(ehdr->addr); else if (__dnode) salt ^= tipc_node_get_addr(__dnode); memcpy(iv, &salt, 4); memcpy(iv + 4, (u8 *)&ehdr->seqno, 8); /* Prepare request */ ehsz = tipc_ehdr_size(ehdr); aead_request_set_tfm(req, tfm); aead_request_set_ad(req, ehsz); aead_request_set_crypt(req, sg, sg, len - ehsz, iv); /* Set callback function & data */ aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, tipc_aead_encrypt_done, skb); tx_ctx = (struct tipc_crypto_tx_ctx *)ctx; tx_ctx->aead = aead; tx_ctx->bearer = b; memcpy(&tx_ctx->dst, dst, sizeof(*dst)); /* Hold bearer */ if (unlikely(!tipc_bearer_hold(b))) { rc = -ENODEV; goto exit; } /* Now, do encrypt */ rc = crypto_aead_encrypt(req); if (rc == -EINPROGRESS || rc == -EBUSY) return rc; tipc_bearer_put(b); exit: kfree(ctx); TIPC_SKB_CB(skb)->crypto_ctx = NULL; return rc; } static void tipc_aead_encrypt_done(void *data, int err) { struct sk_buff *skb = data; struct tipc_crypto_tx_ctx *tx_ctx = TIPC_SKB_CB(skb)->crypto_ctx; struct tipc_bearer *b = tx_ctx->bearer; struct tipc_aead *aead = tx_ctx->aead; struct tipc_crypto *tx = aead->crypto; struct net *net = tx->net; switch (err) { case 0: this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]); rcu_read_lock(); if (likely(test_bit(0, &b->up))) b->media->send_msg(net, skb, b, &tx_ctx->dst); else kfree_skb(skb); rcu_read_unlock(); break; case -EINPROGRESS: return; default: this_cpu_inc(tx->stats->stat[STAT_ASYNC_NOK]); kfree_skb(skb); break; } kfree(tx_ctx); tipc_bearer_put(b); tipc_aead_put(aead); } /** * tipc_aead_decrypt - Decrypt an encrypted message * @net: struct net * @aead: TIPC AEAD for the message decryption * @skb: the input/output skb * @b: TIPC bearer where the message has been received * * Return: * * 0 : if the decryption has completed * * -EINPROGRESS/-EBUSY : if a callback will be performed * * < 0 : the decryption has failed */ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, struct sk_buff *skb, struct tipc_bearer *b) { struct tipc_crypto_rx_ctx *rx_ctx; struct aead_request *req; struct crypto_aead *tfm; struct sk_buff *unused; struct scatterlist *sg; struct tipc_ehdr *ehdr; int ehsz, nsg, rc; void *ctx; u32 salt; u8 *iv; if (unlikely(!aead)) return -ENOKEY; nsg = skb_cow_data(skb, 0, &unused); if (unlikely(nsg < 0)) { pr_err("RX: skb_cow_data() returned %d\n", nsg); return nsg; } /* Allocate memory for the AEAD operation */ tfm = tipc_aead_tfm_next(aead); ctx = tipc_aead_mem_alloc(tfm, sizeof(*rx_ctx), &iv, &req, &sg, nsg); if (unlikely(!ctx)) return -ENOMEM; TIPC_SKB_CB(skb)->crypto_ctx = ctx; /* Map skb to the sg lists */ sg_init_table(sg, nsg); rc = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(rc < 0)) { pr_err("RX: skb_to_sgvec() returned %d, nsg %d\n", rc, nsg); goto exit; } /* Reconstruct IV: */ ehdr = (struct tipc_ehdr *)skb->data; salt = aead->salt; if (aead->mode == CLUSTER_KEY) salt ^= __be32_to_cpu(ehdr->addr); else if (ehdr->destined) salt ^= tipc_own_addr(net); memcpy(iv, &salt, 4); memcpy(iv + 4, (u8 *)&ehdr->seqno, 8); /* Prepare request */ ehsz = tipc_ehdr_size(ehdr); aead_request_set_tfm(req, tfm); aead_request_set_ad(req, ehsz); aead_request_set_crypt(req, sg, sg, skb->len - ehsz, iv); /* Set callback function & data */ aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, tipc_aead_decrypt_done, skb); rx_ctx = (struct tipc_crypto_rx_ctx *)ctx; rx_ctx->aead = aead; rx_ctx->bearer = b; /* Hold bearer */ if (unlikely(!tipc_bearer_hold(b))) { rc = -ENODEV; goto exit; } /* Now, do decrypt */ rc = crypto_aead_decrypt(req); if (rc == -EINPROGRESS || rc == -EBUSY) return rc; tipc_bearer_put(b); exit: kfree(ctx); TIPC_SKB_CB(skb)->crypto_ctx = NULL; return rc; } static void tipc_aead_decrypt_done(void *data, int err) { struct sk_buff *skb = data; struct tipc_crypto_rx_ctx *rx_ctx = TIPC_SKB_CB(skb)->crypto_ctx; struct tipc_bearer *b = rx_ctx->bearer; struct tipc_aead *aead = rx_ctx->aead; struct tipc_crypto_stats __percpu *stats = aead->crypto->stats; struct net *net = aead->crypto->net; switch (err) { case 0: this_cpu_inc(stats->stat[STAT_ASYNC_OK]); break; case -EINPROGRESS: return; default: this_cpu_inc(stats->stat[STAT_ASYNC_NOK]); break; } kfree(rx_ctx); tipc_crypto_rcv_complete(net, aead, b, &skb, err); if (likely(skb)) { if (likely(test_bit(0, &b->up))) tipc_rcv(net, skb, b); else kfree_skb(skb); } tipc_bearer_put(b); } static inline int tipc_ehdr_size(struct tipc_ehdr *ehdr) { return (ehdr->user != LINK_CONFIG) ? EHDR_SIZE : EHDR_CFG_SIZE; } /** * tipc_ehdr_validate - Validate an encryption message * @skb: the message buffer * * Return: "true" if this is a valid encryption message, otherwise "false" */ bool tipc_ehdr_validate(struct sk_buff *skb) { struct tipc_ehdr *ehdr; int ehsz; if (unlikely(!pskb_may_pull(skb, EHDR_MIN_SIZE))) return false; ehdr = (struct tipc_ehdr *)skb->data; if (unlikely(ehdr->version != TIPC_EVERSION)) return false; ehsz = tipc_ehdr_size(ehdr); if (unlikely(!pskb_may_pull(skb, ehsz))) return false; if (unlikely(skb->len <= ehsz + TIPC_AES_GCM_TAG_SIZE)) return false; return true; } /** * tipc_ehdr_build - Build TIPC encryption message header * @net: struct net * @aead: TX AEAD key to be used for the message encryption * @tx_key: key id used for the message encryption * @skb: input/output message skb * @__rx: RX crypto handle if dest is "known" * * Return: the header size if the building is successful, otherwise < 0 */ static int tipc_ehdr_build(struct net *net, struct tipc_aead *aead, u8 tx_key, struct sk_buff *skb, struct tipc_crypto *__rx) { struct tipc_msg *hdr = buf_msg(skb); struct tipc_ehdr *ehdr; u32 user = msg_user(hdr); u64 seqno; int ehsz; /* Make room for encryption header */ ehsz = (user != LINK_CONFIG) ? EHDR_SIZE : EHDR_CFG_SIZE; WARN_ON(skb_headroom(skb) < ehsz); ehdr = (struct tipc_ehdr *)skb_push(skb, ehsz); /* Obtain a seqno first: * Use the key seqno (= cluster wise) if dest is unknown or we're in * cluster key mode, otherwise it's better for a per-peer seqno! */ if (!__rx || aead->mode == CLUSTER_KEY) seqno = atomic64_inc_return(&aead->seqno); else seqno = atomic64_inc_return(&__rx->sndnxt); /* Revoke the key if seqno is wrapped around */ if (unlikely(!seqno)) return tipc_crypto_key_revoke(net, tx_key); /* Word 1-2 */ ehdr->seqno = cpu_to_be64(seqno); /* Words 0, 3- */ ehdr->version = TIPC_EVERSION; ehdr->user = 0; ehdr->keepalive = 0; ehdr->tx_key = tx_key; ehdr->destined = (__rx) ? 1 : 0; ehdr->rx_key_active = (__rx) ? __rx->key.active : 0; ehdr->rx_nokey = (__rx) ? __rx->nokey : 0; ehdr->master_key = aead->crypto->key_master; ehdr->reserved_1 = 0; ehdr->reserved_2 = 0; switch (user) { case LINK_CONFIG: ehdr->user = LINK_CONFIG; memcpy(ehdr->id, tipc_own_id(net), NODE_ID_LEN); break; default: if (user == LINK_PROTOCOL && msg_type(hdr) == STATE_MSG) { ehdr->user = LINK_PROTOCOL; ehdr->keepalive = msg_is_keepalive(hdr); } ehdr->addr = hdr->hdr[3]; break; } return ehsz; } static inline void tipc_crypto_key_set_state(struct tipc_crypto *c, u8 new_passive, u8 new_active, u8 new_pending) { struct tipc_key old = c->key; char buf[32]; c->key.keys = ((new_passive & KEY_MASK) << (KEY_BITS * 2)) | ((new_active & KEY_MASK) << (KEY_BITS)) | ((new_pending & KEY_MASK)); pr_debug("%s: key changing %s ::%pS\n", c->name, tipc_key_change_dump(old, c->key, buf), __builtin_return_address(0)); } /** * tipc_crypto_key_init - Initiate a new user / AEAD key * @c: TIPC crypto to which new key is attached * @ukey: the user key * @mode: the key mode (CLUSTER_KEY or PER_NODE_KEY) * @master_key: specify this is a cluster master key * * A new TIPC AEAD key will be allocated and initiated with the specified user * key, then attached to the TIPC crypto. * * Return: new key id in case of success, otherwise: < 0 */ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey, u8 mode, bool master_key) { struct tipc_aead *aead = NULL; int rc = 0; /* Initiate with the new user key */ rc = tipc_aead_init(&aead, ukey, mode); /* Attach it to the crypto */ if (likely(!rc)) { rc = tipc_crypto_key_attach(c, aead, 0, master_key); if (rc < 0) tipc_aead_free(&aead->rcu); } return rc; } /** * tipc_crypto_key_attach - Attach a new AEAD key to TIPC crypto * @c: TIPC crypto to which the new AEAD key is attached * @aead: the new AEAD key pointer * @pos: desired slot in the crypto key array, = 0 if any! * @master_key: specify this is a cluster master key * * Return: new key id in case of success, otherwise: -EBUSY */ static int tipc_crypto_key_attach(struct tipc_crypto *c, struct tipc_aead *aead, u8 pos, bool master_key) { struct tipc_key key; int rc = -EBUSY; u8 new_key; spin_lock_bh(&c->lock); key = c->key; if (master_key) { new_key = KEY_MASTER; goto attach; } if (key.active && key.passive) goto exit; if (key.pending) { if (tipc_aead_users(c->aead[key.pending]) > 0) goto exit; /* if (pos): ok with replacing, will be aligned when needed */ /* Replace it */ new_key = key.pending; } else { if (pos) { if (key.active && pos != key_next(key.active)) { key.passive = pos; new_key = pos; goto attach; } else if (!key.active && !key.passive) { key.pending = pos; new_key = pos; goto attach; } } key.pending = key_next(key.active ?: key.passive); new_key = key.pending; } attach: aead->crypto = c; aead->gen = (is_tx(c)) ? ++c->key_gen : c->key_gen; tipc_aead_rcu_replace(c->aead[new_key], aead, &c->lock); if (likely(c->key.keys != key.keys)) tipc_crypto_key_set_state(c, key.passive, key.active, key.pending); c->working = 1; c->nokey = 0; c->key_master |= master_key; rc = new_key; exit: spin_unlock_bh(&c->lock); return rc; } void tipc_crypto_key_flush(struct tipc_crypto *c) { struct tipc_crypto *tx, *rx; int k; spin_lock_bh(&c->lock); if (is_rx(c)) { /* Try to cancel pending work */ rx = c; tx = tipc_net(rx->net)->crypto_tx; if (cancel_delayed_work(&rx->work)) { kfree(rx->skey); rx->skey = NULL; atomic_xchg(&rx->key_distr, 0); tipc_node_put(rx->node); } /* RX stopping => decrease TX key users if any */ k = atomic_xchg(&rx->peer_rx_active, 0); if (k) { tipc_aead_users_dec(tx->aead[k], 0); /* Mark the point TX key users changed */ tx->timer1 = jiffies; } } c->flags = 0; tipc_crypto_key_set_state(c, 0, 0, 0); for (k = KEY_MIN; k <= KEY_MAX; k++) tipc_crypto_key_detach(c->aead[k], &c->lock); atomic64_set(&c->sndnxt, 0); spin_unlock_bh(&c->lock); } /** * tipc_crypto_key_try_align - Align RX keys if possible * @rx: RX crypto handle * @new_pending: new pending slot if aligned (= TX key from peer) * * Peer has used an unknown key slot, this only happens when peer has left and * rejoned, or we are newcomer. * That means, there must be no active key but a pending key at unaligned slot. * If so, we try to move the pending key to the new slot. * Note: A potential passive key can exist, it will be shifted correspondingly! * * Return: "true" if key is successfully aligned, otherwise "false" */ static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending) { struct tipc_aead *tmp1, *tmp2 = NULL; struct tipc_key key; bool aligned = false; u8 new_passive = 0; int x; spin_lock(&rx->lock); key = rx->key; if (key.pending == new_pending) { aligned = true; goto exit; } if (key.active) goto exit; if (!key.pending) goto exit; if (tipc_aead_users(rx->aead[key.pending]) > 0) goto exit; /* Try to "isolate" this pending key first */ tmp1 = tipc_aead_rcu_ptr(rx->aead[key.pending], &rx->lock); if (!refcount_dec_if_one(&tmp1->refcnt)) goto exit; rcu_assign_pointer(rx->aead[key.pending], NULL); /* Move passive key if any */ if (key.passive) { tmp2 = rcu_replace_pointer(rx->aead[key.passive], tmp2, lockdep_is_held(&rx->lock)); x = (key.passive - key.pending + new_pending) % KEY_MAX; new_passive = (x <= 0) ? x + KEY_MAX : x; } /* Re-allocate the key(s) */ tipc_crypto_key_set_state(rx, new_passive, 0, new_pending); rcu_assign_pointer(rx->aead[new_pending], tmp1); if (new_passive) rcu_assign_pointer(rx->aead[new_passive], tmp2); refcount_set(&tmp1->refcnt, 1); aligned = true; pr_info_ratelimited("%s: key[%d] -> key[%d]\n", rx->name, key.pending, new_pending); exit: spin_unlock(&rx->lock); return aligned; } /** * tipc_crypto_key_pick_tx - Pick one TX key for message decryption * @tx: TX crypto handle * @rx: RX crypto handle (can be NULL) * @skb: the message skb which will be decrypted later * @tx_key: peer TX key id * * This function looks up the existing TX keys and pick one which is suitable * for the message decryption, that must be a cluster key and not used before * on the same message (i.e. recursive). * * Return: the TX AEAD key handle in case of success, otherwise NULL */ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx, struct tipc_crypto *rx, struct sk_buff *skb, u8 tx_key) { struct tipc_skb_cb *skb_cb = TIPC_SKB_CB(skb); struct tipc_aead *aead = NULL; struct tipc_key key = tx->key; u8 k, i = 0; /* Initialize data if not yet */ if (!skb_cb->tx_clone_deferred) { skb_cb->tx_clone_deferred = 1; memset(&skb_cb->tx_clone_ctx, 0, sizeof(skb_cb->tx_clone_ctx)); } skb_cb->tx_clone_ctx.rx = rx; if (++skb_cb->tx_clone_ctx.recurs > 2) return NULL; /* Pick one TX key */ spin_lock(&tx->lock); if (tx_key == KEY_MASTER) { aead = tipc_aead_rcu_ptr(tx->aead[KEY_MASTER], &tx->lock); goto done; } do { k = (i == 0) ? key.pending : ((i == 1) ? key.active : key.passive); if (!k) continue; aead = tipc_aead_rcu_ptr(tx->aead[k], &tx->lock); if (!aead) continue; if (aead->mode != CLUSTER_KEY || aead == skb_cb->tx_clone_ctx.last) { aead = NULL; continue; } /* Ok, found one cluster key */ skb_cb->tx_clone_ctx.last = aead; WARN_ON(skb->next); skb->next = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb->next)) pr_warn("Failed to clone skb for next round if any\n"); break; } while (++i < 3); done: if (likely(aead)) WARN_ON(!refcount_inc_not_zero(&aead->refcnt)); spin_unlock(&tx->lock); return aead; } /** * tipc_crypto_key_synch: Synch own key data according to peer key status * @rx: RX crypto handle * @skb: TIPCv2 message buffer (incl. the ehdr from peer) * * This function updates the peer node related data as the peer RX active key * has changed, so the number of TX keys' users on this node are increased and * decreased correspondingly. * * It also considers if peer has no key, then we need to make own master key * (if any) taking over i.e. starting grace period and also trigger key * distributing process. * * The "per-peer" sndnxt is also reset when the peer key has switched. */ static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb) { struct tipc_ehdr *ehdr = (struct tipc_ehdr *)skb_network_header(skb); struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx; struct tipc_msg *hdr = buf_msg(skb); u32 self = tipc_own_addr(rx->net); u8 cur, new; unsigned long delay; /* Update RX 'key_master' flag according to peer, also mark "legacy" if * a peer has no master key. */ rx->key_master = ehdr->master_key; if (!rx->key_master) tx->legacy_user = 1; /* For later cases, apply only if message is destined to this node */ if (!ehdr->destined || msg_short(hdr) || msg_destnode(hdr) != self) return; /* Case 1: Peer has no keys, let's make master key take over */ if (ehdr->rx_nokey) { /* Set or extend grace period */ tx->timer2 = jiffies; /* Schedule key distributing for the peer if not yet */ if (tx->key.keys && !atomic_cmpxchg(&rx->key_distr, 0, KEY_DISTR_SCHED)) { get_random_bytes(&delay, 2); delay %= 5; delay = msecs_to_jiffies(500 * ++delay); if (queue_delayed_work(tx->wq, &rx->work, delay)) tipc_node_get(rx->node); } } else { /* Cancel a pending key distributing if any */ atomic_xchg(&rx->key_distr, 0); } /* Case 2: Peer RX active key has changed, let's update own TX users */ cur = atomic_read(&rx->peer_rx_active); new = ehdr->rx_key_active; if (tx->key.keys && cur != new && atomic_cmpxchg(&rx->peer_rx_active, cur, new) == cur) { if (new) tipc_aead_users_inc(tx->aead[new], INT_MAX); if (cur) tipc_aead_users_dec(tx->aead[cur], 0); atomic64_set(&rx->sndnxt, 0); /* Mark the point TX key users changed */ tx->timer1 = jiffies; pr_debug("%s: key users changed %d-- %d++, peer %s\n", tx->name, cur, new, rx->name); } } static int tipc_crypto_key_revoke(struct net *net, u8 tx_key) { struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_key key; spin_lock_bh(&tx->lock); key = tx->key; WARN_ON(!key.active || tx_key != key.active); /* Free the active key */ tipc_crypto_key_set_state(tx, key.passive, 0, key.pending); tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); spin_unlock_bh(&tx->lock); pr_warn("%s: key is revoked\n", tx->name); return -EKEYREVOKED; } int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net, struct tipc_node *node) { struct tipc_crypto *c; if (*crypto) return -EEXIST; /* Allocate crypto */ c = kzalloc(sizeof(*c), GFP_ATOMIC); if (!c) return -ENOMEM; /* Allocate workqueue on TX */ if (!node) { c->wq = alloc_ordered_workqueue("tipc_crypto", 0); if (!c->wq) { kfree(c); return -ENOMEM; } } /* Allocate statistic structure */ c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC); if (!c->stats) { if (c->wq) destroy_workqueue(c->wq); kfree_sensitive(c); return -ENOMEM; } c->flags = 0; c->net = net; c->node = node; get_random_bytes(&c->key_gen, 2); tipc_crypto_key_set_state(c, 0, 0, 0); atomic_set(&c->key_distr, 0); atomic_set(&c->peer_rx_active, 0); atomic64_set(&c->sndnxt, 0); c->timer1 = jiffies; c->timer2 = jiffies; c->rekeying_intv = TIPC_REKEYING_INTV_DEF; spin_lock_init(&c->lock); scnprintf(c->name, 48, "%s(%s)", (is_rx(c)) ? "RX" : "TX", (is_rx(c)) ? tipc_node_get_id_str(c->node) : tipc_own_id_string(c->net)); if (is_rx(c)) INIT_DELAYED_WORK(&c->work, tipc_crypto_work_rx); else INIT_DELAYED_WORK(&c->work, tipc_crypto_work_tx); *crypto = c; return 0; } void tipc_crypto_stop(struct tipc_crypto **crypto) { struct tipc_crypto *c = *crypto; u8 k; if (!c) return; /* Flush any queued works & destroy wq */ if (is_tx(c)) { c->rekeying_intv = 0; cancel_delayed_work_sync(&c->work); destroy_workqueue(c->wq); } /* Release AEAD keys */ rcu_read_lock(); for (k = KEY_MIN; k <= KEY_MAX; k++) tipc_aead_put(rcu_dereference(c->aead[k])); rcu_read_unlock(); pr_debug("%s: has been stopped\n", c->name); /* Free this crypto statistics */ free_percpu(c->stats); *crypto = NULL; kfree_sensitive(c); } void tipc_crypto_timeout(struct tipc_crypto *rx) { struct tipc_net *tn = tipc_net(rx->net); struct tipc_crypto *tx = tn->crypto_tx; struct tipc_key key; int cmd; /* TX pending: taking all users & stable -> active */ spin_lock(&tx->lock); key = tx->key; if (key.active && tipc_aead_users(tx->aead[key.active]) > 0) goto s1; if (!key.pending || tipc_aead_users(tx->aead[key.pending]) <= 0) goto s1; if (time_before(jiffies, tx->timer1 + TIPC_TX_LASTING_TIME)) goto s1; tipc_crypto_key_set_state(tx, key.passive, key.pending, 0); if (key.active) tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); this_cpu_inc(tx->stats->stat[STAT_SWITCHES]); pr_info("%s: key[%d] is activated\n", tx->name, key.pending); s1: spin_unlock(&tx->lock); /* RX pending: having user -> active */ spin_lock(&rx->lock); key = rx->key; if (!key.pending || tipc_aead_users(rx->aead[key.pending]) <= 0) goto s2; if (key.active) key.passive = key.active; key.active = key.pending; rx->timer2 = jiffies; tipc_crypto_key_set_state(rx, key.passive, key.active, 0); this_cpu_inc(rx->stats->stat[STAT_SWITCHES]); pr_info("%s: key[%d] is activated\n", rx->name, key.pending); goto s5; s2: /* RX pending: not working -> remove */ if (!key.pending || tipc_aead_users(rx->aead[key.pending]) > -10) goto s3; tipc_crypto_key_set_state(rx, key.passive, key.active, 0); tipc_crypto_key_detach(rx->aead[key.pending], &rx->lock); pr_debug("%s: key[%d] is removed\n", rx->name, key.pending); goto s5; s3: /* RX active: timed out or no user -> pending */ if (!key.active) goto s4; if (time_before(jiffies, rx->timer1 + TIPC_RX_ACTIVE_LIM) && tipc_aead_users(rx->aead[key.active]) > 0) goto s4; if (key.pending) key.passive = key.active; else key.pending = key.active; rx->timer2 = jiffies; tipc_crypto_key_set_state(rx, key.passive, 0, key.pending); tipc_aead_users_set(rx->aead[key.pending], 0); pr_debug("%s: key[%d] is deactivated\n", rx->name, key.active); goto s5; s4: /* RX passive: outdated or not working -> free */ if (!key.passive) goto s5; if (time_before(jiffies, rx->timer2 + TIPC_RX_PASSIVE_LIM) && tipc_aead_users(rx->aead[key.passive]) > -10) goto s5; tipc_crypto_key_set_state(rx, 0, key.active, key.pending); tipc_crypto_key_detach(rx->aead[key.passive], &rx->lock); pr_debug("%s: key[%d] is freed\n", rx->name, key.passive); s5: spin_unlock(&rx->lock); /* Relax it here, the flag will be set again if it really is, but only * when we are not in grace period for safety! */ if (time_after(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD)) tx->legacy_user = 0; /* Limit max_tfms & do debug commands if needed */ if (likely(sysctl_tipc_max_tfms <= TIPC_MAX_TFMS_LIM)) return; cmd = sysctl_tipc_max_tfms; sysctl_tipc_max_tfms = TIPC_MAX_TFMS_DEF; tipc_crypto_do_cmd(rx->net, cmd); } static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb, struct tipc_bearer *b, struct tipc_media_addr *dst, struct tipc_node *__dnode, u8 type) { struct sk_buff *skb; skb = skb_clone(_skb, GFP_ATOMIC); if (skb) { TIPC_SKB_CB(skb)->xmit_type = type; tipc_crypto_xmit(net, &skb, b, dst, __dnode); if (skb) b->media->send_msg(net, skb, b, dst); } } /** * tipc_crypto_xmit - Build & encrypt TIPC message for xmit * @net: struct net * @skb: input/output message skb pointer * @b: bearer used for xmit later * @dst: destination media address * @__dnode: destination node for reference if any * * First, build an encryption message header on the top of the message, then * encrypt the original TIPC message by using the pending, master or active * key with this preference order. * If the encryption is successful, the encrypted skb is returned directly or * via the callback. * Otherwise, the skb is freed! * * Return: * * 0 : the encryption has succeeded (or no encryption) * * -EINPROGRESS/-EBUSY : the encryption is ongoing, a callback will be made * * -ENOKEK : the encryption has failed due to no key * * -EKEYREVOKED : the encryption has failed due to key revoked * * -ENOMEM : the encryption has failed due to no memory * * < 0 : the encryption has failed due to other reasons */ int tipc_crypto_xmit(struct net *net, struct sk_buff **skb, struct tipc_bearer *b, struct tipc_media_addr *dst, struct tipc_node *__dnode) { struct tipc_crypto *__rx = tipc_node_crypto_rx(__dnode); struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_crypto_stats __percpu *stats = tx->stats; struct tipc_msg *hdr = buf_msg(*skb); struct tipc_key key = tx->key; struct tipc_aead *aead = NULL; u32 user = msg_user(hdr); u32 type = msg_type(hdr); int rc = -ENOKEY; u8 tx_key = 0; /* No encryption? */ if (!tx->working) return 0; /* Pending key if peer has active on it or probing time */ if (unlikely(key.pending)) { tx_key = key.pending; if (!tx->key_master && !key.active) goto encrypt; if (__rx && atomic_read(&__rx->peer_rx_active) == tx_key) goto encrypt; if (TIPC_SKB_CB(*skb)->xmit_type == SKB_PROBING) { pr_debug("%s: probing for key[%d]\n", tx->name, key.pending); goto encrypt; } if (user == LINK_CONFIG || user == LINK_PROTOCOL) tipc_crypto_clone_msg(net, *skb, b, dst, __dnode, SKB_PROBING); } /* Master key if this is a *vital* message or in grace period */ if (tx->key_master) { tx_key = KEY_MASTER; if (!key.active) goto encrypt; if (TIPC_SKB_CB(*skb)->xmit_type == SKB_GRACING) { pr_debug("%s: gracing for msg (%d %d)\n", tx->name, user, type); goto encrypt; } if (user == LINK_CONFIG || (user == LINK_PROTOCOL && type == RESET_MSG) || (user == MSG_CRYPTO && type == KEY_DISTR_MSG) || time_before(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD)) { if (__rx && __rx->key_master && !atomic_read(&__rx->peer_rx_active)) goto encrypt; if (!__rx) { if (likely(!tx->legacy_user)) goto encrypt; tipc_crypto_clone_msg(net, *skb, b, dst, __dnode, SKB_GRACING); } } } /* Else, use the active key if any */ if (likely(key.active)) { tx_key = key.active; goto encrypt; } goto exit; encrypt: aead = tipc_aead_get(tx->aead[tx_key]); if (unlikely(!aead)) goto exit; rc = tipc_ehdr_build(net, aead, tx_key, *skb, __rx); if (likely(rc > 0)) rc = tipc_aead_encrypt(aead, *skb, b, dst, __dnode); exit: switch (rc) { case 0: this_cpu_inc(stats->stat[STAT_OK]); break; case -EINPROGRESS: case -EBUSY: this_cpu_inc(stats->stat[STAT_ASYNC]); *skb = NULL; return rc; default: this_cpu_inc(stats->stat[STAT_NOK]); if (rc == -ENOKEY) this_cpu_inc(stats->stat[STAT_NOKEYS]); else if (rc == -EKEYREVOKED) this_cpu_inc(stats->stat[STAT_BADKEYS]); kfree_skb(*skb); *skb = NULL; break; } tipc_aead_put(aead); return rc; } /** * tipc_crypto_rcv - Decrypt an encrypted TIPC message from peer * @net: struct net * @rx: RX crypto handle * @skb: input/output message skb pointer * @b: bearer where the message has been received * * If the decryption is successful, the decrypted skb is returned directly or * as the callback, the encryption header and auth tag will be trimed out * before forwarding to tipc_rcv() via the tipc_crypto_rcv_complete(). * Otherwise, the skb will be freed! * Note: RX key(s) can be re-aligned, or in case of no key suitable, TX * cluster key(s) can be taken for decryption (- recursive). * * Return: * * 0 : the decryption has successfully completed * * -EINPROGRESS/-EBUSY : the decryption is ongoing, a callback will be made * * -ENOKEY : the decryption has failed due to no key * * -EBADMSG : the decryption has failed due to bad message * * -ENOMEM : the decryption has failed due to no memory * * < 0 : the decryption has failed due to other reasons */ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx, struct sk_buff **skb, struct tipc_bearer *b) { struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_crypto_stats __percpu *stats; struct tipc_aead *aead = NULL; struct tipc_key key; int rc = -ENOKEY; u8 tx_key, n; tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key; /* New peer? * Let's try with TX key (i.e. cluster mode) & verify the skb first! */ if (unlikely(!rx || tx_key == KEY_MASTER)) goto pick_tx; /* Pick RX key according to TX key if any */ key = rx->key; if (tx_key == key.active || tx_key == key.pending || tx_key == key.passive) goto decrypt; /* Unknown key, let's try to align RX key(s) */ if (tipc_crypto_key_try_align(rx, tx_key)) goto decrypt; pick_tx: /* No key suitable? Try to pick one from TX... */ aead = tipc_crypto_key_pick_tx(tx, rx, *skb, tx_key); if (aead) goto decrypt; goto exit; decrypt: rcu_read_lock(); if (!aead) aead = tipc_aead_get(rx->aead[tx_key]); rc = tipc_aead_decrypt(net, aead, *skb, b); rcu_read_unlock(); exit: stats = ((rx) ?: tx)->stats; switch (rc) { case 0: this_cpu_inc(stats->stat[STAT_OK]); break; case -EINPROGRESS: case -EBUSY: this_cpu_inc(stats->stat[STAT_ASYNC]); *skb = NULL; return rc; default: this_cpu_inc(stats->stat[STAT_NOK]); if (rc == -ENOKEY) { kfree_skb(*skb); *skb = NULL; if (rx) { /* Mark rx->nokey only if we dont have a * pending received session key, nor a newer * one i.e. in the next slot. */ n = key_next(tx_key); rx->nokey = !(rx->skey || rcu_access_pointer(rx->aead[n])); pr_debug_ratelimited("%s: nokey %d, key %d/%x\n", rx->name, rx->nokey, tx_key, rx->key.keys); tipc_node_put(rx->node); } this_cpu_inc(stats->stat[STAT_NOKEYS]); return rc; } else if (rc == -EBADMSG) { this_cpu_inc(stats->stat[STAT_BADMSGS]); } break; } tipc_crypto_rcv_complete(net, aead, b, skb, rc); return rc; } static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, struct tipc_bearer *b, struct sk_buff **skb, int err) { struct tipc_skb_cb *skb_cb = TIPC_SKB_CB(*skb); struct tipc_crypto *rx = aead->crypto; struct tipc_aead *tmp = NULL; struct tipc_ehdr *ehdr; struct tipc_node *n; /* Is this completed by TX? */ if (unlikely(is_tx(aead->crypto))) { rx = skb_cb->tx_clone_ctx.rx; pr_debug("TX->RX(%s): err %d, aead %p, skb->next %p, flags %x\n", (rx) ? tipc_node_get_id_str(rx->node) : "-", err, aead, (*skb)->next, skb_cb->flags); pr_debug("skb_cb [recurs %d, last %p], tx->aead [%p %p %p]\n", skb_cb->tx_clone_ctx.recurs, skb_cb->tx_clone_ctx.last, aead->crypto->aead[1], aead->crypto->aead[2], aead->crypto->aead[3]); if (unlikely(err)) { if (err == -EBADMSG && (*skb)->next) tipc_rcv(net, (*skb)->next, b); goto free_skb; } if (likely((*skb)->next)) { kfree_skb((*skb)->next); (*skb)->next = NULL; } ehdr = (struct tipc_ehdr *)(*skb)->data; if (!rx) { WARN_ON(ehdr->user != LINK_CONFIG); n = tipc_node_create(net, 0, ehdr->id, 0xffffu, 0, true); rx = tipc_node_crypto_rx(n); if (unlikely(!rx)) goto free_skb; } /* Ignore cloning if it was TX master key */ if (ehdr->tx_key == KEY_MASTER) goto rcv; if (tipc_aead_clone(&tmp, aead) < 0) goto rcv; WARN_ON(!refcount_inc_not_zero(&tmp->refcnt)); if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key, false) < 0) { tipc_aead_free(&tmp->rcu); goto rcv; } tipc_aead_put(aead); aead = tmp; } if (unlikely(err)) { tipc_aead_users_dec((struct tipc_aead __force __rcu *)aead, INT_MIN); goto free_skb; } /* Set the RX key's user */ tipc_aead_users_set((struct tipc_aead __force __rcu *)aead, 1); /* Mark this point, RX works */ rx->timer1 = jiffies; rcv: /* Remove ehdr & auth. tag prior to tipc_rcv() */ ehdr = (struct tipc_ehdr *)(*skb)->data; /* Mark this point, RX passive still works */ if (rx->key.passive && ehdr->tx_key == rx->key.passive) rx->timer2 = jiffies; skb_reset_network_header(*skb); skb_pull(*skb, tipc_ehdr_size(ehdr)); if (pskb_trim(*skb, (*skb)->len - aead->authsize)) goto free_skb; /* Validate TIPCv2 message */ if (unlikely(!tipc_msg_validate(skb))) { pr_err_ratelimited("Packet dropped after decryption!\n"); goto free_skb; } /* Ok, everything's fine, try to synch own keys according to peers' */ tipc_crypto_key_synch(rx, *skb); /* Re-fetch skb cb as skb might be changed in tipc_msg_validate */ skb_cb = TIPC_SKB_CB(*skb); /* Mark skb decrypted */ skb_cb->decrypted = 1; /* Clear clone cxt if any */ if (likely(!skb_cb->tx_clone_deferred)) goto exit; skb_cb->tx_clone_deferred = 0; memset(&skb_cb->tx_clone_ctx, 0, sizeof(skb_cb->tx_clone_ctx)); goto exit; free_skb: kfree_skb(*skb); *skb = NULL; exit: tipc_aead_put(aead); if (rx) tipc_node_put(rx->node); } static void tipc_crypto_do_cmd(struct net *net, int cmd) { struct tipc_net *tn = tipc_net(net); struct tipc_crypto *tx = tn->crypto_tx, *rx; struct list_head *p; unsigned int stat; int i, j, cpu; char buf[200]; /* Currently only one command is supported */ switch (cmd) { case 0xfff1: goto print_stats; default: return; } print_stats: /* Print a header */ pr_info("\n=============== TIPC Crypto Statistics ===============\n\n"); /* Print key status */ pr_info("Key status:\n"); pr_info("TX(%7.7s)\n%s", tipc_own_id_string(net), tipc_crypto_key_dump(tx, buf)); rcu_read_lock(); for (p = tn->node_list.next; p != &tn->node_list; p = p->next) { rx = tipc_node_crypto_rx_by_list(p); pr_info("RX(%7.7s)\n%s", tipc_node_get_id_str(rx->node), tipc_crypto_key_dump(rx, buf)); } rcu_read_unlock(); /* Print crypto statistics */ for (i = 0, j = 0; i < MAX_STATS; i++) j += scnprintf(buf + j, 200 - j, "|%11s ", hstats[i]); pr_info("Counter %s", buf); memset(buf, '-', 115); buf[115] = '\0'; pr_info("%s\n", buf); j = scnprintf(buf, 200, "TX(%7.7s) ", tipc_own_id_string(net)); for_each_possible_cpu(cpu) { for (i = 0; i < MAX_STATS; i++) { stat = per_cpu_ptr(tx->stats, cpu)->stat[i]; j += scnprintf(buf + j, 200 - j, "|%11d ", stat); } pr_info("%s", buf); j = scnprintf(buf, 200, "%12s", " "); } rcu_read_lock(); for (p = tn->node_list.next; p != &tn->node_list; p = p->next) { rx = tipc_node_crypto_rx_by_list(p); j = scnprintf(buf, 200, "RX(%7.7s) ", tipc_node_get_id_str(rx->node)); for_each_possible_cpu(cpu) { for (i = 0; i < MAX_STATS; i++) { stat = per_cpu_ptr(rx->stats, cpu)->stat[i]; j += scnprintf(buf + j, 200 - j, "|%11d ", stat); } pr_info("%s", buf); j = scnprintf(buf, 200, "%12s", " "); } } rcu_read_unlock(); pr_info("\n======================== Done ========================\n"); } static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf) { struct tipc_key key = c->key; struct tipc_aead *aead; int k, i = 0; char *s; for (k = KEY_MIN; k <= KEY_MAX; k++) { if (k == KEY_MASTER) { if (is_rx(c)) continue; if (time_before(jiffies, c->timer2 + TIPC_TX_GRACE_PERIOD)) s = "ACT"; else s = "PAS"; } else { if (k == key.passive) s = "PAS"; else if (k == key.active) s = "ACT"; else if (k == key.pending) s = "PEN"; else s = "-"; } i += scnprintf(buf + i, 200 - i, "\tKey%d: %s", k, s); rcu_read_lock(); aead = rcu_dereference(c->aead[k]); if (aead) i += scnprintf(buf + i, 200 - i, "{\"0x...%s\", \"%s\"}/%d:%d", aead->hint, (aead->mode == CLUSTER_KEY) ? "c" : "p", atomic_read(&aead->users), refcount_read(&aead->refcnt)); rcu_read_unlock(); i += scnprintf(buf + i, 200 - i, "\n"); } if (is_rx(c)) i += scnprintf(buf + i, 200 - i, "\tPeer RX active: %d\n", atomic_read(&c->peer_rx_active)); return buf; } static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new, char *buf) { struct tipc_key *key = &old; int k, i = 0; char *s; /* Output format: "[%s %s %s] -> [%s %s %s]", max len = 32 */ again: i += scnprintf(buf + i, 32 - i, "["); for (k = KEY_1; k <= KEY_3; k++) { if (k == key->passive) s = "pas"; else if (k == key->active) s = "act"; else if (k == key->pending) s = "pen"; else s = "-"; i += scnprintf(buf + i, 32 - i, (k != KEY_3) ? "%s " : "%s", s); } if (key != &new) { i += scnprintf(buf + i, 32 - i, "] -> "); key = &new; goto again; } i += scnprintf(buf + i, 32 - i, "]"); return buf; } /** * tipc_crypto_msg_rcv - Common 'MSG_CRYPTO' processing point * @net: the struct net * @skb: the receiving message buffer */ void tipc_crypto_msg_rcv(struct net *net, struct sk_buff *skb) { struct tipc_crypto *rx; struct tipc_msg *hdr; if (unlikely(skb_linearize(skb))) goto exit; hdr = buf_msg(skb); rx = tipc_node_crypto_rx_by_addr(net, msg_prevnode(hdr)); if (unlikely(!rx)) goto exit; switch (msg_type(hdr)) { case KEY_DISTR_MSG: if (tipc_crypto_key_rcv(rx, hdr)) goto exit; break; default: break; } tipc_node_put(rx->node); exit: kfree_skb(skb); } /** * tipc_crypto_key_distr - Distribute a TX key * @tx: the TX crypto * @key: the key's index * @dest: the destination tipc node, = NULL if distributing to all nodes * * Return: 0 in case of success, otherwise < 0 */ int tipc_crypto_key_distr(struct tipc_crypto *tx, u8 key, struct tipc_node *dest) { struct tipc_aead *aead; u32 dnode = tipc_node_get_addr(dest); int rc = -ENOKEY; if (!sysctl_tipc_key_exchange_enabled) return 0; if (key) { rcu_read_lock(); aead = tipc_aead_get(tx->aead[key]); if (likely(aead)) { rc = tipc_crypto_key_xmit(tx->net, aead->key, aead->gen, aead->mode, dnode); tipc_aead_put(aead); } rcu_read_unlock(); } return rc; } /** * tipc_crypto_key_xmit - Send a session key * @net: the struct net * @skey: the session key to be sent * @gen: the key's generation * @mode: the key's mode * @dnode: the destination node address, = 0 if broadcasting to all nodes * * The session key 'skey' is packed in a TIPC v2 'MSG_CRYPTO/KEY_DISTR_MSG' * as its data section, then xmit-ed through the uc/bc link. * * Return: 0 in case of success, otherwise < 0 */ static int tipc_crypto_key_xmit(struct net *net, struct tipc_aead_key *skey, u16 gen, u8 mode, u32 dnode) { struct sk_buff_head pkts; struct tipc_msg *hdr; struct sk_buff *skb; u16 size, cong_link_cnt; u8 *data; int rc; size = tipc_aead_key_size(skey); skb = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC); if (!skb) return -ENOMEM; hdr = buf_msg(skb); tipc_msg_init(tipc_own_addr(net), hdr, MSG_CRYPTO, KEY_DISTR_MSG, INT_H_SIZE, dnode); msg_set_size(hdr, INT_H_SIZE + size); msg_set_key_gen(hdr, gen); msg_set_key_mode(hdr, mode); data = msg_data(hdr); *((__be32 *)(data + TIPC_AEAD_ALG_NAME)) = htonl(skey->keylen); memcpy(data, skey->alg_name, TIPC_AEAD_ALG_NAME); memcpy(data + TIPC_AEAD_ALG_NAME + sizeof(__be32), skey->key, skey->keylen); __skb_queue_head_init(&pkts); __skb_queue_tail(&pkts, skb); if (dnode) rc = tipc_node_xmit(net, &pkts, dnode, 0); else rc = tipc_bcast_xmit(net, &pkts, &cong_link_cnt); return rc; } /** * tipc_crypto_key_rcv - Receive a session key * @rx: the RX crypto * @hdr: the TIPC v2 message incl. the receiving session key in its data * * This function retrieves the session key in the message from peer, then * schedules a RX work to attach the key to the corresponding RX crypto. * * Return: "true" if the key has been scheduled for attaching, otherwise * "false". */ static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr) { struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx; struct tipc_aead_key *skey = NULL; u16 key_gen = msg_key_gen(hdr); u32 size = msg_data_sz(hdr); u8 *data = msg_data(hdr); unsigned int keylen; /* Verify whether the size can exist in the packet */ if (unlikely(size < sizeof(struct tipc_aead_key) + TIPC_AEAD_KEYLEN_MIN)) { pr_debug("%s: message data size is too small\n", rx->name); goto exit; } keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME))); /* Verify the supplied size values */ if (unlikely(size != keylen + sizeof(struct tipc_aead_key) || keylen > TIPC_AEAD_KEY_SIZE_MAX)) { pr_debug("%s: invalid MSG_CRYPTO key size\n", rx->name); goto exit; } spin_lock(&rx->lock); if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) { pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name, rx->skey, key_gen, rx->key_gen); goto exit_unlock; } /* Allocate memory for the key */ skey = kmalloc(size, GFP_ATOMIC); if (unlikely(!skey)) { pr_err("%s: unable to allocate memory for skey\n", rx->name); goto exit_unlock; } /* Copy key from msg data */ skey->keylen = keylen; memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME); memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32), skey->keylen); rx->key_gen = key_gen; rx->skey_mode = msg_key_mode(hdr); rx->skey = skey; rx->nokey = 0; mb(); /* for nokey flag */ exit_unlock: spin_unlock(&rx->lock); exit: /* Schedule the key attaching on this crypto */ if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0))) return true; return false; } /** * tipc_crypto_work_rx - Scheduled RX works handler * @work: the struct RX work * * The function processes the previous scheduled works i.e. distributing TX key * or attaching a received session key on RX crypto. */ static void tipc_crypto_work_rx(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct tipc_crypto *rx = container_of(dwork, struct tipc_crypto, work); struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx; unsigned long delay = msecs_to_jiffies(5000); bool resched = false; u8 key; int rc; /* Case 1: Distribute TX key to peer if scheduled */ if (atomic_cmpxchg(&rx->key_distr, KEY_DISTR_SCHED, KEY_DISTR_COMPL) == KEY_DISTR_SCHED) { /* Always pick the newest one for distributing */ key = tx->key.pending ?: tx->key.active; rc = tipc_crypto_key_distr(tx, key, rx->node); if (unlikely(rc)) pr_warn("%s: unable to distr key[%d] to %s, err %d\n", tx->name, key, tipc_node_get_id_str(rx->node), rc); /* Sched for key_distr releasing */ resched = true; } else { atomic_cmpxchg(&rx->key_distr, KEY_DISTR_COMPL, 0); } /* Case 2: Attach a pending received session key from peer if any */ if (rx->skey) { rc = tipc_crypto_key_init(rx, rx->skey, rx->skey_mode, false); if (unlikely(rc < 0)) pr_warn("%s: unable to attach received skey, err %d\n", rx->name, rc); switch (rc) { case -EBUSY: case -ENOMEM: /* Resched the key attaching */ resched = true; break; default: synchronize_rcu(); kfree(rx->skey); rx->skey = NULL; break; } } if (resched && queue_delayed_work(tx->wq, &rx->work, delay)) return; tipc_node_put(rx->node); } /** * tipc_crypto_rekeying_sched - (Re)schedule rekeying w/o new interval * @tx: TX crypto * @changed: if the rekeying needs to be rescheduled with new interval * @new_intv: new rekeying interval (when "changed" = true) */ void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed, u32 new_intv) { unsigned long delay; bool now = false; if (changed) { if (new_intv == TIPC_REKEYING_NOW) now = true; else tx->rekeying_intv = new_intv; cancel_delayed_work_sync(&tx->work); } if (tx->rekeying_intv || now) { delay = (now) ? 0 : tx->rekeying_intv * 60 * 1000; queue_delayed_work(tx->wq, &tx->work, msecs_to_jiffies(delay)); } } /** * tipc_crypto_work_tx - Scheduled TX works handler * @work: the struct TX work * * The function processes the previous scheduled work, i.e. key rekeying, by * generating a new session key based on current one, then attaching it to the * TX crypto and finally distributing it to peers. It also re-schedules the * rekeying if needed. */ static void tipc_crypto_work_tx(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct tipc_crypto *tx = container_of(dwork, struct tipc_crypto, work); struct tipc_aead_key *skey = NULL; struct tipc_key key = tx->key; struct tipc_aead *aead; int rc = -ENOMEM; if (unlikely(key.pending)) goto resched; /* Take current key as a template */ rcu_read_lock(); aead = rcu_dereference(tx->aead[key.active ?: KEY_MASTER]); if (unlikely(!aead)) { rcu_read_unlock(); /* At least one key should exist for securing */ return; } /* Lets duplicate it first */ skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_ATOMIC); rcu_read_unlock(); /* Now, generate new key, initiate & distribute it */ if (likely(skey)) { rc = tipc_aead_key_generate(skey) ?: tipc_crypto_key_init(tx, skey, PER_NODE_KEY, false); if (likely(rc > 0)) rc = tipc_crypto_key_distr(tx, rc, NULL); kfree_sensitive(skey); } if (unlikely(rc)) pr_warn_ratelimited("%s: rekeying returns %d\n", tx->name, rc); resched: /* Re-schedule rekeying if any */ tipc_crypto_rekeying_sched(tx, false, 0); } |
| 5 5 5 5 5 2 1 17 2 2 6 7 4 2 3 5 1 4 7 23 1 18 1 9 1 9 1 1 1 1 2 1 1 8 8 8 8 8 9 9 18 16 3 2 2 2 2 12 12 9 8 1 9 9 17 17 17 7 8 8 2 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 | /* AFS superblock handling * * Copyright (c) 2002, 2007, 2018 Red Hat, Inc. All rights reserved. * * This software may be freely redistributed under the terms of the * GNU General Public License. * * 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. * * Authors: David Howells <dhowells@redhat.com> * David Woodhouse <dwmw2@infradead.org> * */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/fs_parser.h> #include <linux/statfs.h> #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/magic.h> #include <net/net_namespace.h> #include "internal.h" static void afs_i_init_once(void *foo); static void afs_kill_super(struct super_block *sb); static struct inode *afs_alloc_inode(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); static void afs_free_inode(struct inode *inode); static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); static int afs_show_devname(struct seq_file *m, struct dentry *root); static int afs_show_options(struct seq_file *m, struct dentry *root); static int afs_init_fs_context(struct fs_context *fc); static const struct fs_parameter_spec afs_fs_parameters[]; struct file_system_type afs_fs_type = { .owner = THIS_MODULE, .name = "afs", .init_fs_context = afs_init_fs_context, .parameters = afs_fs_parameters, .kill_sb = afs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE, }; MODULE_ALIAS_FS("afs"); int afs_net_id; static const struct super_operations afs_super_ops = { .statfs = afs_statfs, .alloc_inode = afs_alloc_inode, .write_inode = netfs_unpin_writeback, .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .free_inode = afs_free_inode, .evict_inode = afs_evict_inode, .show_devname = afs_show_devname, .show_options = afs_show_options, }; static struct kmem_cache *afs_inode_cachep; static atomic_t afs_count_active_inodes; enum afs_param { Opt_autocell, Opt_dyn, Opt_flock, Opt_source, }; static const struct constant_table afs_param_flock[] = { {"local", afs_flock_mode_local }, {"openafs", afs_flock_mode_openafs }, {"strict", afs_flock_mode_strict }, {"write", afs_flock_mode_write }, {} }; static const struct fs_parameter_spec afs_fs_parameters[] = { fsparam_flag ("autocell", Opt_autocell), fsparam_flag ("dyn", Opt_dyn), fsparam_enum ("flock", Opt_flock, afs_param_flock), fsparam_string("source", Opt_source), {} }; /* * initialise the filesystem */ int __init afs_fs_init(void) { int ret; _enter(""); /* create ourselves an inode cache */ atomic_set(&afs_count_active_inodes, 0); ret = -ENOMEM; afs_inode_cachep = kmem_cache_create("afs_inode_cache", sizeof(struct afs_vnode), 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, afs_i_init_once); if (!afs_inode_cachep) { printk(KERN_NOTICE "kAFS: Failed to allocate inode cache\n"); return ret; } /* now export our filesystem to lesser mortals */ ret = register_filesystem(&afs_fs_type); if (ret < 0) { kmem_cache_destroy(afs_inode_cachep); _leave(" = %d", ret); return ret; } _leave(" = 0"); return 0; } /* * clean up the filesystem */ void afs_fs_exit(void) { _enter(""); afs_mntpt_kill_timer(); unregister_filesystem(&afs_fs_type); if (atomic_read(&afs_count_active_inodes) != 0) { printk("kAFS: %d active inode objects still present\n", atomic_read(&afs_count_active_inodes)); BUG(); } /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(afs_inode_cachep); _leave(""); } /* * Display the mount device name in /proc/mounts. */ static int afs_show_devname(struct seq_file *m, struct dentry *root) { struct afs_super_info *as = AFS_FS_S(root->d_sb); struct afs_volume *volume = as->volume; struct afs_cell *cell = as->cell; const char *suf = ""; char pref = '%'; if (as->dyn_root) { seq_puts(m, "none"); return 0; } switch (volume->type) { case AFSVL_RWVOL: break; case AFSVL_ROVOL: pref = '#'; if (volume->type_force) suf = ".readonly"; break; case AFSVL_BACKVOL: pref = '#'; suf = ".backup"; break; } seq_printf(m, "%c%s:%s%s", pref, cell->name, volume->name, suf); return 0; } /* * Display the mount options in /proc/mounts. */ static int afs_show_options(struct seq_file *m, struct dentry *root) { struct afs_super_info *as = AFS_FS_S(root->d_sb); const char *p = NULL; if (as->dyn_root) seq_puts(m, ",dyn"); if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags)) seq_puts(m, ",autocell"); switch (as->flock_mode) { case afs_flock_mode_unset: break; case afs_flock_mode_local: p = "local"; break; case afs_flock_mode_openafs: p = "openafs"; break; case afs_flock_mode_strict: p = "strict"; break; case afs_flock_mode_write: p = "write"; break; } if (p) seq_printf(m, ",flock=%s", p); return 0; } /* * Parse the source name to get cell name, volume name, volume type and R/W * selector. * * This can be one of the following: * "%[cell:]volume[.]" R/W volume * "#[cell:]volume[.]" R/O or R/W volume (R/O parent), * or R/W (R/W parent) volume * "%[cell:]volume.readonly" R/O volume * "#[cell:]volume.readonly" R/O volume * "%[cell:]volume.backup" Backup volume * "#[cell:]volume.backup" Backup volume */ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) { struct afs_fs_context *ctx = fc->fs_private; struct afs_cell *cell; const char *cellname, *suffix, *name = param->string; int cellnamesz; _enter(",%s", name); if (fc->source) return invalf(fc, "kAFS: Multiple sources not supported"); if (!name) { printk(KERN_ERR "kAFS: no volume name specified\n"); return -EINVAL; } if ((name[0] != '%' && name[0] != '#') || !name[1]) { /* To use dynroot, we don't want to have to provide a source */ if (strcmp(name, "none") == 0) { ctx->no_cell = true; return 0; } printk(KERN_ERR "kAFS: unparsable volume name\n"); return -EINVAL; } /* determine the type of volume we're looking for */ if (name[0] == '%') { ctx->type = AFSVL_RWVOL; ctx->force = true; } name++; /* split the cell name out if there is one */ ctx->volname = strchr(name, ':'); if (ctx->volname) { cellname = name; cellnamesz = ctx->volname - name; ctx->volname++; } else { ctx->volname = name; cellname = NULL; cellnamesz = 0; } /* the volume type is further affected by a possible suffix */ suffix = strrchr(ctx->volname, '.'); if (suffix) { if (strcmp(suffix, ".readonly") == 0) { ctx->type = AFSVL_ROVOL; ctx->force = true; } else if (strcmp(suffix, ".backup") == 0) { ctx->type = AFSVL_BACKVOL; ctx->force = true; } else if (suffix[1] == 0) { } else { suffix = NULL; } } ctx->volnamesz = suffix ? suffix - ctx->volname : strlen(ctx->volname); _debug("cell %*.*s [%p]", cellnamesz, cellnamesz, cellname ?: "", ctx->cell); /* lookup the cell record */ if (cellname) { cell = afs_lookup_cell(ctx->net, cellname, cellnamesz, NULL, false); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%*.*s'\n", cellnamesz, cellnamesz, cellname ?: ""); return PTR_ERR(cell); } afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_parse); afs_see_cell(cell, afs_cell_trace_see_source); ctx->cell = cell; } _debug("CELL:%s [%p] VOLUME:%*.*s SUFFIX:%s TYPE:%d%s", ctx->cell->name, ctx->cell, ctx->volnamesz, ctx->volnamesz, ctx->volname, suffix ?: "-", ctx->type, ctx->force ? " FORCE" : ""); fc->source = param->string; param->string = NULL; return 0; } /* * Parse a single mount parameter. */ static int afs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct afs_fs_context *ctx = fc->fs_private; int opt; opt = fs_parse(fc, afs_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_source: return afs_parse_source(fc, param); case Opt_autocell: ctx->autocell = true; break; case Opt_dyn: ctx->dyn_root = true; break; case Opt_flock: ctx->flock_mode = result.uint_32; break; default: return -EINVAL; } _leave(" = 0"); return 0; } /* * Validate the options, get the cell key and look up the volume. */ static int afs_validate_fc(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct afs_volume *volume; struct afs_cell *cell; struct key *key; int ret; if (!ctx->dyn_root) { if (ctx->no_cell) { pr_warn("kAFS: Can only specify source 'none' with -o dyn\n"); return -EINVAL; } if (!ctx->cell) { pr_warn("kAFS: No cell specified\n"); return -EDESTADDRREQ; } reget_key: /* We try to do the mount securely. */ key = afs_request_key(ctx->cell); if (IS_ERR(key)) return PTR_ERR(key); ctx->key = key; if (ctx->volume) { afs_put_volume(ctx->volume, afs_volume_trace_put_validate_fc); ctx->volume = NULL; } if (test_bit(AFS_CELL_FL_CHECK_ALIAS, &ctx->cell->flags)) { ret = afs_cell_detect_alias(ctx->cell, key); if (ret < 0) return ret; if (ret == 1) { _debug("switch to alias"); key_put(ctx->key); ctx->key = NULL; cell = afs_use_cell(ctx->cell->alias_of, afs_cell_trace_use_fc_alias); afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc); ctx->cell = cell; goto reget_key; } } volume = afs_create_volume(ctx); if (IS_ERR(volume)) return PTR_ERR(volume); ctx->volume = volume; if (volume->type != AFSVL_RWVOL) { ctx->flock_mode = afs_flock_mode_local; fc->sb_flags |= SB_RDONLY; } } return 0; } /* * check a superblock to see if it's the one we're looking for */ static int afs_test_super(struct super_block *sb, struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct afs_super_info *as = AFS_FS_S(sb); return (as->net_ns == fc->net_ns && as->volume && as->volume->vid == ctx->volume->vid && as->cell == ctx->cell && !as->dyn_root); } static int afs_dynroot_test_super(struct super_block *sb, struct fs_context *fc) { struct afs_super_info *as = AFS_FS_S(sb); return (as->net_ns == fc->net_ns && as->dyn_root); } static int afs_set_super(struct super_block *sb, struct fs_context *fc) { return set_anon_super(sb, NULL); } /* * fill in the superblock */ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) { struct afs_super_info *as = AFS_FS_S(sb); struct inode *inode = NULL; int ret; _enter(""); /* fill in the superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; if (!as->dyn_root) sb->s_xattr = afs_xattr_handlers; ret = super_setup_bdi(sb); if (ret) return ret; /* allocate the root inode and dentry */ if (as->dyn_root) { inode = afs_iget_pseudo_dir(sb, true); } else { sprintf(sb->s_id, "%llu", as->volume->vid); afs_activate_volume(as->volume); inode = afs_root_iget(sb, ctx->key); } if (IS_ERR(inode)) return PTR_ERR(inode); if (ctx->autocell || as->dyn_root) set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags); ret = -ENOMEM; sb->s_root = d_make_root(inode); if (!sb->s_root) goto error; if (as->dyn_root) { sb->s_d_op = &afs_dynroot_dentry_operations; ret = afs_dynroot_populate(sb); if (ret < 0) goto error; } else { sb->s_d_op = &afs_fs_dentry_operations; rcu_assign_pointer(as->volume->sb, sb); } _leave(" = 0"); return 0; error: _leave(" = %d", ret); return ret; } static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct afs_super_info *as; as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); if (as) { as->net_ns = get_net(fc->net_ns); as->flock_mode = ctx->flock_mode; if (ctx->dyn_root) { as->dyn_root = true; } else { as->cell = afs_use_cell(ctx->cell, afs_cell_trace_use_sbi); as->volume = afs_get_volume(ctx->volume, afs_volume_trace_get_alloc_sbi); } } return as; } static void afs_destroy_sbi(struct afs_super_info *as) { if (as) { struct afs_net *net = afs_net(as->net_ns); afs_put_volume(as->volume, afs_volume_trace_put_destroy_sbi); afs_unuse_cell(net, as->cell, afs_cell_trace_unuse_sbi); put_net(as->net_ns); kfree(as); } } static void afs_kill_super(struct super_block *sb) { struct afs_super_info *as = AFS_FS_S(sb); if (as->dyn_root) afs_dynroot_depopulate(sb); /* Clear the callback interests (which will do ilookup5) before * deactivating the superblock. */ if (as->volume) rcu_assign_pointer(as->volume->sb, NULL); kill_anon_super(sb); if (as->volume) afs_deactivate_volume(as->volume); afs_destroy_sbi(as); } /* * Get an AFS superblock and root directory. */ static int afs_get_tree(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; struct super_block *sb; struct afs_super_info *as; int ret; ret = afs_validate_fc(fc); if (ret) goto error; _enter(""); /* allocate a superblock info record */ ret = -ENOMEM; as = afs_alloc_sbi(fc); if (!as) goto error; fc->s_fs_info = as; /* allocate a deviceless superblock */ sb = sget_fc(fc, as->dyn_root ? afs_dynroot_test_super : afs_test_super, afs_set_super); if (IS_ERR(sb)) { ret = PTR_ERR(sb); goto error; } if (!sb->s_root) { /* initial superblock/root creation */ _debug("create"); ret = afs_fill_super(sb, ctx); if (ret < 0) goto error_sb; sb->s_flags |= SB_ACTIVE; } else { _debug("reuse"); ASSERTCMP(sb->s_flags, &, SB_ACTIVE); } fc->root = dget(sb->s_root); trace_afs_get_tree(as->cell, as->volume); _leave(" = 0 [%p]", sb); return 0; error_sb: deactivate_locked_super(sb); error: _leave(" = %d", ret); return ret; } static void afs_free_fc(struct fs_context *fc) { struct afs_fs_context *ctx = fc->fs_private; afs_destroy_sbi(fc->s_fs_info); afs_put_volume(ctx->volume, afs_volume_trace_put_free_fc); afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc); key_put(ctx->key); kfree(ctx); } static const struct fs_context_operations afs_context_ops = { .free = afs_free_fc, .parse_param = afs_parse_param, .get_tree = afs_get_tree, }; /* * Set up the filesystem mount context. */ static int afs_init_fs_context(struct fs_context *fc) { struct afs_fs_context *ctx; struct afs_cell *cell; ctx = kzalloc(sizeof(struct afs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->type = AFSVL_ROVOL; ctx->net = afs_net(fc->net_ns); /* Default to the workstation cell. */ cell = afs_find_cell(ctx->net, NULL, 0, afs_cell_trace_use_fc); if (IS_ERR(cell)) cell = NULL; ctx->cell = cell; fc->fs_private = ctx; fc->ops = &afs_context_ops; return 0; } /* * Initialise an inode cache slab element prior to any use. Note that * afs_alloc_inode() *must* reset anything that could incorrectly leak from one * inode to another. */ static void afs_i_init_once(void *_vnode) { struct afs_vnode *vnode = _vnode; memset(vnode, 0, sizeof(*vnode)); inode_init_once(&vnode->netfs.inode); mutex_init(&vnode->io_lock); init_rwsem(&vnode->validate_lock); spin_lock_init(&vnode->wb_lock); spin_lock_init(&vnode->lock); INIT_LIST_HEAD(&vnode->wb_keys); INIT_LIST_HEAD(&vnode->pending_locks); INIT_LIST_HEAD(&vnode->granted_locks); INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work); INIT_LIST_HEAD(&vnode->cb_mmap_link); seqlock_init(&vnode->cb_lock); } /* * allocate an AFS inode struct from our slab cache */ static struct inode *afs_alloc_inode(struct super_block *sb) { struct afs_vnode *vnode; vnode = alloc_inode_sb(sb, afs_inode_cachep, GFP_KERNEL); if (!vnode) return NULL; atomic_inc(&afs_count_active_inodes); /* Reset anything that shouldn't leak from one inode to the next. */ memset(&vnode->fid, 0, sizeof(vnode->fid)); memset(&vnode->status, 0, sizeof(vnode->status)); afs_vnode_set_cache(vnode, NULL); vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; vnode->flags = 1 << AFS_VNODE_UNSET; vnode->lock_state = AFS_VNODE_LOCK_NONE; init_rwsem(&vnode->rmdir_lock); INIT_WORK(&vnode->cb_work, afs_invalidate_mmap_work); _leave(" = %p", &vnode->netfs.inode); return &vnode->netfs.inode; } static void afs_free_inode(struct inode *inode) { kmem_cache_free(afs_inode_cachep, AFS_FS_I(inode)); } /* * destroy an AFS inode struct */ static void afs_destroy_inode(struct inode *inode) { struct afs_vnode *vnode = AFS_FS_I(inode); _enter("%p{%llx:%llu}", inode, vnode->fid.vid, vnode->fid.vnode); _debug("DESTROY INODE %p", inode); atomic_dec(&afs_count_active_inodes); } static void afs_get_volume_status_success(struct afs_operation *op) { struct afs_volume_status *vs = &op->volstatus.vs; struct kstatfs *buf = op->volstatus.buf; if (vs->max_quota == 0) buf->f_blocks = vs->part_max_blocks; else buf->f_blocks = vs->max_quota; if (buf->f_blocks > vs->blocks_in_use) buf->f_bavail = buf->f_bfree = buf->f_blocks - vs->blocks_in_use; } static const struct afs_operation_ops afs_get_volume_status_operation = { .issue_afs_rpc = afs_fs_get_volume_status, .issue_yfs_rpc = yfs_fs_get_volume_status, .success = afs_get_volume_status_success, }; /* * return information about an AFS volume */ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct afs_super_info *as = AFS_FS_S(dentry->d_sb); struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = AFS_BLOCK_SIZE; buf->f_namelen = AFSNAMEMAX - 1; if (as->dyn_root) { buf->f_blocks = 1; buf->f_bavail = 0; buf->f_bfree = 0; return 0; } op = afs_alloc_operation(NULL, as->volume); if (IS_ERR(op)) return PTR_ERR(op); afs_op_set_vnode(op, 0, vnode); op->nr_files = 1; op->volstatus.buf = buf; op->ops = &afs_get_volume_status_operation; return afs_do_sync_operation(op); } |
| 6 4 3 4 3 1 5 1 1 1 1 1 1 16 5 3 2 1 2 1 1 2 13 1 6 5 1 40 40 41 1 13 1 1 11 12 1 11 15 1 13 12 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1994 Linus Torvalds * * Cyrix stuff, June 1998 by: * - Rafael R. Reilova (moved everything from head.S), * <rreilova@ececs.uc.edu> * - Channing Corn (tests & fixes), * - Andrew D. Balsa (code cleanup). */ #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched/smt.h> #include <linux/pgtable.h> #include <linux/bpf.h> #include <asm/spec-ctrl.h> #include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> #include <asm/fpu/api.h> #include <asm/msr.h> #include <asm/vmx.h> #include <asm/paravirt.h> #include <asm/cpu_device_id.h> #include <asm/e820/api.h> #include <asm/hypervisor.h> #include <asm/tlbflush.h> #include <asm/cpu.h> #include "cpu.h" static void __init spectre_v1_select_mitigation(void); static void __init spectre_v2_select_mitigation(void); static void __init retbleed_select_mitigation(void); static void __init spectre_v2_user_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); static void __init md_clear_update_mitigation(void); static void __init md_clear_select_mitigation(void); static void __init taa_select_mitigation(void); static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); /* The current value of the SPEC_CTRL MSR with task-specific bits set */ DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); static u64 __ro_after_init x86_arch_cap_msr; static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { this_cpu_write(x86_spec_ctrl_current, val); wrmsrl(MSR_IA32_SPEC_CTRL, val); } /* * Keep track of the SPEC_CTRL MSR value for the current task, which may differ * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update(). */ void update_spec_ctrl_cond(u64 val) { if (this_cpu_read(x86_spec_ctrl_current) == val) return; this_cpu_write(x86_spec_ctrl_current, val); /* * When KERNEL_IBRS this MSR is written on return-to-user, unless * forced the update can be delayed until that time. */ if (!cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) wrmsrl(MSR_IA32_SPEC_CTRL, val); } noinstr u64 spec_ctrl_current(void) { return this_cpu_read(x86_spec_ctrl_current); } EXPORT_SYMBOL_GPL(spec_ctrl_current); /* * AMD specific MSR info for Speculative Store Bypass control. * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu(). */ u64 __ro_after_init x86_amd_ls_cfg_base; u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; /* Control conditional STIBP in switch_to() */ DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp); /* Control conditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); /* * Controls whether l1d flush based mitigations are enabled, * based on hw features and admin setting via boot parameter * defaults to false */ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); /* Controls CPU Fill buffer clear before KVM guest MMIO accesses */ DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear); EXPORT_SYMBOL_GPL(mmio_stale_data_clear); void __init cpu_select_mitigations(void) { /* * Read the SPEC_CTRL MSR to account for reserved bits which may * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD * init code as it is not enumerated and depends on the family. */ if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) { rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); /* * Previously running kernel (kexec), may have some controls * turned ON. Clear them and let the mitigations setup below * rediscover them based on configuration. */ x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; } x86_arch_cap_msr = x86_read_arch_cap_msr(); /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); /* * retbleed_select_mitigation() relies on the state set by * spectre_v2_select_mitigation(); specifically it wants to know about * spectre_v2=ibrs. */ retbleed_select_mitigation(); /* * spectre_v2_user_select_mitigation() relies on the state set by * retbleed_select_mitigation(); specifically the STIBP selection is * forced for UNRET or IBPB. */ spectre_v2_user_select_mitigation(); ssb_select_mitigation(); l1tf_select_mitigation(); md_clear_select_mitigation(); srbds_select_mitigation(); l1d_flush_select_mitigation(); /* * srso_select_mitigation() depends and must run after * retbleed_select_mitigation(). */ srso_select_mitigation(); gds_select_mitigation(); } /* * NOTE: This function is *only* called for SVM, since Intel uses * MSR_IA32_SPEC_CTRL for SSBD. */ void x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool setguest) { u64 guestval, hostval; struct thread_info *ti = current_thread_info(); /* * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. */ if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) && !static_cpu_has(X86_FEATURE_VIRT_SSBD)) return; /* * If the host has SSBD mitigation enabled, force it in the host's * virtual MSR value. If its not permanently enabled, evaluate * current's TIF_SSBD thread flag. */ if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE)) hostval = SPEC_CTRL_SSBD; else hostval = ssbd_tif_to_spec_ctrl(ti->flags); /* Sanitize the guest value */ guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD; if (hostval != guestval) { unsigned long tif; tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : ssbd_spec_ctrl_to_tif(hostval); speculation_ctrl_update(tif); } } EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); static void x86_amd_ssb_disable(void) { u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask; if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD); else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) wrmsrl(MSR_AMD64_LS_CFG, msrval); } #undef pr_fmt #define pr_fmt(fmt) "MDS: " fmt /* Default mitigation for MDS-affected CPUs */ static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL; static bool mds_nosmt __ro_after_init = false; static const char * const mds_strings[] = { [MDS_MITIGATION_OFF] = "Vulnerable", [MDS_MITIGATION_FULL] = "Mitigation: Clear CPU buffers", [MDS_MITIGATION_VMWERV] = "Vulnerable: Clear CPU buffers attempted, no microcode", }; static void __init mds_select_mitigation(void) { if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) { mds_mitigation = MDS_MITIGATION_OFF; return; } if (mds_mitigation == MDS_MITIGATION_FULL) { if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) cpu_smt_disable(false); } } static int __init mds_cmdline(char *str) { if (!boot_cpu_has_bug(X86_BUG_MDS)) return 0; if (!str) return -EINVAL; if (!strcmp(str, "off")) mds_mitigation = MDS_MITIGATION_OFF; else if (!strcmp(str, "full")) mds_mitigation = MDS_MITIGATION_FULL; else if (!strcmp(str, "full,nosmt")) { mds_mitigation = MDS_MITIGATION_FULL; mds_nosmt = true; } return 0; } early_param("mds", mds_cmdline); #undef pr_fmt #define pr_fmt(fmt) "TAA: " fmt enum taa_mitigations { TAA_MITIGATION_OFF, TAA_MITIGATION_UCODE_NEEDED, TAA_MITIGATION_VERW, TAA_MITIGATION_TSX_DISABLED, }; /* Default mitigation for TAA-affected CPUs */ static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; static bool taa_nosmt __ro_after_init; static const char * const taa_strings[] = { [TAA_MITIGATION_OFF] = "Vulnerable", [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", }; static void __init taa_select_mitigation(void) { if (!boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_OFF; return; } /* TSX previously disabled by tsx=off */ if (!boot_cpu_has(X86_FEATURE_RTM)) { taa_mitigation = TAA_MITIGATION_TSX_DISABLED; return; } if (cpu_mitigations_off()) { taa_mitigation = TAA_MITIGATION_OFF; return; } /* * TAA mitigation via VERW is turned off if both * tsx_async_abort=off and mds=off are specified. */ if (taa_mitigation == TAA_MITIGATION_OFF && mds_mitigation == MDS_MITIGATION_OFF) return; if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) taa_mitigation = TAA_MITIGATION_VERW; else taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. * A microcode update fixes this behavior to clear CPU buffers. It also * adds support for MSR_IA32_TSX_CTRL which is enumerated by the * ARCH_CAP_TSX_CTRL_MSR bit. * * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode * update is required. */ if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)) taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* * TSX is enabled, select alternate mitigation for TAA which is * the same as MDS. Enable MDS static branch to clear CPU buffers. * * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); } static int __init tsx_async_abort_parse_cmdline(char *str) { if (!boot_cpu_has_bug(X86_BUG_TAA)) return 0; if (!str) return -EINVAL; if (!strcmp(str, "off")) { taa_mitigation = TAA_MITIGATION_OFF; } else if (!strcmp(str, "full")) { taa_mitigation = TAA_MITIGATION_VERW; } else if (!strcmp(str, "full,nosmt")) { taa_mitigation = TAA_MITIGATION_VERW; taa_nosmt = true; } return 0; } early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "MMIO Stale Data: " fmt enum mmio_mitigations { MMIO_MITIGATION_OFF, MMIO_MITIGATION_UCODE_NEEDED, MMIO_MITIGATION_VERW, }; /* Default mitigation for Processor MMIO Stale Data vulnerabilities */ static enum mmio_mitigations mmio_mitigation __ro_after_init = MMIO_MITIGATION_VERW; static bool mmio_nosmt __ro_after_init = false; static const char * const mmio_strings[] = { [MMIO_MITIGATION_OFF] = "Vulnerable", [MMIO_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", [MMIO_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", }; static void __init mmio_select_mitigation(void) { if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || cpu_mitigations_off()) { mmio_mitigation = MMIO_MITIGATION_OFF; return; } if (mmio_mitigation == MMIO_MITIGATION_OFF) return; /* * Enable CPU buffer clear mitigation for host and VMM, if also affected * by MDS or TAA. Otherwise, enable mitigation for VMM only. */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); /* * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based * mitigations, disable KVM-only mitigation in that case. */ if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); /* * If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can * be propagated to uncore buffers, clearing the Fill buffers on idle * is required irrespective of SMT state. */ if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) static_branch_enable(&mds_idle_clear); /* * Check if the system has the right microcode. * * CPU Fill buffer clear mitigation is enumerated by either an explicit * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS * affected systems. */ if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) || (boot_cpu_has(X86_FEATURE_MD_CLEAR) && boot_cpu_has(X86_FEATURE_FLUSH_L1D) && !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))) mmio_mitigation = MMIO_MITIGATION_VERW; else mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; if (mmio_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); } static int __init mmio_stale_data_parse_cmdline(char *str) { if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) return 0; if (!str) return -EINVAL; if (!strcmp(str, "off")) { mmio_mitigation = MMIO_MITIGATION_OFF; } else if (!strcmp(str, "full")) { mmio_mitigation = MMIO_MITIGATION_VERW; } else if (!strcmp(str, "full,nosmt")) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_nosmt = true; } return 0; } early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "Register File Data Sampling: " fmt enum rfds_mitigations { RFDS_MITIGATION_OFF, RFDS_MITIGATION_VERW, RFDS_MITIGATION_UCODE_NEEDED, }; /* Default mitigation for Register File Data Sampling */ static enum rfds_mitigations rfds_mitigation __ro_after_init = IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; static const char * const rfds_strings[] = { [RFDS_MITIGATION_OFF] = "Vulnerable", [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", }; static void __init rfds_select_mitigation(void) { if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { rfds_mitigation = RFDS_MITIGATION_OFF; return; } if (rfds_mitigation == RFDS_MITIGATION_OFF) return; if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; } static __init int rfds_parse_cmdline(char *str) { if (!str) return -EINVAL; if (!boot_cpu_has_bug(X86_BUG_RFDS)) return 0; if (!strcmp(str, "off")) rfds_mitigation = RFDS_MITIGATION_OFF; else if (!strcmp(str, "on")) rfds_mitigation = RFDS_MITIGATION_VERW; return 0; } early_param("reg_file_data_sampling", rfds_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "" fmt static void __init md_clear_update_mitigation(void) { if (cpu_mitigations_off()) return; if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { mds_mitigation = MDS_MITIGATION_FULL; mds_select_mitigation(); } if (taa_mitigation == TAA_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } /* * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. */ if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } if (rfds_mitigation == RFDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_RFDS)) { rfds_mitigation = RFDS_MITIGATION_VERW; rfds_select_mitigation(); } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); if (boot_cpu_has_bug(X86_BUG_TAA)) pr_info("TAA: %s\n", taa_strings[taa_mitigation]); if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); if (boot_cpu_has_bug(X86_BUG_RFDS)) pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) { mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); rfds_select_mitigation(); /* * As these mitigations are inter-related and rely on VERW instruction * to clear the microarchitural buffers, update and print their status * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } #undef pr_fmt #define pr_fmt(fmt) "SRBDS: " fmt enum srbds_mitigations { SRBDS_MITIGATION_OFF, SRBDS_MITIGATION_UCODE_NEEDED, SRBDS_MITIGATION_FULL, SRBDS_MITIGATION_TSX_OFF, SRBDS_MITIGATION_HYPERVISOR, }; static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL; static const char * const srbds_strings[] = { [SRBDS_MITIGATION_OFF] = "Vulnerable", [SRBDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", [SRBDS_MITIGATION_FULL] = "Mitigation: Microcode", [SRBDS_MITIGATION_TSX_OFF] = "Mitigation: TSX disabled", [SRBDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", }; static bool srbds_off; void update_srbds_msr(void) { u64 mcu_ctrl; if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) return; /* * A MDS_NO CPU for which SRBDS mitigation is not needed due to TSX * being disabled and it hasn't received the SRBDS MSR microcode. */ if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) return; rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); switch (srbds_mitigation) { case SRBDS_MITIGATION_OFF: case SRBDS_MITIGATION_TSX_OFF: mcu_ctrl |= RNGDS_MITG_DIS; break; case SRBDS_MITIGATION_FULL: mcu_ctrl &= ~RNGDS_MITG_DIS; break; default: break; } wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); } static void __init srbds_select_mitigation(void) { if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; /* * Check to see if this is one of the MDS_NO systems supporting TSX that * are only exposed to SRBDS when TSX is enabled or when CPU is affected * by Processor MMIO Stale Data vulnerability. */ if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR; else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED; else if (cpu_mitigations_off() || srbds_off) srbds_mitigation = SRBDS_MITIGATION_OFF; update_srbds_msr(); pr_info("%s\n", srbds_strings[srbds_mitigation]); } static int __init srbds_parse_cmdline(char *str) { if (!str) return -EINVAL; if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return 0; srbds_off = !strcmp(str, "off"); return 0; } early_param("srbds", srbds_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "L1D Flush : " fmt enum l1d_flush_mitigations { L1D_FLUSH_OFF = 0, L1D_FLUSH_ON, }; static enum l1d_flush_mitigations l1d_flush_mitigation __initdata = L1D_FLUSH_OFF; static void __init l1d_flush_select_mitigation(void) { if (!l1d_flush_mitigation || !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) return; static_branch_enable(&switch_mm_cond_l1d_flush); pr_info("Conditional flush on switch_mm() enabled\n"); } static int __init l1d_flush_parse_cmdline(char *str) { if (!strcmp(str, "on")) l1d_flush_mitigation = L1D_FLUSH_ON; return 0; } early_param("l1d_flush", l1d_flush_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "GDS: " fmt enum gds_mitigations { GDS_MITIGATION_OFF, GDS_MITIGATION_UCODE_NEEDED, GDS_MITIGATION_FORCE, GDS_MITIGATION_FULL, GDS_MITIGATION_FULL_LOCKED, GDS_MITIGATION_HYPERVISOR, }; #if IS_ENABLED(CONFIG_MITIGATION_GDS_FORCE) static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; #else static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; #endif static const char * const gds_strings[] = { [GDS_MITIGATION_OFF] = "Vulnerable", [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode", [GDS_MITIGATION_FULL] = "Mitigation: Microcode", [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)", [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", }; bool gds_ucode_mitigated(void) { return (gds_mitigation == GDS_MITIGATION_FULL || gds_mitigation == GDS_MITIGATION_FULL_LOCKED); } EXPORT_SYMBOL_GPL(gds_ucode_mitigated); void update_gds_msr(void) { u64 mcu_ctrl_after; u64 mcu_ctrl; switch (gds_mitigation) { case GDS_MITIGATION_OFF: rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); mcu_ctrl |= GDS_MITG_DIS; break; case GDS_MITIGATION_FULL_LOCKED: /* * The LOCKED state comes from the boot CPU. APs might not have * the same state. Make sure the mitigation is enabled on all * CPUs. */ case GDS_MITIGATION_FULL: rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); mcu_ctrl &= ~GDS_MITG_DIS; break; case GDS_MITIGATION_FORCE: case GDS_MITIGATION_UCODE_NEEDED: case GDS_MITIGATION_HYPERVISOR: return; } wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); /* * Check to make sure that the WRMSR value was not ignored. Writes to * GDS_MITG_DIS will be ignored if this processor is locked but the boot * processor was not. */ rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after); WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after); } static void __init gds_select_mitigation(void) { u64 mcu_ctrl; if (!boot_cpu_has_bug(X86_BUG_GDS)) return; if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { gds_mitigation = GDS_MITIGATION_HYPERVISOR; goto out; } if (cpu_mitigations_off()) gds_mitigation = GDS_MITIGATION_OFF; /* Will verify below that mitigation _can_ be disabled */ /* No microcode */ if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) { if (gds_mitigation == GDS_MITIGATION_FORCE) { /* * This only needs to be done on the boot CPU so do it * here rather than in update_gds_msr() */ setup_clear_cpu_cap(X86_FEATURE_AVX); pr_warn("Microcode update needed! Disabling AVX as mitigation.\n"); } else { gds_mitigation = GDS_MITIGATION_UCODE_NEEDED; } goto out; } /* Microcode has mitigation, use it */ if (gds_mitigation == GDS_MITIGATION_FORCE) gds_mitigation = GDS_MITIGATION_FULL; rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); if (mcu_ctrl & GDS_MITG_LOCKED) { if (gds_mitigation == GDS_MITIGATION_OFF) pr_warn("Mitigation locked. Disable failed.\n"); /* * The mitigation is selected from the boot CPU. All other CPUs * _should_ have the same state. If the boot CPU isn't locked * but others are then update_gds_msr() will WARN() of the state * mismatch. If the boot CPU is locked update_gds_msr() will * ensure the other CPUs have the mitigation enabled. */ gds_mitigation = GDS_MITIGATION_FULL_LOCKED; } update_gds_msr(); out: pr_info("%s\n", gds_strings[gds_mitigation]); } static int __init gds_parse_cmdline(char *str) { if (!str) return -EINVAL; if (!boot_cpu_has_bug(X86_BUG_GDS)) return 0; if (!strcmp(str, "off")) gds_mitigation = GDS_MITIGATION_OFF; else if (!strcmp(str, "force")) gds_mitigation = GDS_MITIGATION_FORCE; return 0; } early_param("gather_data_sampling", gds_parse_cmdline); #undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { SPECTRE_V1_MITIGATION_NONE, SPECTRE_V1_MITIGATION_AUTO, }; static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init = SPECTRE_V1_MITIGATION_AUTO; static const char * const spectre_v1_strings[] = { [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers", [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", }; /* * Does SMAP provide full mitigation against speculative kernel access to * userspace? */ static bool smap_works_speculatively(void) { if (!boot_cpu_has(X86_FEATURE_SMAP)) return false; /* * On CPUs which are vulnerable to Meltdown, SMAP does not * prevent speculative access to user data in the L1 cache. * Consider SMAP to be non-functional as a mitigation on these * CPUs. */ if (boot_cpu_has(X86_BUG_CPU_MELTDOWN)) return false; return true; } static void __init spectre_v1_select_mitigation(void) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) { spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; return; } if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) { /* * With Spectre v1, a user can speculatively control either * path of a conditional swapgs with a user-controlled GS * value. The mitigation is to add lfences to both code paths. * * If FSGSBASE is enabled, the user can put a kernel address in * GS, in which case SMAP provides no protection. * * If FSGSBASE is disabled, the user can only put a user space * address in GS. That makes an attack harder, but still * possible if there's no SMAP protection. */ if (boot_cpu_has(X86_FEATURE_FSGSBASE) || !smap_works_speculatively()) { /* * Mitigation can be provided from SWAPGS itself or * PTI as the CR3 write in the Meltdown mitigation * is serializing. * * If neither is there, mitigate with an LFENCE to * stop speculation through swapgs. */ if (boot_cpu_has_bug(X86_BUG_SWAPGS) && !boot_cpu_has(X86_FEATURE_PTI)) setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER); /* * Enable lfences in the kernel entry (non-swapgs) * paths, to prevent user entry from speculatively * skipping swapgs. */ setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL); } } pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]); } static int __init nospectre_v1_cmdline(char *str) { spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; return 0; } early_param("nospectre_v1", nospectre_v1_cmdline); enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE; #undef pr_fmt #define pr_fmt(fmt) "RETBleed: " fmt enum retbleed_mitigation { RETBLEED_MITIGATION_NONE, RETBLEED_MITIGATION_UNRET, RETBLEED_MITIGATION_IBPB, RETBLEED_MITIGATION_IBRS, RETBLEED_MITIGATION_EIBRS, RETBLEED_MITIGATION_STUFF, }; enum retbleed_mitigation_cmd { RETBLEED_CMD_OFF, RETBLEED_CMD_AUTO, RETBLEED_CMD_UNRET, RETBLEED_CMD_IBPB, RETBLEED_CMD_STUFF, }; static const char * const retbleed_strings[] = { [RETBLEED_MITIGATION_NONE] = "Vulnerable", [RETBLEED_MITIGATION_UNRET] = "Mitigation: untrained return thunk", [RETBLEED_MITIGATION_IBPB] = "Mitigation: IBPB", [RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS", [RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS", [RETBLEED_MITIGATION_STUFF] = "Mitigation: Stuffing", }; static enum retbleed_mitigation retbleed_mitigation __ro_after_init = RETBLEED_MITIGATION_NONE; static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init = RETBLEED_CMD_AUTO; static int __ro_after_init retbleed_nosmt = false; static int __init retbleed_parse_cmdline(char *str) { if (!str) return -EINVAL; while (str) { char *next = strchr(str, ','); if (next) { *next = 0; next++; } if (!strcmp(str, "off")) { retbleed_cmd = RETBLEED_CMD_OFF; } else if (!strcmp(str, "auto")) { retbleed_cmd = RETBLEED_CMD_AUTO; } else if (!strcmp(str, "unret")) { retbleed_cmd = RETBLEED_CMD_UNRET; } else if (!strcmp(str, "ibpb")) { retbleed_cmd = RETBLEED_CMD_IBPB; } else if (!strcmp(str, "stuff")) { retbleed_cmd = RETBLEED_CMD_STUFF; } else if (!strcmp(str, "nosmt")) { retbleed_nosmt = true; } else if (!strcmp(str, "force")) { setup_force_cpu_bug(X86_BUG_RETBLEED); } else { pr_err("Ignoring unknown retbleed option (%s).", str); } str = next; } return 0; } early_param("retbleed", retbleed_parse_cmdline); #define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n" #define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n" static void __init retbleed_select_mitigation(void) { bool mitigate_smt = false; if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off()) return; switch (retbleed_cmd) { case RETBLEED_CMD_OFF: return; case RETBLEED_CMD_UNRET: if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) { retbleed_mitigation = RETBLEED_MITIGATION_UNRET; } else { pr_err("WARNING: kernel not compiled with MITIGATION_UNRET_ENTRY.\n"); goto do_cmd_auto; } break; case RETBLEED_CMD_IBPB: if (!boot_cpu_has(X86_FEATURE_IBPB)) { pr_err("WARNING: CPU does not support IBPB.\n"); goto do_cmd_auto; } else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { retbleed_mitigation = RETBLEED_MITIGATION_IBPB; } else { pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); goto do_cmd_auto; } break; case RETBLEED_CMD_STUFF: if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && spectre_v2_enabled == SPECTRE_V2_RETPOLINE) { retbleed_mitigation = RETBLEED_MITIGATION_STUFF; } else { if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)) pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n"); else pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n"); goto do_cmd_auto; } break; do_cmd_auto: case RETBLEED_CMD_AUTO: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) retbleed_mitigation = RETBLEED_MITIGATION_UNRET; else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB)) retbleed_mitigation = RETBLEED_MITIGATION_IBPB; } /* * The Intel mitigation (IBRS or eIBRS) was already selected in * spectre_v2_select_mitigation(). 'retbleed_mitigation' will * be set accordingly below. */ break; } switch (retbleed_mitigation) { case RETBLEED_MITIGATION_UNRET: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); x86_return_thunk = retbleed_return_thunk; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) pr_err(RETBLEED_UNTRAIN_MSG); mitigate_smt = true; break; case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); mitigate_smt = true; break; case RETBLEED_MITIGATION_STUFF: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); x86_return_thunk = call_depth_return_thunk; break; default: break; } if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) && (retbleed_nosmt || cpu_mitigations_auto_nosmt())) cpu_smt_disable(false); /* * Let IBRS trump all on Intel without affecting the effects of the * retbleed= cmdline option except for call depth based stuffing */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { switch (spectre_v2_enabled) { case SPECTRE_V2_IBRS: retbleed_mitigation = RETBLEED_MITIGATION_IBRS; break; case SPECTRE_V2_EIBRS: case SPECTRE_V2_EIBRS_RETPOLINE: case SPECTRE_V2_EIBRS_LFENCE: retbleed_mitigation = RETBLEED_MITIGATION_EIBRS; break; default: if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF) pr_err(RETBLEED_INTEL_MSG); } } pr_info("%s\n", retbleed_strings[retbleed_mitigation]); } #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = SPECTRE_V2_USER_NONE; static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; #ifdef CONFIG_MITIGATION_RETPOLINE static bool spectre_v2_bad_module; bool retpoline_module_ok(bool has_retpoline) { if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline) return true; pr_err("System may be vulnerable to spectre v2\n"); spectre_v2_bad_module = true; return false; } static inline const char *spectre_v2_module_string(void) { return spectre_v2_bad_module ? " - vulnerable module loaded" : ""; } #else static inline const char *spectre_v2_module_string(void) { return ""; } #endif #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" #define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" #define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" #define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n" #ifdef CONFIG_BPF_SYSCALL void unpriv_ebpf_notify(int new_state) { if (new_state) return; /* Unprivileged eBPF is enabled */ switch (spectre_v2_enabled) { case SPECTRE_V2_EIBRS: pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); break; case SPECTRE_V2_EIBRS_LFENCE: if (sched_smt_active()) pr_err(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); break; default: break; } } #endif static inline bool match_option(const char *arg, int arglen, const char *opt) { int len = strlen(opt); return len == arglen && !strncmp(arg, opt, len); } /* The kernel command line selection for spectre v2 */ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_NONE, SPECTRE_V2_CMD_AUTO, SPECTRE_V2_CMD_FORCE, SPECTRE_V2_CMD_RETPOLINE, SPECTRE_V2_CMD_RETPOLINE_GENERIC, SPECTRE_V2_CMD_RETPOLINE_LFENCE, SPECTRE_V2_CMD_EIBRS, SPECTRE_V2_CMD_EIBRS_RETPOLINE, SPECTRE_V2_CMD_EIBRS_LFENCE, SPECTRE_V2_CMD_IBRS, }; enum spectre_v2_user_cmd { SPECTRE_V2_USER_CMD_NONE, SPECTRE_V2_USER_CMD_AUTO, SPECTRE_V2_USER_CMD_FORCE, SPECTRE_V2_USER_CMD_PRCTL, SPECTRE_V2_USER_CMD_PRCTL_IBPB, SPECTRE_V2_USER_CMD_SECCOMP, SPECTRE_V2_USER_CMD_SECCOMP_IBPB, }; static const char * const spectre_v2_user_strings[] = { [SPECTRE_V2_USER_NONE] = "User space: Vulnerable", [SPECTRE_V2_USER_STRICT] = "User space: Mitigation: STIBP protection", [SPECTRE_V2_USER_STRICT_PREFERRED] = "User space: Mitigation: STIBP always-on protection", [SPECTRE_V2_USER_PRCTL] = "User space: Mitigation: STIBP via prctl", [SPECTRE_V2_USER_SECCOMP] = "User space: Mitigation: STIBP via seccomp and prctl", }; static const struct { const char *option; enum spectre_v2_user_cmd cmd; bool secure; } v2_user_options[] __initconst = { { "auto", SPECTRE_V2_USER_CMD_AUTO, false }, { "off", SPECTRE_V2_USER_CMD_NONE, false }, { "on", SPECTRE_V2_USER_CMD_FORCE, true }, { "prctl", SPECTRE_V2_USER_CMD_PRCTL, false }, { "prctl,ibpb", SPECTRE_V2_USER_CMD_PRCTL_IBPB, false }, { "seccomp", SPECTRE_V2_USER_CMD_SECCOMP, false }, { "seccomp,ibpb", SPECTRE_V2_USER_CMD_SECCOMP_IBPB, false }, }; static void __init spec_v2_user_print_cond(const char *reason, bool secure) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure) pr_info("spectre_v2_user=%s forced on command line.\n", reason); } static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd; static enum spectre_v2_user_cmd __init spectre_v2_parse_user_cmdline(void) { char arg[20]; int ret, i; switch (spectre_v2_cmd) { case SPECTRE_V2_CMD_NONE: return SPECTRE_V2_USER_CMD_NONE; case SPECTRE_V2_CMD_FORCE: return SPECTRE_V2_USER_CMD_FORCE; default: break; } ret = cmdline_find_option(boot_command_line, "spectre_v2_user", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_USER_CMD_AUTO; for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) { if (match_option(arg, ret, v2_user_options[i].option)) { spec_v2_user_print_cond(v2_user_options[i].option, v2_user_options[i].secure); return v2_user_options[i].cmd; } } pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg); return SPECTRE_V2_USER_CMD_AUTO; } static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) { return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS; } static void __init spectre_v2_user_select_mitigation(void) { enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE; bool smt_possible = IS_ENABLED(CONFIG_SMP); enum spectre_v2_user_cmd cmd; if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP)) return; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED || cpu_smt_control == CPU_SMT_NOT_SUPPORTED) smt_possible = false; cmd = spectre_v2_parse_user_cmdline(); switch (cmd) { case SPECTRE_V2_USER_CMD_NONE: goto set_mode; case SPECTRE_V2_USER_CMD_FORCE: mode = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_AUTO: case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: mode = SPECTRE_V2_USER_PRCTL; break; case SPECTRE_V2_USER_CMD_SECCOMP: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: if (IS_ENABLED(CONFIG_SECCOMP)) mode = SPECTRE_V2_USER_SECCOMP; else mode = SPECTRE_V2_USER_PRCTL; break; } /* Initialize Indirect Branch Prediction Barrier */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); spectre_v2_user_ibpb = mode; switch (cmd) { case SPECTRE_V2_USER_CMD_NONE: break; case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: static_branch_enable(&switch_mm_always_ibpb); spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT; break; case SPECTRE_V2_USER_CMD_PRCTL: case SPECTRE_V2_USER_CMD_AUTO: case SPECTRE_V2_USER_CMD_SECCOMP: static_branch_enable(&switch_mm_cond_ibpb); break; } pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); } /* * If no STIBP, Intel enhanced IBRS is enabled, or SMT impossible, STIBP * is not required. * * Intel's Enhanced IBRS also protects against cross-thread branch target * injection in user-mode as the IBRS bit remains always set which * implicitly enables cross-thread protections. However, in legacy IBRS * mode, the IBRS bit is set only on kernel entry and cleared on return * to userspace. AMD Automatic IBRS also does not protect userspace. * These modes therefore disable the implicit cross-thread protection, * so allow for STIBP to be selected in those cases. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && !boot_cpu_has(X86_FEATURE_AUTOIBRS))) return; /* * At this point, an STIBP mode other than "off" has been set. * If STIBP support is not being forced, check if STIBP always-on * is preferred. */ if (mode != SPECTRE_V2_USER_STRICT && boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) mode = SPECTRE_V2_USER_STRICT_PREFERRED; if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { if (mode != SPECTRE_V2_USER_STRICT && mode != SPECTRE_V2_USER_STRICT_PREFERRED) pr_info("Selecting STIBP always-on mode to complement retbleed mitigation\n"); mode = SPECTRE_V2_USER_STRICT_PREFERRED; } spectre_v2_user_stibp = mode; set_mode: pr_info("%s\n", spectre_v2_user_strings[mode]); } static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS", [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE", [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines", [SPECTRE_V2_IBRS] = "Mitigation: IBRS", }; static const struct { const char *option; enum spectre_v2_mitigation_cmd cmd; bool secure; } mitigation_options[] __initconst = { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, { "retpoline,lfence", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, { "eibrs", SPECTRE_V2_CMD_EIBRS, false }, { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, { "ibrs", SPECTRE_V2_CMD_IBRS, false }, }; static void __init spec_v2_print_cond(const char *reason, bool secure) { if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure) pr_info("%s selected on command line.\n", reason); } static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; char arg[20]; int ret, i; if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") || cpu_mitigations_off()) return SPECTRE_V2_CMD_NONE; ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) return SPECTRE_V2_CMD_AUTO; for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { if (!match_option(arg, ret, mitigation_options[i].option)) continue; cmd = mitigation_options[i].cmd; break; } if (i >= ARRAY_SIZE(mitigation_options)) { pr_err("unknown option (%s). Switching to AUTO select\n", arg); return SPECTRE_V2_CMD_AUTO; } if ((cmd == SPECTRE_V2_CMD_RETPOLINE || cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC || cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } if ((cmd == SPECTRE_V2_CMD_EIBRS || cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } if ((cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_LFENCE) && !boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { pr_err("%s selected, but CPU doesn't have a serializing LFENCE. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY)) { pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { pr_err("%s selected but not Intel CPU. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } if (cmd == SPECTRE_V2_CMD_IBRS && !boot_cpu_has(X86_FEATURE_IBRS)) { pr_err("%s selected but CPU doesn't have IBRS. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } if (cmd == SPECTRE_V2_CMD_IBRS && cpu_feature_enabled(X86_FEATURE_XENPV)) { pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } spec_v2_print_cond(mitigation_options[i].option, mitigation_options[i].secure); return cmd; } static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) { if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("Kernel not compiled with retpoline; no mitigation available!"); return SPECTRE_V2_NONE; } return SPECTRE_V2_RETPOLINE; } static bool __ro_after_init rrsba_disabled; /* Disable in-kernel use of non-RSB RET predictors */ static void __init spec_ctrl_disable_kernel_rrsba(void) { if (rrsba_disabled) return; if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) { rrsba_disabled = true; return; } if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) return; x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; update_spec_ctrl(x86_spec_ctrl_base); rrsba_disabled = true; } static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) { /* * Similar to context switches, there are two types of RSB attacks * after VM exit: * * 1) RSB underflow * * 2) Poisoned RSB entry * * When retpoline is enabled, both are mitigated by filling/clearing * the RSB. * * When IBRS is enabled, while #1 would be mitigated by the IBRS branch * prediction isolation protections, RSB still needs to be cleared * because of #2. Note that SMEP provides no protection here, unlike * user-space-poisoned RSB entries. * * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB * bug is present then a LITE version of RSB protection is required, * just a single call needs to retire before a RET is executed. */ switch (mode) { case SPECTRE_V2_NONE: return; case SPECTRE_V2_EIBRS_LFENCE: case SPECTRE_V2_EIBRS: if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE); pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n"); } return; case SPECTRE_V2_EIBRS_RETPOLINE: case SPECTRE_V2_RETPOLINE: case SPECTRE_V2_LFENCE: case SPECTRE_V2_IBRS: setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n"); return; } pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit"); dump_stack(); } /* * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by * branch history in userspace. Not needed if BHI_NO is set. */ static bool __init spec_ctrl_bhi_dis(void) { if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) return false; x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; update_spec_ctrl(x86_spec_ctrl_base); setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); return true; } enum bhi_mitigations { BHI_MITIGATION_OFF, BHI_MITIGATION_ON, BHI_MITIGATION_VMEXIT_ONLY, }; static enum bhi_mitigations bhi_mitigation __ro_after_init = IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF; static int __init spectre_bhi_parse_cmdline(char *str) { if (!str) return -EINVAL; if (!strcmp(str, "off")) bhi_mitigation = BHI_MITIGATION_OFF; else if (!strcmp(str, "on")) bhi_mitigation = BHI_MITIGATION_ON; else if (!strcmp(str, "vmexit")) bhi_mitigation = BHI_MITIGATION_VMEXIT_ONLY; else pr_err("Ignoring unknown spectre_bhi option (%s)", str); return 0; } early_param("spectre_bhi", spectre_bhi_parse_cmdline); static void __init bhi_select_mitigation(void) { if (bhi_mitigation == BHI_MITIGATION_OFF) return; /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ if (boot_cpu_has(X86_FEATURE_RETPOLINE) && !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { spec_ctrl_disable_kernel_rrsba(); if (rrsba_disabled) return; } /* Mitigate in hardware if supported */ if (spec_ctrl_bhi_dis()) return; if (!IS_ENABLED(CONFIG_X86_64)) return; if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) { pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n"); setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); return; } pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n"); setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); } static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; /* * If the CPU is not affected and the command line mode is NONE or AUTO * then nothing to do. */ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) return; switch (cmd) { case SPECTRE_V2_CMD_NONE: return; case SPECTRE_V2_CMD_FORCE: case SPECTRE_V2_CMD_AUTO: if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { mode = SPECTRE_V2_EIBRS; break; } if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) && boot_cpu_has_bug(X86_BUG_RETBLEED) && retbleed_cmd != RETBLEED_CMD_OFF && retbleed_cmd != RETBLEED_CMD_STUFF && boot_cpu_has(X86_FEATURE_IBRS) && boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { mode = SPECTRE_V2_IBRS; break; } mode = spectre_v2_select_retpoline(); break; case SPECTRE_V2_CMD_RETPOLINE_LFENCE: pr_err(SPECTRE_V2_LFENCE_MSG); mode = SPECTRE_V2_LFENCE; break; case SPECTRE_V2_CMD_RETPOLINE_GENERIC: mode = SPECTRE_V2_RETPOLINE; break; case SPECTRE_V2_CMD_RETPOLINE: mode = spectre_v2_select_retpoline(); break; case SPECTRE_V2_CMD_IBRS: mode = SPECTRE_V2_IBRS; break; case SPECTRE_V2_CMD_EIBRS: mode = SPECTRE_V2_EIBRS; break; case SPECTRE_V2_CMD_EIBRS_LFENCE: mode = SPECTRE_V2_EIBRS_LFENCE; break; case SPECTRE_V2_CMD_EIBRS_RETPOLINE: mode = SPECTRE_V2_EIBRS_RETPOLINE; break; } if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); if (spectre_v2_in_ibrs_mode(mode)) { if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) { msr_set_bit(MSR_EFER, _EFER_AUTOIBRS); } else { x86_spec_ctrl_base |= SPEC_CTRL_IBRS; update_spec_ctrl(x86_spec_ctrl_base); } } switch (mode) { case SPECTRE_V2_NONE: case SPECTRE_V2_EIBRS: break; case SPECTRE_V2_IBRS: setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS); if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) pr_warn(SPECTRE_V2_IBRS_PERF_MSG); break; case SPECTRE_V2_LFENCE: case SPECTRE_V2_EIBRS_LFENCE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); fallthrough; case SPECTRE_V2_RETPOLINE: case SPECTRE_V2_EIBRS_RETPOLINE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE); break; } /* * Disable alternate RSB predictions in kernel when indirect CALLs and * JMPs gets protection against BHI and Intramode-BTI, but RET * prediction from a non-RSB predictor is still a risk. */ if (mode == SPECTRE_V2_EIBRS_LFENCE || mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); if (boot_cpu_has(X86_BUG_BHI)) bhi_select_mitigation(); spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); /* * If Spectre v2 protection has been enabled, fill the RSB during a * context switch. In general there are two types of RSB attacks * across context switches, for which the CALLs/RETs may be unbalanced. * * 1) RSB underflow * * Some Intel parts have "bottomless RSB". When the RSB is empty, * speculated return targets may come from the branch predictor, * which could have a user-poisoned BTB or BHB entry. * * AMD has it even worse: *all* returns are speculated from the BTB, * regardless of the state of the RSB. * * When IBRS or eIBRS is enabled, the "user -> kernel" attack * scenario is mitigated by the IBRS branch prediction isolation * properties, so the RSB buffer filling wouldn't be necessary to * protect against this type of attack. * * The "user -> user" attack scenario is mitigated by RSB filling. * * 2) Poisoned RSB entry * * If the 'next' in-kernel return stack is shorter than 'prev', * 'next' could be tricked into speculating with a user-poisoned RSB * entry. * * The "user -> kernel" attack scenario is mitigated by SMEP and * eIBRS. * * The "user -> user" scenario, also known as SpectreBHB, requires * RSB clearing. * * So to mitigate all cases, unconditionally fill RSB on context * switches. * * FIXME: Is this pointless for retbleed-affected AMD? */ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); spectre_v2_determine_rsb_fill_type_at_vmexit(mode); /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around * firmware calls only when IBRS / Enhanced / Automatic IBRS aren't * otherwise enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ if (boot_cpu_has_bug(X86_BUG_RETBLEED) && boot_cpu_has(X86_FEATURE_IBPB) && (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) { if (retbleed_cmd != RETBLEED_CMD_IBPB) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW); pr_info("Enabling Speculation Barrier for firmware calls\n"); } } else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } /* Set up IBPB and STIBP depending on the general spectre V2 command */ spectre_v2_cmd = cmd; } static void update_stibp_msr(void * __unused) { u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP); update_spec_ctrl(val); } /* Update x86_spec_ctrl_base in case SMT state changed. */ static void update_stibp_strict(void) { u64 mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP; if (sched_smt_active()) mask |= SPEC_CTRL_STIBP; if (mask == x86_spec_ctrl_base) return; pr_info("Update user space SMT mitigation: STIBP %s\n", mask & SPEC_CTRL_STIBP ? "always-on" : "off"); x86_spec_ctrl_base = mask; on_each_cpu(update_stibp_msr, NULL, 1); } /* Update the static key controlling the evaluation of TIF_SPEC_IB */ static void update_indir_branch_cond(void) { if (sched_smt_active()) static_branch_enable(&switch_to_cond_stibp); else static_branch_disable(&switch_to_cond_stibp); } #undef pr_fmt #define pr_fmt(fmt) fmt /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. * * The other variants cannot be mitigated when SMT is enabled, so * clearing the buffers on idle just to prevent the Store Buffer * repartitioning leak would be a window dressing exercise. */ if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY)) return; if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); } } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" #define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" #define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); if (sched_smt_active() && unprivileged_ebpf_enabled() && spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; case SPECTRE_V2_USER_STRICT: case SPECTRE_V2_USER_STRICT_PREFERRED: update_stibp_strict(); break; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: update_indir_branch_cond(); break; } switch (mds_mitigation) { case MDS_MITIGATION_FULL: case MDS_MITIGATION_VMWERV: if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) pr_warn_once(MDS_MSG_SMT); update_mds_branch_idle(); break; case MDS_MITIGATION_OFF: break; } switch (taa_mitigation) { case TAA_MITIGATION_VERW: case TAA_MITIGATION_UCODE_NEEDED: if (sched_smt_active()) pr_warn_once(TAA_MSG_SMT); break; case TAA_MITIGATION_TSX_DISABLED: case TAA_MITIGATION_OFF: break; } switch (mmio_mitigation) { case MMIO_MITIGATION_VERW: case MMIO_MITIGATION_UCODE_NEEDED: if (sched_smt_active()) pr_warn_once(MMIO_MSG_SMT); break; case MMIO_MITIGATION_OFF: break; } mutex_unlock(&spec_ctrl_mutex); } #undef pr_fmt #define pr_fmt(fmt) "Speculative Store Bypass: " fmt static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE; /* The kernel command line selection */ enum ssb_mitigation_cmd { SPEC_STORE_BYPASS_CMD_NONE, SPEC_STORE_BYPASS_CMD_AUTO, SPEC_STORE_BYPASS_CMD_ON, SPEC_STORE_BYPASS_CMD_PRCTL, SPEC_STORE_BYPASS_CMD_SECCOMP, }; static const char * const ssb_strings[] = { [SPEC_STORE_BYPASS_NONE] = "Vulnerable", [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp", }; static const struct { const char *option; enum ssb_mitigation_cmd cmd; } ssb_mitigation_options[] __initconst = { { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */ { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */ }; static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) { enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO; char arg[20]; int ret, i; if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") || cpu_mitigations_off()) { return SPEC_STORE_BYPASS_CMD_NONE; } else { ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", arg, sizeof(arg)); if (ret < 0) return SPEC_STORE_BYPASS_CMD_AUTO; for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) { if (!match_option(arg, ret, ssb_mitigation_options[i].option)) continue; cmd = ssb_mitigation_options[i].cmd; break; } if (i >= ARRAY_SIZE(ssb_mitigation_options)) { pr_err("unknown option (%s). Switching to AUTO select\n", arg); return SPEC_STORE_BYPASS_CMD_AUTO; } } return cmd; } static enum ssb_mitigation __init __ssb_select_mitigation(void) { enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE; enum ssb_mitigation_cmd cmd; if (!boot_cpu_has(X86_FEATURE_SSBD)) return mode; cmd = ssb_parse_cmdline(); if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) && (cmd == SPEC_STORE_BYPASS_CMD_NONE || cmd == SPEC_STORE_BYPASS_CMD_AUTO)) return mode; switch (cmd) { case SPEC_STORE_BYPASS_CMD_SECCOMP: /* * Choose prctl+seccomp as the default mode if seccomp is * enabled. */ if (IS_ENABLED(CONFIG_SECCOMP)) mode = SPEC_STORE_BYPASS_SECCOMP; else mode = SPEC_STORE_BYPASS_PRCTL; break; case SPEC_STORE_BYPASS_CMD_ON: mode = SPEC_STORE_BYPASS_DISABLE; break; case SPEC_STORE_BYPASS_CMD_AUTO: case SPEC_STORE_BYPASS_CMD_PRCTL: mode = SPEC_STORE_BYPASS_PRCTL; break; case SPEC_STORE_BYPASS_CMD_NONE: break; } /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation */ if (mode == SPEC_STORE_BYPASS_DISABLE) { setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); /* * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may * use a completely different MSR and bit dependent on family. */ if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && !static_cpu_has(X86_FEATURE_AMD_SSBD)) { x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; update_spec_ctrl(x86_spec_ctrl_base); } } return mode; } static void ssb_select_mitigation(void) { ssb_mode = __ssb_select_mitigation(); if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) pr_info("%s\n", ssb_strings[ssb_mode]); } #undef pr_fmt #define pr_fmt(fmt) "Speculation prctl: " fmt static void task_update_spec_tif(struct task_struct *tsk) { /* Force the update of the real TIF bits */ set_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE); /* * Immediately update the speculation control MSRs for the current * task, but for a non-current task delay setting the CPU * mitigation until it is scheduled next. * * This can only happen for SECCOMP mitigation. For PRCTL it's * always the current task. */ if (tsk == current) speculation_ctrl_update_current(); } static int l1d_flush_prctl_set(struct task_struct *task, unsigned long ctrl) { if (!static_branch_unlikely(&switch_mm_cond_l1d_flush)) return -EPERM; switch (ctrl) { case PR_SPEC_ENABLE: set_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH); return 0; case PR_SPEC_DISABLE: clear_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH); return 0; default: return -ERANGE; } } static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) { if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && ssb_mode != SPEC_STORE_BYPASS_SECCOMP) return -ENXIO; switch (ctrl) { case PR_SPEC_ENABLE: /* If speculation is force disabled, enable is not allowed */ if (task_spec_ssb_force_disable(task)) return -EPERM; task_clear_spec_ssb_disable(task); task_clear_spec_ssb_noexec(task); task_update_spec_tif(task); break; case PR_SPEC_DISABLE: task_set_spec_ssb_disable(task); task_clear_spec_ssb_noexec(task); task_update_spec_tif(task); break; case PR_SPEC_FORCE_DISABLE: task_set_spec_ssb_disable(task); task_set_spec_ssb_force_disable(task); task_clear_spec_ssb_noexec(task); task_update_spec_tif(task); break; case PR_SPEC_DISABLE_NOEXEC: if (task_spec_ssb_force_disable(task)) return -EPERM; task_set_spec_ssb_disable(task); task_set_spec_ssb_noexec(task); task_update_spec_tif(task); break; default: return -ERANGE; } return 0; } static bool is_spec_ib_user_controlled(void) { return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP; } static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { case PR_SPEC_ENABLE: if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; /* * With strict mode for both IBPB and STIBP, the instruction * code paths avoid checking this task flag and instead, * unconditionally run the instruction. However, STIBP and IBPB * are independent and either can be set to conditionally * enabled regardless of the mode of the other. * * If either is set to conditional, allow the task flag to be * updated, unless it was force-disabled by a previous prctl * call. Currently, this is possible on an AMD CPU which has the * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the * kernel is booted with 'spectre_v2_user=seccomp', then * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED. */ if (!is_spec_ib_user_controlled() || task_spec_ib_force_disable(task)) return -EPERM; task_clear_spec_ib_disable(task); task_update_spec_tif(task); break; case PR_SPEC_DISABLE: case PR_SPEC_FORCE_DISABLE: /* * Indirect branch speculation is always allowed when * mitigation is force disabled. */ if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; if (!is_spec_ib_user_controlled()) return 0; task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); task_update_spec_tif(task); if (task == current) indirect_branch_prediction_barrier(); break; default: return -ERANGE; } return 0; } int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, unsigned long ctrl) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_set(task, ctrl); case PR_SPEC_INDIRECT_BRANCH: return ib_prctl_set(task, ctrl); case PR_SPEC_L1D_FLUSH: return l1d_flush_prctl_set(task, ctrl); default: return -ENODEV; } } #ifdef CONFIG_SECCOMP void arch_seccomp_spec_mitigate(struct task_struct *task) { if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); if (spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) ib_prctl_set(task, PR_SPEC_FORCE_DISABLE); } #endif static int l1d_flush_prctl_get(struct task_struct *task) { if (!static_branch_unlikely(&switch_mm_cond_l1d_flush)) return PR_SPEC_FORCE_DISABLE; if (test_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH)) return PR_SPEC_PRCTL | PR_SPEC_ENABLE; else return PR_SPEC_PRCTL | PR_SPEC_DISABLE; } static int ssb_prctl_get(struct task_struct *task) { switch (ssb_mode) { case SPEC_STORE_BYPASS_NONE: if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) return PR_SPEC_ENABLE; return PR_SPEC_NOT_AFFECTED; case SPEC_STORE_BYPASS_DISABLE: return PR_SPEC_DISABLE; case SPEC_STORE_BYPASS_SECCOMP: case SPEC_STORE_BYPASS_PRCTL: if (task_spec_ssb_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ssb_noexec(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE_NOEXEC; if (task_spec_ssb_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; } BUG(); } static int ib_prctl_get(struct task_struct *task) { if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return PR_SPEC_NOT_AFFECTED; if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; else if (is_spec_ib_user_controlled()) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) return PR_SPEC_DISABLE; else return PR_SPEC_NOT_AFFECTED; } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_get(task); case PR_SPEC_INDIRECT_BRANCH: return ib_prctl_get(task); case PR_SPEC_L1D_FLUSH: return l1d_flush_prctl_get(task); default: return -ENODEV; } } void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) update_spec_ctrl(x86_spec_ctrl_base); if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) x86_amd_ssb_disable(); } bool itlb_multihit_kvm_mitigation; EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt /* Default mitigation for L1TF-affected CPUs */ enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH; #if IS_ENABLED(CONFIG_KVM_INTEL) EXPORT_SYMBOL_GPL(l1tf_mitigation); #endif enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); /* * These CPUs all support 44bits physical address space internally in the * cache but CPUID can report a smaller number of physical address bits. * * The L1TF mitigation uses the top most address bit for the inversion of * non present PTEs. When the installed memory reaches into the top most * address bit due to memory holes, which has been observed on machines * which report 36bits physical address bits and have 32G RAM installed, * then the mitigation range check in l1tf_select_mitigation() triggers. * This is a false positive because the mitigation is still possible due to * the fact that the cache uses 44bit internally. Use the cache bits * instead of the reported physical bits and adjust them on the affected * machines to 44bit if the reported bits are less than 44. */ static void override_cache_bits(struct cpuinfo_x86 *c) { if (c->x86 != 6) return; switch (c->x86_vfm) { case INTEL_NEHALEM: case INTEL_WESTMERE: case INTEL_SANDYBRIDGE: case INTEL_IVYBRIDGE: case INTEL_HASWELL: case INTEL_HASWELL_L: case INTEL_HASWELL_G: case INTEL_BROADWELL: case INTEL_BROADWELL_G: case INTEL_SKYLAKE_L: case INTEL_SKYLAKE: case INTEL_KABYLAKE_L: case INTEL_KABYLAKE: if (c->x86_cache_bits < 44) c->x86_cache_bits = 44; break; } } static void __init l1tf_select_mitigation(void) { u64 half_pa; if (!boot_cpu_has_bug(X86_BUG_L1TF)) return; if (cpu_mitigations_off()) l1tf_mitigation = L1TF_MITIGATION_OFF; else if (cpu_mitigations_auto_nosmt()) l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; override_cache_bits(&boot_cpu_data); switch (l1tf_mitigation) { case L1TF_MITIGATION_OFF: case L1TF_MITIGATION_FLUSH_NOWARN: case L1TF_MITIGATION_FLUSH: break; case L1TF_MITIGATION_FLUSH_NOSMT: case L1TF_MITIGATION_FULL: cpu_smt_disable(false); break; case L1TF_MITIGATION_FULL_FORCE: cpu_smt_disable(true); break; } #if CONFIG_PGTABLE_LEVELS == 2 pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n"); return; #endif half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; if (l1tf_mitigation != L1TF_MITIGATION_OFF && e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) { pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n", half_pa); pr_info("However, doing so will make a part of your RAM unusable.\n"); pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html might help you decide.\n"); return; } setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV); } static int __init l1tf_cmdline(char *str) { if (!boot_cpu_has_bug(X86_BUG_L1TF)) return 0; if (!str) return -EINVAL; if (!strcmp(str, "off")) l1tf_mitigation = L1TF_MITIGATION_OFF; else if (!strcmp(str, "flush,nowarn")) l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN; else if (!strcmp(str, "flush")) l1tf_mitigation = L1TF_MITIGATION_FLUSH; else if (!strcmp(str, "flush,nosmt")) l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; else if (!strcmp(str, "full")) l1tf_mitigation = L1TF_MITIGATION_FULL; else if (!strcmp(str, "full,force")) l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE; return 0; } early_param("l1tf", l1tf_cmdline); #undef pr_fmt #define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt enum srso_mitigation { SRSO_MITIGATION_NONE, SRSO_MITIGATION_UCODE_NEEDED, SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED, SRSO_MITIGATION_MICROCODE, SRSO_MITIGATION_SAFE_RET, SRSO_MITIGATION_IBPB, SRSO_MITIGATION_IBPB_ON_VMEXIT, }; enum srso_mitigation_cmd { SRSO_CMD_OFF, SRSO_CMD_MICROCODE, SRSO_CMD_SAFE_RET, SRSO_CMD_IBPB, SRSO_CMD_IBPB_ON_VMEXIT, }; static const char * const srso_strings[] = { [SRSO_MITIGATION_NONE] = "Vulnerable", [SRSO_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", [SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED] = "Vulnerable: Safe RET, no microcode", [SRSO_MITIGATION_MICROCODE] = "Vulnerable: Microcode, no safe RET", [SRSO_MITIGATION_SAFE_RET] = "Mitigation: Safe RET", [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET; static int __init srso_parse_cmdline(char *str) { if (!str) return -EINVAL; if (!strcmp(str, "off")) srso_cmd = SRSO_CMD_OFF; else if (!strcmp(str, "microcode")) srso_cmd = SRSO_CMD_MICROCODE; else if (!strcmp(str, "safe-ret")) srso_cmd = SRSO_CMD_SAFE_RET; else if (!strcmp(str, "ibpb")) srso_cmd = SRSO_CMD_IBPB; else if (!strcmp(str, "ibpb-vmexit")) srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT; else pr_err("Ignoring unknown SRSO option (%s).", str); return 0; } early_param("spec_rstack_overflow", srso_parse_cmdline); #define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options." static void __init srso_select_mitigation(void) { bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE); if (cpu_mitigations_off()) return; if (!boot_cpu_has_bug(X86_BUG_SRSO)) { if (boot_cpu_has(X86_FEATURE_SBPB)) x86_pred_cmd = PRED_CMD_SBPB; return; } if (has_microcode) { /* * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. * * Zen1/2 don't have SBPB, no need to try to enable it here. */ if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) { setup_force_cpu_cap(X86_FEATURE_SRSO_NO); return; } if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { srso_mitigation = SRSO_MITIGATION_IBPB; goto out; } } else { pr_warn("IBPB-extending microcode not applied!\n"); pr_warn(SRSO_NOTICE); /* may be overwritten by SRSO_CMD_SAFE_RET below */ srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED; } switch (srso_cmd) { case SRSO_CMD_OFF: if (boot_cpu_has(X86_FEATURE_SBPB)) x86_pred_cmd = PRED_CMD_SBPB; return; case SRSO_CMD_MICROCODE: if (has_microcode) { srso_mitigation = SRSO_MITIGATION_MICROCODE; pr_warn(SRSO_NOTICE); } break; case SRSO_CMD_SAFE_RET: if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { /* * Enable the return thunk for generated code * like ftrace, static_call, etc. */ setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); x86_return_thunk = srso_alias_return_thunk; } else { setup_force_cpu_cap(X86_FEATURE_SRSO); x86_return_thunk = srso_return_thunk; } if (has_microcode) srso_mitigation = SRSO_MITIGATION_SAFE_RET; else srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED; } else { pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); } break; case SRSO_CMD_IBPB: if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); srso_mitigation = SRSO_MITIGATION_IBPB; } } else { pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); } break; case SRSO_CMD_IBPB_ON_VMEXIT: if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; } } else { pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); } break; } out: pr_info("%s\n", srso_strings[srso_mitigation]); } #undef pr_fmt #define pr_fmt(fmt) fmt #ifdef CONFIG_SYSFS #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" #if IS_ENABLED(CONFIG_KVM_INTEL) static const char * const l1tf_vmx_states[] = { [VMENTER_L1D_FLUSH_AUTO] = "auto", [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", [VMENTER_L1D_FLUSH_ALWAYS] = "cache flushes", [VMENTER_L1D_FLUSH_EPT_DISABLED] = "EPT disabled", [VMENTER_L1D_FLUSH_NOT_REQUIRED] = "flush not necessary" }; static ssize_t l1tf_show_state(char *buf) { if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && sched_smt_active())) { return sysfs_emit(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, l1tf_vmx_states[l1tf_vmx_mitigation]); } return sysfs_emit(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t itlb_multihit_show_state(char *buf) { if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || !boot_cpu_has(X86_FEATURE_VMX)) return sysfs_emit(buf, "KVM: Mitigation: VMX unsupported\n"); else if (!(cr4_read_shadow() & X86_CR4_VMXE)) return sysfs_emit(buf, "KVM: Mitigation: VMX disabled\n"); else if (itlb_multihit_kvm_mitigation) return sysfs_emit(buf, "KVM: Mitigation: Split huge pages\n"); else return sysfs_emit(buf, "KVM: Vulnerable\n"); } #else static ssize_t l1tf_show_state(char *buf) { return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); } static ssize_t itlb_multihit_show_state(char *buf) { return sysfs_emit(buf, "Processor vulnerable\n"); } #endif static ssize_t mds_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { return sysfs_emit(buf, "%s; SMT Host state unknown\n", mds_strings[mds_mitigation]); } if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : sched_smt_active() ? "mitigated" : "disabled")); } return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t tsx_async_abort_show_state(char *buf) { if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || (taa_mitigation == TAA_MITIGATION_OFF)) return sysfs_emit(buf, "%s\n", taa_strings[taa_mitigation]); if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { return sysfs_emit(buf, "%s; SMT Host state unknown\n", taa_strings[taa_mitigation]); } return sysfs_emit(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t mmio_stale_data_show_state(char *buf) { if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) return sysfs_emit(buf, "Unknown: No mitigations\n"); if (mmio_mitigation == MMIO_MITIGATION_OFF) return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]); if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { return sysfs_emit(buf, "%s; SMT Host state unknown\n", mmio_strings[mmio_mitigation]); } return sysfs_emit(buf, "%s; SMT %s\n", mmio_strings[mmio_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t rfds_show_state(char *buf) { return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); } static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && !boot_cpu_has(X86_FEATURE_AUTOIBRS)) return ""; switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) return "; STIBP: conditional"; } return ""; } static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) return "; IBPB: conditional"; return "; IBPB: disabled"; } return ""; } static char *pbrsb_eibrs_state(void) { if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) return "; PBRSB-eIBRS: SW sequence"; else return "; PBRSB-eIBRS: Vulnerable"; } else { return "; PBRSB-eIBRS: Not affected"; } } static const char *spectre_bhi_state(void) { if (!boot_cpu_has_bug(X86_BUG_BHI)) return "; BHI: Not affected"; else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) return "; BHI: BHI_DIS_S"; else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) return "; BHI: SW loop, KVM: SW loop"; else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && rrsba_disabled) return "; BHI: Retpoline"; else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) return "; BHI: Vulnerable, KVM: SW loop"; return "; BHI: Vulnerable"; } static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) return sysfs_emit(buf, "Vulnerable: LFENCE\n"); if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) return sysfs_emit(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); if (sched_smt_active() && unprivileged_ebpf_enabled() && spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", stibp_state(), boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", pbrsb_eibrs_state(), spectre_bhi_state(), /* this should always be at the end */ spectre_v2_module_string()); } static ssize_t srbds_show_state(char *buf) { return sysfs_emit(buf, "%s\n", srbds_strings[srbds_mitigation]); } static ssize_t retbleed_show_state(char *buf) { if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) return sysfs_emit(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); return sysfs_emit(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], !sched_smt_active() ? "disabled" : spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? "enabled with STIBP protection" : "vulnerable"); } return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } static ssize_t srso_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_SRSO_NO)) return sysfs_emit(buf, "Mitigation: SMT disabled\n"); return sysfs_emit(buf, "%s\n", srso_strings[srso_mitigation]); } static ssize_t gds_show_state(char *buf) { return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); } static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { if (!boot_cpu_has_bug(bug)) return sysfs_emit(buf, "Not affected\n"); switch (bug) { case X86_BUG_CPU_MELTDOWN: if (boot_cpu_has(X86_FEATURE_PTI)) return sysfs_emit(buf, "Mitigation: PTI\n"); if (hypervisor_is_type(X86_HYPER_XEN_PV)) return sysfs_emit(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); break; case X86_BUG_SPECTRE_V1: return sysfs_emit(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: return sysfs_emit(buf, "%s\n", ssb_strings[ssb_mode]); case X86_BUG_L1TF: if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) return l1tf_show_state(buf); break; case X86_BUG_MDS: return mds_show_state(buf); case X86_BUG_TAA: return tsx_async_abort_show_state(buf); case X86_BUG_ITLB_MULTIHIT: return itlb_multihit_show_state(buf); case X86_BUG_SRBDS: return srbds_show_state(buf); case X86_BUG_MMIO_STALE_DATA: case X86_BUG_MMIO_UNKNOWN: return mmio_stale_data_show_state(buf); case X86_BUG_RETBLEED: return retbleed_show_state(buf); case X86_BUG_SRSO: return srso_show_state(buf); case X86_BUG_GDS: return gds_show_state(buf); case X86_BUG_RFDS: return rfds_show_state(buf); default: break; } return sysfs_emit(buf, "Vulnerable\n"); } ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN); } ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1); } ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); } ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); } ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_TAA); } ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); } ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS); } ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf) { if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN); else return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); } ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_SRSO); } ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_GDS); } ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) { return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } #endif void __warn_thunk(void) { WARN_ONCE(1, "Unpatched return thunk in use. This should not happen!\n"); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Media device * * Copyright (C) 2010 Nokia Corporation * * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com> * Sakari Ailus <sakari.ailus@iki.fi> */ #ifndef _MEDIA_DEVICE_H #define _MEDIA_DEVICE_H #include <linux/list.h> #include <linux/mutex.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <media/media-devnode.h> #include <media/media-entity.h> struct ida; struct media_device; /** * struct media_entity_notify - Media Entity Notify * * @list: List head * @notify_data: Input data to invoke the callback * @notify: Callback function pointer * * Drivers may register a callback to take action when new entities get * registered with the media device. This handler is intended for creating * links between existing entities and should not create entities and register * them. */ struct media_entity_notify { struct list_head list; void *notify_data; void (*notify)(struct media_entity *entity, void *notify_data); }; /** * struct media_device_ops - Media device operations * @link_notify: Link state change notification callback. This callback is * called with the graph_mutex held. * @req_alloc: Allocate a request. Set this if you need to allocate a struct * larger then struct media_request. @req_alloc and @req_free must * either both be set or both be NULL. * @req_free: Free a request. Set this if @req_alloc was set as well, leave * to NULL otherwise. * @req_validate: Validate a request, but do not queue yet. The req_queue_mutex * lock is held when this op is called. * @req_queue: Queue a validated request, cannot fail. If something goes * wrong when queueing this request then it should be marked * as such internally in the driver and any related buffers * must eventually return to vb2 with state VB2_BUF_STATE_ERROR. * The req_queue_mutex lock is held when this op is called. * It is important that vb2 buffer objects are queued last after * all other object types are queued: queueing a buffer kickstarts * the request processing, so all other objects related to the * request (and thus the buffer) must be available to the driver. * And once a buffer is queued, then the driver can complete * or delete objects from the request before req_queue exits. */ struct media_device_ops { int (*link_notify)(struct media_link *link, u32 flags, unsigned int notification); struct media_request *(*req_alloc)(struct media_device *mdev); void (*req_free)(struct media_request *req); int (*req_validate)(struct media_request *req); void (*req_queue)(struct media_request *req); }; /** * struct media_device - Media device * @dev: Parent device * @devnode: Media device node * @driver_name: Optional device driver name. If not set, calls to * %MEDIA_IOC_DEVICE_INFO will return ``dev->driver->name``. * This is needed for USB drivers for example, as otherwise * they'll all appear as if the driver name was "usb". * @model: Device model name * @serial: Device serial number (optional) * @bus_info: Unique and stable device location identifier * @hw_revision: Hardware device revision * @topology_version: Monotonic counter for storing the version of the graph * topology. Should be incremented each time the topology changes. * @id: Unique ID used on the last registered graph object * @entity_internal_idx: Unique internal entity ID used by the graph traversal * algorithms * @entity_internal_idx_max: Allocated internal entity indices * @entities: List of registered entities * @interfaces: List of registered interfaces * @pads: List of registered pads * @links: List of registered links * @entity_notify: List of registered entity_notify callbacks * @graph_mutex: Protects access to struct media_device data * @pm_count_walk: Graph walk for power state walk. Access serialised using * graph_mutex. * * @source_priv: Driver Private data for enable/disable source handlers * @enable_source: Enable Source Handler function pointer * @disable_source: Disable Source Handler function pointer * * @ops: Operation handler callbacks * @req_queue_mutex: Serialise the MEDIA_REQUEST_IOC_QUEUE ioctl w.r.t. * other operations that stop or start streaming. * @request_id: Used to generate unique request IDs * * This structure represents an abstract high-level media device. It allows easy * access to entities and provides basic media device-level support. The * structure can be allocated directly or embedded in a larger structure. * * The parent @dev is a physical device. It must be set before registering the * media device. * * @model is a descriptive model name exported through sysfs. It doesn't have to * be unique. * * @enable_source is a handler to find source entity for the * sink entity and activate the link between them if source * entity is free. Drivers should call this handler before * accessing the source. * * @disable_source is a handler to find source entity for the * sink entity and deactivate the link between them. Drivers * should call this handler to release the source. * * Use-case: find tuner entity connected to the decoder * entity and check if it is available, and activate the * link between them from @enable_source and deactivate * from @disable_source. * * .. note:: * * Bridge driver is expected to implement and set the * handler when &media_device is registered or when * bridge driver finds the media_device during probe. * Bridge driver sets source_priv with information * necessary to run @enable_source and @disable_source handlers. * Callers should hold graph_mutex to access and call @enable_source * and @disable_source handlers. */ struct media_device { /* dev->driver_data points to this struct. */ struct device *dev; struct media_devnode *devnode; char model[32]; char driver_name[32]; char serial[40]; char bus_info[32]; u32 hw_revision; u64 topology_version; u32 id; struct ida entity_internal_idx; int entity_internal_idx_max; struct list_head entities; struct list_head interfaces; struct list_head pads; struct list_head links; /* notify callback list invoked when a new entity is registered */ struct list_head entity_notify; /* Serializes graph operations. */ struct mutex graph_mutex; struct media_graph pm_count_walk; void *source_priv; int (*enable_source)(struct media_entity *entity, struct media_pipeline *pipe); void (*disable_source)(struct media_entity *entity); const struct media_device_ops *ops; struct mutex req_queue_mutex; atomic_t request_id; }; /* We don't need to include usb.h here */ struct usb_device; #ifdef CONFIG_MEDIA_CONTROLLER /* Supported link_notify @notification values. */ #define MEDIA_DEV_NOTIFY_PRE_LINK_CH 0 #define MEDIA_DEV_NOTIFY_POST_LINK_CH 1 /** * media_device_init() - Initializes a media device element * * @mdev: pointer to struct &media_device * * This function initializes the media device prior to its registration. * The media device initialization and registration is split in two functions * to avoid race conditions and make the media device available to user-space * before the media graph has been completed. * * So drivers need to first initialize the media device, register any entity * within the media device, create pad to pad links and then finally register * the media device by calling media_device_register() as a final step. * * The caller is responsible for initializing the media device before * registration. The following fields must be set: * * - dev must point to the parent device * - model must be filled with the device model name * * The bus_info field is set by media_device_init() for PCI and platform devices * if the field begins with '\0'. */ void media_device_init(struct media_device *mdev); /** * media_device_cleanup() - Cleanups a media device element * * @mdev: pointer to struct &media_device * * This function that will destroy the graph_mutex that is * initialized in media_device_init(). */ void media_device_cleanup(struct media_device *mdev); /** * __media_device_register() - Registers a media device element * * @mdev: pointer to struct &media_device * @owner: should be filled with %THIS_MODULE * * Users, should, instead, call the media_device_register() macro. * * The caller is responsible for initializing the &media_device structure * before registration. The following fields of &media_device must be set: * * - &media_device.model must be filled with the device model name as a * NUL-terminated UTF-8 string. The device/model revision must not be * stored in this field. * * The following fields are optional: * * - &media_device.serial is a unique serial number stored as a * NUL-terminated ASCII string. The field is big enough to store a GUID * in text form. If the hardware doesn't provide a unique serial number * this field must be left empty. * * - &media_device.bus_info represents the location of the device in the * system as a NUL-terminated ASCII string. For PCI/PCIe devices * &media_device.bus_info must be set to "PCI:" (or "PCIe:") followed by * the value of pci_name(). For USB devices,the usb_make_path() function * must be used. This field is used by applications to distinguish between * otherwise identical devices that don't provide a serial number. * * - &media_device.hw_revision is the hardware device revision in a * driver-specific format. When possible the revision should be formatted * with the KERNEL_VERSION() macro. * * .. note:: * * #) Upon successful registration a character device named media[0-9]+ is created. The device major and minor numbers are dynamic. The model name is exported as a sysfs attribute. * * #) Unregistering a media device that hasn't been registered is **NOT** safe. * * Return: returns zero on success or a negative error code. */ int __must_check __media_device_register(struct media_device *mdev, struct module *owner); /** * media_device_register() - Registers a media device element * * @mdev: pointer to struct &media_device * * This macro calls __media_device_register() passing %THIS_MODULE as * the __media_device_register() second argument (**owner**). */ #define media_device_register(mdev) __media_device_register(mdev, THIS_MODULE) /** * media_device_unregister() - Unregisters a media device element * * @mdev: pointer to struct &media_device * * It is safe to call this function on an unregistered (but initialised) * media device. */ void media_device_unregister(struct media_device *mdev); /** * media_device_register_entity() - registers a media entity inside a * previously registered media device. * * @mdev: pointer to struct &media_device * @entity: pointer to struct &media_entity to be registered * * Entities are identified by a unique positive integer ID. The media * controller framework will such ID automatically. IDs are not guaranteed * to be contiguous, and the ID number can change on newer Kernel versions. * So, neither the driver nor userspace should hardcode ID numbers to refer * to the entities, but, instead, use the framework to find the ID, when * needed. * * The media_entity name, type and flags fields should be initialized before * calling media_device_register_entity(). Entities embedded in higher-level * standard structures can have some of those fields set by the higher-level * framework. * * If the device has pads, media_entity_pads_init() should be called before * this function. Otherwise, the &media_entity.pad and &media_entity.num_pads * should be zeroed before calling this function. * * Entities have flags that describe the entity capabilities and state: * * %MEDIA_ENT_FL_DEFAULT * indicates the default entity for a given type. * This can be used to report the default audio and video devices or the * default camera sensor. * * .. note:: * * Drivers should set the entity function before calling this function. * Please notice that the values %MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN and * %MEDIA_ENT_F_UNKNOWN should not be used by the drivers. */ int __must_check media_device_register_entity(struct media_device *mdev, struct media_entity *entity); /** * media_device_unregister_entity() - unregisters a media entity. * * @entity: pointer to struct &media_entity to be unregistered * * All links associated with the entity and all PADs are automatically * unregistered from the media_device when this function is called. * * Unregistering an entity will not change the IDs of the other entities and * the previoully used ID will never be reused for a newly registered entities. * * When a media device is unregistered, all its entities are unregistered * automatically. No manual entities unregistration is then required. * * .. note:: * * The media_entity instance itself must be freed explicitly by * the driver if required. */ void media_device_unregister_entity(struct media_entity *entity); /** * media_device_register_entity_notify() - Registers a media entity_notify * callback * * @mdev: The media device * @nptr: The media_entity_notify * * .. note:: * * When a new entity is registered, all the registered * media_entity_notify callbacks are invoked. */ void media_device_register_entity_notify(struct media_device *mdev, struct media_entity_notify *nptr); /** * media_device_unregister_entity_notify() - Unregister a media entity notify * callback * * @mdev: The media device * @nptr: The media_entity_notify * */ void media_device_unregister_entity_notify(struct media_device *mdev, struct media_entity_notify *nptr); /* Iterate over all entities. */ #define media_device_for_each_entity(entity, mdev) \ list_for_each_entry(entity, &(mdev)->entities, graph_obj.list) /* Iterate over all interfaces. */ #define media_device_for_each_intf(intf, mdev) \ list_for_each_entry(intf, &(mdev)->interfaces, graph_obj.list) /* Iterate over all pads. */ #define media_device_for_each_pad(pad, mdev) \ list_for_each_entry(pad, &(mdev)->pads, graph_obj.list) /* Iterate over all links. */ #define media_device_for_each_link(link, mdev) \ list_for_each_entry(link, &(mdev)->links, graph_obj.list) /** * media_device_pci_init() - create and initialize a * struct &media_device from a PCI device. * * @mdev: pointer to struct &media_device * @pci_dev: pointer to struct pci_dev * @name: media device name. If %NULL, the routine will use the default * name for the pci device, given by pci_name() macro. */ void media_device_pci_init(struct media_device *mdev, struct pci_dev *pci_dev, const char *name); /** * __media_device_usb_init() - create and initialize a * struct &media_device from a PCI device. * * @mdev: pointer to struct &media_device * @udev: pointer to struct usb_device * @board_name: media device name. If %NULL, the routine will use the usb * product name, if available. * @driver_name: name of the driver. if %NULL, the routine will use the name * given by ``udev->dev->driver->name``, with is usually the wrong * thing to do. * * .. note:: * * It is better to call media_device_usb_init() instead, as * such macro fills driver_name with %KBUILD_MODNAME. */ void __media_device_usb_init(struct media_device *mdev, struct usb_device *udev, const char *board_name, const char *driver_name); #else static inline void media_device_init(struct media_device *mdev) { } static inline int media_device_register(struct media_device *mdev) { return 0; } static inline void media_device_unregister(struct media_device *mdev) { } static inline void media_device_cleanup(struct media_device *mdev) { } static inline int media_device_register_entity(struct media_device *mdev, struct media_entity *entity) { return 0; } static inline void media_device_unregister_entity(struct media_entity *entity) { } static inline void media_device_register_entity_notify( struct media_device *mdev, struct media_entity_notify *nptr) { } static inline void media_device_unregister_entity_notify( struct media_device *mdev, struct media_entity_notify *nptr) { } static inline void media_device_pci_init(struct media_device *mdev, struct pci_dev *pci_dev, char *name) { } static inline void __media_device_usb_init(struct media_device *mdev, struct usb_device *udev, char *board_name, char *driver_name) { } #endif /* CONFIG_MEDIA_CONTROLLER */ /** * media_device_usb_init() - create and initialize a * struct &media_device from a PCI device. * * @mdev: pointer to struct &media_device * @udev: pointer to struct usb_device * @name: media device name. If %NULL, the routine will use the usb * product name, if available. * * This macro calls media_device_usb_init() passing the * media_device_usb_init() **driver_name** parameter filled with * %KBUILD_MODNAME. */ #define media_device_usb_init(mdev, udev, name) \ __media_device_usb_init(mdev, udev, name, KBUILD_MODNAME) /** * media_set_bus_info() - Set bus_info field * * @bus_info: Variable where to write the bus info (char array) * @bus_info_size: Length of the bus_info * @dev: Related struct device * * Sets bus information based on &dev. This is currently done for PCI and * platform devices. dev is required to be non-NULL for this to happen. * * This function is not meant to be called from drivers. */ static inline void media_set_bus_info(char *bus_info, size_t bus_info_size, struct device *dev) { if (!dev) strscpy(bus_info, "no bus info", bus_info_size); else if (dev_is_platform(dev)) snprintf(bus_info, bus_info_size, "platform:%s", dev_name(dev)); else if (dev_is_pci(dev)) snprintf(bus_info, bus_info_size, "PCI:%s", dev_name(dev)); } #endif |
| 1 20 15 1 1 14 1 1 1 1 1 1 1 1 1 1 1 1 1 9 7 4 3 1 2 3 3 1 1 1 6 6 2 1 8 1 2 2 3 2 3 4 7 1 1 5 3 1 1 1 6 1 2 3 6 1 2 1 2 6 1 2 1 2 4 1 2 1 2 1 1 2 5 2 2 11 1 2 8 2 7 1 2 1 3 1 7 1 2 4 2 14 3 3 3 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 2 14 14 1 13 1 13 14 4 15 3 1 2 2 1 3 3 3 3 3 3 7 4 4 2 5 2 8 3 2 1 1 1 2 1 1 136 135 142 24 16 15 1 1 15 1 15 1 14 2 15 1 15 1 15 1 15 1 16 15 1 7 1 1 1 1 3 2 3 3 3 3 3 3 1 1 1 1 1 1 13 13 2 9 2 11 3 3 2 3 13 13 13 13 24 5 1 1 17 17 15 13 1 16 1 1 14 2 2 9 1 14 2 11 13 2 11 47 2 40 5 35 1 9 2 7 43 1 38 3 39 16 34 34 34 34 33 31 1 137 24 135 1 1 1 3 3 2 5 3 2 1 1 134 1106 1100 10 4 4 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 | // 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 <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 struct macsec_rx_sa *macsec_active_rxsa_get(struct macsec_rx_sc *rx_sc) { struct macsec_rx_sa *sa = NULL; int an; for (an = 0; an < MACSEC_NUM_AN; an++) { sa = macsec_rxsa_get(rx_sc->sa[an]); if (sa) break; } 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_frame_sci(struct macsec_eth_header *hdr, bool sci_present) { sci_t sci; if (sci_present) memcpy(&sci, hdr->secure_channel_id, sizeof(hdr->secure_channel_id)); 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; 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; sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci); rcu_read_lock(); rxd = macsec_data_rcu(skb->dev); 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 */ struct macsec_rx_sa *active_rx_sa = macsec_active_rxsa_get(rx_sc); 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); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); 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); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsUnusedSA); 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); 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(sizeof(*rx_sc), GFP_KERNEL); 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); if (*assoc_num >= MACSEC_NUM_AN) return ERR_PTR(-EINVAL); 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]); if (*assoc_num >= MACSEC_NUM_AN) return ERR_PTR(-EINVAL); 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] = { .type = NLA_U8 }, }; static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = { [MACSEC_SA_ATTR_AN] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_ACTIVE] = { .type = NLA_U8 }, [MACSEC_SA_ATTR_PN] = NLA_POLICY_MIN_LEN(4), [MACSEC_SA_ATTR_KEYID] = { .type = NLA_BINARY, .len = MACSEC_KEYID_LEN, }, [MACSEC_SA_ATTR_KEY] = { .type = NLA_BINARY, .len = MACSEC_MAX_KEY_LEN, }, [MACSEC_SA_ATTR_SSCI] = { .type = NLA_U32 }, [MACSEC_SA_ATTR_SALT] = { .type = NLA_BINARY, .len = MACSEC_SALT_LEN, }, }; static const struct nla_policy macsec_genl_offload_policy[NUM_MACSEC_OFFLOAD_ATTR] = { [MACSEC_OFFLOAD_ATTR_TYPE] = { .type = NLA_U8 }, }; /* 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; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) 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; } if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) { pr_notice("macsec: nl: add_rxsa: bad salt length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_SALT]), MACSEC_SALT_LEN); rtnl_unlock(); return -EINVAL; } } rx_sa = rtnl_dereference(rx_sc->sa[assoc_num]); if (rx_sa) { rtnl_unlock(); return -EBUSY; } rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); 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_u64(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 bool validate_add_rxsc(struct nlattr **attrs) { if (!attrs[MACSEC_RXSC_ATTR_SCI]) return false; if (attrs[MACSEC_RXSC_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_RXSC_ATTR_ACTIVE]) > 1) return false; } return true; } 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 (!validate_add_rxsc(tb_rxsc)) 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; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) return false; } if (nla_len(attrs[MACSEC_SA_ATTR_KEYID]) != MACSEC_KEYID_LEN) 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; } if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) { pr_notice("macsec: nl: add_txsa: bad salt length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_SALT]), MACSEC_SALT_LEN); rtnl_unlock(); return -EINVAL; } } tx_sa = rtnl_dereference(tx_sc->sa[assoc_num]); if (tx_sa) { rtnl_unlock(); return -EBUSY; } tx_sa = kmalloc(sizeof(*tx_sa), GFP_KERNEL); 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_u64(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; if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN) return false; if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0) return false; if (attrs[MACSEC_SA_ATTR_ACTIVE]) { if (nla_get_u8(attrs[MACSEC_SA_ATTR_ACTIVE]) > 1) 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_u64(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_u64(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 (!validate_add_rxsc(tb_rxsc)) 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 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); 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); memcpy(&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); memcpy(&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); memcpy(&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) 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; dev->features = real_dev->features & MACSEC_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; 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; features &= (real_dev->features & MACSEC_FEATURES) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; features |= NETIF_F_LLTX; 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 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] = { .type = NLA_U8 }, [IFLA_MACSEC_CIPHER_SUITE] = { .type = NLA_U64 }, [IFLA_MACSEC_WINDOW] = { .type = NLA_U32 }, [IFLA_MACSEC_ENCODING_SA] = { .type = NLA_U8 }, [IFLA_MACSEC_ENCRYPT] = { .type = NLA_U8 }, [IFLA_MACSEC_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_INC_SCI] = { .type = NLA_U8 }, [IFLA_MACSEC_ES] = { .type = NLA_U8 }, [IFLA_MACSEC_SCB] = { .type = NLA_U8 }, [IFLA_MACSEC_REPLAY_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_VALIDATION] = { .type = NLA_U8 }, [IFLA_MACSEC_OFFLOAD] = { .type = NLA_U8 }, }; static void macsec_free_netdev(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); if (macsec->secy.tx_sc.md_dst) metadata_dst_free(macsec->secy.tx_sc.md_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; 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(sizeof(*rxd), GFP_KERNEL); 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 *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); 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(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; 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 macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u64 csid = MACSEC_DEFAULT_CIPHER_ID; u8 icv_len = MACSEC_DEFAULT_ICV_LEN; int flag; bool es, scb, sci; if (!data) return 0; if (data[IFLA_MACSEC_CIPHER_SUITE]) csid = nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE]); 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); } } switch (csid) { 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: if (icv_len < MACSEC_MIN_ICV_LEN || icv_len > MACSEC_STD_ICV_LEN) return -EINVAL; break; default: return -EINVAL; } if (data[IFLA_MACSEC_ENCODING_SA]) { if (nla_get_u8(data[IFLA_MACSEC_ENCODING_SA]) >= MACSEC_NUM_AN) return -EINVAL; } for (flag = IFLA_MACSEC_ENCODING_SA + 1; flag < IFLA_MACSEC_VALIDATION; flag++) { if (data[flag]) { if (nla_get_u8(data[flag]) > 1) return -EINVAL; } } es = data[IFLA_MACSEC_ES] ? nla_get_u8(data[IFLA_MACSEC_ES]) : false; sci = data[IFLA_MACSEC_INC_SCI] ? nla_get_u8(data[IFLA_MACSEC_INC_SCI]) : false; scb = data[IFLA_MACSEC_SCB] ? nla_get_u8(data[IFLA_MACSEC_SCB]) : false; if ((sci && (scb || es)) || (scb && es)) return -EINVAL; if (data[IFLA_MACSEC_VALIDATION] && nla_get_u8(data[IFLA_MACSEC_VALIDATION]) > MACSEC_VALIDATE_MAX) 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); LIST_HEAD(head); if (!is_macsec_master(real_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_DOWN: case NETDEV_UP: case NETDEV_CHANGE: { struct macsec_dev *m, *n; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); 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: { struct macsec_dev *m, *n; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); 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: { struct macsec_dev *m; struct macsec_rxh_data *rxd; rxd = macsec_data_rtnl(real_dev); 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); } } } 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"); |
| 5 3 4 2 2 1 1 1 1 4 5 5 1 6 6 3 4 4 4 6 6 5 1 9 8 1 7 10 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 | // SPDX-License-Identifier: GPL-2.0 /* XDP sockets monitoring support * * Copyright(c) 2019 Intel Corporation. * * Author: Björn Töpel <bjorn.topel@intel.com> */ #include <linux/module.h> #include <net/xdp_sock.h> #include <linux/xdp_diag.h> #include <linux/sock_diag.h> #include "xsk_queue.h" #include "xsk.h" static int xsk_diag_put_info(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xdp_diag_info di = {}; di.ifindex = xs->dev ? xs->dev->ifindex : 0; di.queue_id = xs->queue_id; return nla_put(nlskb, XDP_DIAG_INFO, sizeof(di), &di); } static int xsk_diag_put_ring(const struct xsk_queue *queue, int nl_type, struct sk_buff *nlskb) { struct xdp_diag_ring dr = {}; dr.entries = queue->nentries; return nla_put(nlskb, nl_type, sizeof(dr), &dr); } static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, struct sk_buff *nlskb) { int err = 0; if (xs->rx) err = xsk_diag_put_ring(xs->rx, XDP_DIAG_RX_RING, nlskb); if (!err && xs->tx) err = xsk_diag_put_ring(xs->tx, XDP_DIAG_TX_RING, nlskb); return err; } static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xsk_buff_pool *pool = xs->pool; struct xdp_umem *umem = xs->umem; struct xdp_diag_umem du = {}; int err; if (!umem) return 0; du.id = umem->id; du.size = umem->size; du.num_pages = umem->npgs; du.chunk_size = umem->chunk_size; du.headroom = umem->headroom; du.ifindex = (pool && pool->netdev) ? pool->netdev->ifindex : 0; du.queue_id = pool ? pool->queue_id : 0; du.flags = 0; if (umem->zc) du.flags |= XDP_DU_F_ZEROCOPY; du.refs = refcount_read(&umem->users); err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); if (!err && pool && pool->fq) err = xsk_diag_put_ring(pool->fq, XDP_DIAG_UMEM_FILL_RING, nlskb); if (!err && pool && pool->cq) err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING, nlskb); return err; } static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xdp_diag_stats du = {}; du.n_rx_dropped = xs->rx_dropped; du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx); du.n_rx_full = xs->rx_queue_full; du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx); du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx); return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du); } static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, struct xdp_diag_req *req, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, int sk_ino) { struct xdp_sock *xs = xdp_sk(sk); struct xdp_diag_msg *msg; struct nlmsghdr *nlh; nlh = nlmsg_put(nlskb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*msg), flags); if (!nlh) return -EMSGSIZE; msg = nlmsg_data(nlh); memset(msg, 0, sizeof(*msg)); msg->xdiag_family = AF_XDP; msg->xdiag_type = sk->sk_type; msg->xdiag_ino = sk_ino; sock_diag_save_cookie(sk, msg->xdiag_cookie); mutex_lock(&xs->mutex); if (READ_ONCE(xs->state) == XSK_UNBOUND) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_INFO) && nla_put_u32(nlskb, XDP_DIAG_UID, from_kuid_munged(user_ns, sock_i_uid(sk)))) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_RING_CFG) && xsk_diag_put_rings_cfg(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_UMEM) && xsk_diag_put_umem(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_MEMINFO) && sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_STATS) && xsk_diag_put_stats(xs, nlskb)) goto out_nlmsg_trim; mutex_unlock(&xs->mutex); nlmsg_end(nlskb, nlh); return 0; out_nlmsg_trim: mutex_unlock(&xs->mutex); nlmsg_cancel(nlskb, nlh); return -EMSGSIZE; } static int xsk_diag_dump(struct sk_buff *nlskb, struct netlink_callback *cb) { struct xdp_diag_req *req = nlmsg_data(cb->nlh); struct net *net = sock_net(nlskb->sk); int num = 0, s_num = cb->args[0]; struct sock *sk; mutex_lock(&net->xdp.lock); sk_for_each(sk, &net->xdp.list) { if (!net_eq(sock_net(sk), net)) continue; if (num++ < s_num) continue; if (xsk_diag_fill(sk, nlskb, req, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, sock_i_ino(sk)) < 0) { num--; break; } } mutex_unlock(&net->xdp.lock); cb->args[0] = num; return nlskb->len; } static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr) { struct netlink_dump_control c = { .dump = xsk_diag_dump }; int hdrlen = sizeof(struct xdp_diag_req); struct net *net = sock_net(nlskb->sk); if (nlmsg_len(hdr) < hdrlen) return -EINVAL; if (!(hdr->nlmsg_flags & NLM_F_DUMP)) return -EOPNOTSUPP; return netlink_dump_start(net->diag_nlsk, nlskb, hdr, &c); } static const struct sock_diag_handler xsk_diag_handler = { .owner = THIS_MODULE, .family = AF_XDP, .dump = xsk_diag_handler_dump, }; static int __init xsk_diag_init(void) { return sock_diag_register(&xsk_diag_handler); } static void __exit xsk_diag_exit(void) { sock_diag_unregister(&xsk_diag_handler); } module_init(xsk_diag_init); module_exit(xsk_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XDP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NFS internal definitions */ #include "nfs4_fs.h" #include <linux/fs_context.h> #include <linux/security.h> #include <linux/crc32.h> #include <linux/sunrpc/addr.h> #include <linux/nfs_page.h> #include <linux/wait_bit.h> #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS) extern const struct export_operations nfs_export_ops; struct nfs_string; struct nfs_pageio_descriptor; static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct nfs_fattr *fattr) { if (!nfs_fsid_equal(&NFS_SB(parent)->fsid, &fattr->fsid)) fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; } static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) { if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) return 0; return 1; } static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) { if (!(NFS_SB(dentry->d_sb)->flags & NFS_MOUNT_SOFTREVAL)) return false; if (!d_is_positive(dentry) || !NFS_FH(d_inode(dentry))->size) return false; return true; } static inline fmode_t flags_to_mode(int flags) { fmode_t res = (__force fmode_t)flags & FMODE_EXEC; if ((flags & O_ACCMODE) != O_WRONLY) res |= FMODE_READ; if ((flags & O_ACCMODE) != O_RDONLY) res |= FMODE_WRITE; return res; } /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. */ #define NFS_MAX_SECFLAVORS (12) /* * Value used if the user did not specify a port value. */ #define NFS_UNSPEC_PORT (-1) #define NFS_UNSPEC_RETRANS (UINT_MAX) #define NFS_UNSPEC_TIMEO (UINT_MAX) struct nfs_client_initdata { unsigned long init_flags; const char *hostname; /* Hostname of the server */ const struct sockaddr_storage *addr; /* Address of the server */ const char *nodename; /* Hostname of the client */ const char *ip_addr; /* IP address of the client */ size_t addrlen; struct nfs_subversion *nfs_mod; int proto; u32 minorversion; unsigned int nconnect; unsigned int max_connect; struct net *net; const struct rpc_timeout *timeparms; const struct cred *cred; struct xprtsec_parms xprtsec; unsigned long connect_timeout; unsigned long reconnect_timeout; }; /* * In-kernel mount arguments */ struct nfs_fs_context { bool internal; bool skip_reconfig_option_check; bool need_mount; bool sloppy; unsigned int flags; /* NFS{,4}_MOUNT_* flags */ unsigned int rsize, wsize; unsigned int timeo, retrans; unsigned int acregmin, acregmax; unsigned int acdirmin, acdirmax; unsigned int namlen; unsigned int options; unsigned int bsize; struct nfs_auth_info auth_info; rpc_authflavor_t selected_flavor; struct xprtsec_parms xprtsec; char *client_address; unsigned int version; unsigned int minorversion; char *fscache_uniq; unsigned short protofamily; unsigned short mountfamily; bool has_sec_mnt_opts; int lock_status; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; u32 version; int port; unsigned short protocol; } mount_server; struct { union { struct sockaddr address; struct sockaddr_storage _address; }; size_t addrlen; char *hostname; char *export_path; int port; unsigned short protocol; unsigned short nconnect; unsigned short max_connect; unsigned short export_path_len; } nfs_server; struct nfs_fh *mntfh; struct nfs_server *server; struct nfs_subversion *nfs_mod; /* Information for a cloned mount. */ struct nfs_clone_mount { struct super_block *sb; struct dentry *dentry; struct nfs_fattr *fattr; unsigned int inherited_bsize; } clone_data; }; enum nfs_lock_status { NFS_LOCK_NOT_SET = 0, NFS_LOCK_LOCK = 1, NFS_LOCK_NOLOCK = 2, }; #define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \ errorf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) #define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \ invalf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; })) #define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dprintk(fmt "\n", ## __VA_ARGS__); })) #define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \ warnf(fc, fmt, ## __VA_ARGS__) : \ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); })) static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) { return fc->fs_private; } /* mount_clnt.c */ struct nfs_mount_request { struct sockaddr_storage *sap; size_t salen; char *hostname; char *dirpath; u32 version; unsigned short protocol; struct nfs_fh *fh; int noresvport; unsigned int *auth_flav_len; rpc_authflavor_t *auth_flavs; struct net *net; }; extern int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans); extern void nfs_umount(const struct nfs_mount_request *info); /* client.c */ extern const struct rpc_program nfs_program; extern void nfs_clients_init(struct net *net); extern void nfs_clients_exit(struct net *net); extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t); struct nfs_client *nfs_get_client(const struct nfs_client_initdata *); int nfs_probe_server(struct nfs_server *, struct nfs_fh *); void nfs_server_insert_lists(struct nfs_server *); void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); struct nfs_server *nfs_alloc_server(void); void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *); extern void nfs_put_client(struct nfs_client *); extern void nfs_free_client(struct nfs_client *); extern struct nfs_client *nfs4_find_client_ident(struct net *, int); extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *, u32); extern struct nfs_server *nfs_create_server(struct fs_context *); extern void nfs4_server_set_init_caps(struct nfs_server *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, struct sockaddr_storage *sap, size_t salen, struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); extern bool nfs_client_init_is_complete(const struct nfs_client *clp); extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, u32 minor_version); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); extern int nfs_fs_proc_net_init(struct net *net); extern void nfs_fs_proc_net_exit(struct net *net); #else static inline int nfs_fs_proc_net_init(struct net *net) { return 0; } static inline void nfs_fs_proc_net_exit(struct net *net) { } static inline int nfs_fs_proc_init(void) { return 0; } static inline void nfs_fs_proc_exit(void) { } #endif /* callback_xdr.c */ extern const struct svc_version nfs4_callback_version1; extern const struct svc_version nfs4_callback_version4; /* fs_context.c */ extern struct file_system_type nfs_fs_type; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); extern int __init nfs_init_readpagecache(void); extern void nfs_destroy_readpagecache(void); extern int __init nfs_init_writepagecache(void); extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { return cred_fscmp(ctx1->cred, ctx2->cred) == 0 && ctx1->state == ctx2->state; } /* nfs2xdr.c */ extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs3xdr.c */ extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); /* nfs4xdr.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, bool); #endif #ifdef CONFIG_NFS_V4_1 extern const u32 nfs41_maxread_overhead; extern const u32 nfs41_maxwrite_overhead; extern const u32 nfs41_maxgetdevinfo_overhead; #endif /* nfs4proc.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern const struct rpc_procinfo nfs4_procedures[]; #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { if (!dst || !src) return NULL; if (src->len > NFS4_MAXLABELLEN) return NULL; dst->lfs = src->lfs; dst->pi = src->pi; dst->len = src->len; memcpy(dst->label, src->label, src->len); return dst; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) nfsi->cache_validity |= NFS_INO_INVALID_LABEL; } #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } static inline struct nfs4_label * nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) { return NULL; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); /* dir.c */ extern void nfs_readdir_record_entry_cache_hit(struct inode *dir); extern void nfs_readdir_record_entry_cache_miss(struct inode *dir); extern unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc); extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int nfs_rmdir(struct inode *, struct dentry *); int nfs_unlink(struct inode *, struct dentry *); int nfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int nfs_link(struct dentry *, struct inode *, struct dentry *); int nfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int nfs_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); #ifdef CONFIG_NFS_V4_2 static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { if (!(server->caps & NFS_CAP_XATTR)) return 0; return NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | NFS4_ACCESS_XALIST; } #else static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) { return 0; } #endif /* file.c */ int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); ssize_t nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int nfs_file_mmap(struct file *, struct vm_area_struct *); ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_free_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); extern void nfs_zap_acl_cache(struct inode *inode); extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags); extern bool nfs_check_cache_invalid(struct inode *, unsigned long); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); /* super.c */ extern const struct super_operations nfs_sops; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); int nfs_try_get_tree(struct fs_context *); int nfs_get_tree_common(struct fs_context *); void nfs_kill_super(struct super_block *); extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern bool nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); extern int nfs_client_for_each_server(struct nfs_client *clp, int (*fn)(struct nfs_server *, void *), void *data); #ifdef CONFIG_NFS_FSCACHE extern const struct netfs_request_ops nfs_netfs_ops; #endif /* io.c */ extern void nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); extern void nfs_start_io_write(struct inode *inode); extern void nfs_end_io_write(struct inode *inode); extern void nfs_start_io_direct(struct inode *inode); extern void nfs_end_io_direct(struct inode *inode); static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) { return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, unsigned flags); extern struct vfsmount *nfs_d_automount(struct path *path); int nfs_submount(struct fs_context *, struct nfs_server *); int nfs_do_submount(struct fs_context *); /* getroot.c */ extern int nfs_get_root(struct super_block *s, struct fs_context *fc); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool); #endif struct nfs_pgio_completion_ops; /* read.c */ extern const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size); extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, struct nfs_open_context *ctx, struct folio *folio); extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ void nfs_umount_begin(struct super_block *); int nfs_statfs(struct dentry *, struct kstatfs *); int nfs_show_options(struct seq_file *, struct dentry *); int nfs_show_devname(struct seq_file *, struct dentry *); int nfs_show_path(struct seq_file *, struct dentry *); int nfs_show_stats(struct seq_file *, struct dentry *); int nfs_reconfigure(struct fs_context *); /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_commit_free(struct nfs_commit_data *p); extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, int how, int flags); extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo); int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_commit_info *cinfo, int max); unsigned long nfs_reqs_to_commit(struct nfs_commit_info *); int nfs_scan_commit(struct inode *inode, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); int nfs_write_need_commit(struct nfs_pgio_header *); void nfs_writeback_update_inode(struct nfs_pgio_header *hdr); int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo, u32 ds_commit_idx); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_request_remove_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo); void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct inode *inode, struct nfs_direct_req *dreq); int nfs_key_timeout_notify(struct file *filp, struct inode *inode); bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode); void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); int nfs_filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); #ifdef CONFIG_NFS_V4_1 static inline void pnfs_bucket_clear_pnfs_ds_commit_verifiers(struct pnfs_commit_bucket *buckets, unsigned int nbuckets) { unsigned int i; for (i = 0; i < nbuckets; i++) buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW; } static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { struct pnfs_commit_array *array; rcu_read_lock(); list_for_each_entry_rcu(array, &cinfo->commits, cinfo_list) pnfs_bucket_clear_pnfs_ds_commit_verifiers(array->buckets, array->nbuckets); rcu_read_unlock(); } #else static inline void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo) { } #endif #ifdef CONFIG_MIGRATION int nfs_migrate_folio(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); #else #define nfs_migrate_folio NULL #endif static inline int nfs_write_verifier_cmp(const struct nfs_write_verifier *v1, const struct nfs_write_verifier *v2) { return memcmp(v1->data, v2->data, sizeof(v1->data)); } static inline bool nfs_write_match_verf(const struct nfs_writeverf *verf, struct nfs_page *req) { return verf->committed > NFS_UNSTABLE && !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } static inline gfp_t nfs_io_gfp_mask(void) { if (current->flags & PF_WQ_WORKER) return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; return GFP_KERNEL; } /* * Special version of should_remove_suid() that ignores capabilities. */ static inline int nfs_should_remove_suid(const struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; /* * sgid without any exec bits is just a mandatory locking mark; leave * it alone. If some exec bits are set, it's a real sgid; kill it. */ if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; if (unlikely(kill && S_ISREG(mode))) return kill; return 0; } /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, struct dentry *old_dentry, struct dentry *new_dentry, void (*complete)(struct rpc_task *, struct nfs_renamedata *)); extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry); /* direct.c */ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset); /* nfs4proc.c */ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); extern int nfs40_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern int nfs41_walk_client_list(struct nfs_client *clp, struct nfs_client **result, const struct cred *cred); extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data); static inline struct inode *nfs_igrab_and_active(struct inode *inode) { struct super_block *sb = inode->i_sb; if (sb && nfs_sb_active(sb)) { if (igrab(inode)) return inode; nfs_sb_deactive(sb); } return NULL; } static inline void nfs_iput_and_deactive(struct inode *inode) { if (inode != NULL) { struct super_block *sb = inode->i_sb; iput(inode); nfs_sb_deactive(sb); } } /* * Determine the device name as a string */ static inline char *nfs_devname(struct dentry *dentry, char *buffer, ssize_t buflen) { char *dummy; return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL); } /* * Determine the actual block size (and log2 thereof) */ static inline unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) { /* make sure blocksize is a power of two */ if ((bsize & (bsize - 1)) || nrbitsp) { unsigned char nrbits; for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--) ; bsize = 1UL << nrbits; if (nrbitsp) *nrbitsp = nrbits; } return bsize; } /* * Calculate the number of 512byte blocks used. */ static inline blkcnt_t nfs_calc_block_size(u64 tsize) { blkcnt_t used = (tsize + 511) >> 9; return (used > ULONG_MAX) ? ULONG_MAX : used; } /* * Compute and set NFS server blocksize */ static inline unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) { if (bsize < NFS_MIN_FILE_IO_SIZE) bsize = NFS_DEF_FILE_IO_SIZE; else if (bsize >= NFS_MAX_FILE_IO_SIZE) bsize = NFS_MAX_FILE_IO_SIZE; return nfs_block_bits(bsize, nrbitsp); } /* * Compute and set NFS server rsize / wsize */ static inline unsigned long nfs_io_size(unsigned long iosize, enum xprt_transports proto) { if (iosize < NFS_MIN_FILE_IO_SIZE) iosize = NFS_DEF_FILE_IO_SIZE; else if (iosize >= NFS_MAX_FILE_IO_SIZE) iosize = NFS_MAX_FILE_IO_SIZE; if (proto == XPRT_TRANSPORT_UDP || iosize < PAGE_SIZE) return nfs_block_bits(iosize, NULL); return iosize & PAGE_MASK; } /* * Determine the maximum file size for a superblock */ static inline void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) { sb->s_maxbytes = (loff_t)maxfilesize; if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0) sb->s_maxbytes = MAX_LFS_FILESIZE; } /* * Record the page as unstable (an extra writeback period) and mark its * inode as dirty. */ static inline void nfs_folio_mark_unstable(struct folio *folio, struct nfs_commit_info *cinfo) { if (folio && !cinfo->dreq) { struct inode *inode = folio->mapping->host; long nr = folio_nr_pages(folio); /* This page is really still in write-back - just that the * writeback is happening on the server now. */ node_stat_mod_folio(folio, NR_WRITEBACK, nr); wb_stat_mod(&inode_to_bdi(inode)->wb, WB_WRITEBACK, nr); __mark_inode_dirty(inode, I_DIRTY_DATASYNC); } } /* * Determine the number of bytes of data the page contains */ static inline size_t nfs_folio_length(struct folio *folio) { loff_t i_size = i_size_read(folio->mapping->host); if (i_size > 0) { pgoff_t index = folio->index >> folio_order(folio); pgoff_t end_index = (i_size - 1) >> folio_shift(folio); if (index < end_index) return folio_size(folio); if (index == end_index) return offset_in_folio(folio, i_size - 1) + 1; } return 0; } /* * Convert a umode to a dirent->d_type */ static inline unsigned char nfs_umode_to_dtype(umode_t mode) { return (mode >> 12) & 15; } /* * Determine the number of pages in an array of length 'len' and * with a base offset of 'base' */ static inline unsigned int nfs_page_array_len(unsigned int base, size_t len) { return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >> PAGE_SHIFT; } /* * Convert a struct timespec64 into a 64-bit change attribute * * This does approximately the same thing as timespec64_to_ns(), * but for calculation efficiency, we multiply the seconds by * 1024*1024*1024. */ static inline u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } #ifdef CONFIG_CRC32 static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } #else static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) { return 0; } #endif static inline bool nfs_error_is_fatal(int err) { switch (err) { case -ERESTARTSYS: case -EINTR: case -EACCES: case -EDQUOT: case -EFBIG: case -EIO: case -ENOSPC: case -EROFS: case -ESTALE: case -E2BIG: case -ENOMEM: case -ETIMEDOUT: return true; default: return false; } } static inline bool nfs_error_is_fatal_on_server(int err) { switch (err) { case 0: case -ERESTARTSYS: case -EINTR: case -ENOMEM: return false; } return nfs_error_is_fatal(err); } /* * Select between a default port value and a user-specified port value. * If a zero value is set, then autobind will be used. */ static inline void nfs_set_port(struct sockaddr_storage *sap, int *port, const unsigned short default_port) { if (*port == NFS_UNSPEC_PORT) *port = default_port; rpc_set_port((struct sockaddr *)sap, *port); } struct nfs_direct_req { struct kref kref; /* release manager */ /* I/O parameters */ struct nfs_open_context *ctx; /* file open context info */ struct nfs_lock_context *l_ctx; /* Lock context info */ struct kiocb * iocb; /* controlling i/o request */ struct inode * inode; /* target file of i/o */ /* completion state */ atomic_t io_count; /* i/os we're waiting for */ spinlock_t lock; /* protect completion state */ loff_t io_start; /* Start offset for I/O */ ssize_t count, /* bytes actually processed */ max_count, /* max expected count */ error; /* any reported error */ struct completion completion; /* wait for i/o completion */ /* commit state */ struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ struct work_struct work; int flags; /* for write */ #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ /* for read */ #define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ #define NFS_ODIRECT_DONE INT_MAX /* write verification failed */ }; |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz> * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br> * Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon */ #include <linux/module.h> #include "../../dccp.h" #include "tfrc.h" #define TFRC_CALC_X_ARRSIZE 500 #define TFRC_CALC_X_SPLIT 50000 /* 0.05 * 1000000, details below */ #define TFRC_SMALLEST_P (TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE) /* TFRC TCP Reno Throughput Equation Lookup Table for f(p) The following two-column lookup table implements a part of the TCP throughput equation from [RFC 3448, sec. 3.1]: s X_calc = -------------------------------------------------------------- R * sqrt(2*b*p/3) + (3 * t_RTO * sqrt(3*b*p/8) * (p + 32*p^3)) Where: X is the transmit rate in bytes/second s is the packet size in bytes R is the round trip time in seconds p is the loss event rate, between 0 and 1.0, of the number of loss events as a fraction of the number of packets transmitted t_RTO is the TCP retransmission timeout value in seconds b is the number of packets acknowledged by a single TCP ACK We can assume that b = 1 and t_RTO is 4 * R. The equation now becomes: s X_calc = ------------------------------------------------------- R * sqrt(p*2/3) + (12 * R * sqrt(p*3/8) * (p + 32*p^3)) which we can break down into: s X_calc = --------- R * f(p) where f(p) is given for 0 < p <= 1 by: f(p) = sqrt(2*p/3) + 12 * sqrt(3*p/8) * (p + 32*p^3) Since this is kernel code, floating-point arithmetic is avoided in favour of integer arithmetic. This means that nearly all fractional parameters are scaled by 1000000: * the parameters p and R * the return result f(p) The lookup table therefore actually tabulates the following function g(q): g(q) = 1000000 * f(q/1000000) Hence, when p <= 1, q must be less than or equal to 1000000. To achieve finer granularity for the practically more relevant case of small values of p (up to 5%), the second column is used; the first one ranges up to 100%. This split corresponds to the value of q = TFRC_CALC_X_SPLIT. At the same time this also determines the smallest resolution possible with this lookup table: TFRC_SMALLEST_P = TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE The entire table is generated by: for(i=0; i < TFRC_CALC_X_ARRSIZE; i++) { lookup[i][0] = g((i+1) * 1000000/TFRC_CALC_X_ARRSIZE); lookup[i][1] = g((i+1) * TFRC_CALC_X_SPLIT/TFRC_CALC_X_ARRSIZE); } With the given configuration, we have, with M = TFRC_CALC_X_ARRSIZE-1, lookup[0][0] = g(1000000/(M+1)) = 1000000 * f(0.2%) lookup[M][0] = g(1000000) = 1000000 * f(100%) lookup[0][1] = g(TFRC_SMALLEST_P) = 1000000 * f(0.01%) lookup[M][1] = g(TFRC_CALC_X_SPLIT) = 1000000 * f(5%) In summary, the two columns represent f(p) for the following ranges: * The first column is for 0.002 <= p <= 1.0 * The second column is for 0.0001 <= p <= 0.05 Where the columns overlap, the second (finer-grained) is given preference, i.e. the first column is used only for p >= 0.05. */ static const u32 tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE][2] = { { 37172, 8172 }, { 53499, 11567 }, { 66664, 14180 }, { 78298, 16388 }, { 89021, 18339 }, { 99147, 20108 }, { 108858, 21738 }, { 118273, 23260 }, { 127474, 24693 }, { 136520, 26052 }, { 145456, 27348 }, { 154316, 28589 }, { 163130, 29783 }, { 171919, 30935 }, { 180704, 32049 }, { 189502, 33130 }, { 198328, 34180 }, { 207194, 35202 }, { 216114, 36198 }, { 225097, 37172 }, { 234153, 38123 }, { 243294, 39055 }, { 252527, 39968 }, { 261861, 40864 }, { 271305, 41743 }, { 280866, 42607 }, { 290553, 43457 }, { 300372, 44293 }, { 310333, 45117 }, { 320441, 45929 }, { 330705, 46729 }, { 341131, 47518 }, { 351728, 48297 }, { 362501, 49066 }, { 373460, 49826 }, { 384609, 50577 }, { 395958, 51320 }, { 407513, 52054 }, { 419281, 52780 }, { 431270, 53499 }, { 443487, 54211 }, { 455940, 54916 }, { 468635, 55614 }, { 481581, 56306 }, { 494785, 56991 }, { 508254, 57671 }, { 521996, 58345 }, { 536019, 59014 }, { 550331, 59677 }, { 564939, 60335 }, { 579851, 60988 }, { 595075, 61636 }, { 610619, 62279 }, { 626491, 62918 }, { 642700, 63553 }, { 659253, 64183 }, { 676158, 64809 }, { 693424, 65431 }, { 711060, 66050 }, { 729073, 66664 }, { 747472, 67275 }, { 766266, 67882 }, { 785464, 68486 }, { 805073, 69087 }, { 825103, 69684 }, { 845562, 70278 }, { 866460, 70868 }, { 887805, 71456 }, { 909606, 72041 }, { 931873, 72623 }, { 954614, 73202 }, { 977839, 73778 }, { 1001557, 74352 }, { 1025777, 74923 }, { 1050508, 75492 }, { 1075761, 76058 }, { 1101544, 76621 }, { 1127867, 77183 }, { 1154739, 77741 }, { 1182172, 78298 }, { 1210173, 78852 }, { 1238753, 79405 }, { 1267922, 79955 }, { 1297689, 80503 }, { 1328066, 81049 }, { 1359060, 81593 }, { 1390684, 82135 }, { 1422947, 82675 }, { 1455859, 83213 }, { 1489430, 83750 }, { 1523671, 84284 }, { 1558593, 84817 }, { 1594205, 85348 }, { 1630518, 85878 }, { 1667543, 86406 }, { 1705290, 86932 }, { 1743770, 87457 }, { 1782994, 87980 }, { 1822973, 88501 }, { 1863717, 89021 }, { 1905237, 89540 }, { 1947545, 90057 }, { 1990650, 90573 }, { 2034566, 91087 }, { 2079301, 91600 }, { 2124869, 92111 }, { 2171279, 92622 }, { 2218543, 93131 }, { 2266673, 93639 }, { 2315680, 94145 }, { 2365575, 94650 }, { 2416371, 95154 }, { 2468077, 95657 }, { 2520707, 96159 }, { 2574271, 96660 }, { 2628782, 97159 }, { 2684250, 97658 }, { 2740689, 98155 }, { 2798110, 98651 }, { 2856524, 99147 }, { 2915944, 99641 }, { 2976382, 100134 }, { 3037850, 100626 }, { 3100360, 101117 }, { 3163924, 101608 }, { 3228554, 102097 }, { 3294263, 102586 }, { 3361063, 103073 }, { 3428966, 103560 }, { 3497984, 104045 }, { 3568131, 104530 }, { 3639419, 105014 }, { 3711860, 105498 }, { 3785467, 105980 }, { 3860253, 106462 }, { 3936229, 106942 }, { 4013410, 107422 }, { 4091808, 107902 }, { 4171435, 108380 }, { 4252306, 108858 }, { 4334431, 109335 }, { 4417825, 109811 }, { 4502501, 110287 }, { 4588472, 110762 }, { 4675750, 111236 }, { 4764349, 111709 }, { 4854283, 112182 }, { 4945564, 112654 }, { 5038206, 113126 }, { 5132223, 113597 }, { 5227627, 114067 }, { 5324432, 114537 }, { 5422652, 115006 }, { 5522299, 115474 }, { 5623389, 115942 }, { 5725934, 116409 }, { 5829948, 116876 }, { 5935446, 117342 }, { 6042439, 117808 }, { 6150943, 118273 }, { 6260972, 118738 }, { 6372538, 119202 }, { 6485657, 119665 }, { 6600342, 120128 }, { 6716607, 120591 }, { 6834467, 121053 }, { 6953935, 121514 }, { 7075025, 121976 }, { 7197752, 122436 }, { 7322131, 122896 }, { 7448175, 123356 }, { 7575898, 123815 }, { 7705316, 124274 }, { 7836442, 124733 }, { 7969291, 125191 }, { 8103877, 125648 }, { 8240216, 126105 }, { 8378321, 126562 }, { 8518208, 127018 }, { 8659890, 127474 }, { 8803384, 127930 }, { 8948702, 128385 }, { 9095861, 128840 }, { 9244875, 129294 }, { 9395760, 129748 }, { 9548529, 130202 }, { 9703198, 130655 }, { 9859782, 131108 }, { 10018296, 131561 }, { 10178755, 132014 }, { 10341174, 132466 }, { 10505569, 132917 }, { 10671954, 133369 }, { 10840345, 133820 }, { 11010757, 134271 }, { 11183206, 134721 }, { 11357706, 135171 }, { 11534274, 135621 }, { 11712924, 136071 }, { 11893673, 136520 }, { 12076536, 136969 }, { 12261527, 137418 }, { 12448664, 137867 }, { 12637961, 138315 }, { 12829435, 138763 }, { 13023101, 139211 }, { 13218974, 139658 }, { 13417071, 140106 }, { 13617407, 140553 }, { 13819999, 140999 }, { 14024862, 141446 }, { 14232012, 141892 }, { 14441465, 142339 }, { 14653238, 142785 }, { 14867346, 143230 }, { 15083805, 143676 }, { 15302632, 144121 }, { 15523842, 144566 }, { 15747453, 145011 }, { 15973479, 145456 }, { 16201939, 145900 }, { 16432847, 146345 }, { 16666221, 146789 }, { 16902076, 147233 }, { 17140429, 147677 }, { 17381297, 148121 }, { 17624696, 148564 }, { 17870643, 149007 }, { 18119154, 149451 }, { 18370247, 149894 }, { 18623936, 150336 }, { 18880241, 150779 }, { 19139176, 151222 }, { 19400759, 151664 }, { 19665007, 152107 }, { 19931936, 152549 }, { 20201564, 152991 }, { 20473907, 153433 }, { 20748982, 153875 }, { 21026807, 154316 }, { 21307399, 154758 }, { 21590773, 155199 }, { 21876949, 155641 }, { 22165941, 156082 }, { 22457769, 156523 }, { 22752449, 156964 }, { 23049999, 157405 }, { 23350435, 157846 }, { 23653774, 158287 }, { 23960036, 158727 }, { 24269236, 159168 }, { 24581392, 159608 }, { 24896521, 160049 }, { 25214642, 160489 }, { 25535772, 160929 }, { 25859927, 161370 }, { 26187127, 161810 }, { 26517388, 162250 }, { 26850728, 162690 }, { 27187165, 163130 }, { 27526716, 163569 }, { 27869400, 164009 }, { 28215234, 164449 }, { 28564236, 164889 }, { 28916423, 165328 }, { 29271815, 165768 }, { 29630428, 166208 }, { 29992281, 166647 }, { 30357392, 167087 }, { 30725779, 167526 }, { 31097459, 167965 }, { 31472452, 168405 }, { 31850774, 168844 }, { 32232445, 169283 }, { 32617482, 169723 }, { 33005904, 170162 }, { 33397730, 170601 }, { 33792976, 171041 }, { 34191663, 171480 }, { 34593807, 171919 }, { 34999428, 172358 }, { 35408544, 172797 }, { 35821174, 173237 }, { 36237335, 173676 }, { 36657047, 174115 }, { 37080329, 174554 }, { 37507197, 174993 }, { 37937673, 175433 }, { 38371773, 175872 }, { 38809517, 176311 }, { 39250924, 176750 }, { 39696012, 177190 }, { 40144800, 177629 }, { 40597308, 178068 }, { 41053553, 178507 }, { 41513554, 178947 }, { 41977332, 179386 }, { 42444904, 179825 }, { 42916290, 180265 }, { 43391509, 180704 }, { 43870579, 181144 }, { 44353520, 181583 }, { 44840352, 182023 }, { 45331092, 182462 }, { 45825761, 182902 }, { 46324378, 183342 }, { 46826961, 183781 }, { 47333531, 184221 }, { 47844106, 184661 }, { 48358706, 185101 }, { 48877350, 185541 }, { 49400058, 185981 }, { 49926849, 186421 }, { 50457743, 186861 }, { 50992759, 187301 }, { 51531916, 187741 }, { 52075235, 188181 }, { 52622735, 188622 }, { 53174435, 189062 }, { 53730355, 189502 }, { 54290515, 189943 }, { 54854935, 190383 }, { 55423634, 190824 }, { 55996633, 191265 }, { 56573950, 191706 }, { 57155606, 192146 }, { 57741621, 192587 }, { 58332014, 193028 }, { 58926806, 193470 }, { 59526017, 193911 }, { 60129666, 194352 }, { 60737774, 194793 }, { 61350361, 195235 }, { 61967446, 195677 }, { 62589050, 196118 }, { 63215194, 196560 }, { 63845897, 197002 }, { 64481179, 197444 }, { 65121061, 197886 }, { 65765563, 198328 }, { 66414705, 198770 }, { 67068508, 199213 }, { 67726992, 199655 }, { 68390177, 200098 }, { 69058085, 200540 }, { 69730735, 200983 }, { 70408147, 201426 }, { 71090343, 201869 }, { 71777343, 202312 }, { 72469168, 202755 }, { 73165837, 203199 }, { 73867373, 203642 }, { 74573795, 204086 }, { 75285124, 204529 }, { 76001380, 204973 }, { 76722586, 205417 }, { 77448761, 205861 }, { 78179926, 206306 }, { 78916102, 206750 }, { 79657310, 207194 }, { 80403571, 207639 }, { 81154906, 208084 }, { 81911335, 208529 }, { 82672880, 208974 }, { 83439562, 209419 }, { 84211402, 209864 }, { 84988421, 210309 }, { 85770640, 210755 }, { 86558080, 211201 }, { 87350762, 211647 }, { 88148708, 212093 }, { 88951938, 212539 }, { 89760475, 212985 }, { 90574339, 213432 }, { 91393551, 213878 }, { 92218133, 214325 }, { 93048107, 214772 }, { 93883493, 215219 }, { 94724314, 215666 }, { 95570590, 216114 }, { 96422343, 216561 }, { 97279594, 217009 }, { 98142366, 217457 }, { 99010679, 217905 }, { 99884556, 218353 }, { 100764018, 218801 }, { 101649086, 219250 }, { 102539782, 219698 }, { 103436128, 220147 }, { 104338146, 220596 }, { 105245857, 221046 }, { 106159284, 221495 }, { 107078448, 221945 }, { 108003370, 222394 }, { 108934074, 222844 }, { 109870580, 223294 }, { 110812910, 223745 }, { 111761087, 224195 }, { 112715133, 224646 }, { 113675069, 225097 }, { 114640918, 225548 }, { 115612702, 225999 }, { 116590442, 226450 }, { 117574162, 226902 }, { 118563882, 227353 }, { 119559626, 227805 }, { 120561415, 228258 }, { 121569272, 228710 }, { 122583219, 229162 }, { 123603278, 229615 }, { 124629471, 230068 }, { 125661822, 230521 }, { 126700352, 230974 }, { 127745083, 231428 }, { 128796039, 231882 }, { 129853241, 232336 }, { 130916713, 232790 }, { 131986475, 233244 }, { 133062553, 233699 }, { 134144966, 234153 }, { 135233739, 234608 }, { 136328894, 235064 }, { 137430453, 235519 }, { 138538440, 235975 }, { 139652876, 236430 }, { 140773786, 236886 }, { 141901190, 237343 }, { 143035113, 237799 }, { 144175576, 238256 }, { 145322604, 238713 }, { 146476218, 239170 }, { 147636442, 239627 }, { 148803298, 240085 }, { 149976809, 240542 }, { 151156999, 241000 }, { 152343890, 241459 }, { 153537506, 241917 }, { 154737869, 242376 }, { 155945002, 242835 }, { 157158929, 243294 }, { 158379673, 243753 }, { 159607257, 244213 }, { 160841704, 244673 }, { 162083037, 245133 }, { 163331279, 245593 }, { 164586455, 246054 }, { 165848586, 246514 }, { 167117696, 246975 }, { 168393810, 247437 }, { 169676949, 247898 }, { 170967138, 248360 }, { 172264399, 248822 }, { 173568757, 249284 }, { 174880235, 249747 }, { 176198856, 250209 }, { 177524643, 250672 }, { 178857621, 251136 }, { 180197813, 251599 }, { 181545242, 252063 }, { 182899933, 252527 }, { 184261908, 252991 }, { 185631191, 253456 }, { 187007807, 253920 }, { 188391778, 254385 }, { 189783129, 254851 }, { 191181884, 255316 }, { 192588065, 255782 }, { 194001698, 256248 }, { 195422805, 256714 }, { 196851411, 257181 }, { 198287540, 257648 }, { 199731215, 258115 }, { 201182461, 258582 }, { 202641302, 259050 }, { 204107760, 259518 }, { 205581862, 259986 }, { 207063630, 260454 }, { 208553088, 260923 }, { 210050262, 261392 }, { 211555174, 261861 }, { 213067849, 262331 }, { 214588312, 262800 }, { 216116586, 263270 }, { 217652696, 263741 }, { 219196666, 264211 }, { 220748520, 264682 }, { 222308282, 265153 }, { 223875978, 265625 }, { 225451630, 266097 }, { 227035265, 266569 }, { 228626905, 267041 }, { 230226576, 267514 }, { 231834302, 267986 }, { 233450107, 268460 }, { 235074016, 268933 }, { 236706054, 269407 }, { 238346244, 269881 }, { 239994613, 270355 }, { 241651183, 270830 }, { 243315981, 271305 } }; /* return largest index i such that fval <= lookup[i][small] */ static inline u32 tfrc_binsearch(u32 fval, u8 small) { u32 try, low = 0, high = TFRC_CALC_X_ARRSIZE - 1; while (low < high) { try = (low + high) / 2; if (fval <= tfrc_calc_x_lookup[try][small]) high = try; else low = try + 1; } return high; } /** * tfrc_calc_x - Calculate the send rate as per section 3.1 of RFC3448 * @s: packet size in bytes * @R: RTT scaled by 1000000 (i.e., microseconds) * @p: loss ratio estimate scaled by 1000000 * * Returns X_calc in bytes per second (not scaled). */ u32 tfrc_calc_x(u16 s, u32 R, u32 p) { u16 index; u32 f; u64 result; /* check against invalid parameters and divide-by-zero */ BUG_ON(p > 1000000); /* p must not exceed 100% */ BUG_ON(p == 0); /* f(0) = 0, divide by zero */ if (R == 0) { /* possible divide by zero */ DCCP_CRIT("WARNING: RTT is 0, returning maximum X_calc."); return ~0U; } if (p <= TFRC_CALC_X_SPLIT) { /* 0.0000 < p <= 0.05 */ if (p < TFRC_SMALLEST_P) { /* 0.0000 < p < 0.0001 */ DCCP_WARN("Value of p (%d) below resolution. " "Substituting %d\n", p, TFRC_SMALLEST_P); index = 0; } else /* 0.0001 <= p <= 0.05 */ index = p/TFRC_SMALLEST_P - 1; f = tfrc_calc_x_lookup[index][1]; } else { /* 0.05 < p <= 1.00 */ index = p/(1000000/TFRC_CALC_X_ARRSIZE) - 1; f = tfrc_calc_x_lookup[index][0]; } /* * Compute X = s/(R*f(p)) in bytes per second. * Since f(p) and R are both scaled by 1000000, we need to multiply by * 1000000^2. To avoid overflow, the result is computed in two stages. * This works under almost all reasonable operational conditions, for a * wide range of parameters. Yet, should some strange combination of * parameters result in overflow, the use of scaled_div32 will catch * this and return UINT_MAX - which is a logically adequate consequence. */ result = scaled_div(s, R); return scaled_div32(result, f); } /** * tfrc_calc_x_reverse_lookup - try to find p given f(p) * @fvalue: function value to match, scaled by 1000000 * * Returns closest match for p, also scaled by 1000000 */ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) { int index; if (fvalue == 0) /* f(p) = 0 whenever p = 0 */ return 0; /* Error cases. */ if (fvalue < tfrc_calc_x_lookup[0][1]) { DCCP_WARN("fvalue %u smaller than resolution\n", fvalue); return TFRC_SMALLEST_P; } if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) { DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue); return 1000000; } if (fvalue <= tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][1]) { index = tfrc_binsearch(fvalue, 1); return (index + 1) * TFRC_CALC_X_SPLIT / TFRC_CALC_X_ARRSIZE; } /* else ... it must be in the coarse-grained column */ index = tfrc_binsearch(fvalue, 0); return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE; } /** * tfrc_invert_loss_event_rate - Compute p so that 10^6 corresponds to 100% * @loss_event_rate: loss event rate to invert * When @loss_event_rate is large, there is a chance that p is truncated to 0. * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0. */ u32 tfrc_invert_loss_event_rate(u32 loss_event_rate) { if (loss_event_rate == UINT_MAX) /* see RFC 4342, 8.5 */ return 0; if (unlikely(loss_event_rate == 0)) /* map 1/0 into 100% */ return 1000000; return max_t(u32, scaled_div(1, loss_event_rate), TFRC_SMALLEST_P); } |
| 3 7 7 7 1 6 3 3 2 3 1101 3 3 1 1 1 10 1 10 1 8 2 3 14 14 13 14 10 14 12 12 12 6 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Frame handler other utility functions for HSR and PRP. */ #include "hsr_slave.h" #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_forward.h" #include "hsr_framereg.h" bool hsr_invalid_dan_ingress_frame(__be16 protocol) { return (protocol != htons(ETH_P_PRP) && protocol != htons(ETH_P_HSR)); } static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; struct hsr_priv *hsr; __be16 protocol; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); return RX_HANDLER_PASS; } port = hsr_port_get_rcu(skb->dev); if (!port) goto finish_pass; hsr = port->hsr; if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { /* Directly kill frames sent by ourselves */ kfree_skb(skb); goto finish_consume; } /* For HSR, only tagged frames are expected (unless the device offloads * HSR tag removal), but for PRP there could be non tagged frames as * well from Single attached nodes (SANs). */ protocol = eth_hdr(skb)->h_proto; if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && port->type != HSR_PT_INTERLINK && hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || protocol == htons(ETH_P_HSR)) skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); skb_reset_mac_len(skb); hsr_forward_skb(skb, port); finish_consume: return RX_HANDLER_CONSUMED; finish_pass: return RX_HANDLER_PASS; } bool hsr_port_exists(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame; } static int hsr_check_dev_ok(struct net_device *dev, struct netlink_ext_ack *extack) { /* Don't allow HSR on non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) { NL_SET_ERR_MSG_MOD(extack, "Cannot use loopback or non-ethernet device as HSR slave."); return -EINVAL; } /* Don't allow enslaving hsr devices */ if (is_hsr_master(dev)) { NL_SET_ERR_MSG_MOD(extack, "Cannot create trees of HSR devices."); return -EINVAL; } if (hsr_port_exists(dev)) { NL_SET_ERR_MSG_MOD(extack, "This device is already a HSR slave."); return -EINVAL; } if (is_vlan_dev(dev)) { NL_SET_ERR_MSG_MOD(extack, "HSR on top of VLAN is not yet supported in this driver."); return -EINVAL; } if (dev->priv_flags & IFF_DONT_BRIDGE) { NL_SET_ERR_MSG_MOD(extack, "This device does not support bridging."); return -EOPNOTSUPP; } /* HSR over bonded devices has not been tested, but I'm not sure it * won't work... */ return 0; } /* Setup device to be added to the HSR bridge. */ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, struct hsr_port *port, struct netlink_ext_ack *extack) { struct net_device *hsr_dev; struct hsr_port *master; int res; /* Don't use promiscuous mode for offload since L2 frame forward * happens at the offloaded hardware. */ if (!port->hsr->fwd_offloaded) { res = dev_set_promiscuity(dev, 1); if (res) return res; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr_dev = master->dev; res = netdev_upper_dev_link(dev, hsr_dev, extack); if (res) goto fail_upper_dev_link; res = netdev_rx_handler_register(dev, hsr_handle_frame, port); if (res) goto fail_rx_handler; dev_disable_lro(dev); return 0; fail_rx_handler: netdev_upper_dev_unlink(dev, hsr_dev); fail_upper_dev_link: if (!port->hsr->fwd_offloaded) dev_set_promiscuity(dev, -1); return res; } int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type type, struct netlink_ext_ack *extack) { struct hsr_port *port, *master; int res; if (type != HSR_PT_MASTER) { res = hsr_check_dev_ok(dev, extack); if (res) return res; } port = hsr_port_get_hsr(hsr, type); if (port) return -EBUSY; /* This port already exists */ port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; port->hsr = hsr; port->dev = dev; port->type = type; if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(hsr, dev, port, extack); if (res) goto fail_dev_setup; } list_add_tail_rcu(&port->port_list, &hsr->ports); synchronize_rcu(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); return 0; fail_dev_setup: kfree(port); return res; } void hsr_del_port(struct hsr_port *port) { struct hsr_priv *hsr; struct hsr_port *master; hsr = port->hsr; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); list_del_rcu(&port->port_list); if (port != master) { netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); if (!port->hsr->fwd_offloaded) dev_set_promiscuity(port->dev, -1); netdev_upper_dev_unlink(port->dev, master->dev); } synchronize_rcu(); kfree(port); } |
| 32 44 32 81 30 1 79 80 5 74 5 2 3 5 75 18 57 9 72 5 81 58 81 41 4 1 2 2 2 1 1 2 1 1 12 10 31 2 1 1 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * algif_skcipher: User-space interface for skcipher algorithms * * This file provides the user-space API for symmetric key ciphers. * * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> * * The following concept of the memory management is used: * * The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is * filled by user space with the data submitted via sendmsg. Filling up the TX * SGL does not cause a crypto operation -- the data will only be tracked by * the kernel. Upon receipt of one recvmsg call, the caller must provide a * buffer which is tracked with the RX SGL. * * During the processing of the recvmsg operation, the cipher request is * allocated and prepared. As part of the recvmsg operation, the processed * TX buffers are extracted from the TX SGL into a separate SGL. * * After the completion of the crypto operation, the RX SGL and the cipher * request is released. The extracted TX SGL parts are released together with * the RX SGL release. */ #include <crypto/scatterwalk.h> #include <crypto/skcipher.h> #include <crypto/if_alg.h> #include <linux/init.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/net.h> #include <net/sock.h> static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct crypto_skcipher *tfm = pask->private; unsigned ivsize = crypto_skcipher_ivsize(tfm); return af_alg_sendmsg(sock, msg, size, ivsize); } static int algif_skcipher_export(struct sock *sk, struct skcipher_request *req) { struct alg_sock *ask = alg_sk(sk); struct crypto_skcipher *tfm; struct af_alg_ctx *ctx; struct alg_sock *pask; unsigned statesize; struct sock *psk; int err; if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL)) return 0; ctx = ask->private; psk = ask->parent; pask = alg_sk(psk); tfm = pask->private; statesize = crypto_skcipher_statesize(tfm); ctx->state = sock_kmalloc(sk, statesize, GFP_ATOMIC); if (!ctx->state) return -ENOMEM; err = crypto_skcipher_export(req, ctx->state); if (err) { sock_kzfree_s(sk, ctx->state, statesize); ctx->state = NULL; } return err; } static void algif_skcipher_done(void *data, int err) { struct af_alg_async_req *areq = data; struct sock *sk = areq->sk; if (err) goto out; err = algif_skcipher_export(sk, &areq->cra_u.skcipher_req); out: af_alg_async_cb(data, err); } static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct af_alg_ctx *ctx = ask->private; struct crypto_skcipher *tfm = pask->private; unsigned int bs = crypto_skcipher_chunksize(tfm); struct af_alg_async_req *areq; unsigned cflags = 0; int err = 0; size_t len = 0; if (!ctx->init || (ctx->more && ctx->used < bs)) { err = af_alg_wait_for_data(sk, flags, bs); if (err) return err; } /* Allocate cipher request for current operation. */ areq = af_alg_alloc_areq(sk, sizeof(struct af_alg_async_req) + crypto_skcipher_reqsize(tfm)); if (IS_ERR(areq)) return PTR_ERR(areq); /* convert iovecs of output buffers into RX SGL */ err = af_alg_get_rsgl(sk, msg, flags, areq, ctx->used, &len); if (err) goto free; /* * If more buffers are to be expected to be processed, process only * full block size buffers. */ if (ctx->more || len < ctx->used) { len -= len % bs; cflags |= CRYPTO_SKCIPHER_REQ_NOTFINAL; } /* * Create a per request TX SGL for this request which tracks the * SG entries from the global TX SGL. */ areq->tsgl_entries = af_alg_count_tsgl(sk, len, 0); if (!areq->tsgl_entries) areq->tsgl_entries = 1; areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl), areq->tsgl_entries), GFP_KERNEL); if (!areq->tsgl) { err = -ENOMEM; goto free; } sg_init_table(areq->tsgl, areq->tsgl_entries); af_alg_pull_tsgl(sk, len, areq->tsgl, 0); /* Initialize the crypto operation */ skcipher_request_set_tfm(&areq->cra_u.skcipher_req, tfm); skcipher_request_set_crypt(&areq->cra_u.skcipher_req, areq->tsgl, areq->first_rsgl.sgl.sgt.sgl, len, ctx->iv); if (ctx->state) { err = crypto_skcipher_import(&areq->cra_u.skcipher_req, ctx->state); sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm)); ctx->state = NULL; if (err) goto free; cflags |= CRYPTO_SKCIPHER_REQ_CONT; } if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) { /* AIO operation */ sock_hold(sk); areq->iocb = msg->msg_iocb; /* Remember output size that will be generated. */ areq->outlen = len; skcipher_request_set_callback(&areq->cra_u.skcipher_req, cflags | CRYPTO_TFM_REQ_MAY_SLEEP, algif_skcipher_done, areq); err = ctx->enc ? crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) : crypto_skcipher_decrypt(&areq->cra_u.skcipher_req); /* AIO operation in progress */ if (err == -EINPROGRESS) return -EIOCBQUEUED; sock_put(sk); } else { /* Synchronous operation */ skcipher_request_set_callback(&areq->cra_u.skcipher_req, cflags | CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &ctx->wait); err = crypto_wait_req(ctx->enc ? crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) : crypto_skcipher_decrypt(&areq->cra_u.skcipher_req), &ctx->wait); if (!err) err = algif_skcipher_export( sk, &areq->cra_u.skcipher_req); } free: af_alg_free_resources(areq); return err ? err : len; } static int skcipher_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { struct sock *sk = sock->sk; int ret = 0; lock_sock(sk); while (msg_data_left(msg)) { int err = _skcipher_recvmsg(sock, msg, ignored, flags); /* * This error covers -EIOCBQUEUED which implies that we can * only handle one AIO request. If the caller wants to have * multiple AIO requests in parallel, he must make multiple * separate AIO calls. * * Also return the error if no data has been processed so far. */ if (err <= 0) { if (err == -EIOCBQUEUED || !ret) ret = err; goto out; } ret += err; } out: af_alg_wmem_wakeup(sk); release_sock(sk); return ret; } static struct proto_ops algif_skcipher_ops = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .release = af_alg_release, .sendmsg = skcipher_sendmsg, .recvmsg = skcipher_recvmsg, .poll = af_alg_poll, }; static int skcipher_check_key(struct socket *sock) { int err = 0; struct sock *psk; struct alg_sock *pask; struct crypto_skcipher *tfm; struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); lock_sock(sk); if (!atomic_read(&ask->nokey_refcnt)) goto unlock_child; psk = ask->parent; pask = alg_sk(ask->parent); tfm = pask->private; err = -ENOKEY; lock_sock_nested(psk, SINGLE_DEPTH_NESTING); if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) goto unlock; atomic_dec(&pask->nokey_refcnt); atomic_set(&ask->nokey_refcnt, 0); err = 0; unlock: release_sock(psk); unlock_child: release_sock(sk); return err; } static int skcipher_sendmsg_nokey(struct socket *sock, struct msghdr *msg, size_t size) { int err; err = skcipher_check_key(sock); if (err) return err; return skcipher_sendmsg(sock, msg, size); } static int skcipher_recvmsg_nokey(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { int err; err = skcipher_check_key(sock); if (err) return err; return skcipher_recvmsg(sock, msg, ignored, flags); } static struct proto_ops algif_skcipher_ops_nokey = { .family = PF_ALG, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, .release = af_alg_release, .sendmsg = skcipher_sendmsg_nokey, .recvmsg = skcipher_recvmsg_nokey, .poll = af_alg_poll, }; static void *skcipher_bind(const char *name, u32 type, u32 mask) { return crypto_alloc_skcipher(name, type, mask); } static void skcipher_release(void *private) { crypto_free_skcipher(private); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { return crypto_skcipher_setkey(private, key, keylen); } static void skcipher_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct af_alg_ctx *ctx = ask->private; struct sock *psk = ask->parent; struct alg_sock *pask = alg_sk(psk); struct crypto_skcipher *tfm = pask->private; af_alg_pull_tsgl(sk, ctx->used, NULL, 0); sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm)); if (ctx->state) sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm)); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); } static int skcipher_accept_parent_nokey(void *private, struct sock *sk) { struct af_alg_ctx *ctx; struct alg_sock *ask = alg_sk(sk); struct crypto_skcipher *tfm = private; unsigned int len = sizeof(*ctx); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; memset(ctx, 0, len); ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(tfm), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } memset(ctx->iv, 0, crypto_skcipher_ivsize(tfm)); INIT_LIST_HEAD(&ctx->tsgl_list); ctx->len = len; crypto_init_wait(&ctx->wait); ask->private = ctx; sk->sk_destruct = skcipher_sock_destruct; return 0; } static int skcipher_accept_parent(void *private, struct sock *sk) { struct crypto_skcipher *tfm = private; if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return skcipher_accept_parent_nokey(private, sk); } static const struct af_alg_type algif_type_skcipher = { .bind = skcipher_bind, .release = skcipher_release, .setkey = skcipher_setkey, .accept = skcipher_accept_parent, .accept_nokey = skcipher_accept_parent_nokey, .ops = &algif_skcipher_ops, .ops_nokey = &algif_skcipher_ops_nokey, .name = "skcipher", .owner = THIS_MODULE }; static int __init algif_skcipher_init(void) { return af_alg_register_type(&algif_type_skcipher); } static void __exit algif_skcipher_exit(void) { int err = af_alg_unregister_type(&algif_type_skcipher); BUG_ON(err); } module_init(algif_skcipher_init); module_exit(algif_skcipher_exit); MODULE_DESCRIPTION("Userspace interface for skcipher algorithms"); MODULE_LICENSE("GPL"); |
| 215 189 192 196 196 192 28 25 197 197 28 25 191 10 197 195 195 196 170 12 20 19 191 1106 1093 197 195 195 195 192 25 191 55 55 331 244 209 203 6 120 96 38 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dsa/user.c - user device handling * Copyright (c) 2008-2009 Marvell Semiconductor */ #include <linux/list.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> #include <linux/phylink.h> #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/selftests.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/if_hsr.h> #include <net/dcbnl.h> #include <linux/netpoll.h> #include <linux/string.h> #include "conduit.h" #include "dsa.h" #include "netlink.h" #include "port.h" #include "switch.h" #include "tag.h" #include "user.h" struct dsa_switchdev_event_work { struct net_device *dev; struct net_device *orig_dev; struct work_struct work; unsigned long event; /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and * SWITCHDEV_FDB_DEL_TO_DEVICE */ unsigned char addr[ETH_ALEN]; u16 vid; bool host_addr; }; enum dsa_standalone_event { DSA_UC_ADD, DSA_UC_DEL, DSA_MC_ADD, DSA_MC_DEL, }; struct dsa_standalone_event_work { struct work_struct work; struct net_device *dev; enum dsa_standalone_event event; unsigned char addr[ETH_ALEN]; u16 vid; }; struct dsa_host_vlan_rx_filtering_ctx { struct net_device *dev; const unsigned char *addr; enum dsa_standalone_event event; }; static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) { return ds->ops->port_fdb_add && ds->ops->port_fdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) { return ds->ops->port_mdb_add && ds->ops->port_mdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static void dsa_user_standalone_event_work(struct work_struct *work) { struct dsa_standalone_event_work *standalone_work = container_of(work, struct dsa_standalone_event_work, work); const unsigned char *addr = standalone_work->addr; struct net_device *dev = standalone_work->dev; struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_mdb mdb; struct dsa_switch *ds = dp->ds; u16 vid = standalone_work->vid; int err; switch (standalone_work->event) { case DSA_UC_ADD: err = dsa_port_standalone_host_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_UC_DEL: err = dsa_port_standalone_host_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; case DSA_MC_ADD: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_add(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to mdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_MC_DEL: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_del(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from mdb: %d\n", dp->index, addr, vid, err); } break; } kfree(standalone_work); } static int dsa_user_schedule_standalone_work(struct net_device *dev, enum dsa_standalone_event event, const unsigned char *addr, u16 vid) { struct dsa_standalone_event_work *standalone_work; standalone_work = kzalloc(sizeof(*standalone_work), GFP_ATOMIC); if (!standalone_work) return -ENOMEM; INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); standalone_work->event = event; standalone_work->dev = dev; ether_addr_copy(standalone_work->addr, addr); standalone_work->vid = vid; dsa_schedule_work(&standalone_work->work); return 0; } static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, ctx->addr, vid); } static int dsa_user_vlan_for_each(struct net_device *dev, int (*cb)(void *arg, int vid), void *arg) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_vlan *v; int err; lockdep_assert_held(&dev->addr_list_lock); err = cb(arg, 0); if (err) return err; list_for_each_entry(v, &dp->user_vlans, list) { err = cb(arg, v->vid); if (err) return err; } return 0; } static int dsa_user_sync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_ADD, }; dev_uc_add(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_DEL, }; dev_uc_del(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_sync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_ADD, }; dev_mc_add(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_DEL, }; dev_mc_del(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } void dsa_user_sync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_sync_mc(dev, ha->addr); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_sync_uc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } void dsa_user_unsync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_unsync_uc(dev, ha->addr); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_unsync_mc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } /* user mii_bus handling ***************************************************/ static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_read(ds, addr, reg); return 0xffff; } static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_write(ds, addr, reg, val); return 0; } void dsa_user_mii_bus_init(struct dsa_switch *ds) { ds->user_mii_bus->priv = (void *)ds; ds->user_mii_bus->name = "dsa user smi"; ds->user_mii_bus->read = dsa_user_phy_read; ds->user_mii_bus->write = dsa_user_phy_write; snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", ds->dst->index, ds->index); ds->user_mii_bus->parent = ds->dev; ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; } /* user device handling ****************************************************/ static int dsa_user_get_iflink(const struct net_device *dev) { return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; if (dsa_switch_supports_uc_filtering(ds)) { err = dsa_port_standalone_host_fdb_add(dp, addr, 0); if (err) goto out; } if (!ether_addr_equal(addr, conduit->dev_addr)) { err = dev_uc_add(conduit, addr); if (err < 0) goto del_host_addr; } return 0; del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, addr, 0); out: return err; } void dsa_user_host_uc_uninstall(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); } static int dsa_user_open(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); int err; err = dev_open(conduit, NULL); if (err < 0) { netdev_err(dev, "failed to open conduit %s\n", conduit->name); goto out; } err = dsa_user_host_uc_install(dev, dev->dev_addr); if (err) goto out; err = dsa_port_enable_rt(dp, dev->phydev); if (err) goto out_del_host_uc; return 0; out_del_host_uc: dsa_user_host_uc_uninstall(dev); out: return err; } static int dsa_user_close(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); dsa_port_disable_rt(dp); dsa_user_host_uc_uninstall(dev); return 0; } static void dsa_user_manage_host_flood(struct net_device *dev) { bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); struct dsa_port *dp = dsa_user_to_port(dev); bool uc = dev->flags & IFF_PROMISC; dsa_port_set_host_flood(dp, uc, mc); } static void dsa_user_change_rx_flags(struct net_device *dev, int change) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (change & IFF_ALLMULTI) dev_set_allmulti(conduit, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(conduit, dev->flags & IFF_PROMISC ? 1 : -1); if (dsa_switch_supports_uc_filtering(ds) && dsa_switch_supports_mc_filtering(ds)) dsa_user_manage_host_flood(dev); } static void dsa_user_set_rx_mode(struct net_device *dev) { __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); } static int dsa_user_set_mac_address(struct net_device *dev, void *a) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (ds->ops->port_set_mac_address) { err = ds->ops->port_set_mac_address(ds, dp->index, addr->sa_data); if (err) return err; } /* If the port is down, the address isn't synced yet to hardware or * to the DSA conduit, so there is nothing to change. */ if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; err = dsa_user_host_uc_install(dev, addr->sa_data); if (err) return err; dsa_user_host_uc_uninstall(dev); out_change_dev_addr: eth_hw_addr_set(dev, addr->sa_data); return 0; } struct dsa_user_dump_ctx { struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; int idx; }; static int dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data) { struct dsa_user_dump_ctx *dump = data; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; if (dump->idx < dump->cb->args[2]) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, sizeof(*ndm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dump->dev->ifindex; ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) goto nla_put_failure; nlmsg_end(dump->skb, nlh); skip: dump->idx++; return 0; nla_put_failure: nlmsg_cancel(dump->skb, nlh); return -EMSGSIZE; } static int dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; int err; err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); *idx = dump.idx; return err; } static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; int port = p->dp->index; /* Pass through to switch driver if it supports timestamping */ switch (cmd) { case SIOCGHWTSTAMP: if (ds->ops->port_hwtstamp_get) return ds->ops->port_hwtstamp_get(ds, port, ifr); break; case SIOCSHWTSTAMP: if (ds->ops->port_hwtstamp_set) return ds->ops->port_hwtstamp_set(ds, port, ifr); break; } return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int ret; if (ctx && ctx != dp) return 0; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_state(dp, attr->u.stp_state, true); break; case SWITCHDEV_ATTR_ID_PORT_MST_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_mst_state(dp, &attr->u.mst_state, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_BRIDGE_MST: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_mst_enable(dp, attr->u.mst, extack); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_VLAN_MSTI: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_msti(dp, &attr->u.vlan_msti); break; default: ret = -EOPNOTSUPP; break; } return ret; } /* Must be called under rcu_read_lock() */ static int dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, const struct switchdev_obj_port_vlan *vlan) { struct net_device *upper_dev; struct list_head *iter; netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { u16 vid; if (!is_vlan_dev(upper_dev)) continue; vid = vlan_dev_vlan_id(upper_dev); if (vid == vlan->vid) return -EBUSY; } return 0; } static int dsa_user_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; int err; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); err = dsa_user_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, "Port already has a VLAN upper with this VID"); return err; } } return dsa_port_vlan_add(dp, vlan, extack); } /* Offload a VLAN installed on the bridge or on a foreign interface by * installing it as a VLAN towards the CPU port. */ static int dsa_user_host_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); /* Even though drivers often handle CPU membership in special ways, * it doesn't make sense to program a PVID, so clear this flag. */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; return dsa_port_host_vlan_add(dp, &vlan, extack); } static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_add(dev, obj, extack); else err = dsa_user_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static int dsa_user_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_vlan_del(dp, vlan); } static int dsa_user_host_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_host_vlan_del(dp, vlan); } static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_del(dev, obj); else err = dsa_user_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER struct dsa_user_priv *p = netdev_priv(dev); return netpoll_send_skb(p->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) return; if (!ds->ops->port_txtstamp) return; ds->ops->port_txtstamp(ds, p->dp->index, skb); } netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) { /* SKB for netpoll still need to be mangled with the protocol-specific * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) return dsa_user_netpoll_send_skb(dev, skb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ skb->dev = dsa_user_to_conduit(dev); dev_queue_xmit(skb); return NETDEV_TX_OK; } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct sk_buff *nskb; dev_sw_netstats_tx_add(dev, 1, skb->len); memset(skb->cb, 0, sizeof(skb->cb)); /* Handle tx timestamp if any */ dsa_skb_tx_timestamp(p, skb); if (skb_ensure_writable_head_tail(skb, dev)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* needed_tailroom should still be 'warm' in the cache line from * skb_ensure_writable_head_tail(), which has also ensured that * padding is safe. */ if (dev->needed_tailroom) eth_skb_pad(skb); /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ nskb = p->xmit(skb, dev); if (!nskb) { kfree_skb(skb); return NETDEV_TX_OK; } return dsa_enqueue_skb(nskb, dev); } /* ethtool operations *******************************************************/ static void dsa_user_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } static int dsa_user_get_regs_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } static void dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) ds->ops->get_regs(ds, dp->index, regs, _p); } static int dsa_user_nway_reset(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_nway_reset(dp->pl); } static int dsa_user_get_eeprom_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; if (ds->ops->get_eeprom_len) return ds->ops->get_eeprom_len(ds); return 0; } static int dsa_user_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static int dsa_user_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static void dsa_user_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { int len = ETH_GSTRING_LEN; strscpy_pad(data, "tx_packets", len); strscpy_pad(data + len, "tx_bytes", len); strscpy_pad(data + 2 * len, "rx_packets", len); strscpy_pad(data + 3 * len, "rx_bytes", len); if (ds->ops->get_strings) ds->ops->get_strings(ds, dp->index, stringset, data + 4 * len); } else if (stringset == ETH_SS_TEST) { net_selftest_get_strings(data); } } static void dsa_user_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; for_each_possible_cpu(i) { u64 tx_packets, tx_bytes, rx_packets, rx_bytes; s = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin(&s->syncp); tx_packets = u64_stats_read(&s->tx_packets); tx_bytes = u64_stats_read(&s->tx_bytes); rx_packets = u64_stats_read(&s->rx_packets); rx_bytes = u64_stats_read(&s->rx_bytes); } while (u64_stats_fetch_retry(&s->syncp, start)); data[0] += tx_packets; data[1] += tx_bytes; data[2] += rx_packets; data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_user_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count = 0; if (ds->ops->get_sset_count) { count = ds->ops->get_sset_count(ds, dp->index, sset); if (count < 0) return count; } return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } return -EOPNOTSUPP; } static void dsa_user_get_eth_phy_stats(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_phy_stats) ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); } static void dsa_user_get_eth_mac_stats(struct net_device *dev, struct ethtool_eth_mac_stats *mac_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_mac_stats) ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); } static void dsa_user_get_eth_ctrl_stats(struct net_device *dev, struct ethtool_eth_ctrl_stats *ctrl_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_ctrl_stats) ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); } static void dsa_user_get_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_rmon_stats) ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } static void dsa_user_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { struct dsa_port *dp = dsa_user_to_port(ndev); struct dsa_switch *ds = dp->ds; if (ds->ops->self_test) { ds->ops->self_test(ds, dp->index, etest, buf); return; } net_selftest(ndev, etest, buf); } static int dsa_user_get_mm(struct net_device *dev, struct ethtool_mm_state *state) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_mm) return -EOPNOTSUPP; return ds->ops->get_mm(ds, dp->index, state); } static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_mm) return -EOPNOTSUPP; return ds->ops->set_mm(ds, dp->index, cfg, extack); } static void dsa_user_get_mm_stats(struct net_device *dev, struct ethtool_mm_stats *stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_mm_stats) ds->ops->get_mm_stats(ds, dp->index, stats); } static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; phylink_ethtool_get_wol(dp->pl, w); if (ds->ops->get_wol) ds->ops->get_wol(ds, dp->index, w); } static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; phylink_ethtool_set_wol(dp->pl, w); if (ds->ops->set_wol) ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_set_eee(dp->pl, e); } static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) return -EOPNOTSUPP; ret = ds->ops->get_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_get_eee(dp->pl, e); } static int dsa_user_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_get(dp->pl, cmd); } static int dsa_user_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_set(dp->pl, cmd); } static void dsa_user_get_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_pause_stats) ds->ops->get_pause_stats(ds, dp->index, pause_stats); } static void dsa_user_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); phylink_ethtool_get_pauseparam(dp->pl, pause); } static int dsa_user_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_set_pauseparam(dp->pl, pause); } #ifdef CONFIG_NET_POLL_CONTROLLER static int dsa_user_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll; int err = 0; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); if (!netpoll) return -ENOMEM; err = __netpoll_setup(netpoll, conduit); if (err) { kfree(netpoll); goto out; } p->netpoll = netpoll; out: return err; } static void dsa_user_netpoll_cleanup(struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll = p->netpoll; if (!netpoll) return; p->netpoll = NULL; __netpoll_free(netpoll); } static void dsa_user_poll_controller(struct net_device *dev) { } #endif static struct dsa_mall_tc_entry * dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) if (mall_tc_entry->cookie == cookie) return mall_tc_entry; return NULL; } static int dsa_user_add_cls_matchall_mirred(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_mirror_tc_entry *mirror; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; struct dsa_port *to_dp; int err; if (!ds->ops->port_mirror_add) return -EOPNOTSUPP; if (!flow_action_basic_hw_stats_check(&cls->rule->action, cls->common.extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; if (!act->dev) return -EINVAL; if (!dsa_user_dev_check(act->dev)) return -EOPNOTSUPP; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; to_dp = dsa_user_to_port(act->dev); mirror->to_local_port = to_dp->index; mirror->ingress = ingress; err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress, extack); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall_police(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_policer_tc_entry *policer; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; int err; if (!ds->ops->port_policer_add) { NL_SET_ERR_MSG_MOD(extack, "Policing offload not implemented"); return -EOPNOTSUPP; } if (!ingress) { NL_SET_ERR_MSG_MOD(extack, "Only supported on ingress qdisc"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, cls->common.extack)) return -EOPNOTSUPP; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) { NL_SET_ERR_MSG_MOD(extack, "Only one port policer allowed"); return -EEXIST; } } act = &cls->rule->action.entries[0]; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_POLICER; policer = &mall_tc_entry->policer; policer->rate_bytes_per_sec = act->police.rate_bytes_ps; policer->burst = act->police.burst; err = ds->ops->port_policer_add(ds, dp->index, policer); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { int err = -EOPNOTSUPP; if (cls->common.protocol == htons(ETH_P_ALL) && flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_MIRRED) err = dsa_user_add_cls_matchall_mirred(dev, cls, ingress); else if (flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_POLICE) err = dsa_user_add_cls_matchall_police(dev, cls, ingress); return err; } static void dsa_user_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; list_del(&mall_tc_entry->list); switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: if (ds->ops->port_mirror_del) ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; case DSA_PORT_MALL_POLICER: if (ds->ops->port_policer_del) ds->ops->port_policer_del(ds, dp->index); break; default: WARN_ON(1); } kfree(mall_tc_entry); } static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { if (cls->common.chain_index) return -EOPNOTSUPP; switch (cls->command) { case TC_CLSMATCHALL_REPLACE: return dsa_user_add_cls_matchall(dev, cls, ingress); case TC_CLSMATCHALL_DESTROY: dsa_user_del_cls_matchall(dev, cls); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_add_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_add) return -EOPNOTSUPP; return ds->ops->cls_flower_add(ds, port, cls, ingress); } static int dsa_user_del_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_del) return -EOPNOTSUPP; return ds->ops->cls_flower_del(ds, port, cls, ingress); } static int dsa_user_stats_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_stats) return -EOPNOTSUPP; return ds->ops->cls_flower_stats(ds, port, cls, ingress); } static int dsa_user_setup_tc_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { switch (cls->command) { case FLOW_CLS_REPLACE: return dsa_user_add_cls_flower(dev, cls, ingress); case FLOW_CLS_DESTROY: return dsa_user_del_cls_flower(dev, cls, ingress); case FLOW_CLS_STATS: return dsa_user_stats_cls_flower(dev, cls, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv, bool ingress) { struct net_device *dev = cb_priv; if (!tc_can_offload(dev)) return -EOPNOTSUPP; switch (type) { case TC_SETUP_CLSMATCHALL: return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); case TC_SETUP_CLSFLOWER: return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); } static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); } static LIST_HEAD(dsa_user_block_cb_list); static int dsa_user_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_user_setup_tc_block_cb_ig; else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) cb = dsa_user_setup_tc_block_cb_eg; else return -EOPNOTSUPP; f->driver_block_list = &dsa_user_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, void *type_data) { struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); if (!conduit->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); } static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; switch (type) { case TC_SETUP_BLOCK: return dsa_user_setup_tc_block(dev, type_data); case TC_SETUP_FT: return dsa_user_setup_ft_block(ds, dp->index, type_data); default: break; } if (!ds->ops->port_setup_tc) return -EOPNOTSUPP; return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } static int dsa_user_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_user_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; return ds->ops->set_rxnfc(ds, dp->index, nfc); } static int dsa_user_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *ts) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; if (!ds->ops->get_ts_info) return -EOPNOTSUPP; return ds->ops->get_ts_info(ds, p->dp->index, ts); } static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct netlink_ext_ack extack = {0}; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int ret; /* User port... */ ret = dsa_port_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); return ret; } /* And CPU port... */ ret = dsa_port_host_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, extack._msg); return ret; } if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { ret = -ENOMEM; goto rollback; } netif_addr_lock_bh(dev); v->vid = vid; list_add_tail(&v->list, &dp->user_vlans); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; rollback: dsa_port_host_vlan_del(dp, &vlan); dsa_port_vlan_del(dp, &vlan); return ret; } static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int err; err = dsa_port_vlan_del(dp, &vlan); if (err) return err; err = dsa_port_host_vlan_del(dp, &vlan); if (err) return err; if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; netif_addr_lock_bh(dev); v = dsa_vlan_find(&dp->user_vlans, &vlan); if (!v) { netif_addr_unlock_bh(dev); return -ENOENT; } list_del(&v->list); kfree(v); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; } static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_add_vid(arg, proto, vid); } static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_kill_vid(arg, proto, vid); } /* Keep the VLAN RX filtering list in sync with the hardware only if VLAN * filtering is enabled. The baseline is that only ports that offload a * VLAN-aware bridge are VLAN-aware, and standalone ports are VLAN-unaware, * but there are exceptions for quirky hardware. * * If ds->vlan_filtering_is_global = true, then standalone ports which share * the same switch with other ports that offload a VLAN-aware bridge are also * inevitably VLAN-aware. * * To summarize, a DSA switch port offloads: * * - If standalone (this includes software bridge, software LAG): * - if ds->needs_standalone_vlan_filtering = true, OR if * (ds->vlan_filtering_is_global = true AND there are bridges spanning * this switch chip which have vlan_filtering=1) * - the 8021q upper VLANs * - else (standalone VLAN filtering is not needed, VLAN filtering is not * global, or it is, but no port is under a VLAN-aware bridge): * - no VLAN (any 8021q upper is a software VLAN) * * - If under a vlan_filtering=0 bridge which it offload: * - if ds->configure_vlan_while_not_filtering = true (default): * - the bridge VLANs. These VLANs are committed to hardware but inactive. * - else (deprecated): * - no VLAN. The bridge VLANs are not restored when VLAN awareness is * enabled, so this behavior is broken and discouraged. * * - If under a vlan_filtering=1 bridge which it offload: * - the bridge VLANs * - the 8021q upper VLANs */ int dsa_user_manage_vlan_filtering(struct net_device *user, bool vlan_filtering) { int err; if (vlan_filtering) { user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; err = vlan_for_each(user, dsa_user_restore_vlan, user); if (err) { vlan_for_each(user, dsa_user_clear_vlan, user); user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; return err; } } else { err = vlan_for_each(user, dsa_user_clear_vlan, user); if (err) return err; user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; } return 0; } struct dsa_hw_port { struct list_head list; struct net_device *dev; int old_mtu; }; static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu) { const struct dsa_hw_port *p; int err; list_for_each_entry(p, hw_port_list, list) { if (p->dev->mtu == mtu) continue; err = dev_set_mtu(p->dev, mtu); if (err) goto rollback; } return 0; rollback: list_for_each_entry_continue_reverse(p, hw_port_list, list) { if (p->dev->mtu == p->old_mtu) continue; if (dev_set_mtu(p->dev, p->old_mtu)) netdev_err(p->dev, "Failed to restore MTU\n"); } return err; } static void dsa_hw_port_list_free(struct list_head *hw_port_list) { struct dsa_hw_port *p, *n; list_for_each_entry_safe(p, n, hw_port_list, list) kfree(p); } /* Make the hardware datapath to/from @dev limited to a common MTU */ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) { struct list_head hw_port_list; struct dsa_switch_tree *dst; int min_mtu = ETH_MAX_MTU; struct dsa_port *other_dp; int err; if (!dp->ds->mtu_enforcement_ingress) return; if (!dp->bridge) return; INIT_LIST_HEAD(&hw_port_list); /* Populate the list of ports that are part of the same bridge * as the newly added/modified port */ list_for_each_entry(dst, &dsa_tree_list, list) { list_for_each_entry(other_dp, &dst->ports, list) { struct dsa_hw_port *hw_port; struct net_device *user; if (other_dp->type != DSA_PORT_TYPE_USER) continue; if (!dsa_port_bridge_same(dp, other_dp)) continue; if (!other_dp->ds->mtu_enforcement_ingress) continue; user = other_dp->user; if (min_mtu > user->mtu) min_mtu = user->mtu; hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); if (!hw_port) goto out; hw_port->dev = user; hw_port->old_mtu = user->mtu; list_add(&hw_port->list, &hw_port_list); } } /* Attempt to configure the entire hardware bridge to the newly added * interface's MTU first, regardless of whether the intention of the * user was to raise or lower it. */ err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); if (!err) goto out; /* Clearly that didn't work out so well, so just set the minimum MTU on * all hardware bridge ports now. If this fails too, then all ports will * still have their old MTU rolled back anyway. */ dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu); out: dsa_hw_port_list_free(&hw_port_list); } int dsa_user_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_port *cpu_dp = dp->cpu_dp; struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int largest_mtu = 0; int new_conduit_mtu; int old_conduit_mtu; int mtu_limit; int overhead; int cpu_mtu; int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; dsa_tree_for_each_user_port(other_dp, ds->dst) { int user_mtu; /* During probe, this function will be called for each user * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ if (!other_dp->user) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ if (dp == other_dp) user_mtu = new_mtu; else user_mtu = other_dp->user->mtu; if (largest_mtu < user_mtu) largest_mtu = user_mtu; } overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); old_conduit_mtu = conduit->mtu; new_conduit_mtu = largest_mtu + overhead; if (new_conduit_mtu > mtu_limit) return -ERANGE; /* If the conduit MTU isn't over limit, there's no need to check the CPU * MTU, since that surely isn't either. */ cpu_mtu = largest_mtu; /* Start applying stuff */ if (new_conduit_mtu != old_conduit_mtu) { err = dev_set_mtu(conduit, new_conduit_mtu); if (err < 0) goto out_conduit_failed; /* We only need to propagate the MTU of the CPU port to * upstream switches, so emit a notifier which updates them. */ err = dsa_port_mtu_change(cpu_dp, cpu_mtu); if (err) goto out_cpu_failed; } err = ds->ops->port_change_mtu(ds, dp->index, new_mtu); if (err) goto out_port_failed; WRITE_ONCE(dev->mtu, new_mtu); dsa_bridge_mtu_normalization(dp); return 0; out_port_failed: if (new_conduit_mtu != old_conduit_mtu) dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); out_cpu_failed: if (new_conduit_mtu != old_conduit_mtu) dev_set_mtu(conduit, old_conduit_mtu); out_conduit_failed: return err; } static int __maybe_unused dsa_user_dcbnl_set_apptrust(struct net_device *dev, u8 *sel, int nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_set_apptrust) return -EOPNOTSUPP; return ds->ops->port_set_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_get_apptrust(struct net_device *dev, u8 *sel, int *nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_get_apptrust) return -EOPNOTSUPP; return ds->ops->port_get_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } return 0; } /* Update the DSCP prio entries on all user ports of the switch in case * the switch supports global DSCP prio instead of per port DSCP prios. */ static int dsa_user_dcbnl_ieee_global_dscp_setdel(struct net_device *dev, struct dcb_app *app, bool del) { int (*setdel)(struct net_device *dev, struct dcb_app *app); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int err, restore_err; if (del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; err = setdel(user, app); if (err) goto err_try_to_restore; } return 0; err_try_to_restore: /* Revert logic to restore previous state of app entries */ if (!del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port_continue_reverse(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; restore_err = setdel(user, app); if (restore_err) netdev_err(user, "Failed to restore DSCP prio entry configuration\n"); } return err; } static int __maybe_unused dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_add_dscp_prio) return -EOPNOTSUPP; if (dscp >= 64) { netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n", dscp); return -EINVAL; } err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_add_dscp_prio(ds, port, dscp, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, false); if (err) { if (ds->ops->port_del_dscp_prio) ds->ops->port_del_dscp_prio(ds, port, dscp, new_prio); dcb_ieee_delapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_set_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_add_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } static int __maybe_unused dsa_user_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = mask ? __fls(mask) : 0; err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_del_dscp_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; err = ds->ops->port_del_dscp_prio(ds, port, dscp, app->priority); if (err) { dcb_ieee_setapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, true); if (err) { if (ds->ops->port_add_dscp_prio) ds->ops->port_add_dscp_prio(ds, port, dscp, app->priority); dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_del_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_del_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } /* Pre-populate the DCB application priority table with the priorities * configured during switch setup, which we read from hardware here. */ static int dsa_user_dcbnl_init(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; int err; if (ds->ops->port_get_default_prio) { int prio = ds->ops->port_get_default_prio(ds, port); struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE, .protocol = 0, .priority = prio, }; if (prio < 0) return prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } if (ds->ops->port_get_dscp_prio) { int protocol; for (protocol = 0; protocol < 64; protocol++) { struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_DSCP, .protocol = protocol, }; int prio; prio = ds->ops->port_get_dscp_prio(ds, port, protocol); if (prio == -EOPNOTSUPP) continue; if (prio < 0) return prio; app.priority = prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } } return 0; } static const struct ethtool_ops dsa_user_ethtool_ops = { .get_drvinfo = dsa_user_get_drvinfo, .get_regs_len = dsa_user_get_regs_len, .get_regs = dsa_user_get_regs, .nway_reset = dsa_user_nway_reset, .get_link = ethtool_op_get_link, .get_eeprom_len = dsa_user_get_eeprom_len, .get_eeprom = dsa_user_get_eeprom, .set_eeprom = dsa_user_set_eeprom, .get_strings = dsa_user_get_strings, .get_ethtool_stats = dsa_user_get_ethtool_stats, .get_sset_count = dsa_user_get_sset_count, .get_eth_phy_stats = dsa_user_get_eth_phy_stats, .get_eth_mac_stats = dsa_user_get_eth_mac_stats, .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, .get_rmon_stats = dsa_user_get_rmon_stats, .set_wol = dsa_user_set_wol, .get_wol = dsa_user_get_wol, .set_eee = dsa_user_set_eee, .get_eee = dsa_user_get_eee, .get_link_ksettings = dsa_user_get_link_ksettings, .set_link_ksettings = dsa_user_set_link_ksettings, .get_pause_stats = dsa_user_get_pause_stats, .get_pauseparam = dsa_user_get_pauseparam, .set_pauseparam = dsa_user_set_pauseparam, .get_rxnfc = dsa_user_get_rxnfc, .set_rxnfc = dsa_user_set_rxnfc, .get_ts_info = dsa_user_get_ts_info, .self_test = dsa_user_net_selftest, .get_mm = dsa_user_get_mm, .set_mm = dsa_user_set_mm, .get_mm_stats = dsa_user_get_mm_stats, }; static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { .ieee_setapp = dsa_user_dcbnl_ieee_setapp, .ieee_delapp = dsa_user_dcbnl_ieee_delapp, .dcbnl_setapptrust = dsa_user_dcbnl_set_apptrust, .dcbnl_getapptrust = dsa_user_dcbnl_get_apptrust, }; static void dsa_user_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_stats64) ds->ops->get_stats64(ds, dp->index, s); else dev_get_tstats64(dev, s); } static int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct dsa_port *dp = dsa_user_to_port(ctx->dev); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_port *cpu_dp = dp->cpu_dp; path->dev = ctx->dev; path->type = DEV_PATH_DSA; path->dsa.proto = cpu_dp->tag_ops->proto; path->dsa.port = dp->index; ctx->dev = conduit; return 0; } static const struct net_device_ops dsa_user_netdev_ops = { .ndo_open = dsa_user_open, .ndo_stop = dsa_user_close, .ndo_start_xmit = dsa_user_xmit, .ndo_change_rx_flags = dsa_user_change_rx_flags, .ndo_set_rx_mode = dsa_user_set_rx_mode, .ndo_set_mac_address = dsa_user_set_mac_address, .ndo_fdb_dump = dsa_user_fdb_dump, .ndo_eth_ioctl = dsa_user_ioctl, .ndo_get_iflink = dsa_user_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = dsa_user_netpoll_setup, .ndo_netpoll_cleanup = dsa_user_netpoll_cleanup, .ndo_poll_controller = dsa_user_poll_controller, #endif .ndo_setup_tc = dsa_user_setup_tc, .ndo_get_stats64 = dsa_user_get_stats64, .ndo_vlan_rx_add_vid = dsa_user_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_user_vlan_rx_kill_vid, .ndo_change_mtu = dsa_user_change_mtu, .ndo_fill_forward_path = dsa_user_fill_forward_path, }; static const struct device_type dsa_type = { .name = "dsa", }; void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) { const struct dsa_port *dp = dsa_to_port(ds, port); if (dp->pl) phylink_mac_change(dp->pl, up); } EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); static void dsa_user_phylink_fixed_state(struct phylink_config *config, struct phylink_link_state *state) { struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; /* No need to check that this operation is valid, the callback would * not be called if it was not. */ ds->ops->phylink_fixed_state(ds, dp->index, state); } /* user device setup *******************************************************/ static int dsa_user_phy_connect(struct net_device *user_dev, int addr, u32 flags) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_switch *ds = dp->ds; user_dev->phydev = mdiobus_get_phy(ds->user_mii_bus, addr); if (!user_dev->phydev) { netdev_err(user_dev, "no phy at %d\n", addr); return -ENODEV; } user_dev->phydev->dev_flags |= flags; return phylink_connect_phy(dp->pl, user_dev->phydev); } static int dsa_user_phy_setup(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; u32 phy_flags = 0; int ret; dp->pl_config.dev = &user_dev->dev; dp->pl_config.type = PHYLINK_NETDEV; /* The get_fixed_state callback takes precedence over polling the * link GPIO in PHYLINK (see phylink_get_fixed_state). Only set * this if the switch provides such a callback. */ if (ds->ops->phylink_fixed_state) { dp->pl_config.get_fixed_state = dsa_user_phylink_fixed_state; dp->pl_config.poll_fixed_state = true; } ret = dsa_port_phylink_create(dp); if (ret) return ret; if (ds->ops->get_phy_flags) phy_flags = ds->ops->get_phy_flags(ds, dp->index); ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); if (ret == -ENODEV && ds->user_mii_bus) { /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ ret = dsa_user_phy_connect(user_dev, dp->index, phy_flags); } if (ret) { netdev_err(user_dev, "failed to connect to PHY: %pe\n", ERR_PTR(ret)); dsa_port_phylink_destroy(dp); } return ret; } void dsa_user_setup_tagger(struct net_device *user) { struct dsa_port *dp = dsa_user_to_port(user); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_user_priv *p = netdev_priv(user); const struct dsa_port *cpu_dp = dp->cpu_dp; const struct dsa_switch *ds = dp->ds; user->needed_headroom = cpu_dp->tag_ops->needed_headroom; user->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; /* Try to save one extra realloc later in the TX path (in the conduit) * by also inheriting the conduit's needed headroom and tailroom. * The 8021q driver also does this. */ user->needed_headroom += conduit->needed_headroom; user->needed_tailroom += conduit->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; user->features = conduit->vlan_features | NETIF_F_HW_TC; user->hw_features |= NETIF_F_HW_TC; user->features |= NETIF_F_LLTX; if (user->needed_tailroom) user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } int dsa_user_suspend(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_detach(user_dev); rtnl_lock(); phylink_stop(dp->pl); rtnl_unlock(); return 0; } int dsa_user_resume(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_attach(user_dev); rtnl_lock(); phylink_start(dp->pl); rtnl_unlock(); return 0; } int dsa_user_create(struct dsa_port *port) { struct net_device *conduit = dsa_port_to_conduit(port); struct dsa_switch *ds = port->ds; struct net_device *user_dev; struct dsa_user_priv *p; const char *name; int assign_type; int ret; if (!ds->num_tx_queues) ds->num_tx_queues = 1; if (port->name) { name = port->name; assign_type = NET_NAME_PREDICTABLE; } else { name = "eth%d"; assign_type = NET_NAME_ENUM; } user_dev = alloc_netdev_mqs(sizeof(struct dsa_user_priv), name, assign_type, ether_setup, ds->num_tx_queues, 1); if (user_dev == NULL) return -ENOMEM; user_dev->rtnl_link_ops = &dsa_link_ops; user_dev->ethtool_ops = &dsa_user_ethtool_ops; #if IS_ENABLED(CONFIG_DCB) user_dev->dcbnl_ops = &dsa_user_dcbnl_ops; #endif if (!is_zero_ether_addr(port->mac)) eth_hw_addr_set(user_dev, port->mac); else eth_hw_addr_inherit(user_dev, conduit); user_dev->priv_flags |= IFF_NO_QUEUE; if (dsa_switch_supports_uc_filtering(ds)) user_dev->priv_flags |= IFF_UNICAST_FLT; user_dev->netdev_ops = &dsa_user_netdev_ops; if (ds->ops->port_max_mtu) user_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); SET_NETDEV_DEVTYPE(user_dev, &dsa_type); SET_NETDEV_DEV(user_dev, port->ds->dev); SET_NETDEV_DEVLINK_PORT(user_dev, &port->devlink_port); user_dev->dev.of_node = port->dn; user_dev->vlan_features = conduit->vlan_features; p = netdev_priv(user_dev); user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ret = gro_cells_init(&p->gcells, user_dev); if (ret) goto out_free; p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); port->user = user_dev; dsa_user_setup_tagger(user_dev); netif_carrier_off(user_dev); ret = dsa_user_phy_setup(user_dev); if (ret) { netdev_err(user_dev, "error %d setting up PHY for tree %d, switch %d, port %d\n", ret, ds->dst->index, ds->index, port->index); goto out_gcells; } rtnl_lock(); ret = dsa_user_change_mtu(user_dev, ETH_DATA_LEN); if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n", ret, ETH_DATA_LEN, port->index); ret = register_netdevice(user_dev); if (ret) { netdev_err(conduit, "error %d registering interface %s\n", ret, user_dev->name); rtnl_unlock(); goto out_phy; } if (IS_ENABLED(CONFIG_DCB)) { ret = dsa_user_dcbnl_init(user_dev); if (ret) { netdev_err(user_dev, "failed to initialize DCB: %pe\n", ERR_PTR(ret)); rtnl_unlock(); goto out_unregister; } } ret = netdev_upper_dev_link(conduit, user_dev, NULL); rtnl_unlock(); if (ret) goto out_unregister; return 0; out_unregister: unregister_netdev(user_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(p->dp); out_gcells: gro_cells_destroy(&p->gcells); out_free: free_netdev(user_dev); port->user = NULL; return ret; } void dsa_user_destroy(struct net_device *user_dev) { struct net_device *conduit = dsa_user_to_conduit(user_dev); struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_user_priv *p = netdev_priv(user_dev); netif_carrier_off(user_dev); rtnl_lock(); netdev_upper_dev_unlink(conduit, user_dev); unregister_netdevice(user_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); free_netdev(user_dev); } int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack) { struct net_device *old_conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct net_device *upper; struct list_head *iter; int err; if (conduit == old_conduit) return 0; if (!ds->ops->port_change_conduit) { NL_SET_ERR_MSG_MOD(extack, "Driver does not support changing DSA conduit"); return -EOPNOTSUPP; } if (!netdev_uses_dsa(conduit)) { NL_SET_ERR_MSG_MOD(extack, "Interface not eligible as DSA conduit"); return -EOPNOTSUPP; } netdev_for_each_upper_dev_rcu(conduit, upper, iter) { if (dsa_user_dev_check(upper)) continue; if (netif_is_bridge_master(upper)) continue; NL_SET_ERR_MSG_MOD(extack, "Cannot join conduit with unknown uppers"); return -EOPNOTSUPP; } /* Since we allow live-changing the DSA conduit, plus we auto-open the * DSA conduit when the user port opens => we need to ensure that the * new DSA conduit is open too. */ if (dev->flags & IFF_UP) { err = dev_open(conduit, extack); if (err) return err; } netdev_upper_dev_unlink(old_conduit, dev); err = netdev_upper_dev_link(conduit, dev, extack); if (err) goto out_revert_old_conduit_unlink; err = dsa_port_change_conduit(dp, conduit, extack); if (err) goto out_revert_conduit_link; /* Update the MTU of the new CPU port through cross-chip notifiers */ err = dsa_user_change_mtu(dev, dev->mtu); if (err && err != -EOPNOTSUPP) { netdev_warn(dev, "nonfatal error updating MTU with new conduit: %pe\n", ERR_PTR(err)); } return 0; out_revert_conduit_link: netdev_upper_dev_unlink(conduit, dev); out_revert_old_conduit_unlink: netdev_upper_dev_link(old_conduit, dev, NULL); return err; } bool dsa_user_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_user_netdev_ops; } EXPORT_SYMBOL_GPL(dsa_user_dev_check); static int dsa_user_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return err; dp = dsa_user_to_port(dev); extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) { err = dsa_port_bridge_join(dp, info->upper_dev, extack); if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_bridge_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_port_lag_join(dp, info->upper_dev, info->upper_info, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_lag_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (is_hsr_master(info->upper_dev)) { if (info->linking) { err = dsa_port_hsr_join(dp, info->upper_dev, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_hsr_leave(dp, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; dp = dsa_user_to_port(dev); if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) dsa_port_pre_lag_leave(dp, info->upper_dev); /* dsa_port_pre_hsr_leave is not yet necessary since hsr devices cannot * meaningfully placed under a bridge yet */ return NOTIFY_DONE; } static int dsa_user_lag_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_changeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } /* Same as dsa_user_lag_changeupper() except that it calls * dsa_user_prechangeupper() */ static int dsa_user_lag_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_prechangeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } static int dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; struct net_device *user, *br; struct dsa_port *dp; ext_ack = netdev_notifier_info_to_extack(&info->info); if (!is_vlan_dev(dev)) return NOTIFY_DONE; user = vlan_dev_real_dev(dev); if (!dsa_user_dev_check(user)) return NOTIFY_DONE; dp = dsa_user_to_port(user); br = dsa_port_bridge_dev_get(dp); if (!br) return NOTIFY_DONE; /* Deny enslaving a VLAN device into a VLAN-aware bridge */ if (br_vlan_enabled(br) && netif_is_bridge_master(info->upper_dev) && info->linking) { NL_SET_ERR_MSG_MOD(ext_ack, "Cannot make VLAN device join VLAN-aware bridge"); return notifier_from_errno(-EINVAL); } return NOTIFY_DONE; } static int dsa_user_check_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct bridge_vlan_info br_info; struct netlink_ext_ack *extack; int err = NOTIFY_DONE; u16 vid; if (!br || !br_vlan_enabled(br)) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); vid = vlan_dev_vlan_id(info->upper_dev); /* br_vlan_get_info() returns -EINVAL or -ENOENT if the * device, respectively the VID is not found, returning * 0 means success, which is a failure for us here. */ err = br_vlan_get_info(br, vid, &br_info); if (err == 0) { NL_SET_ERR_MSG_MOD(extack, "This VLAN is already configured by the bridge"); return notifier_from_errno(-EBUSY); } return NOTIFY_DONE; } static int dsa_user_prechangeupper_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_switch *ds; struct dsa_port *dp; int err; if (!dsa_user_dev_check(dev)) return dsa_prevent_bridging_8021q_upper(dev, info); dp = dsa_user_to_port(dev); ds = dp->ds; if (ds->ops->port_prechangeupper) { err = ds->ops->port_prechangeupper(ds, dp->index, info); if (err) return notifier_from_errno(err); } if (is_vlan_dev(info->upper_dev)) return dsa_user_check_8021q_upper(dev, info); return NOTIFY_DONE; } /* To be eligible as a DSA conduit, a LAG must have all lower interfaces be * eligible DSA conduits. Additionally, all LAG slaves must be DSA conduits of * switches in the same switch tree. */ static int dsa_lag_conduit_validate(struct net_device *lag_dev, struct netlink_ext_ack *extack) { struct net_device *lower1, *lower2; struct list_head *iter1, *iter2; netdev_for_each_lower_dev(lag_dev, lower1, iter1) { netdev_for_each_lower_dev(lag_dev, lower2, iter2) { if (!netdev_uses_dsa(lower1) || !netdev_uses_dsa(lower2)) { NL_SET_ERR_MSG_MOD(extack, "All LAG ports must be eligible as DSA conduits"); return notifier_from_errno(-EINVAL); } if (lower1 == lower2) continue; if (!dsa_port_tree_same(lower1->dsa_ptr, lower2->dsa_ptr)) { NL_SET_ERR_MSG_MOD(extack, "LAG contains DSA conduits of disjoint switch trees"); return notifier_from_errno(-EINVAL); } } } return NOTIFY_DONE; } static int dsa_conduit_prechangeupper_sanity_check(struct net_device *conduit, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); if (!netdev_uses_dsa(conduit)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; /* Allow DSA switch uppers */ if (dsa_user_dev_check(info->upper_dev)) return NOTIFY_DONE; /* Allow bridge uppers of DSA conduits, subject to further * restrictions in dsa_bridge_prechangelower_sanity_check() */ if (netif_is_bridge_master(info->upper_dev)) return NOTIFY_DONE; /* Allow LAG uppers, subject to further restrictions in * dsa_lag_conduit_prechangelower_sanity_check() */ if (netif_is_lag_master(info->upper_dev)) return dsa_lag_conduit_validate(info->upper_dev, extack); NL_SET_ERR_MSG_MOD(extack, "DSA conduit cannot join unknown upper interfaces"); return notifier_from_errno(-EBUSY); } static int dsa_lag_conduit_prechangelower_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); struct net_device *lag_dev = info->upper_dev; struct net_device *lower; struct list_head *iter; if (!netdev_uses_dsa(lag_dev) || !netif_is_lag_master(lag_dev)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; if (!netdev_uses_dsa(dev)) { NL_SET_ERR_MSG(extack, "Only DSA conduits can join a LAG DSA conduit"); return notifier_from_errno(-EINVAL); } netdev_for_each_lower_dev(lag_dev, lower, iter) { if (!dsa_port_tree_same(dev->dsa_ptr, lower->dsa_ptr)) { NL_SET_ERR_MSG(extack, "Interface is DSA conduit for a different switch tree than this LAG"); return notifier_from_errno(-EINVAL); } break; } return NOTIFY_DONE; } /* Don't allow bridging of DSA conduits, since the bridge layer rx_handler * prevents the DSA fake ethertype handler to be invoked, so we don't get the * chance to strip off and parse the DSA switch tag protocol header (the bridge * layer just returns RX_HANDLER_CONSUMED, stopping RX processing for these * frames). * The only case where that would not be an issue is when bridging can already * be offloaded, such as when the DSA conduit is itself a DSA or plain switchdev * port, and is bridged only with other ports from the same hardware device. */ static int dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, struct netdev_notifier_changeupper_info *info) { struct net_device *br = info->upper_dev; struct netlink_ext_ack *extack; struct net_device *lower; struct list_head *iter; if (!netif_is_bridge_master(br)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); netdev_for_each_lower_dev(br, lower, iter) { if (!netdev_uses_dsa(new_lower) && !netdev_uses_dsa(lower)) continue; if (!netdev_port_same_parent_id(lower, new_lower)) { NL_SET_ERR_MSG(extack, "Cannot do software bridging with a DSA conduit"); return notifier_from_errno(-EINVAL); } } return NOTIFY_DONE; } static void dsa_tree_migrate_ports_from_lag_conduit(struct dsa_switch_tree *dst, struct net_device *lag_dev) { struct net_device *new_conduit = dsa_tree_find_first_conduit(dst); struct dsa_port *dp; int err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, new_conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", new_conduit->name, ERR_PTR(err)); } } } static int dsa_conduit_lag_join(struct net_device *conduit, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack) { struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; int err; err = dsa_conduit_lag_setup(lag_dev, cpu_dp, uinfo, extack); if (err) return err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != conduit) continue; err = dsa_user_change_conduit(dp->user, lag_dev, extack); if (err) goto restore; } return 0; restore: dsa_tree_for_each_user_port_continue_reverse(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", conduit->name, ERR_PTR(err)); } } dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); return err; } static void dsa_conduit_lag_leave(struct net_device *conduit, struct net_device *lag_dev) { struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *new_cpu_dp = NULL; struct net_device *lower; struct list_head *iter; netdev_for_each_lower_dev(lag_dev, lower, iter) { if (netdev_uses_dsa(lower)) { new_cpu_dp = lower->dsa_ptr; break; } } if (new_cpu_dp) { /* Update the CPU port of the user ports still under the LAG * so that dsa_port_to_conduit() continues to work properly */ dsa_tree_for_each_user_port(dp, dst) if (dsa_port_to_conduit(dp) == lag_dev) dp->cpu_dp = new_cpu_dp; /* Update the index of the virtual CPU port to match the lowest * physical CPU port */ lag_dev->dsa_ptr = new_cpu_dp; wmb(); } else { /* If the LAG DSA conduit has no ports left, migrate back all * user ports to the first physical CPU port */ dsa_tree_migrate_ports_from_lag_conduit(dst, lag_dev); } /* This DSA conduit has left its LAG in any case, so let * the CPU port leave the hardware LAG as well */ dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); } static int dsa_conduit_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; if (!netdev_uses_dsa(dev)) return err; extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_conduit_lag_join(dev, info->upper_dev, info->upper_info, extack); err = notifier_from_errno(err); } else { dsa_conduit_lag_leave(dev, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_PRECHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; int err; err = dsa_user_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_conduit_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_lag_conduit_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_bridge_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_user_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGEUPPER: { int err; err = dsa_user_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_conduit_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGELOWERSTATE: { struct netdev_notifier_changelowerstate_info *info = ptr; struct dsa_port *dp; int err = 0; if (dsa_user_dev_check(dev)) { dp = dsa_user_to_port(dev); err = dsa_port_lag_change(dp, info->lower_state_info); } /* Mirror LAG port events on DSA conduits that are in * a LAG towards their respective switch CPU ports */ if (netdev_uses_dsa(dev)) { dp = dev->dsa_ptr; err = dsa_port_lag_change(dp, info->lower_state_info); } return notifier_from_errno(err); } case NETDEV_CHANGE: case NETDEV_UP: { /* Track state of conduit port. * DSA driver may require the conduit port (and indirectly * the tagger) to be available for some special operation. */ if (netdev_uses_dsa(dev)) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->ds->dst; /* Track when the conduit port is UP */ dsa_tree_conduit_oper_state_change(dst, dev, netif_oper_up(dev)); /* Track when the conduit port is ready and can accept * packet. * NETDEV_UP event is not enough to flag a port as ready. * We also have to wait for linkwatch_do_dev to dev_activate * and emit a NETDEV_CHANGE event. * We check if a conduit port is ready by checking if the dev * have a qdisc assigned and is not noop. */ dsa_tree_conduit_admin_state_change(dst, dev, !qdisc_tx_is_noop(dev)); return NOTIFY_OK; } return NOTIFY_DONE; } case NETDEV_GOING_DOWN: { struct dsa_port *dp, *cpu_dp; struct dsa_switch_tree *dst; LIST_HEAD(close_list); if (!netdev_uses_dsa(dev)) return NOTIFY_DONE; cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; dsa_tree_conduit_admin_state_change(dst, dev, false); list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) continue; if (dp->cpu_dp != cpu_dp) continue; list_add(&dp->user->close_list, &close_list); } dev_close_many(&close_list, true); return NOTIFY_OK; } default: break; } return NOTIFY_DONE; } static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { struct switchdev_notifier_fdb_info info = {}; info.addr = switchdev_work->addr; info.vid = switchdev_work->vid; info.offloaded = true; call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, switchdev_work->orig_dev, &info.info, NULL); } static void dsa_user_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); const unsigned char *addr = switchdev_work->addr; struct net_device *dev = switchdev_work->dev; u16 vid = switchdev_work->vid; struct dsa_switch *ds; struct dsa_port *dp; int err; dp = dsa_user_to_port(dev); ds = dp->ds; switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_add(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_add(dp, addr, vid); else err = dsa_port_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } dsa_fdb_offload_notify(switchdev_work); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_del(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_del(dp, addr, vid); else err = dsa_port_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; } kfree(switchdev_work); } static bool dsa_foreign_dev_check(const struct net_device *dev, const struct net_device *foreign_dev) { const struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch_tree *dst = dp->ds->dst; if (netif_is_bridge_master(foreign_dev)) return !dsa_tree_offloads_bridge_dev(dst, foreign_dev); if (netif_is_bridge_port(foreign_dev)) return !dsa_tree_offloads_bridge_port(dst, foreign_dev); /* Everything else is foreign */ return true; } static int dsa_user_fdb_event(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info) { struct dsa_switchdev_event_work *switchdev_work; struct dsa_port *dp = dsa_user_to_port(dev); bool host_addr = fdb_info->is_local; struct dsa_switch *ds = dp->ds; if (ctx && ctx != dp) return 0; if (!dp->bridge) return 0; if (switchdev_fdb_is_dynamically_learned(fdb_info)) { if (dsa_port_offloads_bridge_port(dp, orig_dev)) return 0; /* FDB entries learned by the software bridge or by foreign * bridge ports should be installed as host addresses only if * the driver requests assisted learning. */ if (!ds->assisted_learning_on_cpu_port) return 0; } /* Also treat FDB entries on foreign interfaces bridged with us as host * addresses. */ if (dsa_foreign_dev_check(dev, orig_dev)) host_addr = true; /* Check early that we're not doing work in vain. * Host addresses on LAG ports still require regular FDB ops, * since the CPU port isn't in a LAG. */ if (dp->lag && !host_addr) { if (!ds->ops->lag_fdb_add || !ds->ops->lag_fdb_del) return -EOPNOTSUPP; } else { if (!ds->ops->port_fdb_add || !ds->ops->port_fdb_del) return -EOPNOTSUPP; } switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); if (!switchdev_work) return -ENOMEM; netdev_dbg(dev, "%s FDB entry towards %s, addr %pM vid %d%s\n", event == SWITCHDEV_FDB_ADD_TO_DEVICE ? "Adding" : "Deleting", orig_dev->name, fdb_info->addr, fdb_info->vid, host_addr ? " as host address" : ""); INIT_WORK(&switchdev_work->work, dsa_user_switchdev_event_work); switchdev_work->event = event; switchdev_work->dev = dev; switchdev_work->orig_dev = orig_dev; ether_addr_copy(switchdev_work->addr, fdb_info->addr); switchdev_work->vid = fdb_info->vid; switchdev_work->host_addr = host_addr; dsa_schedule_work(&switchdev_work->work); return 0; } /* Called under rcu_read_lock() */ static int dsa_user_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: err = switchdev_handle_fdb_event_to_device(dev, event, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_fdb_event); return notifier_from_errno(err); default: return NOTIFY_DONE; } return NOTIFY_OK; } static int dsa_user_switchdev_blocking_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_OBJ_ADD: err = switchdev_handle_port_obj_add_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_add); return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: err = switchdev_handle_port_obj_del_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_del); return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); } return NOTIFY_DONE; } static struct notifier_block dsa_user_nb __read_mostly = { .notifier_call = dsa_user_netdevice_event, }; struct notifier_block dsa_user_switchdev_notifier = { .notifier_call = dsa_user_switchdev_event, }; struct notifier_block dsa_user_switchdev_blocking_notifier = { .notifier_call = dsa_user_switchdev_blocking_event, }; int dsa_user_register_notifier(void) { struct notifier_block *nb; int err; err = register_netdevice_notifier(&dsa_user_nb); if (err) return err; err = register_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) goto err_switchdev_nb; nb = &dsa_user_switchdev_blocking_notifier; err = register_switchdev_blocking_notifier(nb); if (err) goto err_switchdev_blocking_nb; return 0; err_switchdev_blocking_nb: unregister_switchdev_notifier(&dsa_user_switchdev_notifier); err_switchdev_nb: unregister_netdevice_notifier(&dsa_user_nb); return err; } void dsa_user_unregister_notifier(void) { struct notifier_block *nb; int err; nb = &dsa_user_switchdev_blocking_notifier; err = unregister_switchdev_blocking_notifier(nb); if (err) pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); err = unregister_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); err = unregister_netdevice_notifier(&dsa_user_nb); if (err) pr_err("DSA: failed to unregister user notifier (%d)\n", err); } |
| 3 13 14 1 1 1 1 6 6 6 6 6 4 3 4 1 3 3 1 1 1 7 6 1 1 2 1 1 1 7 1 1 1 1 3 1 1 6 1 4 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 | // SPDX-License-Identifier: GPL-2.0-only /* * 6pack.c This module implements the 6pack protocol for kernel-based * devices like TTY. It interfaces between a raw TTY and the * kernel's AX.25 protocol layers. * * Authors: Andreas Könsgen <ajk@comnets.uni-bremen.de> * Ralf Baechle DL5RB <ralf@linux-mips.org> * * Quite a lot of stuff "stolen" by Joerg Reuter from slip.c, written by * * Laurence Culhane, <loz@holmes.demon.co.uk> * Fred N. van Kempen, <waltje@uwalt.nl.mugnet.org> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/tty.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/timer.h> #include <linux/slab.h> #include <net/ax25.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/semaphore.h> #include <linux/refcount.h> #define SIXPACK_VERSION "Revision: 0.3.0" /* sixpack priority commands */ #define SIXP_SEOF 0x40 /* start and end of a 6pack frame */ #define SIXP_TX_URUN 0x48 /* transmit overrun */ #define SIXP_RX_ORUN 0x50 /* receive overrun */ #define SIXP_RX_BUF_OVL 0x58 /* receive buffer overflow */ #define SIXP_CHKSUM 0xFF /* valid checksum of a 6pack frame */ /* masks to get certain bits out of the status bytes sent by the TNC */ #define SIXP_CMD_MASK 0xC0 #define SIXP_CHN_MASK 0x07 #define SIXP_PRIO_CMD_MASK 0x80 #define SIXP_STD_CMD_MASK 0x40 #define SIXP_PRIO_DATA_MASK 0x38 #define SIXP_TX_MASK 0x20 #define SIXP_RX_MASK 0x10 #define SIXP_RX_DCD_MASK 0x18 #define SIXP_LEDS_ON 0x78 #define SIXP_LEDS_OFF 0x60 #define SIXP_CON 0x08 #define SIXP_STA 0x10 #define SIXP_FOUND_TNC 0xe9 #define SIXP_CON_ON 0x68 #define SIXP_DCD_MASK 0x08 #define SIXP_DAMA_OFF 0 /* default level 2 parameters */ #define SIXP_TXDELAY 25 /* 250 ms */ #define SIXP_PERSIST 50 /* in 256ths */ #define SIXP_SLOTTIME 10 /* 100 ms */ #define SIXP_INIT_RESYNC_TIMEOUT (3*HZ/2) /* in 1 s */ #define SIXP_RESYNC_TIMEOUT 5*HZ /* in 1 s */ /* 6pack configuration. */ #define SIXP_NRUNIT 31 /* MAX number of 6pack channels */ #define SIXP_MTU 256 /* Default MTU */ enum sixpack_flags { SIXPF_ERROR, /* Parity, etc. error */ }; struct sixpack { /* Various fields. */ struct tty_struct *tty; /* ptr to TTY structure */ struct net_device *dev; /* easy for intr handling */ /* These are pointers to the malloc()ed frame buffers. */ unsigned char *rbuff; /* receiver buffer */ int rcount; /* received chars counter */ unsigned char *xbuff; /* transmitter buffer */ unsigned char *xhead; /* next byte to XMIT */ int xleft; /* bytes left in XMIT queue */ unsigned char raw_buf[4]; unsigned char cooked_buf[400]; unsigned int rx_count; unsigned int rx_count_cooked; spinlock_t rxlock; int mtu; /* Our mtu (to spot changes!) */ int buffsize; /* Max buffers sizes */ unsigned long flags; /* Flag values/ mode etc */ unsigned char mode; /* 6pack mode */ /* 6pack stuff */ unsigned char tx_delay; unsigned char persistence; unsigned char slottime; unsigned char duplex; unsigned char led_state; unsigned char status; unsigned char status1; unsigned char status2; unsigned char tx_enable; unsigned char tnc_state; struct timer_list tx_t; struct timer_list resync_t; refcount_t refcnt; struct completion dead; spinlock_t lock; }; #define AX25_6PACK_HEADER_LEN 0 static void sixpack_decode(struct sixpack *, const unsigned char[], int); static int encode_sixpack(unsigned char *, unsigned char *, int, unsigned char); /* * Perform the persistence/slottime algorithm for CSMA access. If the * persistence check was successful, write the data to the serial driver. * Note that in case of DAMA operation, the data is not sent here. */ static void sp_xmit_on_air(struct timer_list *t) { struct sixpack *sp = from_timer(sp, t, tx_t); int actual, when = sp->slottime; static unsigned char random; random = random * 17 + 41; if (((sp->status1 & SIXP_DCD_MASK) == 0) && (random < sp->persistence)) { sp->led_state = 0x70; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tx_enable = 1; actual = sp->tty->ops->write(sp->tty, sp->xbuff, sp->status2); sp->xleft -= actual; sp->xhead += actual; sp->led_state = 0x60; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->status2 = 0; } else mod_timer(&sp->tx_t, jiffies + ((when + 1) * HZ) / 100); } /* ----> 6pack timer interrupt handler and friends. <---- */ /* Encapsulate one AX.25 frame and stuff into a TTY queue. */ static void sp_encaps(struct sixpack *sp, unsigned char *icp, int len) { unsigned char *msg, *p = icp; int actual, count; if (len > sp->mtu) { /* sp->mtu = AX25_MTU = max. PACLEN = 256 */ msg = "oversized transmit packet!"; goto out_drop; } if (p[0] > 5) { msg = "invalid KISS command"; goto out_drop; } if ((p[0] != 0) && (len > 2)) { msg = "KISS control packet too long"; goto out_drop; } if ((p[0] == 0) && (len < 15)) { msg = "bad AX.25 packet to transmit"; goto out_drop; } count = encode_sixpack(p, sp->xbuff, len, sp->tx_delay); set_bit(TTY_DO_WRITE_WAKEUP, &sp->tty->flags); switch (p[0]) { case 1: sp->tx_delay = p[1]; return; case 2: sp->persistence = p[1]; return; case 3: sp->slottime = p[1]; return; case 4: /* ignored */ return; case 5: sp->duplex = p[1]; return; } if (p[0] != 0) return; /* * In case of fullduplex or DAMA operation, we don't take care about the * state of the DCD or of any timers, as the determination of the * correct time to send is the job of the AX.25 layer. We send * immediately after data has arrived. */ if (sp->duplex == 1) { sp->led_state = 0x70; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tx_enable = 1; actual = sp->tty->ops->write(sp->tty, sp->xbuff, count); sp->xleft = count - actual; sp->xhead = sp->xbuff + actual; sp->led_state = 0x60; sp->tty->ops->write(sp->tty, &sp->led_state, 1); } else { sp->xleft = count; sp->xhead = sp->xbuff; sp->status2 = count; sp_xmit_on_air(&sp->tx_t); } return; out_drop: sp->dev->stats.tx_dropped++; netif_start_queue(sp->dev); if (net_ratelimit()) printk(KERN_DEBUG "%s: %s - dropped.\n", sp->dev->name, msg); } /* Encapsulate an IP datagram and kick it into a TTY queue. */ static netdev_tx_t sp_xmit(struct sk_buff *skb, struct net_device *dev) { struct sixpack *sp = netdev_priv(dev); if (skb->protocol == htons(ETH_P_IP)) return ax25_ip_xmit(skb); spin_lock_bh(&sp->lock); /* We were not busy, so we are now... :-) */ netif_stop_queue(dev); dev->stats.tx_bytes += skb->len; sp_encaps(sp, skb->data, skb->len); spin_unlock_bh(&sp->lock); dev_kfree_skb(skb); return NETDEV_TX_OK; } static int sp_open_dev(struct net_device *dev) { struct sixpack *sp = netdev_priv(dev); if (sp->tty == NULL) return -ENODEV; return 0; } /* Close the low-level part of the 6pack channel. */ static int sp_close(struct net_device *dev) { struct sixpack *sp = netdev_priv(dev); spin_lock_bh(&sp->lock); if (sp->tty) { /* TTY discipline is running. */ clear_bit(TTY_DO_WRITE_WAKEUP, &sp->tty->flags); } netif_stop_queue(dev); spin_unlock_bh(&sp->lock); return 0; } static int sp_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr_ax25 *sa = addr; netif_tx_lock_bh(dev); netif_addr_lock(dev); __dev_addr_set(dev, &sa->sax25_call, AX25_ADDR_LEN); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); return 0; } static const struct net_device_ops sp_netdev_ops = { .ndo_open = sp_open_dev, .ndo_stop = sp_close, .ndo_start_xmit = sp_xmit, .ndo_set_mac_address = sp_set_mac_address, }; static void sp_setup(struct net_device *dev) { /* Finish setting up the DEVICE info. */ dev->netdev_ops = &sp_netdev_ops; dev->mtu = SIXP_MTU; dev->hard_header_len = AX25_MAX_HEADER_LEN; dev->header_ops = &ax25_header_ops; dev->addr_len = AX25_ADDR_LEN; dev->type = ARPHRD_AX25; dev->tx_queue_len = 10; /* Only activated in AX.25 mode */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->flags = 0; } /* Send one completely decapsulated IP datagram to the IP layer. */ /* * This is the routine that sends the received data to the kernel AX.25. * 'cmd' is the KISS command. For AX.25 data, it is zero. */ static void sp_bump(struct sixpack *sp, char cmd) { struct sk_buff *skb; int count; unsigned char *ptr; count = sp->rcount + 1; sp->dev->stats.rx_bytes += count; if ((skb = dev_alloc_skb(count + 1)) == NULL) goto out_mem; ptr = skb_put(skb, count + 1); *ptr++ = cmd; /* KISS command */ memcpy(ptr, sp->cooked_buf + 1, count); skb->protocol = ax25_type_trans(skb, sp->dev); netif_rx(skb); sp->dev->stats.rx_packets++; return; out_mem: sp->dev->stats.rx_dropped++; } /* ----------------------------------------------------------------------- */ /* * We have a potential race on dereferencing tty->disc_data, because the tty * layer provides no locking at all - thus one cpu could be running * sixpack_receive_buf while another calls sixpack_close, which zeroes * tty->disc_data and frees the memory that sixpack_receive_buf is using. The * best way to fix this is to use a rwlock in the tty struct, but for now we * use a single global rwlock for all ttys in ppp line discipline. */ static DEFINE_RWLOCK(disc_data_lock); static struct sixpack *sp_get(struct tty_struct *tty) { struct sixpack *sp; read_lock(&disc_data_lock); sp = tty->disc_data; if (sp) refcount_inc(&sp->refcnt); read_unlock(&disc_data_lock); return sp; } static void sp_put(struct sixpack *sp) { if (refcount_dec_and_test(&sp->refcnt)) complete(&sp->dead); } /* * Called by the TTY driver when there's room for more data. If we have * more packets to send, we send them here. */ static void sixpack_write_wakeup(struct tty_struct *tty) { struct sixpack *sp = sp_get(tty); int actual; if (!sp) return; if (sp->xleft <= 0) { /* Now serial buffer is almost free & we can start * transmission of another packet */ sp->dev->stats.tx_packets++; clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); sp->tx_enable = 0; netif_wake_queue(sp->dev); goto out; } if (sp->tx_enable) { actual = tty->ops->write(tty, sp->xhead, sp->xleft); sp->xleft -= actual; sp->xhead += actual; } out: sp_put(sp); } /* ----------------------------------------------------------------------- */ /* * Handle the 'receiver data ready' interrupt. * This function is called by the tty module in the kernel when * a block of 6pack data has been received, which can now be decapsulated * and sent on to some IP layer for further processing. */ static void sixpack_receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, size_t count) { struct sixpack *sp; int count1; if (!count) return; sp = sp_get(tty); if (!sp) return; /* Read the characters out of the buffer */ count1 = count; while (count) { count--; if (fp && *fp++) { if (!test_and_set_bit(SIXPF_ERROR, &sp->flags)) sp->dev->stats.rx_errors++; continue; } } sixpack_decode(sp, cp, count1); sp_put(sp); tty_unthrottle(tty); } /* * Try to resync the TNC. Called by the resync timer defined in * decode_prio_command */ #define TNC_UNINITIALIZED 0 #define TNC_UNSYNC_STARTUP 1 #define TNC_UNSYNCED 2 #define TNC_IN_SYNC 3 static void __tnc_set_sync_state(struct sixpack *sp, int new_tnc_state) { char *msg; switch (new_tnc_state) { default: /* gcc oh piece-o-crap ... */ case TNC_UNSYNC_STARTUP: msg = "Synchronizing with TNC"; break; case TNC_UNSYNCED: msg = "Lost synchronization with TNC\n"; break; case TNC_IN_SYNC: msg = "Found TNC"; break; } sp->tnc_state = new_tnc_state; printk(KERN_INFO "%s: %s\n", sp->dev->name, msg); } static inline void tnc_set_sync_state(struct sixpack *sp, int new_tnc_state) { int old_tnc_state = sp->tnc_state; if (old_tnc_state != new_tnc_state) __tnc_set_sync_state(sp, new_tnc_state); } static void resync_tnc(struct timer_list *t) { struct sixpack *sp = from_timer(sp, t, resync_t); static char resync_cmd = 0xe8; /* clear any data that might have been received */ sp->rx_count = 0; sp->rx_count_cooked = 0; /* reset state machine */ sp->status = 1; sp->status1 = 1; sp->status2 = 0; /* resync the TNC */ sp->led_state = 0x60; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tty->ops->write(sp->tty, &resync_cmd, 1); /* Start resync timer again -- the TNC might be still absent */ mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT); } static inline int tnc_init(struct sixpack *sp) { unsigned char inbyte = 0xe8; tnc_set_sync_state(sp, TNC_UNSYNC_STARTUP); sp->tty->ops->write(sp->tty, &inbyte, 1); mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT); return 0; } /* * Open the high-level part of the 6pack channel. * This function is called by the TTY module when the * 6pack line discipline is called for. Because we are * sure the tty line exists, we only have to link it to * a free 6pcack channel... */ static int sixpack_open(struct tty_struct *tty) { char *rbuff = NULL, *xbuff = NULL; struct net_device *dev; struct sixpack *sp; unsigned long len; int err = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (tty->ops->write == NULL) return -EOPNOTSUPP; dev = alloc_netdev(sizeof(struct sixpack), "sp%d", NET_NAME_UNKNOWN, sp_setup); if (!dev) { err = -ENOMEM; goto out; } sp = netdev_priv(dev); sp->dev = dev; spin_lock_init(&sp->lock); spin_lock_init(&sp->rxlock); refcount_set(&sp->refcnt, 1); init_completion(&sp->dead); /* !!! length of the buffers. MTU is IP MTU, not PACLEN! */ len = dev->mtu * 2; rbuff = kmalloc(len + 4, GFP_KERNEL); xbuff = kmalloc(len + 4, GFP_KERNEL); if (rbuff == NULL || xbuff == NULL) { err = -ENOBUFS; goto out_free; } spin_lock_bh(&sp->lock); sp->tty = tty; sp->rbuff = rbuff; sp->xbuff = xbuff; sp->mtu = AX25_MTU + 73; sp->buffsize = len; sp->rcount = 0; sp->rx_count = 0; sp->rx_count_cooked = 0; sp->xleft = 0; sp->flags = 0; /* Clear ESCAPE & ERROR flags */ sp->duplex = 0; sp->tx_delay = SIXP_TXDELAY; sp->persistence = SIXP_PERSIST; sp->slottime = SIXP_SLOTTIME; sp->led_state = 0x60; sp->status = 1; sp->status1 = 1; sp->status2 = 0; sp->tx_enable = 0; netif_start_queue(dev); timer_setup(&sp->tx_t, sp_xmit_on_air, 0); timer_setup(&sp->resync_t, resync_tnc, 0); spin_unlock_bh(&sp->lock); /* Done. We have linked the TTY line to a channel. */ tty->disc_data = sp; tty->receive_room = 65536; /* Now we're ready to register. */ err = register_netdev(dev); if (err) goto out_free; tnc_init(sp); return 0; out_free: kfree(xbuff); kfree(rbuff); free_netdev(dev); out: return err; } /* * Close down a 6pack channel. * This means flushing out any pending queues, and then restoring the * TTY line discipline to what it was before it got hooked to 6pack * (which usually is TTY again). */ static void sixpack_close(struct tty_struct *tty) { struct sixpack *sp; write_lock_irq(&disc_data_lock); sp = tty->disc_data; tty->disc_data = NULL; write_unlock_irq(&disc_data_lock); if (!sp) return; /* * We have now ensured that nobody can start using ap from now on, but * we have to wait for all existing users to finish. */ if (!refcount_dec_and_test(&sp->refcnt)) wait_for_completion(&sp->dead); /* We must stop the queue to avoid potentially scribbling * on the free buffers. The sp->dead completion is not sufficient * to protect us from sp->xbuff access. */ netif_stop_queue(sp->dev); unregister_netdev(sp->dev); del_timer_sync(&sp->tx_t); del_timer_sync(&sp->resync_t); /* Free all 6pack frame buffers after unreg. */ kfree(sp->rbuff); kfree(sp->xbuff); free_netdev(sp->dev); } /* Perform I/O control on an active 6pack channel. */ static int sixpack_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct sixpack *sp = sp_get(tty); struct net_device *dev; unsigned int tmp, err; if (!sp) return -ENXIO; dev = sp->dev; switch(cmd) { case SIOCGIFNAME: err = copy_to_user((void __user *) arg, dev->name, strlen(dev->name) + 1) ? -EFAULT : 0; break; case SIOCGIFENCAP: err = put_user(0, (int __user *) arg); break; case SIOCSIFENCAP: if (get_user(tmp, (int __user *) arg)) { err = -EFAULT; break; } sp->mode = tmp; dev->addr_len = AX25_ADDR_LEN; dev->hard_header_len = AX25_KISS_HEADER_LEN + AX25_MAX_HEADER_LEN + 3; dev->type = ARPHRD_AX25; err = 0; break; case SIOCSIFHWADDR: { char addr[AX25_ADDR_LEN]; if (copy_from_user(&addr, (void __user *)arg, AX25_ADDR_LEN)) { err = -EFAULT; break; } netif_tx_lock_bh(dev); __dev_addr_set(dev, &addr, AX25_ADDR_LEN); netif_tx_unlock_bh(dev); err = 0; break; } default: err = tty_mode_ioctl(tty, cmd, arg); } sp_put(sp); return err; } static struct tty_ldisc_ops sp_ldisc = { .owner = THIS_MODULE, .num = N_6PACK, .name = "6pack", .open = sixpack_open, .close = sixpack_close, .ioctl = sixpack_ioctl, .receive_buf = sixpack_receive_buf, .write_wakeup = sixpack_write_wakeup, }; /* Initialize 6pack control device -- register 6pack line discipline */ static const char msg_banner[] __initconst = KERN_INFO \ "AX.25: 6pack driver, " SIXPACK_VERSION "\n"; static const char msg_regfail[] __initconst = KERN_ERR \ "6pack: can't register line discipline (err = %d)\n"; static int __init sixpack_init_driver(void) { int status; printk(msg_banner); /* Register the provided line protocol discipline */ status = tty_register_ldisc(&sp_ldisc); if (status) printk(msg_regfail, status); return status; } static void __exit sixpack_exit_driver(void) { tty_unregister_ldisc(&sp_ldisc); } /* encode an AX.25 packet into 6pack */ static int encode_sixpack(unsigned char *tx_buf, unsigned char *tx_buf_raw, int length, unsigned char tx_delay) { int count = 0; unsigned char checksum = 0, buf[400]; int raw_count = 0; tx_buf_raw[raw_count++] = SIXP_PRIO_CMD_MASK | SIXP_TX_MASK; tx_buf_raw[raw_count++] = SIXP_SEOF; buf[0] = tx_delay; for (count = 1; count < length; count++) buf[count] = tx_buf[count]; for (count = 0; count < length; count++) checksum += buf[count]; buf[length] = (unsigned char) 0xff - checksum; for (count = 0; count <= length; count++) { if ((count % 3) == 0) { tx_buf_raw[raw_count++] = (buf[count] & 0x3f); tx_buf_raw[raw_count] = ((buf[count] >> 2) & 0x30); } else if ((count % 3) == 1) { tx_buf_raw[raw_count++] |= (buf[count] & 0x0f); tx_buf_raw[raw_count] = ((buf[count] >> 2) & 0x3c); } else { tx_buf_raw[raw_count++] |= (buf[count] & 0x03); tx_buf_raw[raw_count++] = (buf[count] >> 2); } } if ((length % 3) != 2) raw_count++; tx_buf_raw[raw_count++] = SIXP_SEOF; return raw_count; } /* decode 4 sixpack-encoded bytes into 3 data bytes */ static void decode_data(struct sixpack *sp, unsigned char inbyte) { unsigned char *buf; if (sp->rx_count != 3) { sp->raw_buf[sp->rx_count++] = inbyte; return; } if (sp->rx_count_cooked + 2 >= sizeof(sp->cooked_buf)) { pr_err("6pack: cooked buffer overrun, data loss\n"); sp->rx_count = 0; return; } buf = sp->raw_buf; sp->cooked_buf[sp->rx_count_cooked++] = buf[0] | ((buf[1] << 2) & 0xc0); sp->cooked_buf[sp->rx_count_cooked++] = (buf[1] & 0x0f) | ((buf[2] << 2) & 0xf0); sp->cooked_buf[sp->rx_count_cooked++] = (buf[2] & 0x03) | (inbyte << 2); sp->rx_count = 0; } /* identify and execute a 6pack priority command byte */ static void decode_prio_command(struct sixpack *sp, unsigned char cmd) { int actual; if ((cmd & SIXP_PRIO_DATA_MASK) != 0) { /* idle ? */ /* RX and DCD flags can only be set in the same prio command, if the DCD flag has been set without the RX flag in the previous prio command. If DCD has not been set before, something in the transmission has gone wrong. In this case, RX and DCD are cleared in order to prevent the decode_data routine from reading further data that might be corrupt. */ if (((sp->status & SIXP_DCD_MASK) == 0) && ((cmd & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK)) { if (sp->status != 1) printk(KERN_DEBUG "6pack: protocol violation\n"); else sp->status = 0; cmd &= ~SIXP_RX_DCD_MASK; } sp->status = cmd & SIXP_PRIO_DATA_MASK; } else { /* output watchdog char if idle */ if ((sp->status2 != 0) && (sp->duplex == 1)) { sp->led_state = 0x70; sp->tty->ops->write(sp->tty, &sp->led_state, 1); sp->tx_enable = 1; actual = sp->tty->ops->write(sp->tty, sp->xbuff, sp->status2); sp->xleft -= actual; sp->xhead += actual; sp->led_state = 0x60; sp->status2 = 0; } } /* needed to trigger the TNC watchdog */ sp->tty->ops->write(sp->tty, &sp->led_state, 1); /* if the state byte has been received, the TNC is present, so the resync timer can be reset. */ if (sp->tnc_state == TNC_IN_SYNC) mod_timer(&sp->resync_t, jiffies + SIXP_INIT_RESYNC_TIMEOUT); sp->status1 = cmd & SIXP_PRIO_DATA_MASK; } /* identify and execute a standard 6pack command byte */ static void decode_std_command(struct sixpack *sp, unsigned char cmd) { unsigned char checksum = 0, rest = 0; short i; switch (cmd & SIXP_CMD_MASK) { /* normal command */ case SIXP_SEOF: if ((sp->rx_count == 0) && (sp->rx_count_cooked == 0)) { if ((sp->status & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK) { sp->led_state = 0x68; sp->tty->ops->write(sp->tty, &sp->led_state, 1); } } else { sp->led_state = 0x60; /* fill trailing bytes with zeroes */ sp->tty->ops->write(sp->tty, &sp->led_state, 1); spin_lock_bh(&sp->rxlock); rest = sp->rx_count; if (rest != 0) for (i = rest; i <= 3; i++) decode_data(sp, 0); if (rest == 2) sp->rx_count_cooked -= 2; else if (rest == 3) sp->rx_count_cooked -= 1; for (i = 0; i < sp->rx_count_cooked; i++) checksum += sp->cooked_buf[i]; if (checksum != SIXP_CHKSUM) { printk(KERN_DEBUG "6pack: bad checksum %2.2x\n", checksum); } else { sp->rcount = sp->rx_count_cooked-2; sp_bump(sp, 0); } sp->rx_count_cooked = 0; spin_unlock_bh(&sp->rxlock); } break; case SIXP_TX_URUN: printk(KERN_DEBUG "6pack: TX underrun\n"); break; case SIXP_RX_ORUN: printk(KERN_DEBUG "6pack: RX overrun\n"); break; case SIXP_RX_BUF_OVL: printk(KERN_DEBUG "6pack: RX buffer overflow\n"); } } /* decode a 6pack packet */ static void sixpack_decode(struct sixpack *sp, const unsigned char *pre_rbuff, int count) { unsigned char inbyte; int count1; for (count1 = 0; count1 < count; count1++) { inbyte = pre_rbuff[count1]; if (inbyte == SIXP_FOUND_TNC) { tnc_set_sync_state(sp, TNC_IN_SYNC); del_timer(&sp->resync_t); } if ((inbyte & SIXP_PRIO_CMD_MASK) != 0) decode_prio_command(sp, inbyte); else if ((inbyte & SIXP_STD_CMD_MASK) != 0) decode_std_command(sp, inbyte); else if ((sp->status & SIXP_RX_DCD_MASK) == SIXP_RX_DCD_MASK) { spin_lock_bh(&sp->rxlock); decode_data(sp, inbyte); spin_unlock_bh(&sp->rxlock); } } } MODULE_AUTHOR("Ralf Baechle DO1GRB <ralf@linux-mips.org>"); MODULE_DESCRIPTION("6pack driver for AX.25"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_6PACK); module_init(sixpack_init_driver); module_exit(sixpack_exit_driver); |
| 92 92 92 | 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 | /* * Copyright (c) 2006-2008 Intel Corporation * Copyright (c) 2007 Dave Airlie <airlied@linux.ie> * * DRM core CRTC related functions * * Permission to use, copy, modify, distribute, and sell this software and its * documentation for any purpose is hereby granted without fee, provided that * the above copyright notice appear in all copies and that both that copyright * notice and this permission notice appear in supporting documentation, and * that the name of the copyright holders not be used in advertising or * publicity pertaining to distribution of the software without specific, * written prior permission. The copyright holders make no representations * about the suitability of this software for any purpose. It is provided "as * is" without express or implied warranty. * * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE * OF THIS SOFTWARE. * * Authors: * Keith Packard * Eric Anholt <eric@anholt.net> * Dave Airlie <airlied@linux.ie> * Jesse Barnes <jesse.barnes@intel.com> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/moduleparam.h> #include <linux/dynamic_debug.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_atomic_uapi.h> #include <drm/drm_bridge.h> #include <drm/drm_crtc.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> #include <drm/drm_edid.h> #include <drm/drm_encoder.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_print.h> #include <drm/drm_vblank.h> #include "drm_crtc_helper_internal.h" DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", "DRM_UT_DRIVER", "DRM_UT_KMS", "DRM_UT_PRIME", "DRM_UT_ATOMIC", "DRM_UT_VBL", "DRM_UT_STATE", "DRM_UT_LEASE", "DRM_UT_DP", "DRM_UT_DRMRES"); /** * DOC: overview * * The CRTC modeset helper library provides a default set_config implementation * in drm_crtc_helper_set_config(). Plus a few other convenience functions using * the same callbacks which drivers can use to e.g. restore the modeset * configuration on resume with drm_helper_resume_force_mode(). * * Note that this helper library doesn't track the current power state of CRTCs * and encoders. It can call callbacks like &drm_encoder_helper_funcs.dpms even * though the hardware is already in the desired state. This deficiency has been * fixed in the atomic helpers. * * The driver callbacks are mostly compatible with the atomic modeset helpers, * except for the handling of the primary plane: Atomic helpers require that the * primary plane is implemented as a real standalone plane and not directly tied * to the CRTC state. For easier transition this library provides functions to * implement the old semantics required by the CRTC helpers using the new plane * and atomic helper callbacks. * * Drivers are strongly urged to convert to the atomic helpers (by way of first * converting to the plane helpers). New drivers must not use these functions * but need to implement the atomic interface instead, potentially using the * atomic helpers for that. * * These legacy modeset helpers use the same function table structures as * all other modesetting helpers. See the documentation for struct * &drm_crtc_helper_funcs, &struct drm_encoder_helper_funcs and struct * &drm_connector_helper_funcs. */ /** * drm_helper_encoder_in_use - check if a given encoder is in use * @encoder: encoder to check * * Checks whether @encoder is with the current mode setting output configuration * in use by any connector. This doesn't mean that it is actually enabled since * the DPMS state is tracked separately. * * Returns: * True if @encoder is used, false otherwise. */ bool drm_helper_encoder_in_use(struct drm_encoder *encoder) { struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct drm_device *dev = encoder->dev; drm_WARN_ON(dev, drm_drv_uses_atomic_modeset(dev)); /* * We can expect this mutex to be locked if we are not panicking. * Locking is currently fubar in the panic handler. */ if (!oops_in_progress) { drm_WARN_ON(dev, !mutex_is_locked(&dev->mode_config.mutex)); drm_WARN_ON(dev, !drm_modeset_is_locked(&dev->mode_config.connection_mutex)); } drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { if (connector->encoder == encoder) { drm_connector_list_iter_end(&conn_iter); return true; } } drm_connector_list_iter_end(&conn_iter); return false; } EXPORT_SYMBOL(drm_helper_encoder_in_use); /** * drm_helper_crtc_in_use - check if a given CRTC is in a mode_config * @crtc: CRTC to check * * Checks whether @crtc is with the current mode setting output configuration * in use by any connector. This doesn't mean that it is actually enabled since * the DPMS state is tracked separately. * * Returns: * True if @crtc is used, false otherwise. */ bool drm_helper_crtc_in_use(struct drm_crtc *crtc) { struct drm_encoder *encoder; struct drm_device *dev = crtc->dev; drm_WARN_ON(dev, drm_drv_uses_atomic_modeset(dev)); /* * We can expect this mutex to be locked if we are not panicking. * Locking is currently fubar in the panic handler. */ if (!oops_in_progress) drm_WARN_ON(dev, !mutex_is_locked(&dev->mode_config.mutex)); drm_for_each_encoder(encoder, dev) if (encoder->crtc == crtc && drm_helper_encoder_in_use(encoder)) return true; return false; } EXPORT_SYMBOL(drm_helper_crtc_in_use); static void drm_encoder_disable(struct drm_encoder *encoder) { const struct drm_encoder_helper_funcs *encoder_funcs = encoder->helper_private; if (!encoder_funcs) return; if (encoder_funcs->disable) (*encoder_funcs->disable)(encoder); else if (encoder_funcs->dpms) (*encoder_funcs->dpms)(encoder, DRM_MODE_DPMS_OFF); } static void __drm_helper_disable_unused_functions(struct drm_device *dev) { struct drm_encoder *encoder; struct drm_crtc *crtc; drm_warn_on_modeset_not_all_locked(dev); drm_for_each_encoder(encoder, dev) { if (!drm_helper_encoder_in_use(encoder)) { drm_encoder_disable(encoder); /* disconnect encoder from any connector */ encoder->crtc = NULL; } } drm_for_each_crtc(crtc, dev) { const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private; crtc->enabled = drm_helper_crtc_in_use(crtc); if (!crtc->enabled) { if (crtc_funcs->disable) (*crtc_funcs->disable)(crtc); else (*crtc_funcs->dpms)(crtc, DRM_MODE_DPMS_OFF); crtc->primary->fb = NULL; } } } /** * drm_helper_disable_unused_functions - disable unused objects * @dev: DRM device * * This function walks through the entire mode setting configuration of @dev. It * will remove any CRTC links of unused encoders and encoder links of * disconnected connectors. Then it will disable all unused encoders and CRTCs * either by calling their disable callback if available or by calling their * dpms callback with DRM_MODE_DPMS_OFF. * * NOTE: * * This function is part of the legacy modeset helper library and will cause * major confusion with atomic drivers. This is because atomic helpers guarantee * to never call ->disable() hooks on a disabled function, or ->enable() hooks * on an enabled functions. drm_helper_disable_unused_functions() on the other * hand throws such guarantees into the wind and calls disable hooks * unconditionally on unused functions. */ void drm_helper_disable_unused_functions(struct drm_device *dev) { drm_WARN_ON(dev, drm_drv_uses_atomic_modeset(dev)); drm_modeset_lock_all(dev); __drm_helper_disable_unused_functions(dev); drm_modeset_unlock_all(dev); } EXPORT_SYMBOL(drm_helper_disable_unused_functions); /* * Check the CRTC we're going to map each output to vs. its current * CRTC. If they don't match, we have to disable the output and the CRTC * since the driver will have to re-route things. */ static void drm_crtc_prepare_encoders(struct drm_device *dev) { const struct drm_encoder_helper_funcs *encoder_funcs; struct drm_encoder *encoder; drm_for_each_encoder(encoder, dev) { encoder_funcs = encoder->helper_private; if (!encoder_funcs) continue; /* Disable unused encoders */ if (encoder->crtc == NULL) drm_encoder_disable(encoder); } } /** * drm_crtc_helper_set_mode - internal helper to set a mode * @crtc: CRTC to program * @mode: mode to use * @x: horizontal offset into the surface * @y: vertical offset into the surface * @old_fb: old framebuffer, for cleanup * * Try to set @mode on @crtc. Give @crtc and its associated connectors a chance * to fixup or reject the mode prior to trying to set it. This is an internal * helper that drivers could e.g. use to update properties that require the * entire output pipe to be disabled and re-enabled in a new configuration. For * example for changing whether audio is enabled on a hdmi link or for changing * panel fitter or dither attributes. It is also called by the * drm_crtc_helper_set_config() helper function to drive the mode setting * sequence. * * Returns: * True if the mode was set successfully, false otherwise. */ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, struct drm_display_mode *mode, int x, int y, struct drm_framebuffer *old_fb) { struct drm_device *dev = crtc->dev; struct drm_display_mode *adjusted_mode, saved_mode, saved_hwmode; const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private; const struct drm_encoder_helper_funcs *encoder_funcs; int saved_x, saved_y; bool saved_enabled; struct drm_encoder *encoder; bool ret = true; drm_WARN_ON(dev, drm_drv_uses_atomic_modeset(dev)); drm_warn_on_modeset_not_all_locked(dev); saved_enabled = crtc->enabled; crtc->enabled = drm_helper_crtc_in_use(crtc); if (!crtc->enabled) return true; adjusted_mode = drm_mode_duplicate(dev, mode); if (!adjusted_mode) { crtc->enabled = saved_enabled; return false; } drm_mode_init(&saved_mode, &crtc->mode); drm_mode_init(&saved_hwmode, &crtc->hwmode); saved_x = crtc->x; saved_y = crtc->y; /* Update crtc values up front so the driver can rely on them for mode * setting. */ drm_mode_copy(&crtc->mode, mode); crtc->x = x; crtc->y = y; /* Pass our mode to the connectors and the CRTC to give them a chance to * adjust it according to limitations or connector properties, and also * a chance to reject the mode entirely. */ drm_for_each_encoder(encoder, dev) { if (encoder->crtc != crtc) continue; encoder_funcs = encoder->helper_private; if (!encoder_funcs) continue; encoder_funcs = encoder->helper_private; if (encoder_funcs->mode_fixup) { if (!(ret = encoder_funcs->mode_fixup(encoder, mode, adjusted_mode))) { drm_dbg_kms(dev, "[ENCODER:%d:%s] mode fixup failed\n", encoder->base.id, encoder->name); goto done; } } } if (crtc_funcs->mode_fixup) { if (!(ret = crtc_funcs->mode_fixup(crtc, mode, adjusted_mode))) { drm_dbg_kms(dev, "[CRTC:%d:%s] mode fixup failed\n", crtc->base.id, crtc->name); goto done; } } drm_dbg_kms(dev, "[CRTC:%d:%s]\n", crtc->base.id, crtc->name); drm_mode_copy(&crtc->hwmode, adjusted_mode); /* Prepare the encoders and CRTCs before setting the mode. */ drm_for_each_encoder(encoder, dev) { if (encoder->crtc != crtc) continue; encoder_funcs = encoder->helper_private; if (!encoder_funcs) continue; /* Disable the encoders as the first thing we do. */ if (encoder_funcs->prepare) encoder_funcs->prepare(encoder); } drm_crtc_prepare_encoders(dev); crtc_funcs->prepare(crtc); /* Set up the DPLL and any encoders state that needs to adjust or depend * on the DPLL. */ ret = !crtc_funcs->mode_set(crtc, mode, adjusted_mode, x, y, old_fb); if (!ret) goto done; drm_for_each_encoder(encoder, dev) { if (encoder->crtc != crtc) continue; encoder_funcs = encoder->helper_private; if (!encoder_funcs) continue; drm_dbg_kms(dev, "[ENCODER:%d:%s] set [MODE:%s]\n", encoder->base.id, encoder->name, mode->name); if (encoder_funcs->mode_set) encoder_funcs->mode_set(encoder, mode, adjusted_mode); } /* Now enable the clocks, plane, pipe, and connectors that we set up. */ crtc_funcs->commit(crtc); drm_for_each_encoder(encoder, dev) { if (encoder->crtc != crtc) continue; encoder_funcs = encoder->helper_private; if (!encoder_funcs) continue; if (encoder_funcs->commit) encoder_funcs->commit(encoder); } /* Calculate and store various constants which * are later needed by vblank and swap-completion * timestamping. They are derived from true hwmode. */ drm_calc_timestamping_constants(crtc, &crtc->hwmode); /* FIXME: add subpixel order */ done: drm_mode_destroy(dev, adjusted_mode); if (!ret) { crtc->enabled = saved_enabled; drm_mode_copy(&crtc->mode, &saved_mode); drm_mode_copy(&crtc->hwmode, &saved_hwmode); crtc->x = saved_x; crtc->y = saved_y; } return ret; } EXPORT_SYMBOL(drm_crtc_helper_set_mode); /** * drm_crtc_helper_atomic_check() - Helper to check CRTC atomic-state * @crtc: CRTC to check * @state: atomic state object * * Provides a default CRTC-state check handler for CRTCs that only have * one primary plane attached to it. This is often the case for the CRTC * of simple framebuffers. * * RETURNS: * Zero on success, or an errno code otherwise. */ int drm_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { struct drm_crtc_state *new_crtc_state = drm_atomic_get_new_crtc_state(state, crtc); if (!new_crtc_state->enable) return 0; return drm_atomic_helper_check_crtc_primary_plane(new_crtc_state); } EXPORT_SYMBOL(drm_crtc_helper_atomic_check); static void drm_crtc_helper_disable(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_connector *connector; struct drm_encoder *encoder; /* Decouple all encoders and their attached connectors from this crtc */ drm_for_each_encoder(encoder, dev) { struct drm_connector_list_iter conn_iter; if (encoder->crtc != crtc) continue; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { if (connector->encoder != encoder) continue; connector->encoder = NULL; /* * drm_helper_disable_unused_functions() ought to be * doing this, but since we've decoupled the encoder * from the connector above, the required connection * between them is henceforth no longer available. */ connector->dpms = DRM_MODE_DPMS_OFF; /* we keep a reference while the encoder is bound */ drm_connector_put(connector); } drm_connector_list_iter_end(&conn_iter); } __drm_helper_disable_unused_functions(dev); } /* * For connectors that support multiple encoders, either the * .atomic_best_encoder() or .best_encoder() operation must be implemented. */ struct drm_encoder * drm_connector_get_single_encoder(struct drm_connector *connector) { struct drm_encoder *encoder; drm_WARN_ON(connector->dev, hweight32(connector->possible_encoders) > 1); drm_connector_for_each_possible_encoder(connector, encoder) return encoder; return NULL; } /** * drm_crtc_helper_set_config - set a new config from userspace * @set: mode set configuration * @ctx: lock acquire context, not used here * * The drm_crtc_helper_set_config() helper function implements the of * &drm_crtc_funcs.set_config callback for drivers using the legacy CRTC * helpers. * * It first tries to locate the best encoder for each connector by calling the * connector @drm_connector_helper_funcs.best_encoder helper operation. * * After locating the appropriate encoders, the helper function will call the * mode_fixup encoder and CRTC helper operations to adjust the requested mode, * or reject it completely in which case an error will be returned to the * application. If the new configuration after mode adjustment is identical to * the current configuration the helper function will return without performing * any other operation. * * If the adjusted mode is identical to the current mode but changes to the * frame buffer need to be applied, the drm_crtc_helper_set_config() function * will call the CRTC &drm_crtc_helper_funcs.mode_set_base helper operation. * * If the adjusted mode differs from the current mode, or if the * ->mode_set_base() helper operation is not provided, the helper function * performs a full mode set sequence by calling the ->prepare(), ->mode_set() * and ->commit() CRTC and encoder helper operations, in that order. * Alternatively it can also use the dpms and disable helper operations. For * details see &struct drm_crtc_helper_funcs and struct * &drm_encoder_helper_funcs. * * This function is deprecated. New drivers must implement atomic modeset * support, for which this function is unsuitable. Instead drivers should use * drm_atomic_helper_set_config(). * * Returns: * Returns 0 on success, negative errno numbers on failure. */ int drm_crtc_helper_set_config(struct drm_mode_set *set, struct drm_modeset_acquire_ctx *ctx) { struct drm_device *dev; struct drm_crtc **save_encoder_crtcs, *new_crtc; struct drm_encoder **save_connector_encoders, *new_encoder, *encoder; bool mode_changed = false; /* if true do a full mode set */ bool fb_changed = false; /* if true and !mode_changed just do a flip */ struct drm_connector *connector; struct drm_connector_list_iter conn_iter; int count = 0, ro, fail = 0; const struct drm_crtc_helper_funcs *crtc_funcs; struct drm_mode_set save_set; int ret; int i; BUG_ON(!set); BUG_ON(!set->crtc); BUG_ON(!set->crtc->helper_private); /* Enforce sane interface api - has been abused by the fb helper. */ BUG_ON(!set->mode && set->fb); BUG_ON(set->fb && set->num_connectors == 0); crtc_funcs = set->crtc->helper_private; dev = set->crtc->dev; drm_dbg_kms(dev, "\n"); drm_WARN_ON(dev, drm_drv_uses_atomic_modeset(dev)); if (!set->mode) set->fb = NULL; if (set->fb) { drm_dbg_kms(dev, "[CRTC:%d:%s] [FB:%d] #connectors=%d (x y) (%i %i)\n", set->crtc->base.id, set->crtc->name, set->fb->base.id, (int)set->num_connectors, set->x, set->y); } else { drm_dbg_kms(dev, "[CRTC:%d:%s] [NOFB]\n", set->crtc->base.id, set->crtc->name); drm_crtc_helper_disable(set->crtc); return 0; } drm_warn_on_modeset_not_all_locked(dev); /* * Allocate space for the backup of all (non-pointer) encoder and * connector data. */ save_encoder_crtcs = kcalloc(dev->mode_config.num_encoder, sizeof(struct drm_crtc *), GFP_KERNEL); if (!save_encoder_crtcs) return -ENOMEM; save_connector_encoders = kcalloc(dev->mode_config.num_connector, sizeof(struct drm_encoder *), GFP_KERNEL); if (!save_connector_encoders) { kfree(save_encoder_crtcs); return -ENOMEM; } /* * Copy data. Note that driver private data is not affected. * Should anything bad happen only the expected state is * restored, not the drivers personal bookkeeping. */ count = 0; drm_for_each_encoder(encoder, dev) { save_encoder_crtcs[count++] = encoder->crtc; } count = 0; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) save_connector_encoders[count++] = connector->encoder; drm_connector_list_iter_end(&conn_iter); save_set.crtc = set->crtc; save_set.mode = &set->crtc->mode; save_set.x = set->crtc->x; save_set.y = set->crtc->y; save_set.fb = set->crtc->primary->fb; /* We should be able to check here if the fb has the same properties * and then just flip_or_move it */ if (set->crtc->primary->fb != set->fb) { /* If we have no fb then treat it as a full mode set */ if (set->crtc->primary->fb == NULL) { drm_dbg_kms(dev, "[CRTC:%d:%s] no fb, full mode set\n", set->crtc->base.id, set->crtc->name); mode_changed = true; } else if (set->fb->format != set->crtc->primary->fb->format) { mode_changed = true; } else fb_changed = true; } if (set->x != set->crtc->x || set->y != set->crtc->y) fb_changed = true; if (!drm_mode_equal(set->mode, &set->crtc->mode)) { drm_dbg_kms(dev, "[CRTC:%d:%s] modes are different, full mode set:\n", set->crtc->base.id, set->crtc->name); drm_dbg_kms(dev, DRM_MODE_FMT "\n", DRM_MODE_ARG(&set->crtc->mode)); drm_dbg_kms(dev, DRM_MODE_FMT "\n", DRM_MODE_ARG(set->mode)); mode_changed = true; } /* take a reference on all unbound connectors in set, reuse the * already taken reference for bound connectors */ for (ro = 0; ro < set->num_connectors; ro++) { if (set->connectors[ro]->encoder) continue; drm_connector_get(set->connectors[ro]); } /* a) traverse passed in connector list and get encoders for them */ count = 0; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { const struct drm_connector_helper_funcs *connector_funcs = connector->helper_private; new_encoder = connector->encoder; for (ro = 0; ro < set->num_connectors; ro++) { if (set->connectors[ro] == connector) { if (connector_funcs->best_encoder) new_encoder = connector_funcs->best_encoder(connector); else new_encoder = drm_connector_get_single_encoder(connector); /* if we can't get an encoder for a connector we are setting now - then fail */ if (new_encoder == NULL) /* don't break so fail path works correct */ fail = 1; if (connector->dpms != DRM_MODE_DPMS_ON) { drm_dbg_kms(dev, "[CONNECTOR:%d:%s] DPMS not on, full mode switch\n", connector->base.id, connector->name); mode_changed = true; } break; } } if (new_encoder != connector->encoder) { drm_dbg_kms(dev, "[CONNECTOR:%d:%s] encoder changed, full mode switch\n", connector->base.id, connector->name); mode_changed = true; /* If the encoder is reused for another connector, then * the appropriate crtc will be set later. */ if (connector->encoder) connector->encoder->crtc = NULL; connector->encoder = new_encoder; } } drm_connector_list_iter_end(&conn_iter); if (fail) { ret = -EINVAL; goto fail; } count = 0; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { if (!connector->encoder) continue; if (connector->encoder->crtc == set->crtc) new_crtc = NULL; else new_crtc = connector->encoder->crtc; for (ro = 0; ro < set->num_connectors; ro++) { if (set->connectors[ro] == connector) new_crtc = set->crtc; } /* Make sure the new CRTC will work with the encoder */ if (new_crtc && !drm_encoder_crtc_ok(connector->encoder, new_crtc)) { ret = -EINVAL; drm_connector_list_iter_end(&conn_iter); goto fail; } if (new_crtc != connector->encoder->crtc) { drm_dbg_kms(dev, "[CONNECTOR:%d:%s] CRTC changed, full mode switch\n", connector->base.id, connector->name); mode_changed = true; connector->encoder->crtc = new_crtc; } if (new_crtc) { drm_dbg_kms(dev, "[CONNECTOR:%d:%s] to [CRTC:%d:%s]\n", connector->base.id, connector->name, new_crtc->base.id, new_crtc->name); } else { drm_dbg_kms(dev, "[CONNECTOR:%d:%s] to [NOCRTC]\n", connector->base.id, connector->name); } } drm_connector_list_iter_end(&conn_iter); /* mode_set_base is not a required function */ if (fb_changed && !crtc_funcs->mode_set_base) mode_changed = true; if (mode_changed) { if (drm_helper_crtc_in_use(set->crtc)) { drm_dbg_kms(dev, "[CRTC:%d:%s] attempting to set mode from userspace: " DRM_MODE_FMT "\n", set->crtc->base.id, set->crtc->name, DRM_MODE_ARG(set->mode)); set->crtc->primary->fb = set->fb; if (!drm_crtc_helper_set_mode(set->crtc, set->mode, set->x, set->y, save_set.fb)) { drm_err(dev, "[CRTC:%d:%s] failed to set mode\n", set->crtc->base.id, set->crtc->name); set->crtc->primary->fb = save_set.fb; ret = -EINVAL; goto fail; } drm_dbg_kms(dev, "[CRTC:%d:%s] Setting connector DPMS state to on\n", set->crtc->base.id, set->crtc->name); for (i = 0; i < set->num_connectors; i++) { drm_dbg_kms(dev, "\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id, set->connectors[i]->name); set->connectors[i]->funcs->dpms(set->connectors[i], DRM_MODE_DPMS_ON); } } __drm_helper_disable_unused_functions(dev); } else if (fb_changed) { set->crtc->x = set->x; set->crtc->y = set->y; set->crtc->primary->fb = set->fb; ret = crtc_funcs->mode_set_base(set->crtc, set->x, set->y, save_set.fb); if (ret != 0) { set->crtc->x = save_set.x; set->crtc->y = save_set.y; set->crtc->primary->fb = save_set.fb; goto fail; } } kfree(save_connector_encoders); kfree(save_encoder_crtcs); return 0; fail: /* Restore all previous data. */ count = 0; drm_for_each_encoder(encoder, dev) { encoder->crtc = save_encoder_crtcs[count++]; } count = 0; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) connector->encoder = save_connector_encoders[count++]; drm_connector_list_iter_end(&conn_iter); /* after fail drop reference on all unbound connectors in set, let * bound connectors keep their reference */ for (ro = 0; ro < set->num_connectors; ro++) { if (set->connectors[ro]->encoder) continue; drm_connector_put(set->connectors[ro]); } /* Try to restore the config */ if (mode_changed && !drm_crtc_helper_set_mode(save_set.crtc, save_set.mode, save_set.x, save_set.y, save_set.fb)) drm_err(dev, "failed to restore config after modeset failure\n"); kfree(save_connector_encoders); kfree(save_encoder_crtcs); return ret; } EXPORT_SYMBOL(drm_crtc_helper_set_config); static int drm_helper_choose_encoder_dpms(struct drm_encoder *encoder) { int dpms = DRM_MODE_DPMS_OFF; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct drm_device *dev = encoder->dev; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) if (connector->encoder == encoder) if (connector->dpms < dpms) dpms = connector->dpms; drm_connector_list_iter_end(&conn_iter); return dpms; } /* Helper which handles bridge ordering around encoder dpms */ static void drm_helper_encoder_dpms(struct drm_encoder *encoder, int mode) { const struct drm_encoder_helper_funcs *encoder_funcs; encoder_funcs = encoder->helper_private; if (!encoder_funcs) return; if (encoder_funcs->dpms) encoder_funcs->dpms(encoder, mode); } static int drm_helper_choose_crtc_dpms(struct drm_crtc *crtc) { int dpms = DRM_MODE_DPMS_OFF; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct drm_device *dev = crtc->dev; drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) if (connector->encoder && connector->encoder->crtc == crtc) if (connector->dpms < dpms) dpms = connector->dpms; drm_connector_list_iter_end(&conn_iter); return dpms; } /** * drm_helper_connector_dpms() - connector dpms helper implementation * @connector: affected connector * @mode: DPMS mode * * The drm_helper_connector_dpms() helper function implements the * &drm_connector_funcs.dpms callback for drivers using the legacy CRTC * helpers. * * This is the main helper function provided by the CRTC helper framework for * implementing the DPMS connector attribute. It computes the new desired DPMS * state for all encoders and CRTCs in the output mesh and calls the * &drm_crtc_helper_funcs.dpms and &drm_encoder_helper_funcs.dpms callbacks * provided by the driver. * * This function is deprecated. New drivers must implement atomic modeset * support, where DPMS is handled in the DRM core. * * Returns: * Always returns 0. */ int drm_helper_connector_dpms(struct drm_connector *connector, int mode) { struct drm_encoder *encoder = connector->encoder; struct drm_crtc *crtc = encoder ? encoder->crtc : NULL; int old_dpms, encoder_dpms = DRM_MODE_DPMS_OFF; drm_WARN_ON(connector->dev, drm_drv_uses_atomic_modeset(connector->dev)); if (mode == connector->dpms) return 0; old_dpms = connector->dpms; connector->dpms = mode; if (encoder) encoder_dpms = drm_helper_choose_encoder_dpms(encoder); /* from off to on, do crtc then encoder */ if (mode < old_dpms) { if (crtc) { const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private; if (crtc_funcs->dpms) (*crtc_funcs->dpms) (crtc, drm_helper_choose_crtc_dpms(crtc)); } if (encoder) drm_helper_encoder_dpms(encoder, encoder_dpms); } /* from on to off, do encoder then crtc */ if (mode > old_dpms) { if (encoder) drm_helper_encoder_dpms(encoder, encoder_dpms); if (crtc) { const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private; if (crtc_funcs->dpms) (*crtc_funcs->dpms) (crtc, drm_helper_choose_crtc_dpms(crtc)); } } return 0; } EXPORT_SYMBOL(drm_helper_connector_dpms); /** * drm_helper_resume_force_mode - force-restore mode setting configuration * @dev: drm_device which should be restored * * Drivers which use the mode setting helpers can use this function to * force-restore the mode setting configuration e.g. on resume or when something * else might have trampled over the hw state (like some overzealous old BIOSen * tended to do). * * This helper doesn't provide a error return value since restoring the old * config should never fail due to resource allocation issues since the driver * has successfully set the restored configuration already. Hence this should * boil down to the equivalent of a few dpms on calls, which also don't provide * an error code. * * Drivers where simply restoring an old configuration again might fail (e.g. * due to slight differences in allocating shared resources when the * configuration is restored in a different order than when userspace set it up) * need to use their own restore logic. * * This function is deprecated. New drivers should implement atomic mode- * setting and use the atomic suspend/resume helpers. * * See also: * drm_atomic_helper_suspend(), drm_atomic_helper_resume() */ void drm_helper_resume_force_mode(struct drm_device *dev) { struct drm_crtc *crtc; struct drm_encoder *encoder; const struct drm_crtc_helper_funcs *crtc_funcs; int encoder_dpms; bool ret; drm_WARN_ON(dev, drm_drv_uses_atomic_modeset(dev)); drm_modeset_lock_all(dev); drm_for_each_crtc(crtc, dev) { if (!crtc->enabled) continue; ret = drm_crtc_helper_set_mode(crtc, &crtc->mode, crtc->x, crtc->y, crtc->primary->fb); /* Restoring the old config should never fail! */ if (ret == false) drm_err(dev, "failed to set mode on crtc %p\n", crtc); /* Turn off outputs that were already powered off */ if (drm_helper_choose_crtc_dpms(crtc)) { drm_for_each_encoder(encoder, dev) { if(encoder->crtc != crtc) continue; encoder_dpms = drm_helper_choose_encoder_dpms( encoder); drm_helper_encoder_dpms(encoder, encoder_dpms); } crtc_funcs = crtc->helper_private; if (crtc_funcs->dpms) (*crtc_funcs->dpms) (crtc, drm_helper_choose_crtc_dpms(crtc)); } } /* disable the unused connectors while restoring the modesetting */ __drm_helper_disable_unused_functions(dev); drm_modeset_unlock_all(dev); } EXPORT_SYMBOL(drm_helper_resume_force_mode); /** * drm_helper_force_disable_all - Forcibly turn off all enabled CRTCs * @dev: DRM device whose CRTCs to turn off * * Drivers may want to call this on unload to ensure that all displays are * unlit and the GPU is in a consistent, low power state. Takes modeset locks. * * Note: This should only be used by non-atomic legacy drivers. For an atomic * version look at drm_atomic_helper_shutdown(). * * Returns: * Zero on success, error code on failure. */ int drm_helper_force_disable_all(struct drm_device *dev) { struct drm_crtc *crtc; int ret = 0; drm_modeset_lock_all(dev); drm_for_each_crtc(crtc, dev) if (crtc->enabled) { struct drm_mode_set set = { .crtc = crtc, }; ret = drm_mode_set_config_internal(&set); if (ret) goto out; } out: drm_modeset_unlock_all(dev); return ret; } EXPORT_SYMBOL(drm_helper_force_disable_all); |
| 117 3 87 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KHUGEPAGED_H #define _LINUX_KHUGEPAGED_H #include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); extern bool current_is_khugepaged(void); #ifdef CONFIG_SHMEM extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd); #else static inline int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { return 0; } #endif static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags)) __khugepaged_enter(mm); } static inline void khugepaged_exit(struct mm_struct *mm) { if (test_bit(MMF_VM_HUGEPAGE, &mm->flags)) __khugepaged_exit(mm); } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { } static inline void khugepaged_exit(struct mm_struct *mm) { } static inline void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { } static inline int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { return 0; } static inline void khugepaged_min_free_kbytes_update(void) { } static inline bool current_is_khugepaged(void) { return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_KHUGEPAGED_H */ |
| 8 8 5 4 4 4 5 5 3 3 1 6 10 3 7 7 5 5 5 5 3 3 3 3 1 3 5 7 3 4 6 1 4 5 1 4 4 3 3 5 3 5 9 9 4 5 5 11 10 2 5 6 3 3 11 11 2 8 9 1 5 3 2 6 2 4 2 4 2 5 4 1 8 8 6 7 1 4 3 2 12 3 4 3 3 3 7 16 3 12 13 13 13 7 6 3 3 12 12 2 2 7 7 11 11 11 4 7 4 2 1 11 7 7 7 7 4 3 7 3 3 3 2 1 3 2 2 2 1 1 2 2 2 2 1 1 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk> * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/blktrace_api.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/debugfs.h> #include <linux/export.h> #include <linux/time.h> #include <linux/uaccess.h> #include <linux/list.h> #include <linux/blk-cgroup.h> #include "../../block/blk.h" #include <trace/events/block.h> #include "trace_output.h" #ifdef CONFIG_BLK_DEV_IO_TRACE static unsigned int blktrace_seq __read_mostly = 1; static struct trace_array *blk_tr; static bool blk_tracer_enabled __read_mostly; static LIST_HEAD(running_trace_list); static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(running_trace_lock); /* Select an alternative, minimalistic output than the original one */ #define TRACE_BLK_OPT_CLASSIC 0x1 #define TRACE_BLK_OPT_CGROUP 0x2 #define TRACE_BLK_OPT_CGNAME 0x4 static struct tracer_opt blk_tracer_opts[] = { /* Default disable the minimalistic output */ { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) }, #ifdef CONFIG_BLK_CGROUP { TRACER_OPT(blk_cgroup, TRACE_BLK_OPT_CGROUP) }, { TRACER_OPT(blk_cgname, TRACE_BLK_OPT_CGNAME) }, #endif { } }; static struct tracer_flags blk_tracer_flags = { .val = 0, .opts = blk_tracer_opts, }; /* Global reference count of probes */ static DEFINE_MUTEX(blk_probe_mutex); static int blk_probes_ref; static void blk_register_tracepoints(void); static void blk_unregister_tracepoints(void); /* * Send out a notify message. */ static void trace_note(struct blk_trace *bt, pid_t pid, int action, const void *data, size_t len, u64 cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; struct trace_buffer *buffer = NULL; unsigned int trace_ctx = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (blk_tracer) { buffer = blk_tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len + cgid_len, trace_ctx); if (!event) return; t = ring_buffer_event_data(event); goto record_it; } if (!bt->rchan) return; t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len); if (t) { t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->time = ktime_to_ns(ktime_get()); record_it: t->device = bt->dev; t->action = action | (cgid ? __BLK_TN_CGROUP : 0); t->pid = pid; t->cpu = cpu; t->pdu_len = len + cgid_len; if (cgid_len) memcpy((void *)t + sizeof(*t), &cgid, cgid_len); memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx); } } /* * Send out a notify for this process, if we haven't done so since a trace * started */ static void trace_note_tsk(struct task_struct *tsk) { unsigned long flags; struct blk_trace *bt; tsk->btrace_seq = blktrace_seq; raw_spin_lock_irqsave(&running_trace_lock, flags); list_for_each_entry(bt, &running_trace_list, running_list) { trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm), 0); } raw_spin_unlock_irqrestore(&running_trace_lock, flags); } static void trace_note_time(struct blk_trace *bt) { struct timespec64 now; unsigned long flags; u32 words[2]; /* need to check user space to see if this breaks in y2038 or y2106 */ ktime_get_real_ts64(&now); words[0] = (u32)now.tv_sec; words[1] = now.tv_nsec; local_irq_save(flags); trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0); local_irq_restore(flags); } void __blk_trace_note_message(struct blk_trace *bt, struct cgroup_subsys_state *css, const char *fmt, ...) { int n; va_list args; unsigned long flags; char *buf; u64 cgid = 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer_enabled)) return; /* * If the BLK_TC_NOTIFY action mask isn't set, don't send any note * message to the trace. */ if (!(bt->act_mask & BLK_TC_NOTIFY)) return; local_irq_save(flags); buf = this_cpu_ptr(bt->msg_data); va_start(args, fmt); n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); #ifdef CONFIG_BLK_CGROUP if (css && (blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) cgid = cgroup_id(css->cgroup); else cgid = 1; #endif trace_note(bt, current->pid, BLK_TN_MESSAGE, buf, n, cgid); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(__blk_trace_note_message); static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, pid_t pid) { if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0) return 1; if (sector && (sector < bt->start_lba || sector > bt->end_lba)) return 1; if (bt->pid && pid != bt->pid) return 1; return 0; } /* * Data direction bit lookup */ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; #define BLK_TC_RAHEAD BLK_TC_AHEAD #define BLK_TC_PREFLUSH BLK_TC_FLUSH /* The ilog2() calls fall out because they're constant */ #define MASK_TC_BIT(rw, __name) ((__force u32)(rw & REQ_ ## __name) << \ (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name)) /* * The worker for the various blk_add_trace*() types. Fills out a * blk_io_trace structure and places it in a per-cpu subbuffer. */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, const blk_opf_t opf, u32 what, int error, int pdu_len, void *pdu_data, u64 cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; struct trace_buffer *buffer = NULL; struct blk_io_trace *t; unsigned long flags = 0; unsigned long *sequence; unsigned int trace_ctx = 0; pid_t pid; int cpu; bool blk_tracer = blk_tracer_enabled; ssize_t cgid_len = cgid ? sizeof(cgid) : 0; const enum req_op op = opf & REQ_OP_MASK; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; what |= ddir_act[op_is_write(op) ? WRITE : READ]; what |= MASK_TC_BIT(opf, SYNC); what |= MASK_TC_BIT(opf, RAHEAD); what |= MASK_TC_BIT(opf, META); what |= MASK_TC_BIT(opf, PREFLUSH); what |= MASK_TC_BIT(opf, FUA); if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); if (cgid) what |= __BLK_TA_CGROUP; pid = tsk->pid; if (act_log_check(bt, what, sector, pid)) return; cpu = raw_smp_processor_id(); if (blk_tracer) { tracing_record_cmdline(current); buffer = blk_tr->array_buffer.buffer; trace_ctx = tracing_gen_ctx_flags(0); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len + cgid_len, trace_ctx); if (!event) return; t = ring_buffer_event_data(event); goto record_it; } if (unlikely(tsk->btrace_seq != blktrace_seq)) trace_note_tsk(tsk); /* * A word about the locking here - we disable interrupts to reserve * some space in the relay per-cpu buffer, to prevent an irq * from coming in and stepping on our toes. */ local_irq_save(flags); t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len); if (t) { sequence = per_cpu_ptr(bt->sequence, cpu); t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->sequence = ++(*sequence); t->time = ktime_to_ns(ktime_get()); record_it: /* * These two are not needed in ftrace as they are in the * generic trace_entry, filled by tracing_generic_entry_update, * but for the trace_event->bin() synthesizer benefit we do it * here too. */ t->cpu = cpu; t->pid = pid; t->sector = sector; t->bytes = bytes; t->action = what; t->device = bt->dev; t->error = error; t->pdu_len = pdu_len + cgid_len; if (cgid_len) memcpy((void *)t + sizeof(*t), &cgid, cgid_len); if (pdu_len) memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); if (blk_tracer) { trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx); return; } } local_irq_restore(flags); } static void blk_trace_free(struct request_queue *q, struct blk_trace *bt) { relay_close(bt->rchan); /* * If 'bt->dir' is not set, then both 'dropped' and 'msg' are created * under 'q->debugfs_dir', thus lookup and remove them. */ if (!bt->dir) { debugfs_lookup_and_remove("dropped", q->debugfs_dir); debugfs_lookup_and_remove("msg", q->debugfs_dir); } else { debugfs_remove(bt->dir); } free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); } static void get_probe_ref(void) { mutex_lock(&blk_probe_mutex); if (++blk_probes_ref == 1) blk_register_tracepoints(); mutex_unlock(&blk_probe_mutex); } static void put_probe_ref(void) { mutex_lock(&blk_probe_mutex); if (!--blk_probes_ref) blk_unregister_tracepoints(); mutex_unlock(&blk_probe_mutex); } static int blk_trace_start(struct blk_trace *bt) { if (bt->trace_state != Blktrace_setup && bt->trace_state != Blktrace_stopped) return -EINVAL; blktrace_seq++; smp_mb(); bt->trace_state = Blktrace_running; raw_spin_lock_irq(&running_trace_lock); list_add(&bt->running_list, &running_trace_list); raw_spin_unlock_irq(&running_trace_lock); trace_note_time(bt); return 0; } static int blk_trace_stop(struct blk_trace *bt) { if (bt->trace_state != Blktrace_running) return -EINVAL; bt->trace_state = Blktrace_stopped; raw_spin_lock_irq(&running_trace_lock); list_del_init(&bt->running_list); raw_spin_unlock_irq(&running_trace_lock); relay_flush(bt->rchan); return 0; } static void blk_trace_cleanup(struct request_queue *q, struct blk_trace *bt) { blk_trace_stop(bt); synchronize_rcu(); blk_trace_free(q, bt); put_probe_ref(); } static int __blk_trace_remove(struct request_queue *q) { struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, lockdep_is_held(&q->debugfs_mutex)); if (!bt) return -EINVAL; blk_trace_cleanup(q, bt); return 0; } int blk_trace_remove(struct request_queue *q) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_remove(q); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_remove); static ssize_t blk_dropped_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct blk_trace *bt = filp->private_data; char buf[16]; snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped)); return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); } static const struct file_operations blk_dropped_fops = { .owner = THIS_MODULE, .open = simple_open, .read = blk_dropped_read, .llseek = default_llseek, }; static ssize_t blk_msg_write(struct file *filp, const char __user *buffer, size_t count, loff_t *ppos) { char *msg; struct blk_trace *bt; if (count >= BLK_TN_MAX_MSG) return -EINVAL; msg = memdup_user_nul(buffer, count); if (IS_ERR(msg)) return PTR_ERR(msg); bt = filp->private_data; __blk_trace_note_message(bt, NULL, "%s", msg); kfree(msg); return count; } static const struct file_operations blk_msg_fops = { .owner = THIS_MODULE, .open = simple_open, .write = blk_msg_write, .llseek = noop_llseek, }; /* * Keep track of how many times we encountered a full subbuffer, to aid * the user space app in telling how many lost events there were. */ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf, void *prev_subbuf, size_t prev_padding) { struct blk_trace *bt; if (!relay_buf_full(buf)) return 1; bt = buf->chan->private_data; atomic_inc(&bt->dropped); return 0; } static int blk_remove_buf_file_callback(struct dentry *dentry) { debugfs_remove(dentry); return 0; } static struct dentry *blk_create_buf_file_callback(const char *filename, struct dentry *parent, umode_t mode, struct rchan_buf *buf, int *is_global) { return debugfs_create_file(filename, mode, parent, buf, &relay_file_operations); } static const struct rchan_callbacks blk_relay_callbacks = { .subbuf_start = blk_subbuf_start_callback, .create_buf_file = blk_create_buf_file_callback, .remove_buf_file = blk_remove_buf_file_callback, }; static void blk_trace_setup_lba(struct blk_trace *bt, struct block_device *bdev) { if (bdev) { bt->start_lba = bdev->bd_start_sect; bt->end_lba = bdev->bd_start_sect + bdev_nr_sectors(bdev); } else { bt->start_lba = 0; bt->end_lba = -1ULL; } } /* * Setup everything required to start tracing */ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts) { struct blk_trace *bt = NULL; struct dentry *dir = NULL; int ret; lockdep_assert_held(&q->debugfs_mutex); if (!buts->buf_size || !buts->buf_nr) return -EINVAL; strscpy_pad(buts->name, name, BLKTRACE_BDEV_SIZE); /* * some device names have larger paths - convert the slashes * to underscores for this to work as expected */ strreplace(buts->name, '/', '_'); /* * bdev can be NULL, as with scsi-generic, this is a helpful as * we can be. */ if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) { pr_warn("Concurrent blktraces are not allowed on %s\n", buts->name); return -EBUSY; } bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; ret = -ENOMEM; bt->sequence = alloc_percpu(unsigned long); if (!bt->sequence) goto err; bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto err; /* * When tracing the whole disk reuse the existing debugfs directory * created by the block layer on init. For partitions block devices, * and scsi-generic block devices we create a temporary new debugfs * directory that will be removed once the trace ends. */ if (bdev && !bdev_is_partition(bdev)) dir = q->debugfs_dir; else bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); /* * As blktrace relies on debugfs for its interface the debugfs directory * is required, contrary to the usual mantra of not checking for debugfs * files or directories. */ if (IS_ERR_OR_NULL(dir)) { pr_warn("debugfs_dir not present for %s so skipping\n", buts->name); ret = -ENOENT; goto err; } bt->dev = dev; atomic_set(&bt->dropped, 0); INIT_LIST_HEAD(&bt->running_list); ret = -EIO; debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops); debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops); bt->rchan = relay_open("trace", dir, buts->buf_size, buts->buf_nr, &blk_relay_callbacks, bt); if (!bt->rchan) goto err; bt->act_mask = buts->act_mask; if (!bt->act_mask) bt->act_mask = (u16) -1; blk_trace_setup_lba(bt, bdev); /* overwrite with user settings */ if (buts->start_lba) bt->start_lba = buts->start_lba; if (buts->end_lba) bt->end_lba = buts->end_lba; bt->pid = buts->pid; bt->trace_state = Blktrace_setup; rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); ret = 0; err: if (ret) blk_trace_free(q, bt); return ret; } static int __blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; int ret; ret = copy_from_user(&buts, arg, sizeof(buts)); if (ret) return -EFAULT; ret = do_blk_trace_setup(q, name, dev, bdev, &buts); if (ret) return ret; if (copy_to_user(arg, &buts, sizeof(buts))) { __blk_trace_remove(q); return -EFAULT; } return 0; } int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_setup(q, name, dev, bdev, arg); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_setup); #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) static int compat_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg) { struct blk_user_trace_setup buts; struct compat_blk_user_trace_setup cbuts; int ret; if (copy_from_user(&cbuts, arg, sizeof(cbuts))) return -EFAULT; buts = (struct blk_user_trace_setup) { .act_mask = cbuts.act_mask, .buf_size = cbuts.buf_size, .buf_nr = cbuts.buf_nr, .start_lba = cbuts.start_lba, .end_lba = cbuts.end_lba, .pid = cbuts.pid, }; ret = do_blk_trace_setup(q, name, dev, bdev, &buts); if (ret) return ret; if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { __blk_trace_remove(q); return -EFAULT; } return 0; } #endif static int __blk_trace_startstop(struct request_queue *q, int start) { struct blk_trace *bt; bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; if (start) return blk_trace_start(bt); else return blk_trace_stop(bt); } int blk_trace_startstop(struct request_queue *q, int start) { int ret; mutex_lock(&q->debugfs_mutex); ret = __blk_trace_startstop(q, start); mutex_unlock(&q->debugfs_mutex); return ret; } EXPORT_SYMBOL_GPL(blk_trace_startstop); /* * When reading or writing the blktrace sysfs files, the references to the * opened sysfs or device files should prevent the underlying block device * from being removed. So no further delete protection is really needed. */ /** * blk_trace_ioctl - handle the ioctls associated with tracing * @bdev: the block device * @cmd: the ioctl cmd * @arg: the argument data, if any * **/ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) { struct request_queue *q = bdev_get_queue(bdev); int ret, start = 0; char b[BDEVNAME_SIZE]; mutex_lock(&q->debugfs_mutex); switch (cmd) { case BLKTRACESETUP: snprintf(b, sizeof(b), "%pg", bdev); ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64) case BLKTRACESETUP32: snprintf(b, sizeof(b), "%pg", bdev); ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg); break; #endif case BLKTRACESTART: start = 1; fallthrough; case BLKTRACESTOP: ret = __blk_trace_startstop(q, start); break; case BLKTRACETEARDOWN: ret = __blk_trace_remove(q); break; default: ret = -ENOTTY; break; } mutex_unlock(&q->debugfs_mutex); return ret; } /** * blk_trace_shutdown - stop and cleanup trace structures * @q: the request queue associated with the device * **/ void blk_trace_shutdown(struct request_queue *q) { if (rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex))) __blk_trace_remove(q); } #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { struct cgroup_subsys_state *blkcg_css; struct blk_trace *bt; /* We don't use the 'bt' value here except as an optimization... */ bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; blkcg_css = bio_blkcg_css(bio); if (!blkcg_css) return 0; return cgroup_id(blkcg_css->cgroup); } #else static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { return 0; } #endif static u64 blk_trace_request_get_cgid(struct request *rq) { if (!rq->bio) return 0; /* Use the first bio */ return blk_trace_bio_get_cgid(rq->q, rq->bio); } /* * blktrace probes */ /** * blk_add_trace_rq - Add a trace for a request oriented action * @rq: the source request * @error: return status to log * @nr_bytes: number of completed bytes * @what: the action * @cgid: the cgroup info * * Description: * Records an action against a request. Will log the bio offset + size. * **/ static void blk_add_trace_rq(struct request *rq, blk_status_t error, unsigned int nr_bytes, u32 what, u64 cgid) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); else what |= BLK_TC_ACT(BLK_TC_FS); __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, rq->cmd_flags, what, blk_status_to_errno(error), 0, NULL, cgid); rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_issue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_merge(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_requeue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE, blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_complete(void *ignore, struct request *rq, blk_status_t error, unsigned int nr_bytes) { blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE, blk_trace_request_get_cgid(rq)); } /** * blk_add_trace_bio - Add a trace for a bio oriented action * @q: queue the io is for * @bio: the source bio * @what: the action * @error: error, if any * * Description: * Records an action against a bio. Will log the bio offset + size. * **/ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_BOUNCE, 0); } static void blk_add_trace_bio_complete(void *ignore, struct request_queue *q, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, blk_status_to_errno(bio->bi_status)); } static void blk_add_trace_bio_backmerge(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_BACKMERGE, 0); } static void blk_add_trace_bio_frontmerge(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_FRONTMERGE, 0); } static void blk_add_trace_bio_queue(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_QUEUE, 0); } static void blk_add_trace_getrq(void *ignore, struct bio *bio) { blk_add_trace_bio(bio->bi_bdev->bd_disk->queue, bio, BLK_TA_GETRQ, 0); } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; if (explicit) what = BLK_TA_UNPLUG_IO; else what = BLK_TA_UNPLUG_TIMER; __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio->bi_opf, BLK_TA_SPLIT, blk_status_to_errno(bio->bi_status), sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } rcu_read_unlock(); } /** * blk_add_trace_bio_remap - Add a trace for a bio-remap operation * @ignore: trace callback data parameter (not used) * @bio: the source bio * @dev: source device * @from: source sector * * Called after a bio is remapped to a different device and/or sector. **/ static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev, sector_t from) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio->bi_opf, BLK_TA_REMAP, blk_status_to_errno(bio->bi_status), sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); rcu_read_unlock(); } /** * blk_add_trace_rq_remap - Add a trace for a request-remap operation * @ignore: trace callback data parameter (not used) * @rq: the source request * @dev: target device * @from: source sector * * Description: * Device mapper remaps request to other devices. * Add a trace for that action. * **/ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->q->disk)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq->cmd_flags, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } /** * blk_add_driver_data - Add binary message with driver-specific data * @rq: io request * @data: driver-specific data * @len: length of driver-specific data * * Description: * Some drivers might want to write driver-specific data per request. * **/ void blk_add_driver_data(struct request *rq, void *data, size_t len) { struct blk_trace *bt; rcu_read_lock(); bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); static void blk_register_tracepoints(void) { int ret; ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); WARN_ON(ret); ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); WARN_ON(ret); ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); WARN_ON(ret); ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); WARN_ON(ret); ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); WARN_ON(ret); ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); WARN_ON(ret); ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); WARN_ON(ret); ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); WARN_ON(ret); ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); WARN_ON(ret); ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); WARN_ON(ret); ret = register_trace_block_getrq(blk_add_trace_getrq, NULL); WARN_ON(ret); ret = register_trace_block_plug(blk_add_trace_plug, NULL); WARN_ON(ret); ret = register_trace_block_unplug(blk_add_trace_unplug, NULL); WARN_ON(ret); ret = register_trace_block_split(blk_add_trace_split, NULL); WARN_ON(ret); ret = register_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); WARN_ON(ret); ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); WARN_ON(ret); } static void blk_unregister_tracepoints(void) { unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); unregister_trace_block_split(blk_add_trace_split, NULL); unregister_trace_block_unplug(blk_add_trace_unplug, NULL); unregister_trace_block_plug(blk_add_trace_plug, NULL); unregister_trace_block_getrq(blk_add_trace_getrq, NULL); unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL); unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL); unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL); unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL); unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL); unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL); unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL); unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL); tracepoint_synchronize_unregister(); } /* * struct blk_io_tracer formatting routines */ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) { int i = 0; int tc = t->action >> BLK_TC_SHIFT; if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { rwbs[i++] = 'N'; goto out; } if (tc & BLK_TC_FLUSH) rwbs[i++] = 'F'; if (tc & BLK_TC_DISCARD) rwbs[i++] = 'D'; else if (tc & BLK_TC_WRITE) rwbs[i++] = 'W'; else if (t->bytes) rwbs[i++] = 'R'; else rwbs[i++] = 'N'; if (tc & BLK_TC_FUA) rwbs[i++] = 'F'; if (tc & BLK_TC_AHEAD) rwbs[i++] = 'A'; if (tc & BLK_TC_SYNC) rwbs[i++] = 'S'; if (tc & BLK_TC_META) rwbs[i++] = 'M'; out: rwbs[i] = '\0'; } static inline const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) { return (const struct blk_io_trace *)ent; } static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) { return (void *)(te_blk_io_trace(ent) + 1) + (has_cg ? sizeof(u64) : 0); } static inline u64 t_cgid(const struct trace_entry *ent) { return *(u64 *)(te_blk_io_trace(ent) + 1); } static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg) { return te_blk_io_trace(ent)->pdu_len - (has_cg ? sizeof(u64) : 0); } static inline u32 t_action(const struct trace_entry *ent) { return te_blk_io_trace(ent)->action; } static inline u32 t_bytes(const struct trace_entry *ent) { return te_blk_io_trace(ent)->bytes; } static inline u32 t_sec(const struct trace_entry *ent) { return te_blk_io_trace(ent)->bytes >> 9; } static inline unsigned long long t_sector(const struct trace_entry *ent) { return te_blk_io_trace(ent)->sector; } static inline __u16 t_error(const struct trace_entry *ent) { return te_blk_io_trace(ent)->error; } static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { const __be64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, bool has_cg); static void blk_log_action_classic(struct trace_iterator *iter, const char *act, bool has_cg) { char rwbs[RWBS_LEN]; unsigned long long ts = iter->ts; unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC); unsigned secs = (unsigned long)ts; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); trace_seq_printf(&iter->seq, "%3d,%-3d %2d %5d.%09lu %5u %2s %3s ", MAJOR(t->device), MINOR(t->device), iter->cpu, secs, nsec_rem, iter->ent->pid, act, rwbs); } static void blk_log_action(struct trace_iterator *iter, const char *act, bool has_cg) { char rwbs[RWBS_LEN]; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); if (has_cg) { u64 id = t_cgid(iter->ent); if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) { char blkcg_name_buf[NAME_MAX + 1] = "<...>"; cgroup_path_from_kernfs_id(id, blkcg_name_buf, sizeof(blkcg_name_buf)); trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ", MAJOR(t->device), MINOR(t->device), blkcg_name_buf, act, rwbs); } else { /* * The cgid portion used to be "INO,GEN". Userland * builds a FILEID_INO32_GEN fid out of them and * opens the cgroup using open_by_handle_at(2). * While 32bit ino setups are still the same, 64bit * ones now use the 64bit ino as the whole ID and * no longer use generation. * * Regardless of the content, always output * "LOW32,HIGH32" so that FILEID_INO32_GEN fid can * be mapped back to @id on both 64 and 32bit ino * setups. See __kernfs_fh_to_dentry(). */ trace_seq_printf(&iter->seq, "%3d,%-3d %llx,%-llx %2s %3s ", MAJOR(t->device), MINOR(t->device), id & U32_MAX, id >> 32, act, rwbs); } } else trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", MAJOR(t->device), MINOR(t->device), act, rwbs); } static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { const unsigned char *pdu_buf; int pdu_len; int i, end; pdu_buf = pdu_start(ent, has_cg); pdu_len = pdu_real_len(ent, has_cg); if (!pdu_len) return; /* find the last zero that needs to be printed */ for (end = pdu_len - 1; end >= 0; end--) if (pdu_buf[end]) break; end++; trace_seq_putc(s, '('); for (i = 0; i < pdu_len; i++) { trace_seq_printf(s, "%s%02x", i == 0 ? "" : " ", pdu_buf[i]); /* * stop when the rest is just zeros and indicate so * with a ".." appended */ if (i == end && end != pdu_len - 1) { trace_seq_puts(s, " ..) "); return; } } trace_seq_puts(s, ") "); } static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { trace_seq_printf(s, "%u ", t_bytes(ent)); blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%s]\n", cmd); } else { if (t_sec(ent)) trace_seq_printf(s, "%llu + %u [%s]\n", t_sector(ent), t_sec(ent), cmd); else trace_seq_printf(s, "[%s]\n", cmd); } } static void blk_log_with_error(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%d]\n", t_error(ent)); } else { if (t_sec(ent)) trace_seq_printf(s, "%llu + %u [%d]\n", t_sector(ent), t_sec(ent), t_error(ent)); else trace_seq_printf(s, "%llu [%d]\n", t_sector(ent), t_error(ent)); } } static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), MAJOR(be32_to_cpu(__r->device_from)), MINOR(be32_to_cpu(__r->device_from)), be64_to_cpu(__r->sector_from)); } static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "[%s]\n", cmd); } static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent, has_cg)); } static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent), get_pdu_int(ent, has_cg), cmd); } static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { trace_seq_putmem(s, pdu_start(ent, has_cg), pdu_real_len(ent, has_cg)); trace_seq_putc(s, '\n'); } /* * struct tracer operations */ static void blk_tracer_print_header(struct seq_file *m) { if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return; seq_puts(m, "# DEV CPU TIMESTAMP PID ACT FLG\n" "# | | | | | |\n"); } static void blk_tracer_start(struct trace_array *tr) { blk_tracer_enabled = true; } static int blk_tracer_init(struct trace_array *tr) { blk_tr = tr; blk_tracer_start(tr); return 0; } static void blk_tracer_stop(struct trace_array *tr) { blk_tracer_enabled = false; } static void blk_tracer_reset(struct trace_array *tr) { blk_tracer_stop(tr); } static const struct { const char *act[2]; void (*print)(struct trace_seq *s, const struct trace_entry *ent, bool has_cg); } what2act[] = { [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic }, [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic }, [__BLK_TA_FRONTMERGE] = {{ "F", "frontmerge" }, blk_log_generic }, [__BLK_TA_GETRQ] = {{ "G", "getrq" }, blk_log_generic }, [__BLK_TA_SLEEPRQ] = {{ "S", "sleeprq" }, blk_log_generic }, [__BLK_TA_REQUEUE] = {{ "R", "requeue" }, blk_log_with_error }, [__BLK_TA_ISSUE] = {{ "D", "issue" }, blk_log_generic }, [__BLK_TA_COMPLETE] = {{ "C", "complete" }, blk_log_with_error }, [__BLK_TA_PLUG] = {{ "P", "plug" }, blk_log_plug }, [__BLK_TA_UNPLUG_IO] = {{ "U", "unplug_io" }, blk_log_unplug }, [__BLK_TA_UNPLUG_TIMER] = {{ "UT", "unplug_timer" }, blk_log_unplug }, [__BLK_TA_INSERT] = {{ "I", "insert" }, blk_log_generic }, [__BLK_TA_SPLIT] = {{ "X", "split" }, blk_log_split }, [__BLK_TA_BOUNCE] = {{ "B", "bounce" }, blk_log_generic }, [__BLK_TA_REMAP] = {{ "A", "remap" }, blk_log_remap }, }; static enum print_line_t print_one_line(struct trace_iterator *iter, bool classic) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; const struct blk_io_trace *t; u16 what; bool long_act; blk_log_action_t *log_action; bool has_cg; t = te_blk_io_trace(iter->ent); what = (t->action & ((1 << BLK_TC_SHIFT) - 1)) & ~__BLK_TA_CGROUP; long_act = !!(tr->trace_flags & TRACE_ITER_VERBOSE); log_action = classic ? &blk_log_action_classic : &blk_log_action; has_cg = t->action & __BLK_TA_CGROUP; if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { log_action(iter, long_act ? "message" : "m", has_cg); blk_log_msg(s, iter->ent, has_cg); return trace_handle_return(s); } if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act))) trace_seq_printf(s, "Unknown action %x\n", what); else { log_action(iter, what2act[what].act[long_act], has_cg); what2act[what].print(s, iter->ent, has_cg); } return trace_handle_return(s); } static enum print_line_t blk_trace_event_print(struct trace_iterator *iter, int flags, struct trace_event *event) { return print_one_line(iter, false); } static void blk_trace_synthesize_old_trace(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct blk_io_trace *t = (struct blk_io_trace *)iter->ent; const int offset = offsetof(struct blk_io_trace, sector); struct blk_io_trace old = { .magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION, .time = iter->ts, }; trace_seq_putmem(s, &old, offset); trace_seq_putmem(s, &t->sector, sizeof(old) - offset + t->pdu_len); } static enum print_line_t blk_trace_event_print_binary(struct trace_iterator *iter, int flags, struct trace_event *event) { blk_trace_synthesize_old_trace(iter); return trace_handle_return(&iter->seq); } static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) { if ((iter->ent->type != TRACE_BLK) || !(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return TRACE_TYPE_UNHANDLED; return print_one_line(iter, true); } static int blk_tracer_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { /* don't output context-info for blk_classic output */ if (bit == TRACE_BLK_OPT_CLASSIC) { if (set) tr->trace_flags &= ~TRACE_ITER_CONTEXT_INFO; else tr->trace_flags |= TRACE_ITER_CONTEXT_INFO; } return 0; } static struct tracer blk_tracer __read_mostly = { .name = "blk", .init = blk_tracer_init, .reset = blk_tracer_reset, .start = blk_tracer_start, .stop = blk_tracer_stop, .print_header = blk_tracer_print_header, .print_line = blk_tracer_print_line, .flags = &blk_tracer_flags, .set_flag = blk_tracer_set_flag, }; static struct trace_event_functions trace_blk_event_funcs = { .trace = blk_trace_event_print, .binary = blk_trace_event_print_binary, }; static struct trace_event trace_blk_event = { .type = TRACE_BLK, .funcs = &trace_blk_event_funcs, }; static int __init init_blk_tracer(void) { if (!register_trace_event(&trace_blk_event)) { pr_warn("Warning: could not register block events\n"); return 1; } if (register_tracer(&blk_tracer) != 0) { pr_warn("Warning: could not register the block tracer\n"); unregister_trace_event(&trace_blk_event); return 1; } return 0; } device_initcall(init_blk_tracer); static int blk_trace_remove_queue(struct request_queue *q) { struct blk_trace *bt; bt = rcu_replace_pointer(q->blk_trace, NULL, lockdep_is_held(&q->debugfs_mutex)); if (bt == NULL) return -EINVAL; blk_trace_stop(bt); put_probe_ref(); synchronize_rcu(); blk_trace_free(q, bt); return 0; } /* * Setup everything required to start tracing */ static int blk_trace_setup_queue(struct request_queue *q, struct block_device *bdev) { struct blk_trace *bt = NULL; int ret = -ENOMEM; bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) return -ENOMEM; bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG, __alignof__(char)); if (!bt->msg_data) goto free_bt; bt->dev = bdev->bd_dev; bt->act_mask = (u16)-1; blk_trace_setup_lba(bt, bdev); rcu_assign_pointer(q->blk_trace, bt); get_probe_ref(); return 0; free_bt: blk_trace_free(q, bt); return ret; } /* * sysfs interface to enable and configure tracing */ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf); static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); #define BLK_TRACE_DEVICE_ATTR(_name) \ DEVICE_ATTR(_name, S_IRUGO | S_IWUSR, \ sysfs_blk_trace_attr_show, \ sysfs_blk_trace_attr_store) static BLK_TRACE_DEVICE_ATTR(enable); static BLK_TRACE_DEVICE_ATTR(act_mask); static BLK_TRACE_DEVICE_ATTR(pid); static BLK_TRACE_DEVICE_ATTR(start_lba); static BLK_TRACE_DEVICE_ATTR(end_lba); static struct attribute *blk_trace_attrs[] = { &dev_attr_enable.attr, &dev_attr_act_mask.attr, &dev_attr_pid.attr, &dev_attr_start_lba.attr, &dev_attr_end_lba.attr, NULL }; struct attribute_group blk_trace_attr_group = { .name = "trace", .attrs = blk_trace_attrs, }; static const struct { int mask; const char *str; } mask_maps[] = { { BLK_TC_READ, "read" }, { BLK_TC_WRITE, "write" }, { BLK_TC_FLUSH, "flush" }, { BLK_TC_SYNC, "sync" }, { BLK_TC_QUEUE, "queue" }, { BLK_TC_REQUEUE, "requeue" }, { BLK_TC_ISSUE, "issue" }, { BLK_TC_COMPLETE, "complete" }, { BLK_TC_FS, "fs" }, { BLK_TC_PC, "pc" }, { BLK_TC_NOTIFY, "notify" }, { BLK_TC_AHEAD, "ahead" }, { BLK_TC_META, "meta" }, { BLK_TC_DISCARD, "discard" }, { BLK_TC_DRV_DATA, "drv_data" }, { BLK_TC_FUA, "fua" }, }; static int blk_trace_str2mask(const char *str) { int i; int mask = 0; char *buf, *s, *token; buf = kstrdup(str, GFP_KERNEL); if (buf == NULL) return -ENOMEM; s = strstrip(buf); while (1) { token = strsep(&s, ","); if (token == NULL) break; if (*token == '\0') continue; for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { if (strcasecmp(token, mask_maps[i].str) == 0) { mask |= mask_maps[i].mask; break; } } if (i == ARRAY_SIZE(mask_maps)) { mask = -EINVAL; break; } } kfree(buf); return mask; } static ssize_t blk_trace_mask2str(char *buf, int mask) { int i; char *p = buf; for (i = 0; i < ARRAY_SIZE(mask_maps); i++) { if (mask & mask_maps[i].mask) { p += sprintf(p, "%s%s", (p == buf) ? "" : ",", mask_maps[i].str); } } *p++ = '\n'; return p - buf; } static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf) { struct block_device *bdev = dev_to_bdev(dev); struct request_queue *q = bdev_get_queue(bdev); struct blk_trace *bt; ssize_t ret = -ENXIO; mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); return ret; } static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct block_device *bdev = dev_to_bdev(dev); struct request_queue *q = bdev_get_queue(bdev); struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; if (count == 0) goto out; if (attr == &dev_attr_act_mask) { if (kstrtoull(buf, 0, &value)) { /* Assume it is a list of trace category names */ ret = blk_trace_str2mask(buf); if (ret < 0) goto out; value = ret; } } else { if (kstrtoull(buf, 0, &value)) goto out; } mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); if (attr == &dev_attr_enable) { if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } if (value) ret = blk_trace_setup_queue(q, bdev); else ret = blk_trace_remove_queue(q); goto out_unlock_bdev; } ret = 0; if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); bt = rcu_dereference_protected(q->blk_trace, lockdep_is_held(&q->debugfs_mutex)); } if (ret == 0) { if (attr == &dev_attr_act_mask) bt->act_mask = value; else if (attr == &dev_attr_pid) bt->pid = value; else if (attr == &dev_attr_start_lba) bt->start_lba = value; else if (attr == &dev_attr_end_lba) bt->end_lba = value; } out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); out: return ret ? ret : count; } #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_EVENT_TRACING /** * blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string. * @rwbs: buffer to be filled * @opf: request operation type (REQ_OP_XXX) and flags for the tracepoint * * Description: * Maps each request operation and flag to a single character and fills the * buffer provided by the caller with resulting string. * **/ void blk_fill_rwbs(char *rwbs, blk_opf_t opf) { int i = 0; if (opf & REQ_PREFLUSH) rwbs[i++] = 'F'; switch (opf & REQ_OP_MASK) { case REQ_OP_WRITE: rwbs[i++] = 'W'; break; case REQ_OP_DISCARD: rwbs[i++] = 'D'; break; case REQ_OP_SECURE_ERASE: rwbs[i++] = 'D'; rwbs[i++] = 'E'; break; case REQ_OP_FLUSH: rwbs[i++] = 'F'; break; case REQ_OP_READ: rwbs[i++] = 'R'; break; default: rwbs[i++] = 'N'; } if (opf & REQ_FUA) rwbs[i++] = 'F'; if (opf & REQ_RAHEAD) rwbs[i++] = 'A'; if (opf & REQ_SYNC) rwbs[i++] = 'S'; if (opf & REQ_META) rwbs[i++] = 'M'; rwbs[i] = '\0'; } EXPORT_SYMBOL_GPL(blk_fill_rwbs); #endif /* CONFIG_EVENT_TRACING */ |
| 1 1 1 2 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" struct privflags_req_info { struct ethnl_req_info base; }; struct privflags_reply_data { struct ethnl_reply_data base; const char (*priv_flag_names)[ETH_GSTRING_LEN]; unsigned int n_priv_flags; u32 priv_flags; }; #define PRIVFLAGS_REPDATA(__reply_base) \ container_of(__reply_base, struct privflags_reply_data, base) const struct nla_policy ethnl_privflags_get_policy[] = { [ETHTOOL_A_PRIVFLAGS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int ethnl_get_priv_flags_info(struct net_device *dev, unsigned int *count, const char (**names)[ETH_GSTRING_LEN]) { const struct ethtool_ops *ops = dev->ethtool_ops; int nflags; nflags = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS); if (nflags < 0) return nflags; if (names) { *names = kcalloc(nflags, ETH_GSTRING_LEN, GFP_KERNEL); if (!*names) return -ENOMEM; ops->get_strings(dev, ETH_SS_PRIV_FLAGS, (u8 *)*names); } /* We can pass more than 32 private flags to userspace via netlink but * we cannot get more with ethtool_ops::get_priv_flags(). Note that we * must not adjust nflags before allocating the space for flag names * as the buffer must be large enough for all flags. */ if (WARN_ONCE(nflags > 32, "device %s reports more than 32 private flags (%d)\n", netdev_name(dev), nflags)) nflags = 32; *count = nflags; return 0; } static int privflags_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const char (*names)[ETH_GSTRING_LEN]; const struct ethtool_ops *ops; unsigned int nflags; int ret; ops = dev->ethtool_ops; if (!ops->get_priv_flags || !ops->get_sset_count || !ops->get_strings) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = ethnl_get_priv_flags_info(dev, &nflags, &names); if (ret < 0) goto out_ops; data->priv_flags = ops->get_priv_flags(dev); data->priv_flag_names = names; data->n_priv_flags = nflags; out_ops: ethnl_ops_complete(dev); return ret; } static int privflags_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const u32 all_flags = ~(u32)0 >> (32 - data->n_priv_flags); return ethnl_bitset32_size(&data->priv_flags, &all_flags, data->n_priv_flags, data->priv_flag_names, compact); } static int privflags_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const u32 all_flags = ~(u32)0 >> (32 - data->n_priv_flags); return ethnl_put_bitset32(skb, ETHTOOL_A_PRIVFLAGS_FLAGS, &data->priv_flags, &all_flags, data->n_priv_flags, data->priv_flag_names, compact); } static void privflags_cleanup_data(struct ethnl_reply_data *reply_data) { struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_data); kfree(data->priv_flag_names); } /* PRIVFLAGS_SET */ const struct nla_policy ethnl_privflags_set_policy[] = { [ETHTOOL_A_PRIVFLAGS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_PRIVFLAGS_FLAGS] = { .type = NLA_NESTED }, }; static int ethnl_set_privflags_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; if (!info->attrs[ETHTOOL_A_PRIVFLAGS_FLAGS]) return -EINVAL; if (!ops->get_priv_flags || !ops->set_priv_flags || !ops->get_sset_count || !ops->get_strings) return -EOPNOTSUPP; return 1; } static int ethnl_set_privflags(struct ethnl_req_info *req_info, struct genl_info *info) { const char (*names)[ETH_GSTRING_LEN] = NULL; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; unsigned int nflags; bool mod = false; bool compact; u32 flags; int ret; ret = ethnl_bitset_is_compact(tb[ETHTOOL_A_PRIVFLAGS_FLAGS], &compact); if (ret < 0) return ret; ret = ethnl_get_priv_flags_info(dev, &nflags, compact ? NULL : &names); if (ret < 0) return ret; flags = dev->ethtool_ops->get_priv_flags(dev); ret = ethnl_update_bitset32(&flags, nflags, tb[ETHTOOL_A_PRIVFLAGS_FLAGS], names, info->extack, &mod); if (ret < 0 || !mod) goto out_free; ret = dev->ethtool_ops->set_priv_flags(dev, flags); if (ret < 0) goto out_free; ret = 1; out_free: kfree(names); return ret; } const struct ethnl_request_ops ethnl_privflags_request_ops = { .request_cmd = ETHTOOL_MSG_PRIVFLAGS_GET, .reply_cmd = ETHTOOL_MSG_PRIVFLAGS_GET_REPLY, .hdr_attr = ETHTOOL_A_PRIVFLAGS_HEADER, .req_info_size = sizeof(struct privflags_req_info), .reply_data_size = sizeof(struct privflags_reply_data), .prepare_data = privflags_prepare_data, .reply_size = privflags_reply_size, .fill_reply = privflags_fill_reply, .cleanup_data = privflags_cleanup_data, .set_validate = ethnl_set_privflags_validate, .set = ethnl_set_privflags, .set_ntf_cmd = ETHTOOL_MSG_PRIVFLAGS_NTF, }; |
| 3 41 41 16 24 25 25 119 10 110 4 1 4 118 118 119 120 120 56 63 65 54 178 8 176 112 65 64 112 3 3 3 129 129 94 129 1 3 124 124 3 1 1 1 2 1 1 41 40 1 38 3 41 41 41 41 1 4 2 1 1 1 2 5 2 1 1 1 123 1 123 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Fd transport layer. Includes deprecated socket layer. * * Copyright (C) 2006 by Russ Cox <rsc@swtch.com> * Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net> * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/net.h> #include <linux/ipv6.h> #include <linux/kthread.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/un.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/file.h> #include <linux/parser.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include <linux/syscalls.h> /* killme */ #define P9_PORT 564 #define MAX_SOCK_BUF (1024*1024) #define MAXPOLLWADDR 2 static struct p9_trans_module p9_tcp_trans; static struct p9_trans_module p9_fd_trans; /** * struct p9_fd_opts - per-transport options * @rfd: file descriptor for reading (trans=fd) * @wfd: file descriptor for writing (trans=fd) * @port: port to connect to (trans=tcp) * @privport: port is privileged */ struct p9_fd_opts { int rfd; int wfd; u16 port; bool privport; }; /* * Option Parsing (code inspired by NFS code) * - a little lazy - parse all fd-transport options */ enum { /* Options that take integer arguments */ Opt_port, Opt_rfdno, Opt_wfdno, Opt_err, /* Options that take no arguments */ Opt_privport, }; static const match_table_t tokens = { {Opt_port, "port=%u"}, {Opt_rfdno, "rfdno=%u"}, {Opt_wfdno, "wfdno=%u"}, {Opt_privport, "privport"}, {Opt_err, NULL}, }; enum { Rworksched = 1, /* read work scheduled or running */ Rpending = 2, /* can read */ Wworksched = 4, /* write work scheduled or running */ Wpending = 8, /* can write */ }; struct p9_poll_wait { struct p9_conn *conn; wait_queue_entry_t wait; wait_queue_head_t *wait_addr; }; /** * struct p9_conn - fd mux connection state information * @mux_list: list link for mux to manage multiple connections (?) * @client: reference to client instance for this connection * @err: error state * @req_lock: lock protecting req_list and requests statuses * @req_list: accounting for requests which have been sent * @unsent_req_list: accounting for requests that haven't been sent * @rreq: read request * @wreq: write request * @tmp_buf: temporary buffer to read in header * @rc: temporary fcall for reading current frame * @wpos: write position for current frame * @wsize: amount of data to write for current frame * @wbuf: current write buffer * @poll_pending_link: pending links to be polled per conn * @poll_wait: array of wait_q's for various worker threads * @pt: poll state * @rq: current read work * @wq: current write work * @wsched: ???? * */ struct p9_conn { struct list_head mux_list; struct p9_client *client; int err; spinlock_t req_lock; struct list_head req_list; struct list_head unsent_req_list; struct p9_req_t *rreq; struct p9_req_t *wreq; char tmp_buf[P9_HDRSZ]; struct p9_fcall rc; int wpos; int wsize; char *wbuf; struct list_head poll_pending_link; struct p9_poll_wait poll_wait[MAXPOLLWADDR]; poll_table pt; struct work_struct rq; struct work_struct wq; unsigned long wsched; }; /** * struct p9_trans_fd - transport state * @rd: reference to file to read from * @wr: reference of file to write to * @conn: connection state reference * */ struct p9_trans_fd { struct file *rd; struct file *wr; struct p9_conn conn; }; static void p9_poll_workfn(struct work_struct *work); static DEFINE_SPINLOCK(p9_poll_lock); static LIST_HEAD(p9_poll_pending_list); static DECLARE_WORK(p9_poll_work, p9_poll_workfn); static unsigned int p9_ipport_resv_min = P9_DEF_MIN_RESVPORT; static unsigned int p9_ipport_resv_max = P9_DEF_MAX_RESVPORT; static void p9_mux_poll_stop(struct p9_conn *m) { unsigned long flags; int i; for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) { struct p9_poll_wait *pwait = &m->poll_wait[i]; if (pwait->wait_addr) { remove_wait_queue(pwait->wait_addr, &pwait->wait); pwait->wait_addr = NULL; } } spin_lock_irqsave(&p9_poll_lock, flags); list_del_init(&m->poll_pending_link); spin_unlock_irqrestore(&p9_poll_lock, flags); flush_work(&p9_poll_work); } /** * p9_conn_cancel - cancel all pending requests with error * @m: mux data * @err: error code * */ static void p9_conn_cancel(struct p9_conn *m, int err) { struct p9_req_t *req, *rtmp; LIST_HEAD(cancel_list); p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err); spin_lock(&m->req_lock); if (m->err) { spin_unlock(&m->req_lock); return; } m->err = err; list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { list_move(&req->req_list, &cancel_list); WRITE_ONCE(req->status, REQ_STATUS_ERROR); } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); WRITE_ONCE(req->status, REQ_STATUS_ERROR); } spin_unlock(&m->req_lock); list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); list_del(&req->req_list); if (!req->t_err) req->t_err = err; p9_client_cb(m->client, req, REQ_STATUS_ERROR); } } static __poll_t p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err) { __poll_t ret; struct p9_trans_fd *ts = NULL; if (client && client->status == Connected) ts = client->trans; if (!ts) { if (err) *err = -EREMOTEIO; return EPOLLERR; } ret = vfs_poll(ts->rd, pt); if (ts->rd != ts->wr) ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN); return ret; } /** * p9_fd_read- read from a fd * @client: client instance * @v: buffer to receive data into * @len: size of receive buffer * */ static int p9_fd_read(struct p9_client *client, void *v, int len) { int ret; struct p9_trans_fd *ts = NULL; loff_t pos; if (client && client->status != Disconnected) ts = client->trans; if (!ts) return -EREMOTEIO; if (!(ts->rd->f_flags & O_NONBLOCK)) p9_debug(P9_DEBUG_ERROR, "blocking read ...\n"); pos = ts->rd->f_pos; ret = kernel_read(ts->rd, v, len, &pos); if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN) client->status = Disconnected; return ret; } /** * p9_read_work - called when there is some data to be read from a transport * @work: container of work to be done * */ static void p9_read_work(struct work_struct *work) { __poll_t n; int err; struct p9_conn *m; m = container_of(work, struct p9_conn, rq); if (m->err < 0) return; p9_debug(P9_DEBUG_TRANS, "start mux %p pos %zd\n", m, m->rc.offset); if (!m->rc.sdata) { m->rc.sdata = m->tmp_buf; m->rc.offset = 0; m->rc.capacity = P9_HDRSZ; /* start by reading header */ } clear_bit(Rpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "read mux %p pos %zd size: %zd = %zd\n", m, m->rc.offset, m->rc.capacity, m->rc.capacity - m->rc.offset); err = p9_fd_read(m->client, m->rc.sdata + m->rc.offset, m->rc.capacity - m->rc.offset); p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err); if (err == -EAGAIN) goto end_clear; if (err <= 0) goto error; m->rc.offset += err; /* header read in */ if ((!m->rreq) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new header\n"); /* Header size */ m->rc.size = P9_HDRSZ; err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0); if (err) { p9_debug(P9_DEBUG_ERROR, "error parsing header: %d\n", err); goto error; } p9_debug(P9_DEBUG_TRANS, "mux %p pkt: size: %d bytes tag: %d\n", m, m->rc.size, m->rc.tag); m->rreq = p9_tag_lookup(m->client, m->rc.tag); if (!m->rreq || (m->rreq->status != REQ_STATUS_SENT)) { p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", m->rc.tag); err = -EIO; goto error; } if (m->rc.size > m->rreq->rc.capacity) { p9_debug(P9_DEBUG_ERROR, "requested packet size too big: %d for tag %d with capacity %zd\n", m->rc.size, m->rc.tag, m->rreq->rc.capacity); err = -EIO; goto error; } if (!m->rreq->rc.sdata) { p9_debug(P9_DEBUG_ERROR, "No recv fcall for tag %d (req %p), disconnecting!\n", m->rc.tag, m->rreq); p9_req_put(m->client, m->rreq); m->rreq = NULL; err = -EIO; goto error; } m->rc.sdata = m->rreq->rc.sdata; memcpy(m->rc.sdata, m->tmp_buf, m->rc.capacity); m->rc.capacity = m->rc.size; } /* packet is read in * not an else because some packets (like clunk) have no payload */ if ((m->rreq) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new packet\n"); m->rreq->rc.size = m->rc.offset; spin_lock(&m->req_lock); if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); } else if (m->rreq->status == REQ_STATUS_FLSHD) { /* Ignore replies associated with a cancelled request. */ p9_debug(P9_DEBUG_TRANS, "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->req_lock); p9_debug(P9_DEBUG_ERROR, "Request tag %d errored out while we were reading the reply\n", m->rc.tag); err = -EIO; goto error; } spin_unlock(&m->req_lock); m->rc.sdata = NULL; m->rc.offset = 0; m->rc.capacity = 0; p9_req_put(m->client, m->rreq); m->rreq = NULL; } end_clear: clear_bit(Rworksched, &m->wsched); if (!list_empty(&m->req_list)) { if (test_and_clear_bit(Rpending, &m->wsched)) n = EPOLLIN; else n = p9_fd_poll(m->client, NULL, NULL); if ((n & EPOLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } } return; error: p9_conn_cancel(m, err); clear_bit(Rworksched, &m->wsched); } /** * p9_fd_write - write to a socket * @client: client instance * @v: buffer to send data from * @len: size of send buffer * */ static int p9_fd_write(struct p9_client *client, void *v, int len) { ssize_t ret; struct p9_trans_fd *ts = NULL; if (client && client->status != Disconnected) ts = client->trans; if (!ts) return -EREMOTEIO; if (!(ts->wr->f_flags & O_NONBLOCK)) p9_debug(P9_DEBUG_ERROR, "blocking write ...\n"); ret = kernel_write(ts->wr, v, len, &ts->wr->f_pos); if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN) client->status = Disconnected; return ret; } /** * p9_write_work - called when a transport can send some data * @work: container for work to be done * */ static void p9_write_work(struct work_struct *work) { __poll_t n; int err; struct p9_conn *m; struct p9_req_t *req; m = container_of(work, struct p9_conn, wq); if (m->err < 0) { clear_bit(Wworksched, &m->wsched); return; } if (!m->wsize) { spin_lock(&m->req_lock); if (list_empty(&m->unsent_req_list)) { clear_bit(Wworksched, &m->wsched); spin_unlock(&m->req_lock); return; } req = list_entry(m->unsent_req_list.next, struct p9_req_t, req_list); WRITE_ONCE(req->status, REQ_STATUS_SENT); p9_debug(P9_DEBUG_TRANS, "move req %p\n", req); list_move_tail(&req->req_list, &m->req_list); m->wbuf = req->tc.sdata; m->wsize = req->tc.size; m->wpos = 0; p9_req_get(req); m->wreq = req; spin_unlock(&m->req_lock); } p9_debug(P9_DEBUG_TRANS, "mux %p pos %d size %d\n", m, m->wpos, m->wsize); clear_bit(Wpending, &m->wsched); err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos); p9_debug(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err); if (err == -EAGAIN) goto end_clear; if (err < 0) goto error; else if (err == 0) { err = -EREMOTEIO; goto error; } m->wpos += err; if (m->wpos == m->wsize) { m->wpos = m->wsize = 0; p9_req_put(m->client, m->wreq); m->wreq = NULL; } end_clear: clear_bit(Wworksched, &m->wsched); if (m->wsize || !list_empty(&m->unsent_req_list)) { if (test_and_clear_bit(Wpending, &m->wsched)) n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); if ((n & EPOLLOUT) && !test_and_set_bit(Wworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } } return; error: p9_conn_cancel(m, err); clear_bit(Wworksched, &m->wsched); } static int p9_pollwake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { struct p9_poll_wait *pwait = container_of(wait, struct p9_poll_wait, wait); struct p9_conn *m = pwait->conn; unsigned long flags; spin_lock_irqsave(&p9_poll_lock, flags); if (list_empty(&m->poll_pending_link)) list_add_tail(&m->poll_pending_link, &p9_poll_pending_list); spin_unlock_irqrestore(&p9_poll_lock, flags); schedule_work(&p9_poll_work); return 1; } /** * p9_pollwait - add poll task to the wait queue * @filp: file pointer being polled * @wait_address: wait_q to block on * @p: poll state * * called by files poll operation to add v9fs-poll task to files wait queue */ static void p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct p9_conn *m = container_of(p, struct p9_conn, pt); struct p9_poll_wait *pwait = NULL; int i; for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) { if (m->poll_wait[i].wait_addr == NULL) { pwait = &m->poll_wait[i]; break; } } if (!pwait) { p9_debug(P9_DEBUG_ERROR, "not enough wait_address slots\n"); return; } pwait->conn = m; pwait->wait_addr = wait_address; init_waitqueue_func_entry(&pwait->wait, p9_pollwake); add_wait_queue(wait_address, &pwait->wait); } /** * p9_conn_create - initialize the per-session mux data * @client: client instance * * Note: Creates the polling task if this is the first session. */ static void p9_conn_create(struct p9_client *client) { __poll_t n; struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize); INIT_LIST_HEAD(&m->mux_list); m->client = client; spin_lock_init(&m->req_lock); INIT_LIST_HEAD(&m->req_list); INIT_LIST_HEAD(&m->unsent_req_list); INIT_WORK(&m->rq, p9_read_work); INIT_WORK(&m->wq, p9_write_work); INIT_LIST_HEAD(&m->poll_pending_link); init_poll_funcptr(&m->pt, p9_pollwait); n = p9_fd_poll(client, &m->pt, NULL); if (n & EPOLLIN) { p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); set_bit(Rpending, &m->wsched); } if (n & EPOLLOUT) { p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); set_bit(Wpending, &m->wsched); } } /** * p9_poll_mux - polls a mux and schedules read or write works if necessary * @m: connection to poll * */ static void p9_poll_mux(struct p9_conn *m) { __poll_t n; int err = -ECONNRESET; if (m->err < 0) return; n = p9_fd_poll(m->client, NULL, &err); if (n & (EPOLLERR | EPOLLHUP | EPOLLNVAL)) { p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n); p9_conn_cancel(m, err); } if (n & EPOLLIN) { set_bit(Rpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); if (!test_and_set_bit(Rworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } } if (n & EPOLLOUT) { set_bit(Wpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); if ((m->wsize || !list_empty(&m->unsent_req_list)) && !test_and_set_bit(Wworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } } } /** * p9_fd_request - send 9P request * The function can sleep until the request is scheduled for sending. * The function can be interrupted. Return from the function is not * a guarantee that the request is sent successfully. * * @client: client instance * @req: request to be sent * */ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req) { __poll_t n; struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n", m, current, &req->tc, req->tc.id); spin_lock(&m->req_lock); if (m->err < 0) { spin_unlock(&m->req_lock); return m->err; } WRITE_ONCE(req->status, REQ_STATUS_UNSENT); list_add_tail(&req->req_list, &m->unsent_req_list); spin_unlock(&m->req_lock); if (test_and_clear_bit(Wpending, &m->wsched)) n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); if (n & EPOLLOUT && !test_and_set_bit(Wworksched, &m->wsched)) schedule_work(&m->wq); return 0; } static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; int ret = 1; p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&m->req_lock); if (req->status == REQ_STATUS_UNSENT) { list_del(&req->req_list); WRITE_ONCE(req->status, REQ_STATUS_FLSHD); p9_req_put(client, req); ret = 0; } spin_unlock(&m->req_lock); return ret; } static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&m->req_lock); /* Ignore cancelled request if message has been received * before lock. */ if (req->status == REQ_STATUS_RCVD) { spin_unlock(&m->req_lock); return 0; } /* we haven't received a response for oldreq, * remove it from the list. */ list_del(&req->req_list); WRITE_ONCE(req->status, REQ_STATUS_FLSHD); spin_unlock(&m->req_lock); p9_req_put(client, req); return 0; } static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt) { if (clnt->trans_mod == &p9_tcp_trans) { if (clnt->trans_opts.tcp.port != P9_PORT) seq_printf(m, ",port=%u", clnt->trans_opts.tcp.port); } else if (clnt->trans_mod == &p9_fd_trans) { if (clnt->trans_opts.fd.rfd != ~0) seq_printf(m, ",rfd=%u", clnt->trans_opts.fd.rfd); if (clnt->trans_opts.fd.wfd != ~0) seq_printf(m, ",wfd=%u", clnt->trans_opts.fd.wfd); } return 0; } /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount * @opts: fd transport-specific structure to parse options into * * Returns 0 upon success, -ERRNO upon failure */ static int parse_opts(char *params, struct p9_fd_opts *opts) { char *p; substring_t args[MAX_OPT_ARGS]; int option; char *options, *tmp_options; opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; opts->privport = false; if (!params) return 0; tmp_options = kstrdup(params, GFP_KERNEL); if (!tmp_options) { p9_debug(P9_DEBUG_ERROR, "failed to allocate copy of option string\n"); return -ENOMEM; } options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; int r; if (!*p) continue; token = match_token(p, tokens, args); if ((token != Opt_err) && (token != Opt_privport)) { r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); continue; } } switch (token) { case Opt_port: opts->port = option; break; case Opt_rfdno: opts->rfd = option; break; case Opt_wfdno: opts->wfd = option; break; case Opt_privport: opts->privport = true; break; default: continue; } } kfree(tmp_options); return 0; } static int p9_fd_open(struct p9_client *client, int rfd, int wfd) { struct p9_trans_fd *ts = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!ts) return -ENOMEM; ts->rd = fget(rfd); if (!ts->rd) goto out_free_ts; if (!(ts->rd->f_mode & FMODE_READ)) goto out_put_rd; /* Prevent workers from hanging on IO when fd is a pipe. * It's technically possible for userspace or concurrent mounts to * modify this flag concurrently, which will likely result in a * broken filesystem. However, just having bad flags here should * not crash the kernel or cause any other sort of bug, so mark this * particular data race as intentional so that tooling (like KCSAN) * can allow it and detect further problems. */ data_race(ts->rd->f_flags |= O_NONBLOCK); ts->wr = fget(wfd); if (!ts->wr) goto out_put_rd; if (!(ts->wr->f_mode & FMODE_WRITE)) goto out_put_wr; data_race(ts->wr->f_flags |= O_NONBLOCK); client->trans = ts; client->status = Connected; return 0; out_put_wr: fput(ts->wr); out_put_rd: fput(ts->rd); out_free_ts: kfree(ts); return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) { struct p9_trans_fd *p; struct file *file; p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!p) { sock_release(csocket); return -ENOMEM; } csocket->sk->sk_allocation = GFP_NOIO; csocket->sk->sk_use_task_frag = false; file = sock_alloc_file(csocket, 0, NULL); if (IS_ERR(file)) { pr_err("%s (%d): failed to map fd\n", __func__, task_pid_nr(current)); kfree(p); return PTR_ERR(file); } get_file(file); p->wr = p->rd = file; client->trans = p; client->status = Connected; p->rd->f_flags |= O_NONBLOCK; p9_conn_create(client); return 0; } /** * p9_conn_destroy - cancels all pending requests of mux * @m: mux to destroy * */ static void p9_conn_destroy(struct p9_conn *m) { p9_debug(P9_DEBUG_TRANS, "mux %p prev %p next %p\n", m, m->mux_list.prev, m->mux_list.next); p9_mux_poll_stop(m); cancel_work_sync(&m->rq); if (m->rreq) { p9_req_put(m->client, m->rreq); m->rreq = NULL; } cancel_work_sync(&m->wq); if (m->wreq) { p9_req_put(m->client, m->wreq); m->wreq = NULL; } p9_conn_cancel(m, -ECONNRESET); m->client = NULL; } /** * p9_fd_close - shutdown file descriptor transport * @client: client instance * */ static void p9_fd_close(struct p9_client *client) { struct p9_trans_fd *ts; if (!client) return; ts = client->trans; if (!ts) return; client->status = Disconnected; p9_conn_destroy(&ts->conn); if (ts->rd) fput(ts->rd); if (ts->wr) fput(ts->wr); kfree(ts); } /* * stolen from NFS - maybe should be made a generic function? */ static inline int valid_ipaddr4(const char *buf) { int rc, count, in[4]; rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]); if (rc != 4) return -EINVAL; for (count = 0; count < 4; count++) { if (in[count] > 255) return -EINVAL; } return 0; } static int p9_bind_privport(struct socket *sock) { struct sockaddr_in cl; int port, err = -EINVAL; memset(&cl, 0, sizeof(cl)); cl.sin_family = AF_INET; cl.sin_addr.s_addr = htonl(INADDR_ANY); for (port = p9_ipport_resv_max; port >= p9_ipport_resv_min; port--) { cl.sin_port = htons((ushort)port); err = kernel_bind(sock, (struct sockaddr *)&cl, sizeof(cl)); if (err != -EADDRINUSE) break; } return err; } static int p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) { int err; struct socket *csocket; struct sockaddr_in sin_server; struct p9_fd_opts opts; err = parse_opts(args, &opts); if (err < 0) return err; if (addr == NULL || valid_ipaddr4(addr) < 0) return -EINVAL; csocket = NULL; client->trans_opts.tcp.port = opts.port; client->trans_opts.tcp.privport = opts.privport; sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); err = __sock_create(current->nsproxy->net_ns, PF_INET, SOCK_STREAM, IPPROTO_TCP, &csocket, 1); if (err) { pr_err("%s (%d): problem creating socket\n", __func__, task_pid_nr(current)); return err; } if (opts.privport) { err = p9_bind_privport(csocket); if (err < 0) { pr_err("%s (%d): problem binding to privport\n", __func__, task_pid_nr(current)); sock_release(csocket); return err; } } err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sin_server, sizeof(struct sockaddr_in), 0); if (err < 0) { pr_err("%s (%d): problem connecting socket to %s\n", __func__, task_pid_nr(current), addr); sock_release(csocket); return err; } return p9_socket_open(client, csocket); } static int p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) { int err; struct socket *csocket; struct sockaddr_un sun_server; csocket = NULL; if (!addr || !strlen(addr)) return -EINVAL; if (strlen(addr) >= UNIX_PATH_MAX) { pr_err("%s (%d): address too long: %s\n", __func__, task_pid_nr(current), addr); return -ENAMETOOLONG; } sun_server.sun_family = PF_UNIX; strcpy(sun_server.sun_path, addr); err = __sock_create(current->nsproxy->net_ns, PF_UNIX, SOCK_STREAM, 0, &csocket, 1); if (err < 0) { pr_err("%s (%d): problem creating socket\n", __func__, task_pid_nr(current)); return err; } err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sun_server, sizeof(struct sockaddr_un) - 1, 0); if (err < 0) { pr_err("%s (%d): problem connecting socket: %s: %d\n", __func__, task_pid_nr(current), addr, err); sock_release(csocket); return err; } return p9_socket_open(client, csocket); } static int p9_fd_create(struct p9_client *client, const char *addr, char *args) { int err; struct p9_fd_opts opts; err = parse_opts(args, &opts); if (err < 0) return err; client->trans_opts.fd.rfd = opts.rfd; client->trans_opts.fd.wfd = opts.wfd; if (opts.rfd == ~0 || opts.wfd == ~0) { pr_err("Insufficient options for proto=fd\n"); return -ENOPROTOOPT; } err = p9_fd_open(client, opts.rfd, opts.wfd); if (err < 0) return err; p9_conn_create(client); return 0; } static struct p9_trans_module p9_tcp_trans = { .name = "tcp", .maxsize = MAX_SOCK_BUF, .pooled_rbuffers = false, .def = 0, .create = p9_fd_create_tcp, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("tcp"); static struct p9_trans_module p9_unix_trans = { .name = "unix", .maxsize = MAX_SOCK_BUF, .def = 0, .create = p9_fd_create_unix, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("unix"); static struct p9_trans_module p9_fd_trans = { .name = "fd", .maxsize = MAX_SOCK_BUF, .def = 0, .create = p9_fd_create, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("fd"); /** * p9_poll_workfn - poll worker thread * @work: work queue * * polls all v9fs transports for new events and queues the appropriate * work to the work queue * */ static void p9_poll_workfn(struct work_struct *work) { unsigned long flags; p9_debug(P9_DEBUG_TRANS, "start %p\n", current); spin_lock_irqsave(&p9_poll_lock, flags); while (!list_empty(&p9_poll_pending_list)) { struct p9_conn *conn = list_first_entry(&p9_poll_pending_list, struct p9_conn, poll_pending_link); list_del_init(&conn->poll_pending_link); spin_unlock_irqrestore(&p9_poll_lock, flags); p9_poll_mux(conn); spin_lock_irqsave(&p9_poll_lock, flags); } spin_unlock_irqrestore(&p9_poll_lock, flags); p9_debug(P9_DEBUG_TRANS, "finish\n"); } static int __init p9_trans_fd_init(void) { v9fs_register_trans(&p9_tcp_trans); v9fs_register_trans(&p9_unix_trans); v9fs_register_trans(&p9_fd_trans); return 0; } static void __exit p9_trans_fd_exit(void) { flush_work(&p9_poll_work); v9fs_unregister_trans(&p9_tcp_trans); v9fs_unregister_trans(&p9_unix_trans); v9fs_unregister_trans(&p9_fd_trans); } module_init(p9_trans_fd_init); module_exit(p9_trans_fd_exit); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_DESCRIPTION("Filedescriptor Transport for 9P"); MODULE_LICENSE("GPL"); |
| 2 1 2 1 2 1 2 1 2 2 2 10 10 8 9 9 9 9 3 1 1 1 1 4 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 | // SPDX-License-Identifier: GPL-2.0-only #include <net/xdp_sock_drv.h> #include "netlink.h" #include "common.h" struct channels_req_info { struct ethnl_req_info base; }; struct channels_reply_data { struct ethnl_reply_data base; struct ethtool_channels channels; }; #define CHANNELS_REPDATA(__reply_base) \ container_of(__reply_base, struct channels_reply_data, base) const struct nla_policy ethnl_channels_get_policy[] = { [ETHTOOL_A_CHANNELS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int channels_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_channels) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; dev->ethtool_ops->get_channels(dev, &data->channels); ethnl_ops_complete(dev); return 0; } static int channels_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_COMBINED_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_COUNT */ nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_COUNT */ nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_COUNT */ nla_total_size(sizeof(u32)); /* _CHANNELS_COMBINED_COUNT */ } static int channels_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); const struct ethtool_channels *channels = &data->channels; if ((channels->max_rx && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_MAX, channels->max_rx) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_COUNT, channels->rx_count))) || (channels->max_tx && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_MAX, channels->max_tx) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_COUNT, channels->tx_count))) || (channels->max_other && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_MAX, channels->max_other) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_COUNT, channels->other_count))) || (channels->max_combined && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_MAX, channels->max_combined) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_COUNT, channels->combined_count)))) return -EMSGSIZE; return 0; } /* CHANNELS_SET */ const struct nla_policy ethnl_channels_set_policy[] = { [ETHTOOL_A_CHANNELS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_CHANNELS_RX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_TX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .type = NLA_U32 }, }; static int ethnl_set_channels_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_channels && ops->set_channels ? 1 : -EOPNOTSUPP; } static int ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) { unsigned int from_channel, old_total, i; bool mod = false, mod_combined = false; struct net_device *dev = req_info->dev; struct ethtool_channels channels = {}; struct nlattr **tb = info->attrs; u32 err_attr, max_rxfh_in_use; u64 max_rxnfc_in_use; int ret; dev->ethtool_ops->get_channels(dev, &channels); old_total = channels.combined_count + max(channels.rx_count, channels.tx_count); ethnl_update_u32(&channels.rx_count, tb[ETHTOOL_A_CHANNELS_RX_COUNT], &mod); ethnl_update_u32(&channels.tx_count, tb[ETHTOOL_A_CHANNELS_TX_COUNT], &mod); ethnl_update_u32(&channels.other_count, tb[ETHTOOL_A_CHANNELS_OTHER_COUNT], &mod); ethnl_update_u32(&channels.combined_count, tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT], &mod_combined); mod |= mod_combined; if (!mod) return 0; /* ensure new channel counts are within limits */ if (channels.rx_count > channels.max_rx) err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (channels.tx_count > channels.max_tx) err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else if (channels.other_count > channels.max_other) err_attr = ETHTOOL_A_CHANNELS_OTHER_COUNT; else if (channels.combined_count > channels.max_combined) err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; else err_attr = 0; if (err_attr) { NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel count exceeds maximum"); return -EINVAL; } /* ensure there is at least one RX and one TX channel */ if (!channels.combined_count && !channels.rx_count) err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (!channels.combined_count && !channels.tx_count) err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else err_attr = 0; if (err_attr) { if (mod_combined) err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel counts would result in no RX or TX channel being configured"); return -EINVAL; } /* ensure the new Rx count fits within the configured Rx flow * indirection table/rxnfc settings */ if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) max_rxnfc_in_use = 0; max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use); return -EINVAL; } if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); return -EINVAL; } /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); for (i = from_channel; i < old_total; i++) if (xsk_get_pool_from_qid(dev, i)) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); return -EINVAL; } ret = dev->ethtool_ops->set_channels(dev, &channels); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_channels_request_ops = { .request_cmd = ETHTOOL_MSG_CHANNELS_GET, .reply_cmd = ETHTOOL_MSG_CHANNELS_GET_REPLY, .hdr_attr = ETHTOOL_A_CHANNELS_HEADER, .req_info_size = sizeof(struct channels_req_info), .reply_data_size = sizeof(struct channels_reply_data), .prepare_data = channels_prepare_data, .reply_size = channels_reply_size, .fill_reply = channels_fill_reply, .set_validate = ethnl_set_channels_validate, .set = ethnl_set_channels, .set_ntf_cmd = ETHTOOL_MSG_CHANNELS_NTF, }; |
| 2 19 1 1 1105 1103 19 6 9 7 7 7 2 2 2 2 12 1 1 10 1 1 1 1 1 1 1 1 1 1 10 1 1 1 1 1 1 1 2 1 1 2 1 1 1 3 1 1 3 1 2 2 2 9 1 1 1 1 1 1 1 2 3 3 9 9 9 1 9 1 1 6 2 4 2 4 2 1 1 2 1 1 8 1 2 2 1 1 1 1 24 21 1 1 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Copyright Jonathan Naylor G4KLX (g4klx@g4klx.demon.co.uk) * Copyright Alan Cox GW4PTS (alan@lxorguk.ukuu.org.uk) * Copyright Darryl Miles G7LED (dlm@g7led.demon.co.uk) */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/stat.h> #include <net/ax25.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <net/net_namespace.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/fcntl.h> #include <linux/termios.h> /* For TIOCINQ/OUTQ */ #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <net/netrom.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/ip.h> #include <net/tcp_states.h> #include <net/arp.h> #include <linux/init.h> static int nr_ndevs = 4; int sysctl_netrom_default_path_quality = NR_DEFAULT_QUAL; int sysctl_netrom_obsolescence_count_initialiser = NR_DEFAULT_OBS; int sysctl_netrom_network_ttl_initialiser = NR_DEFAULT_TTL; int sysctl_netrom_transport_timeout = NR_DEFAULT_T1; int sysctl_netrom_transport_maximum_tries = NR_DEFAULT_N2; int sysctl_netrom_transport_acknowledge_delay = NR_DEFAULT_T2; int sysctl_netrom_transport_busy_delay = NR_DEFAULT_T4; int sysctl_netrom_transport_requested_window_size = NR_DEFAULT_WINDOW; int sysctl_netrom_transport_no_activity_timeout = NR_DEFAULT_IDLE; int sysctl_netrom_routing_control = NR_DEFAULT_ROUTING; int sysctl_netrom_link_fails_count = NR_DEFAULT_FAILS; int sysctl_netrom_reset_circuit = NR_DEFAULT_RESET; static unsigned short circuit = 0x101; static HLIST_HEAD(nr_list); static DEFINE_SPINLOCK(nr_list_lock); static const struct proto_ops nr_proto_ops; /* * NETROM network devices are virtual network devices encapsulating NETROM * frames into AX.25 which will be sent through an AX.25 device, so form a * special "super class" of normal net devices; split their locks off into a * separate class since they always nest. */ static struct lock_class_key nr_netdev_xmit_lock_key; static struct lock_class_key nr_netdev_addr_lock_key; static void nr_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, void *_unused) { lockdep_set_class(&txq->_xmit_lock, &nr_netdev_xmit_lock_key); } static void nr_set_lockdep_key(struct net_device *dev) { lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL); } /* * Socket removal during an interrupt is now safe. */ static void nr_remove_socket(struct sock *sk) { spin_lock_bh(&nr_list_lock); sk_del_node_init(sk); spin_unlock_bh(&nr_list_lock); } /* * Kill all bound sockets on a dropped device. */ static void nr_kill_by_device(struct net_device *dev) { struct sock *s; spin_lock_bh(&nr_list_lock); sk_for_each(s, &nr_list) if (nr_sk(s)->device == dev) nr_disconnect(s, ENETUNREACH); spin_unlock_bh(&nr_list_lock); } /* * Handle device status changes. */ static int nr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; if (event != NETDEV_DOWN) return NOTIFY_DONE; nr_kill_by_device(dev); nr_rt_device_down(dev); return NOTIFY_DONE; } /* * Add a socket to the bound sockets list. */ static void nr_insert_socket(struct sock *sk) { spin_lock_bh(&nr_list_lock); sk_add_node(sk, &nr_list); spin_unlock_bh(&nr_list_lock); } /* * Find a socket that wants to accept the Connect Request we just * received. */ static struct sock *nr_find_listener(ax25_address *addr) { struct sock *s; spin_lock_bh(&nr_list_lock); sk_for_each(s, &nr_list) if (!ax25cmp(&nr_sk(s)->source_addr, addr) && s->sk_state == TCP_LISTEN) { sock_hold(s); goto found; } s = NULL; found: spin_unlock_bh(&nr_list_lock); return s; } /* * Find a connected NET/ROM socket given my circuit IDs. */ static struct sock *nr_find_socket(unsigned char index, unsigned char id) { struct sock *s; spin_lock_bh(&nr_list_lock); sk_for_each(s, &nr_list) { struct nr_sock *nr = nr_sk(s); if (nr->my_index == index && nr->my_id == id) { sock_hold(s); goto found; } } s = NULL; found: spin_unlock_bh(&nr_list_lock); return s; } /* * Find a connected NET/ROM socket given their circuit IDs. */ static struct sock *nr_find_peer(unsigned char index, unsigned char id, ax25_address *dest) { struct sock *s; spin_lock_bh(&nr_list_lock); sk_for_each(s, &nr_list) { struct nr_sock *nr = nr_sk(s); if (nr->your_index == index && nr->your_id == id && !ax25cmp(&nr->dest_addr, dest)) { sock_hold(s); goto found; } } s = NULL; found: spin_unlock_bh(&nr_list_lock); return s; } /* * Find next free circuit ID. */ static unsigned short nr_find_next_circuit(void) { unsigned short id = circuit; unsigned char i, j; struct sock *sk; for (;;) { i = id / 256; j = id % 256; if (i != 0 && j != 0) { if ((sk=nr_find_socket(i, j)) == NULL) break; sock_put(sk); } id++; } return id; } /* * Deferred destroy. */ void nr_destroy_socket(struct sock *); /* * Handler for deferred kills. */ static void nr_destroy_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); bh_lock_sock(sk); sock_hold(sk); nr_destroy_socket(sk); bh_unlock_sock(sk); sock_put(sk); } /* * This is called from user mode and the timers. Thus it protects itself * against interrupt users but doesn't worry about being called during * work. Once it is removed from the queue no interrupt or bottom half * will touch it and we are (fairly 8-) ) safe. */ void nr_destroy_socket(struct sock *sk) { struct sk_buff *skb; nr_remove_socket(sk); nr_stop_heartbeat(sk); nr_stop_t1timer(sk); nr_stop_t2timer(sk); nr_stop_t4timer(sk); nr_stop_idletimer(sk); nr_clear_queues(sk); /* Flush the queues */ while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { if (skb->sk != sk) { /* A pending connection */ /* Queue the unaccepted socket for death */ sock_set_flag(skb->sk, SOCK_DEAD); nr_start_heartbeat(skb->sk); nr_sk(skb->sk)->state = NR_STATE_0; } kfree_skb(skb); } if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ sk->sk_timer.function = nr_destroy_timer; sk->sk_timer.expires = jiffies + 2 * HZ; add_timer(&sk->sk_timer); } else sock_put(sk); } /* * Handling for system calls applied via the various interfaces to a * NET/ROM socket object. */ static int nr_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); unsigned int opt; if (level != SOL_NETROM) return -ENOPROTOOPT; if (optlen < sizeof(unsigned int)) return -EINVAL; if (copy_from_sockptr(&opt, optval, sizeof(opt))) return -EFAULT; switch (optname) { case NETROM_T1: if (opt < 1 || opt > UINT_MAX / HZ) return -EINVAL; nr->t1 = opt * HZ; return 0; case NETROM_T2: if (opt < 1 || opt > UINT_MAX / HZ) return -EINVAL; nr->t2 = opt * HZ; return 0; case NETROM_N2: if (opt < 1 || opt > 31) return -EINVAL; nr->n2 = opt; return 0; case NETROM_T4: if (opt < 1 || opt > UINT_MAX / HZ) return -EINVAL; nr->t4 = opt * HZ; return 0; case NETROM_IDLE: if (opt > UINT_MAX / (60 * HZ)) return -EINVAL; nr->idle = opt * 60 * HZ; return 0; default: return -ENOPROTOOPT; } } static int nr_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); int val = 0; int len; if (level != SOL_NETROM) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case NETROM_T1: val = nr->t1 / HZ; break; case NETROM_T2: val = nr->t2 / HZ; break; case NETROM_N2: val = nr->n2; break; case NETROM_T4: val = nr->t4 / HZ; break; case NETROM_IDLE: val = nr->idle / (60 * HZ); break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, len, sizeof(int)); if (put_user(len, optlen)) return -EFAULT; return copy_to_user(optval, &val, len) ? -EFAULT : 0; } static int nr_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; lock_sock(sk); if (sock->state != SS_UNCONNECTED) { release_sock(sk); return -EINVAL; } if (sk->sk_state != TCP_LISTEN) { memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; release_sock(sk); return 0; } release_sock(sk); return -EOPNOTSUPP; } static struct proto nr_proto = { .name = "NETROM", .owner = THIS_MODULE, .obj_size = sizeof(struct nr_sock), }; static int nr_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct nr_sock *nr; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (sock->type != SOCK_SEQPACKET || protocol != 0) return -ESOCKTNOSUPPORT; sk = sk_alloc(net, PF_NETROM, GFP_ATOMIC, &nr_proto, kern); if (sk == NULL) return -ENOMEM; nr = nr_sk(sk); sock_init_data(sock, sk); sock->ops = &nr_proto_ops; sk->sk_protocol = protocol; skb_queue_head_init(&nr->ack_queue); skb_queue_head_init(&nr->reseq_queue); skb_queue_head_init(&nr->frag_queue); nr_init_timers(sk); nr->t1 = msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout)); nr->t2 = msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay)); nr->n2 = msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries)); nr->t4 = msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay)); nr->idle = msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout)); nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size); nr->bpqext = 1; nr->state = NR_STATE_0; return 0; } static struct sock *nr_make_new(struct sock *osk) { struct sock *sk; struct nr_sock *nr, *onr; if (osk->sk_type != SOCK_SEQPACKET) return NULL; sk = sk_alloc(sock_net(osk), PF_NETROM, GFP_ATOMIC, osk->sk_prot, 0); if (sk == NULL) return NULL; nr = nr_sk(sk); sock_init_data(NULL, sk); sk->sk_type = osk->sk_type; sk->sk_priority = READ_ONCE(osk->sk_priority); sk->sk_protocol = osk->sk_protocol; sk->sk_rcvbuf = osk->sk_rcvbuf; sk->sk_sndbuf = osk->sk_sndbuf; sk->sk_state = TCP_ESTABLISHED; sock_copy_flags(sk, osk); skb_queue_head_init(&nr->ack_queue); skb_queue_head_init(&nr->reseq_queue); skb_queue_head_init(&nr->frag_queue); nr_init_timers(sk); onr = nr_sk(osk); nr->t1 = onr->t1; nr->t2 = onr->t2; nr->n2 = onr->n2; nr->t4 = onr->t4; nr->idle = onr->idle; nr->window = onr->window; nr->device = onr->device; nr->bpqext = onr->bpqext; return sk; } static int nr_release(struct socket *sock) { struct sock *sk = sock->sk; struct nr_sock *nr; if (sk == NULL) return 0; sock_hold(sk); sock_orphan(sk); lock_sock(sk); nr = nr_sk(sk); switch (nr->state) { case NR_STATE_0: case NR_STATE_1: case NR_STATE_2: nr_disconnect(sk, 0); nr_destroy_socket(sk); break; case NR_STATE_3: nr_clear_queues(sk); nr->n2count = 0; nr_write_internal(sk, NR_DISCREQ); nr_start_t1timer(sk); nr_stop_t2timer(sk); nr_stop_t4timer(sk); nr_stop_idletimer(sk); nr->state = NR_STATE_2; sk->sk_state = TCP_CLOSE; sk->sk_shutdown |= SEND_SHUTDOWN; sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DESTROY); break; default: break; } sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); struct full_sockaddr_ax25 *addr = (struct full_sockaddr_ax25 *)uaddr; struct net_device *dev; ax25_uid_assoc *user; ax25_address *source; lock_sock(sk); if (!sock_flag(sk, SOCK_ZAPPED)) { release_sock(sk); return -EINVAL; } if (addr_len < sizeof(struct sockaddr_ax25) || addr_len > sizeof(struct full_sockaddr_ax25)) { release_sock(sk); return -EINVAL; } if (addr_len < (addr->fsa_ax25.sax25_ndigis * sizeof(ax25_address) + sizeof(struct sockaddr_ax25))) { release_sock(sk); return -EINVAL; } if (addr->fsa_ax25.sax25_family != AF_NETROM) { release_sock(sk); return -EINVAL; } if ((dev = nr_dev_get(&addr->fsa_ax25.sax25_call)) == NULL) { release_sock(sk); return -EADDRNOTAVAIL; } /* * Only the super user can set an arbitrary user callsign. */ if (addr->fsa_ax25.sax25_ndigis == 1) { if (!capable(CAP_NET_BIND_SERVICE)) { dev_put(dev); release_sock(sk); return -EPERM; } nr->user_addr = addr->fsa_digipeater[0]; nr->source_addr = addr->fsa_ax25.sax25_call; } else { source = &addr->fsa_ax25.sax25_call; user = ax25_findbyuid(current_euid()); if (user) { nr->user_addr = user->call; ax25_uid_put(user); } else { if (ax25_uid_policy && !capable(CAP_NET_BIND_SERVICE)) { release_sock(sk); dev_put(dev); return -EPERM; } nr->user_addr = *source; } nr->source_addr = *source; } nr->device = dev; nr_insert_socket(sk); sock_reset_flag(sk, SOCK_ZAPPED); dev_put(dev); release_sock(sk); return 0; } static int nr_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); struct sockaddr_ax25 *addr = (struct sockaddr_ax25 *)uaddr; const ax25_address *source = NULL; ax25_uid_assoc *user; struct net_device *dev; int err = 0; lock_sock(sk); if (sk->sk_state == TCP_ESTABLISHED && sock->state == SS_CONNECTING) { sock->state = SS_CONNECTED; goto out_release; /* Connect completed during a ERESTARTSYS event */ } if (sk->sk_state == TCP_CLOSE && sock->state == SS_CONNECTING) { sock->state = SS_UNCONNECTED; err = -ECONNREFUSED; goto out_release; } if (sk->sk_state == TCP_ESTABLISHED) { err = -EISCONN; /* No reconnect on a seqpacket socket */ goto out_release; } if (sock->state == SS_CONNECTING) { err = -EALREADY; goto out_release; } sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; if (addr_len != sizeof(struct sockaddr_ax25) && addr_len != sizeof(struct full_sockaddr_ax25)) { err = -EINVAL; goto out_release; } if (addr->sax25_family != AF_NETROM) { err = -EINVAL; goto out_release; } if (sock_flag(sk, SOCK_ZAPPED)) { /* Must bind first - autobinding in this may or may not work */ sock_reset_flag(sk, SOCK_ZAPPED); if ((dev = nr_dev_first()) == NULL) { err = -ENETUNREACH; goto out_release; } source = (const ax25_address *)dev->dev_addr; user = ax25_findbyuid(current_euid()); if (user) { nr->user_addr = user->call; ax25_uid_put(user); } else { if (ax25_uid_policy && !capable(CAP_NET_ADMIN)) { dev_put(dev); err = -EPERM; goto out_release; } nr->user_addr = *source; } nr->source_addr = *source; nr->device = dev; dev_put(dev); nr_insert_socket(sk); /* Finish the bind */ } nr->dest_addr = addr->sax25_call; release_sock(sk); circuit = nr_find_next_circuit(); lock_sock(sk); nr->my_index = circuit / 256; nr->my_id = circuit % 256; circuit++; /* Move to connecting socket, start sending Connect Requests */ sock->state = SS_CONNECTING; sk->sk_state = TCP_SYN_SENT; nr_establish_data_link(sk); nr->state = NR_STATE_1; nr_start_heartbeat(sk); /* Now the loop */ if (sk->sk_state != TCP_ESTABLISHED && (flags & O_NONBLOCK)) { err = -EINPROGRESS; goto out_release; } /* * A Connect Ack with Choke or timeout or failed routing will go to * closed. */ if (sk->sk_state == TCP_SYN_SENT) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_state != TCP_SYN_SENT) break; if (!signal_pending(current)) { release_sock(sk); schedule(); lock_sock(sk); continue; } err = -ERESTARTSYS; break; } finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; } if (sk->sk_state != TCP_ESTABLISHED) { sock->state = SS_UNCONNECTED; err = sock_error(sk); /* Always set at this point */ goto out_release; } sock->state = SS_CONNECTED; out_release: release_sock(sk); return err; } static int nr_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sk_buff *skb; struct sock *newsk; DEFINE_WAIT(wait); struct sock *sk; int err = 0; if ((sk = sock->sk) == NULL) return -EINVAL; lock_sock(sk); if (sk->sk_type != SOCK_SEQPACKET) { err = -EOPNOTSUPP; goto out_release; } if (sk->sk_state != TCP_LISTEN) { err = -EINVAL; goto out_release; } /* * The write queue this time is holding sockets ready to use * hooked into the SABM we saved */ for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); skb = skb_dequeue(&sk->sk_receive_queue); if (skb) break; if (arg->flags & O_NONBLOCK) { err = -EWOULDBLOCK; break; } if (!signal_pending(current)) { release_sock(sk); schedule(); lock_sock(sk); continue; } err = -ERESTARTSYS; break; } finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; newsk = skb->sk; sock_graft(newsk, newsock); /* Now attach up the new socket */ kfree_skb(skb); sk_acceptq_removed(sk); out_release: release_sock(sk); return err; } static int nr_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct full_sockaddr_ax25 *sax = (struct full_sockaddr_ax25 *)uaddr; struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); int uaddr_len; memset(&sax->fsa_ax25, 0, sizeof(struct sockaddr_ax25)); lock_sock(sk); if (peer != 0) { if (sk->sk_state != TCP_ESTABLISHED) { release_sock(sk); return -ENOTCONN; } sax->fsa_ax25.sax25_family = AF_NETROM; sax->fsa_ax25.sax25_ndigis = 1; sax->fsa_ax25.sax25_call = nr->user_addr; memset(sax->fsa_digipeater, 0, sizeof(sax->fsa_digipeater)); sax->fsa_digipeater[0] = nr->dest_addr; uaddr_len = sizeof(struct full_sockaddr_ax25); } else { sax->fsa_ax25.sax25_family = AF_NETROM; sax->fsa_ax25.sax25_ndigis = 0; sax->fsa_ax25.sax25_call = nr->source_addr; uaddr_len = sizeof(struct sockaddr_ax25); } release_sock(sk); return uaddr_len; } int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) { struct sock *sk; struct sock *make; struct nr_sock *nr_make; ax25_address *src, *dest, *user; unsigned short circuit_index, circuit_id; unsigned short peer_circuit_index, peer_circuit_id; unsigned short frametype, flags, window, timeout; int ret; skb_orphan(skb); /* * skb->data points to the netrom frame start */ src = (ax25_address *)(skb->data + 0); dest = (ax25_address *)(skb->data + 7); circuit_index = skb->data[15]; circuit_id = skb->data[16]; peer_circuit_index = skb->data[17]; peer_circuit_id = skb->data[18]; frametype = skb->data[19] & 0x0F; flags = skb->data[19] & 0xF0; /* * Check for an incoming IP over NET/ROM frame. */ if (frametype == NR_PROTOEXT && circuit_index == NR_PROTO_IP && circuit_id == NR_PROTO_IP) { skb_pull(skb, NR_NETWORK_LEN + NR_TRANSPORT_LEN); skb_reset_transport_header(skb); return nr_rx_ip(skb, dev); } /* * Find an existing socket connection, based on circuit ID, if it's * a Connect Request base it on their circuit ID. * * Circuit ID 0/0 is not valid but it could still be a "reset" for a * circuit that no longer exists at the other end ... */ sk = NULL; if (circuit_index == 0 && circuit_id == 0) { if (frametype == NR_CONNACK && flags == NR_CHOKE_FLAG) sk = nr_find_peer(peer_circuit_index, peer_circuit_id, src); } else { if (frametype == NR_CONNREQ) sk = nr_find_peer(circuit_index, circuit_id, src); else sk = nr_find_socket(circuit_index, circuit_id); } if (sk != NULL) { bh_lock_sock(sk); skb_reset_transport_header(skb); if (frametype == NR_CONNACK && skb->len == 22) nr_sk(sk)->bpqext = 1; else nr_sk(sk)->bpqext = 0; ret = nr_process_rx_frame(sk, skb); bh_unlock_sock(sk); sock_put(sk); return ret; } /* * Now it should be a CONNREQ. */ if (frametype != NR_CONNREQ) { /* * Here it would be nice to be able to send a reset but * NET/ROM doesn't have one. We've tried to extend the protocol * by sending NR_CONNACK | NR_CHOKE_FLAGS replies but that * apparently kills BPQ boxes... :-( * So now we try to follow the established behaviour of * G8PZT's Xrouter which is sending packets with command type 7 * as an extension of the protocol. */ if (READ_ONCE(sysctl_netrom_reset_circuit) && (frametype != NR_RESET || flags != 0)) nr_transmit_reset(skb, 1); return 0; } sk = nr_find_listener(dest); user = (ax25_address *)(skb->data + 21); if (sk == NULL || sk_acceptq_is_full(sk) || (make = nr_make_new(sk)) == NULL) { nr_transmit_refusal(skb, 0); if (sk) sock_put(sk); return 0; } bh_lock_sock(sk); window = skb->data[20]; sock_hold(make); skb->sk = make; skb->destructor = sock_efree; make->sk_state = TCP_ESTABLISHED; /* Fill in his circuit details */ nr_make = nr_sk(make); nr_make->source_addr = *dest; nr_make->dest_addr = *src; nr_make->user_addr = *user; nr_make->your_index = circuit_index; nr_make->your_id = circuit_id; bh_unlock_sock(sk); circuit = nr_find_next_circuit(); bh_lock_sock(sk); nr_make->my_index = circuit / 256; nr_make->my_id = circuit % 256; circuit++; /* Window negotiation */ if (window < nr_make->window) nr_make->window = window; /* L4 timeout negotiation */ if (skb->len == 37) { timeout = skb->data[36] * 256 + skb->data[35]; if (timeout * HZ < nr_make->t1) nr_make->t1 = timeout * HZ; nr_make->bpqext = 1; } else { nr_make->bpqext = 0; } nr_write_internal(make, NR_CONNACK); nr_make->condition = 0x00; nr_make->vs = 0; nr_make->va = 0; nr_make->vr = 0; nr_make->vl = 0; nr_make->state = NR_STATE_3; sk_acceptq_added(sk); skb_queue_head(&sk->sk_receive_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); bh_unlock_sock(sk); sock_put(sk); nr_insert_socket(make); nr_start_heartbeat(make); nr_start_idletimer(make); return 1; } static int nr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ax25 *, usax, msg->msg_name); int err; struct sockaddr_ax25 sax; struct sk_buff *skb; unsigned char *asmptr; int size; if (msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_CMSG_COMPAT)) return -EINVAL; lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) { err = -EADDRNOTAVAIL; goto out; } if (sk->sk_shutdown & SEND_SHUTDOWN) { send_sig(SIGPIPE, current, 0); err = -EPIPE; goto out; } if (nr->device == NULL) { err = -ENETUNREACH; goto out; } if (usax) { if (msg->msg_namelen < sizeof(sax)) { err = -EINVAL; goto out; } sax = *usax; if (ax25cmp(&nr->dest_addr, &sax.sax25_call) != 0) { err = -EISCONN; goto out; } if (sax.sax25_family != AF_NETROM) { err = -EINVAL; goto out; } } else { if (sk->sk_state != TCP_ESTABLISHED) { err = -ENOTCONN; goto out; } sax.sax25_family = AF_NETROM; sax.sax25_call = nr->dest_addr; } /* Build a packet - the conventional user limit is 236 bytes. We can do ludicrously large NetROM frames but must not overflow */ if (len > 65536) { err = -EMSGSIZE; goto out; } size = len + NR_NETWORK_LEN + NR_TRANSPORT_LEN; if ((skb = sock_alloc_send_skb(sk, size, msg->msg_flags & MSG_DONTWAIT, &err)) == NULL) goto out; skb_reserve(skb, size - len); skb_reset_transport_header(skb); /* * Push down the NET/ROM header */ asmptr = skb_push(skb, NR_TRANSPORT_LEN); /* Build a NET/ROM Transport header */ *asmptr++ = nr->your_index; *asmptr++ = nr->your_id; *asmptr++ = 0; /* To be filled in later */ *asmptr++ = 0; /* Ditto */ *asmptr++ = NR_INFO; /* * Put the data on the end */ skb_put(skb, len); /* User data follows immediately after the NET/ROM transport header */ if (memcpy_from_msg(skb_transport_header(skb), msg, len)) { kfree_skb(skb); err = -EFAULT; goto out; } if (sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); err = -ENOTCONN; goto out; } nr_output(sk, skb); /* Shove it onto the queue */ err = len; out: release_sock(sk); return err; } static int nr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ax25 *, sax, msg->msg_name); size_t copied; struct sk_buff *skb; int er; /* * This works for seqpacket too. The receiver has ordered the queue for * us! We do one quick check first though */ lock_sock(sk); if (sk->sk_state != TCP_ESTABLISHED) { release_sock(sk); return -ENOTCONN; } /* Now we can treat all alike */ skb = skb_recv_datagram(sk, flags, &er); if (!skb) { release_sock(sk); return er; } skb_reset_transport_header(skb); copied = skb->len; if (copied > size) { copied = size; msg->msg_flags |= MSG_TRUNC; } er = skb_copy_datagram_msg(skb, 0, msg, copied); if (er < 0) { skb_free_datagram(sk, skb); release_sock(sk); return er; } if (sax != NULL) { memset(sax, 0, sizeof(*sax)); sax->sax25_family = AF_NETROM; skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call, AX25_ADDR_LEN); msg->msg_namelen = sizeof(*sax); } skb_free_datagram(sk, skb); release_sock(sk); return copied; } static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; void __user *argp = (void __user *)arg; switch (cmd) { case TIOCOUTQ: { long amount; lock_sock(sk); amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; release_sock(sk); return put_user(amount, (int __user *)argp); } case TIOCINQ: { struct sk_buff *skb; long amount = 0L; lock_sock(sk); /* These two are safe on a single CPU system as only user tasks fiddle here */ if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) amount = skb->len; release_sock(sk); return put_user(amount, (int __user *)argp); } case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFMETRIC: case SIOCSIFMETRIC: return -EINVAL; case SIOCADDRT: case SIOCDELRT: case SIOCNRDECOBS: if (!capable(CAP_NET_ADMIN)) return -EPERM; return nr_rt_ioctl(cmd, argp); default: return -ENOIOCTLCMD; } return 0; } #ifdef CONFIG_PROC_FS static void *nr_info_start(struct seq_file *seq, loff_t *pos) __acquires(&nr_list_lock) { spin_lock_bh(&nr_list_lock); return seq_hlist_start_head(&nr_list, *pos); } static void *nr_info_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_hlist_next(v, &nr_list, pos); } static void nr_info_stop(struct seq_file *seq, void *v) __releases(&nr_list_lock) { spin_unlock_bh(&nr_list_lock); } static int nr_info_show(struct seq_file *seq, void *v) { struct sock *s = sk_entry(v); struct net_device *dev; struct nr_sock *nr; const char *devname; char buf[11]; if (v == SEQ_START_TOKEN) seq_puts(seq, "user_addr dest_node src_node dev my your st vs vr va t1 t2 t4 idle n2 wnd Snd-Q Rcv-Q inode\n"); else { bh_lock_sock(s); nr = nr_sk(s); if ((dev = nr->device) == NULL) devname = "???"; else devname = dev->name; seq_printf(seq, "%-9s ", ax2asc(buf, &nr->user_addr)); seq_printf(seq, "%-9s ", ax2asc(buf, &nr->dest_addr)); seq_printf(seq, "%-9s %-3s %02X/%02X %02X/%02X %2d %3d %3d %3d %3lu/%03lu %2lu/%02lu %3lu/%03lu %3lu/%03lu %2d/%02d %3d %5d %5d %ld\n", ax2asc(buf, &nr->source_addr), devname, nr->my_index, nr->my_id, nr->your_index, nr->your_id, nr->state, nr->vs, nr->vr, nr->va, ax25_display_timer(&nr->t1timer) / HZ, nr->t1 / HZ, ax25_display_timer(&nr->t2timer) / HZ, nr->t2 / HZ, ax25_display_timer(&nr->t4timer) / HZ, nr->t4 / HZ, ax25_display_timer(&nr->idletimer) / (60 * HZ), nr->idle / (60 * HZ), nr->n2count, nr->n2, nr->window, sk_wmem_alloc_get(s), sk_rmem_alloc_get(s), s->sk_socket ? SOCK_INODE(s->sk_socket)->i_ino : 0L); bh_unlock_sock(s); } return 0; } static const struct seq_operations nr_info_seqops = { .start = nr_info_start, .next = nr_info_next, .stop = nr_info_stop, .show = nr_info_show, }; #endif /* CONFIG_PROC_FS */ static const struct net_proto_family nr_family_ops = { .family = PF_NETROM, .create = nr_create, .owner = THIS_MODULE, }; static const struct proto_ops nr_proto_ops = { .family = PF_NETROM, .owner = THIS_MODULE, .release = nr_release, .bind = nr_bind, .connect = nr_connect, .socketpair = sock_no_socketpair, .accept = nr_accept, .getname = nr_getname, .poll = datagram_poll, .ioctl = nr_ioctl, .gettstamp = sock_gettstamp, .listen = nr_listen, .shutdown = sock_no_shutdown, .setsockopt = nr_setsockopt, .getsockopt = nr_getsockopt, .sendmsg = nr_sendmsg, .recvmsg = nr_recvmsg, .mmap = sock_no_mmap, }; static struct notifier_block nr_dev_notifier = { .notifier_call = nr_device_event, }; static struct net_device **dev_nr; static struct ax25_protocol nr_pid = { .pid = AX25_P_NETROM, .func = nr_route_frame }; static struct ax25_linkfail nr_linkfail_notifier = { .func = nr_link_failed, }; static int __init nr_proto_init(void) { int i; int rc = proto_register(&nr_proto, 0); if (rc) return rc; if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) { pr_err("NET/ROM: %s - nr_ndevs parameter too large\n", __func__); rc = -EINVAL; goto unregister_proto; } dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL); if (!dev_nr) { pr_err("NET/ROM: %s - unable to allocate device array\n", __func__); rc = -ENOMEM; goto unregister_proto; } for (i = 0; i < nr_ndevs; i++) { char name[IFNAMSIZ]; struct net_device *dev; sprintf(name, "nr%d", i); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup); if (!dev) { rc = -ENOMEM; goto fail; } dev->base_addr = i; rc = register_netdev(dev); if (rc) { free_netdev(dev); goto fail; } nr_set_lockdep_key(dev); dev_nr[i] = dev; } rc = sock_register(&nr_family_ops); if (rc) goto fail; rc = register_netdevice_notifier(&nr_dev_notifier); if (rc) goto out_sock; ax25_register_pid(&nr_pid); ax25_linkfail_register(&nr_linkfail_notifier); #ifdef CONFIG_SYSCTL rc = nr_register_sysctl(); if (rc) goto out_sysctl; #endif nr_loopback_init(); rc = -ENOMEM; if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops)) goto proc_remove1; if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops)) goto proc_remove2; if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops)) goto proc_remove3; return 0; proc_remove3: remove_proc_entry("nr_neigh", init_net.proc_net); proc_remove2: remove_proc_entry("nr", init_net.proc_net); proc_remove1: nr_loopback_clear(); nr_rt_free(); #ifdef CONFIG_SYSCTL nr_unregister_sysctl(); out_sysctl: #endif ax25_linkfail_release(&nr_linkfail_notifier); ax25_protocol_release(AX25_P_NETROM); unregister_netdevice_notifier(&nr_dev_notifier); out_sock: sock_unregister(PF_NETROM); fail: while (--i >= 0) { unregister_netdev(dev_nr[i]); free_netdev(dev_nr[i]); } kfree(dev_nr); unregister_proto: proto_unregister(&nr_proto); return rc; } module_init(nr_proto_init); module_param(nr_ndevs, int, 0); MODULE_PARM_DESC(nr_ndevs, "number of NET/ROM devices"); MODULE_AUTHOR("Jonathan Naylor G4KLX <g4klx@g4klx.demon.co.uk>"); MODULE_DESCRIPTION("The amateur radio NET/ROM network and transport layer protocol"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_NETROM); static void __exit nr_exit(void) { int i; remove_proc_entry("nr", init_net.proc_net); remove_proc_entry("nr_neigh", init_net.proc_net); remove_proc_entry("nr_nodes", init_net.proc_net); nr_loopback_clear(); nr_rt_free(); #ifdef CONFIG_SYSCTL nr_unregister_sysctl(); #endif ax25_linkfail_release(&nr_linkfail_notifier); ax25_protocol_release(AX25_P_NETROM); unregister_netdevice_notifier(&nr_dev_notifier); sock_unregister(PF_NETROM); for (i = 0; i < nr_ndevs; i++) { struct net_device *dev = dev_nr[i]; if (dev) { unregister_netdev(dev); free_netdev(dev); } } kfree(dev_nr); proto_unregister(&nr_proto); } module_exit(nr_exit); |
| 531 4 4 529 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright © 2006-2015, Intel Corporation. * * Authors: Ashok Raj <ashok.raj@intel.com> * Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> * David Woodhouse <David.Woodhouse@intel.com> */ #ifndef _INTEL_IOMMU_H_ #define _INTEL_IOMMU_H_ #include <linux/types.h> #include <linux/iova.h> #include <linux/io.h> #include <linux/idr.h> #include <linux/mmu_notifier.h> #include <linux/list.h> #include <linux/iommu.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/dmar.h> #include <linux/bitfield.h> #include <linux/xarray.h> #include <linux/perf_event.h> #include <asm/cacheflush.h> #include <asm/iommu.h> #include <uapi/linux/iommufd.h> /* * VT-d hardware uses 4KiB page size regardless of host page size. */ #define VTD_PAGE_SHIFT (12) #define VTD_PAGE_SIZE (1UL << VTD_PAGE_SHIFT) #define VTD_PAGE_MASK (((u64)-1) << VTD_PAGE_SHIFT) #define VTD_PAGE_ALIGN(addr) (((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK) #define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT) #define VTD_STRIDE_SHIFT (9) #define VTD_STRIDE_MASK (((u64)-1) << VTD_STRIDE_SHIFT) #define DMA_PTE_READ BIT_ULL(0) #define DMA_PTE_WRITE BIT_ULL(1) #define DMA_PTE_LARGE_PAGE BIT_ULL(7) #define DMA_PTE_SNP BIT_ULL(11) #define DMA_FL_PTE_PRESENT BIT_ULL(0) #define DMA_FL_PTE_US BIT_ULL(2) #define DMA_FL_PTE_ACCESS BIT_ULL(5) #define DMA_FL_PTE_DIRTY BIT_ULL(6) #define DMA_SL_PTE_DIRTY_BIT 9 #define DMA_SL_PTE_DIRTY BIT_ULL(DMA_SL_PTE_DIRTY_BIT) #define ADDR_WIDTH_5LEVEL (57) #define ADDR_WIDTH_4LEVEL (48) #define CONTEXT_TT_MULTI_LEVEL 0 #define CONTEXT_TT_DEV_IOTLB 1 #define CONTEXT_TT_PASS_THROUGH 2 #define CONTEXT_PASIDE BIT_ULL(3) /* * Intel IOMMU register specification per version 1.0 public spec. */ #define DMAR_VER_REG 0x0 /* Arch version supported by this IOMMU */ #define DMAR_CAP_REG 0x8 /* Hardware supported capabilities */ #define DMAR_ECAP_REG 0x10 /* Extended capabilities supported */ #define DMAR_GCMD_REG 0x18 /* Global command register */ #define DMAR_GSTS_REG 0x1c /* Global status register */ #define DMAR_RTADDR_REG 0x20 /* Root entry table */ #define DMAR_CCMD_REG 0x28 /* Context command reg */ #define DMAR_FSTS_REG 0x34 /* Fault Status register */ #define DMAR_FECTL_REG 0x38 /* Fault control register */ #define DMAR_FEDATA_REG 0x3c /* Fault event interrupt data register */ #define DMAR_FEADDR_REG 0x40 /* Fault event interrupt addr register */ #define DMAR_FEUADDR_REG 0x44 /* Upper address register */ #define DMAR_AFLOG_REG 0x58 /* Advanced Fault control */ #define DMAR_PMEN_REG 0x64 /* Enable Protected Memory Region */ #define DMAR_PLMBASE_REG 0x68 /* PMRR Low addr */ #define DMAR_PLMLIMIT_REG 0x6c /* PMRR low limit */ #define DMAR_PHMBASE_REG 0x70 /* pmrr high base addr */ #define DMAR_PHMLIMIT_REG 0x78 /* pmrr high limit */ #define DMAR_IQH_REG 0x80 /* Invalidation queue head register */ #define DMAR_IQT_REG 0x88 /* Invalidation queue tail register */ #define DMAR_IQ_SHIFT 4 /* Invalidation queue head/tail shift */ #define DMAR_IQA_REG 0x90 /* Invalidation queue addr register */ #define DMAR_ICS_REG 0x9c /* Invalidation complete status register */ #define DMAR_IQER_REG 0xb0 /* Invalidation queue error record register */ #define DMAR_IRTA_REG 0xb8 /* Interrupt remapping table addr register */ #define DMAR_PQH_REG 0xc0 /* Page request queue head register */ #define DMAR_PQT_REG 0xc8 /* Page request queue tail register */ #define DMAR_PQA_REG 0xd0 /* Page request queue address register */ #define DMAR_PRS_REG 0xdc /* Page request status register */ #define DMAR_PECTL_REG 0xe0 /* Page request event control register */ #define DMAR_PEDATA_REG 0xe4 /* Page request event interrupt data register */ #define DMAR_PEADDR_REG 0xe8 /* Page request event interrupt addr register */ #define DMAR_PEUADDR_REG 0xec /* Page request event Upper address register */ #define DMAR_MTRRCAP_REG 0x100 /* MTRR capability register */ #define DMAR_MTRRDEF_REG 0x108 /* MTRR default type register */ #define DMAR_MTRR_FIX64K_00000_REG 0x120 /* MTRR Fixed range registers */ #define DMAR_MTRR_FIX16K_80000_REG 0x128 #define DMAR_MTRR_FIX16K_A0000_REG 0x130 #define DMAR_MTRR_FIX4K_C0000_REG 0x138 #define DMAR_MTRR_FIX4K_C8000_REG 0x140 #define DMAR_MTRR_FIX4K_D0000_REG 0x148 #define DMAR_MTRR_FIX4K_D8000_REG 0x150 #define DMAR_MTRR_FIX4K_E0000_REG 0x158 #define DMAR_MTRR_FIX4K_E8000_REG 0x160 #define DMAR_MTRR_FIX4K_F0000_REG 0x168 #define DMAR_MTRR_FIX4K_F8000_REG 0x170 #define DMAR_MTRR_PHYSBASE0_REG 0x180 /* MTRR Variable range registers */ #define DMAR_MTRR_PHYSMASK0_REG 0x188 #define DMAR_MTRR_PHYSBASE1_REG 0x190 #define DMAR_MTRR_PHYSMASK1_REG 0x198 #define DMAR_MTRR_PHYSBASE2_REG 0x1a0 #define DMAR_MTRR_PHYSMASK2_REG 0x1a8 #define DMAR_MTRR_PHYSBASE3_REG 0x1b0 #define DMAR_MTRR_PHYSMASK3_REG 0x1b8 #define DMAR_MTRR_PHYSBASE4_REG 0x1c0 #define DMAR_MTRR_PHYSMASK4_REG 0x1c8 #define DMAR_MTRR_PHYSBASE5_REG 0x1d0 #define DMAR_MTRR_PHYSMASK5_REG 0x1d8 #define DMAR_MTRR_PHYSBASE6_REG 0x1e0 #define DMAR_MTRR_PHYSMASK6_REG 0x1e8 #define DMAR_MTRR_PHYSBASE7_REG 0x1f0 #define DMAR_MTRR_PHYSMASK7_REG 0x1f8 #define DMAR_MTRR_PHYSBASE8_REG 0x200 #define DMAR_MTRR_PHYSMASK8_REG 0x208 #define DMAR_MTRR_PHYSBASE9_REG 0x210 #define DMAR_MTRR_PHYSMASK9_REG 0x218 #define DMAR_PERFCAP_REG 0x300 #define DMAR_PERFCFGOFF_REG 0x310 #define DMAR_PERFOVFOFF_REG 0x318 #define DMAR_PERFCNTROFF_REG 0x31c #define DMAR_PERFINTRSTS_REG 0x324 #define DMAR_PERFINTRCTL_REG 0x328 #define DMAR_PERFEVNTCAP_REG 0x380 #define DMAR_ECMD_REG 0x400 #define DMAR_ECEO_REG 0x408 #define DMAR_ECRSP_REG 0x410 #define DMAR_ECCAP_REG 0x430 #define DMAR_IQER_REG_IQEI(reg) FIELD_GET(GENMASK_ULL(3, 0), reg) #define DMAR_IQER_REG_ITESID(reg) FIELD_GET(GENMASK_ULL(47, 32), reg) #define DMAR_IQER_REG_ICESID(reg) FIELD_GET(GENMASK_ULL(63, 48), reg) #define OFFSET_STRIDE (9) #define dmar_readq(a) readq(a) #define dmar_writeq(a,v) writeq(v,a) #define dmar_readl(a) readl(a) #define dmar_writel(a, v) writel(v, a) #define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4) #define DMAR_VER_MINOR(v) ((v) & 0x0f) /* * Decoding Capability Register */ #define cap_esrtps(c) (((c) >> 63) & 1) #define cap_esirtps(c) (((c) >> 62) & 1) #define cap_ecmds(c) (((c) >> 61) & 1) #define cap_fl5lp_support(c) (((c) >> 60) & 1) #define cap_pi_support(c) (((c) >> 59) & 1) #define cap_fl1gp_support(c) (((c) >> 56) & 1) #define cap_read_drain(c) (((c) >> 55) & 1) #define cap_write_drain(c) (((c) >> 54) & 1) #define cap_max_amask_val(c) (((c) >> 48) & 0x3f) #define cap_num_fault_regs(c) ((((c) >> 40) & 0xff) + 1) #define cap_pgsel_inv(c) (((c) >> 39) & 1) #define cap_super_page_val(c) (((c) >> 34) & 0xf) #define cap_super_offset(c) (((find_first_bit(&cap_super_page_val(c), 4)) \ * OFFSET_STRIDE) + 21) #define cap_fault_reg_offset(c) ((((c) >> 24) & 0x3ff) * 16) #define cap_max_fault_reg_offset(c) \ (cap_fault_reg_offset(c) + cap_num_fault_regs(c) * 16) #define cap_zlr(c) (((c) >> 22) & 1) #define cap_isoch(c) (((c) >> 23) & 1) #define cap_mgaw(c) ((((c) >> 16) & 0x3f) + 1) #define cap_sagaw(c) (((c) >> 8) & 0x1f) #define cap_caching_mode(c) (((c) >> 7) & 1) #define cap_phmr(c) (((c) >> 6) & 1) #define cap_plmr(c) (((c) >> 5) & 1) #define cap_rwbf(c) (((c) >> 4) & 1) #define cap_afl(c) (((c) >> 3) & 1) #define cap_ndoms(c) (((unsigned long)1) << (4 + 2 * ((c) & 0x7))) /* * Extended Capability Register */ #define ecap_pms(e) (((e) >> 51) & 0x1) #define ecap_rps(e) (((e) >> 49) & 0x1) #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) #define ecap_slads(e) (((e) >> 45) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) (((e) >> 41) & 0x1) #define ecap_pds(e) (((e) >> 42) & 0x1) #define ecap_pasid(e) (((e) >> 40) & 0x1) #define ecap_pss(e) (((e) >> 35) & 0x1f) #define ecap_eafs(e) (((e) >> 34) & 0x1) #define ecap_nwfs(e) (((e) >> 33) & 0x1) #define ecap_srs(e) (((e) >> 31) & 0x1) #define ecap_ers(e) (((e) >> 30) & 0x1) #define ecap_prs(e) (((e) >> 29) & 0x1) #define ecap_broken_pasid(e) (((e) >> 28) & 0x1) #define ecap_dis(e) (((e) >> 27) & 0x1) #define ecap_nest(e) (((e) >> 26) & 0x1) #define ecap_mts(e) (((e) >> 25) & 0x1) #define ecap_iotlb_offset(e) ((((e) >> 8) & 0x3ff) * 16) #define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16) #define ecap_coherent(e) ((e) & 0x1) #define ecap_qis(e) ((e) & 0x2) #define ecap_pass_through(e) (((e) >> 6) & 0x1) #define ecap_eim_support(e) (((e) >> 4) & 0x1) #define ecap_ir_support(e) (((e) >> 3) & 0x1) #define ecap_dev_iotlb_support(e) (((e) >> 2) & 0x1) #define ecap_max_handle_mask(e) (((e) >> 20) & 0xf) #define ecap_sc_support(e) (((e) >> 7) & 0x1) /* Snooping Control */ /* * Decoding Perf Capability Register */ #define pcap_num_cntr(p) ((p) & 0xffff) #define pcap_cntr_width(p) (((p) >> 16) & 0x7f) #define pcap_num_event_group(p) (((p) >> 24) & 0x1f) #define pcap_filters_mask(p) (((p) >> 32) & 0x1f) #define pcap_interrupt(p) (((p) >> 50) & 0x1) /* The counter stride is calculated as 2 ^ (x+10) bytes */ #define pcap_cntr_stride(p) (1ULL << ((((p) >> 52) & 0x7) + 10)) /* * Decoding Perf Event Capability Register */ #define pecap_es(p) ((p) & 0xfffffff) /* Virtual command interface capability */ #define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ /* IOTLB_REG */ #define DMA_TLB_FLUSH_GRANU_OFFSET 60 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60) #define DMA_TLB_DSI_FLUSH (((u64)2) << 60) #define DMA_TLB_PSI_FLUSH (((u64)3) << 60) #define DMA_TLB_IIRG(type) ((type >> 60) & 3) #define DMA_TLB_IAIG(val) (((val) >> 57) & 3) #define DMA_TLB_READ_DRAIN (((u64)1) << 49) #define DMA_TLB_WRITE_DRAIN (((u64)1) << 48) #define DMA_TLB_DID(id) (((u64)((id) & 0xffff)) << 32) #define DMA_TLB_IVT (((u64)1) << 63) #define DMA_TLB_IH_NONLEAF (((u64)1) << 6) #define DMA_TLB_MAX_SIZE (0x3f) /* INVALID_DESC */ #define DMA_CCMD_INVL_GRANU_OFFSET 61 #define DMA_ID_TLB_GLOBAL_FLUSH (((u64)1) << 4) #define DMA_ID_TLB_DSI_FLUSH (((u64)2) << 4) #define DMA_ID_TLB_PSI_FLUSH (((u64)3) << 4) #define DMA_ID_TLB_READ_DRAIN (((u64)1) << 7) #define DMA_ID_TLB_WRITE_DRAIN (((u64)1) << 6) #define DMA_ID_TLB_DID(id) (((u64)((id & 0xffff) << 16))) #define DMA_ID_TLB_IH_NONLEAF (((u64)1) << 6) #define DMA_ID_TLB_ADDR(addr) (addr) #define DMA_ID_TLB_ADDR_MASK(mask) (mask) /* PMEN_REG */ #define DMA_PMEN_EPM (((u32)1)<<31) #define DMA_PMEN_PRS (((u32)1)<<0) /* GCMD_REG */ #define DMA_GCMD_TE (((u32)1) << 31) #define DMA_GCMD_SRTP (((u32)1) << 30) #define DMA_GCMD_SFL (((u32)1) << 29) #define DMA_GCMD_EAFL (((u32)1) << 28) #define DMA_GCMD_WBF (((u32)1) << 27) #define DMA_GCMD_QIE (((u32)1) << 26) #define DMA_GCMD_SIRTP (((u32)1) << 24) #define DMA_GCMD_IRE (((u32) 1) << 25) #define DMA_GCMD_CFI (((u32) 1) << 23) /* GSTS_REG */ #define DMA_GSTS_TES (((u32)1) << 31) #define DMA_GSTS_RTPS (((u32)1) << 30) #define DMA_GSTS_FLS (((u32)1) << 29) #define DMA_GSTS_AFLS (((u32)1) << 28) #define DMA_GSTS_WBFS (((u32)1) << 27) #define DMA_GSTS_QIES (((u32)1) << 26) #define DMA_GSTS_IRTPS (((u32)1) << 24) #define DMA_GSTS_IRES (((u32)1) << 25) #define DMA_GSTS_CFIS (((u32)1) << 23) /* DMA_RTADDR_REG */ #define DMA_RTADDR_SMT (((u64)1) << 10) /* CCMD_REG */ #define DMA_CCMD_ICC (((u64)1) << 63) #define DMA_CCMD_GLOBAL_INVL (((u64)1) << 61) #define DMA_CCMD_DOMAIN_INVL (((u64)2) << 61) #define DMA_CCMD_DEVICE_INVL (((u64)3) << 61) #define DMA_CCMD_FM(m) (((u64)((m) & 0x3)) << 32) #define DMA_CCMD_MASK_NOBIT 0 #define DMA_CCMD_MASK_1BIT 1 #define DMA_CCMD_MASK_2BIT 2 #define DMA_CCMD_MASK_3BIT 3 #define DMA_CCMD_SID(s) (((u64)((s) & 0xffff)) << 16) #define DMA_CCMD_DID(d) ((u64)((d) & 0xffff)) /* ECMD_REG */ #define DMA_MAX_NUM_ECMD 256 #define DMA_MAX_NUM_ECMDCAP (DMA_MAX_NUM_ECMD / 64) #define DMA_ECMD_REG_STEP 8 #define DMA_ECMD_ENABLE 0xf0 #define DMA_ECMD_DISABLE 0xf1 #define DMA_ECMD_FREEZE 0xf4 #define DMA_ECMD_UNFREEZE 0xf5 #define DMA_ECMD_OA_SHIFT 16 #define DMA_ECMD_ECRSP_IP 0x1 #define DMA_ECMD_ECCAP3 3 #define DMA_ECMD_ECCAP3_ECNTS BIT_ULL(48) #define DMA_ECMD_ECCAP3_DCNTS BIT_ULL(49) #define DMA_ECMD_ECCAP3_FCNTS BIT_ULL(52) #define DMA_ECMD_ECCAP3_UFCNTS BIT_ULL(53) #define DMA_ECMD_ECCAP3_ESSENTIAL (DMA_ECMD_ECCAP3_ECNTS | \ DMA_ECMD_ECCAP3_DCNTS | \ DMA_ECMD_ECCAP3_FCNTS | \ DMA_ECMD_ECCAP3_UFCNTS) /* FECTL_REG */ #define DMA_FECTL_IM (((u32)1) << 31) /* FSTS_REG */ #define DMA_FSTS_PFO (1 << 0) /* Primary Fault Overflow */ #define DMA_FSTS_PPF (1 << 1) /* Primary Pending Fault */ #define DMA_FSTS_IQE (1 << 4) /* Invalidation Queue Error */ #define DMA_FSTS_ICE (1 << 5) /* Invalidation Completion Error */ #define DMA_FSTS_ITE (1 << 6) /* Invalidation Time-out Error */ #define DMA_FSTS_PRO (1 << 7) /* Page Request Overflow */ #define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff) /* FRCD_REG, 32 bits access */ #define DMA_FRCD_F (((u32)1) << 31) #define dma_frcd_type(d) ((d >> 30) & 1) #define dma_frcd_fault_reason(c) (c & 0xff) #define dma_frcd_source_id(c) (c & 0xffff) #define dma_frcd_pasid_value(c) (((c) >> 8) & 0xfffff) #define dma_frcd_pasid_present(c) (((c) >> 31) & 1) /* low 64 bit */ #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT)) /* PRS_REG */ #define DMA_PRS_PPR ((u32)1) #define DMA_PRS_PRO ((u32)2) #define DMA_VCS_PAS ((u64)1) /* PERFINTRSTS_REG */ #define DMA_PERFINTRSTS_PIS ((u32)1) #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ cycles_t start_time = get_cycles(); \ while (1) { \ sts = op(iommu->reg + offset); \ if (cond) \ break; \ if (DMAR_OPERATION_TIMEOUT < (get_cycles() - start_time))\ panic("DMAR hardware is malfunctioning\n"); \ cpu_relax(); \ } \ } while (0) #define QI_LENGTH 256 /* queue length */ enum { QI_FREE, QI_IN_USE, QI_DONE, QI_ABORT }; #define QI_CC_TYPE 0x1 #define QI_IOTLB_TYPE 0x2 #define QI_DIOTLB_TYPE 0x3 #define QI_IEC_TYPE 0x4 #define QI_IWD_TYPE 0x5 #define QI_EIOTLB_TYPE 0x6 #define QI_PC_TYPE 0x7 #define QI_DEIOTLB_TYPE 0x8 #define QI_PGRP_RESP_TYPE 0x9 #define QI_PSTRM_RESP_TYPE 0xa #define QI_IEC_SELECTIVE (((u64)1) << 4) #define QI_IEC_IIDEX(idx) (((u64)(idx & 0xffff) << 32)) #define QI_IEC_IM(m) (((u64)(m & 0x1f) << 27)) #define QI_IWD_STATUS_DATA(d) (((u64)d) << 32) #define QI_IWD_STATUS_WRITE (((u64)1) << 5) #define QI_IWD_FENCE (((u64)1) << 6) #define QI_IWD_PRQ_DRAIN (((u64)1) << 7) #define QI_IOTLB_DID(did) (((u64)did) << 16) #define QI_IOTLB_DR(dr) (((u64)dr) << 7) #define QI_IOTLB_DW(dw) (((u64)dw) << 6) #define QI_IOTLB_GRAN(gran) (((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4)) #define QI_IOTLB_ADDR(addr) (((u64)addr) & VTD_PAGE_MASK) #define QI_IOTLB_IH(ih) (((u64)ih) << 6) #define QI_IOTLB_AM(am) (((u8)am) & 0x3f) #define QI_CC_FM(fm) (((u64)fm) << 48) #define QI_CC_SID(sid) (((u64)sid) << 32) #define QI_CC_DID(did) (((u64)did) << 16) #define QI_CC_GRAN(gran) (((u64)gran) >> (DMA_CCMD_INVL_GRANU_OFFSET-4)) #define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) #define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16) #define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) #define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_IOTLB_SIZE 1 #define QI_DEV_IOTLB_MAX_INVS 32 #define QI_PC_PASID(pasid) (((u64)pasid) << 32) #define QI_PC_DID(did) (((u64)did) << 16) #define QI_PC_GRAN(gran) (((u64)gran) << 4) /* PASID cache invalidation granu */ #define QI_PC_ALL_PASIDS 0 #define QI_PC_PASID_SEL 1 #define QI_PC_GLOBAL 3 #define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) #define QI_EIOTLB_IH(ih) (((u64)ih) << 6) #define QI_EIOTLB_AM(am) (((u64)am) & 0x3f) #define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32) #define QI_EIOTLB_DID(did) (((u64)did) << 16) #define QI_EIOTLB_GRAN(gran) (((u64)gran) << 4) /* QI Dev-IOTLB inv granu */ #define QI_DEV_IOTLB_GRAN_ALL 1 #define QI_DEV_IOTLB_GRAN_PASID_SEL 0 #define QI_DEV_EIOTLB_ADDR(a) ((u64)(a) & VTD_PAGE_MASK) #define QI_DEV_EIOTLB_SIZE (((u64)1) << 11) #define QI_DEV_EIOTLB_PASID(p) ((u64)((p) & 0xfffff) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) #define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_EIOTLB_MAX_INVS 32 /* Page group response descriptor QW0 */ #define QI_PGRP_PASID_P(p) (((u64)(p)) << 4) #define QI_PGRP_RESP_CODE(res) (((u64)(res)) << 12) #define QI_PGRP_DID(rid) (((u64)(rid)) << 16) #define QI_PGRP_PASID(pasid) (((u64)(pasid)) << 32) /* Page group response descriptor QW1 */ #define QI_PGRP_LPIG(x) (((u64)(x)) << 2) #define QI_PGRP_IDX(idx) (((u64)(idx)) << 3) #define QI_RESP_SUCCESS 0x0 #define QI_RESP_INVALID 0x1 #define QI_RESP_FAILURE 0xf #define QI_GRAN_NONG_PASID 2 #define QI_GRAN_PSI_PASID 3 #define qi_shift(iommu) (DMAR_IQ_SHIFT + !!ecap_smts((iommu)->ecap)) struct qi_desc { u64 qw0; u64 qw1; u64 qw2; u64 qw3; }; struct q_inval { raw_spinlock_t q_lock; void *desc; /* invalidation queue */ int *desc_status; /* desc status */ int free_head; /* first free entry */ int free_tail; /* last free entry */ int free_cnt; }; /* Page Request Queue depth */ #define PRQ_ORDER 4 #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) #define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) struct dmar_pci_notify_info; #ifdef CONFIG_IRQ_REMAP /* 1MB - maximum possible interrupt remapping table size */ #define INTR_REMAP_PAGE_ORDER 8 #define INTR_REMAP_TABLE_REG_SIZE 0xf #define INTR_REMAP_TABLE_REG_SIZE_MASK 0xf #define INTR_REMAP_TABLE_ENTRIES 65536 struct irq_domain; struct ir_table { struct irte *base; unsigned long *bitmap; }; void intel_irq_remap_add_device(struct dmar_pci_notify_info *info); #else static inline void intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { } #endif struct iommu_flush { void (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm, u64 type); void (*flush_iotlb)(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type); }; enum { SR_DMAR_FECTL_REG, SR_DMAR_FEDATA_REG, SR_DMAR_FEADDR_REG, SR_DMAR_FEUADDR_REG, MAX_SR_DMAR_REGS }; #define VTD_FLAG_TRANS_PRE_ENABLED (1 << 0) #define VTD_FLAG_IRQ_REMAP_PRE_ENABLED (1 << 1) #define VTD_FLAG_SVM_CAPABLE (1 << 2) #define sm_supported(iommu) (intel_iommu_sm && ecap_smts((iommu)->ecap)) #define pasid_supported(iommu) (sm_supported(iommu) && \ ecap_pasid((iommu)->ecap)) #define ssads_supported(iommu) (sm_supported(iommu) && \ ecap_slads((iommu)->ecap)) #define nested_supported(iommu) (sm_supported(iommu) && \ ecap_nest((iommu)->ecap)) struct pasid_entry; struct pasid_state_entry; struct page_req_dsc; /* * 0: Present * 1-11: Reserved * 12-63: Context Ptr (12 - (haw-1)) * 64-127: Reserved */ struct root_entry { u64 lo; u64 hi; }; /* * low 64 bits: * 0: present * 1: fault processing disable * 2-3: translation type * 12-63: address space root * high 64 bits: * 0-2: address width * 3-6: aval * 8-23: domain id */ struct context_entry { u64 lo; u64 hi; }; struct iommu_domain_info { struct intel_iommu *iommu; unsigned int refcnt; /* Refcount of devices per iommu */ u16 did; /* Domain ids per IOMMU. Use u16 since * domain ids are 16 bit wide according * to VT-d spec, section 9.3 */ }; struct dmar_domain { int nid; /* node id */ struct xarray iommu_array; /* Attached IOMMU array */ u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ u8 force_snooping : 1; /* Create IOPTEs with snoop control */ u8 set_pte_snp:1; u8 use_first_level:1; /* DMA translation for the domain goes * through the first level page table, * otherwise, goes through the second * level. */ u8 dirty_tracking:1; /* Dirty tracking is enabled */ u8 nested_parent:1; /* Has other domains nested on it */ u8 has_mappings:1; /* Has mappings configured through * iommu_map() interface. */ spinlock_t lock; /* Protect device tracking lists */ struct list_head devices; /* all devices' list */ struct list_head dev_pasids; /* all attached pasids */ spinlock_t cache_lock; /* Protect the cache tag list */ struct list_head cache_tags; /* Cache tag list */ int iommu_superpage;/* Level of superpages supported: 0 == 4KiB (no superpages), 1 == 2MiB, 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ union { /* DMA remapping domain */ struct { /* virtual address */ struct dma_pte *pgd; /* max guest address width */ int gaw; /* * adjusted guest address width: * 0: level 2 30-bit * 1: level 3 39-bit * 2: level 4 48-bit * 3: level 5 57-bit */ int agaw; /* maximum mapped address */ u64 max_addr; /* Protect the s1_domains list */ spinlock_t s1_lock; /* Track s1_domains nested on this domain */ struct list_head s1_domains; }; /* Nested user domain */ struct { /* parent page table which the user domain is nested on */ struct dmar_domain *s2_domain; /* user page table pointer (in GPA) */ unsigned long s1_pgtbl; /* page table attributes */ struct iommu_hwpt_vtd_s1 s1_cfg; /* link to parent domain siblings */ struct list_head s2_link; }; /* SVA domain */ struct { struct mmu_notifier notifier; }; }; struct iommu_domain domain; /* generic domain data structure for iommu core */ }; /* * In theory, the VT-d 4.0 spec can support up to 2 ^ 16 counters. * But in practice, there are only 14 counters for the existing * platform. Setting the max number of counters to 64 should be good * enough for a long time. Also, supporting more than 64 counters * requires more extras, e.g., extra freeze and overflow registers, * which is not necessary for now. */ #define IOMMU_PMU_IDX_MAX 64 struct iommu_pmu { struct intel_iommu *iommu; u32 num_cntr; /* Number of counters */ u32 num_eg; /* Number of event group */ u32 cntr_width; /* Counter width */ u32 cntr_stride; /* Counter Stride */ u32 filter; /* Bitmask of filter support */ void __iomem *base; /* the PerfMon base address */ void __iomem *cfg_reg; /* counter configuration base address */ void __iomem *cntr_reg; /* counter 0 address*/ void __iomem *overflow; /* overflow status register */ u64 *evcap; /* Indicates all supported events */ u32 **cntr_evcap; /* Supported events of each counter. */ struct pmu pmu; DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX); struct perf_event *event_list[IOMMU_PMU_IDX_MAX]; unsigned char irq_name[16]; struct hlist_node cpuhp_node; int cpu; }; #define IOMMU_IRQ_ID_OFFSET_PRQ (DMAR_UNITS_SUPPORTED) #define IOMMU_IRQ_ID_OFFSET_PERF (2 * DMAR_UNITS_SUPPORTED) struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 reg_phys; /* physical address of hw register set */ u64 reg_size; /* size of hw register set */ u64 cap; u64 ecap; u64 vccap; u64 ecmdcap[DMA_MAX_NUM_ECMDCAP]; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ raw_spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ int agaw; /* agaw of this iommu */ int msagaw; /* max sagaw of this iommu */ unsigned int irq, pr_irq, perf_irq; u16 segment; /* PCI segment# */ unsigned char name[13]; /* Device Name */ #ifdef CONFIG_INTEL_IOMMU unsigned long *domain_ids; /* bitmap of domains */ unsigned long *copied_tables; /* bitmap of copied tables */ spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ struct iommu_flush flush; #endif #ifdef CONFIG_INTEL_IOMMU_SVM struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ unsigned long prq_seq_number; struct completion prq_complete; #endif struct iopf_queue *iopf_queue; unsigned char iopfq_name[16]; /* Synchronization between fault report and iommu device release. */ struct mutex iopf_lock; struct q_inval *qi; /* Queued invalidation info */ u32 iommu_state[MAX_SR_DMAR_REGS]; /* Store iommu states between suspend and resume.*/ /* rb tree for all probed devices */ struct rb_root device_rbtree; /* protect the device_rbtree */ spinlock_t device_rbtree_lock; #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ struct irq_domain *ir_domain; #endif struct iommu_device iommu; /* IOMMU core code handle */ int node; u32 flags; /* Software defined flags */ struct dmar_drhd_unit *drhd; void *perf_statistic; struct iommu_pmu *pmu; }; /* PCI domain-device relationship */ struct device_domain_info { struct list_head link; /* link to domain siblings */ u32 segment; /* PCI segment number */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ u16 pfsid; /* SRIOV physical function source ID */ u8 pasid_supported:3; u8 pasid_enabled:1; u8 pri_supported:1; u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; u8 dtlb_extra_inval:1; /* Quirk for devices need extra flush */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ struct dmar_domain *domain; /* pointer to domain */ struct pasid_table *pasid_table; /* pasid table */ /* device tracking node(lookup by PCI RID) */ struct rb_node node; #ifdef CONFIG_INTEL_IOMMU_DEBUGFS struct dentry *debugfs_dentry; /* pointer to device directory dentry */ #endif }; struct dev_pasid_info { struct list_head link_domain; /* link to domain siblings */ struct device *dev; ioasid_t pasid; #ifdef CONFIG_INTEL_IOMMU_DEBUGFS struct dentry *debugfs_dentry; /* pointer to pasid directory dentry */ #endif }; static inline void __iommu_flush_cache( struct intel_iommu *iommu, void *addr, int size) { if (!ecap_coherent(iommu->ecap)) clflush_cache_range(addr, size); } /* Convert generic struct iommu_domain to private struct dmar_domain */ static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) { return container_of(dom, struct dmar_domain, domain); } /* Retrieve the domain ID which has allocated to the domain */ static inline u16 domain_id_iommu(struct dmar_domain *domain, struct intel_iommu *iommu) { struct iommu_domain_info *info = xa_load(&domain->iommu_array, iommu->seq_id); return info->did; } /* * 0: readable * 1: writable * 2-6: reserved * 7: super page * 8-10: available * 11: snoop behavior * 12-63: Host physical address */ struct dma_pte { u64 val; }; static inline void dma_clear_pte(struct dma_pte *pte) { pte->val = 0; } static inline u64 dma_pte_addr(struct dma_pte *pte) { #ifdef CONFIG_64BIT return pte->val & VTD_PAGE_MASK; #else /* Must have a full atomic 64-bit read */ return __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK; #endif } static inline bool dma_pte_present(struct dma_pte *pte) { return (pte->val & 3) != 0; } static inline bool dma_sl_pte_test_and_clear_dirty(struct dma_pte *pte, unsigned long flags) { if (flags & IOMMU_DIRTY_NO_CLEAR) return (pte->val & DMA_SL_PTE_DIRTY) != 0; return test_and_clear_bit(DMA_SL_PTE_DIRTY_BIT, (unsigned long *)&pte->val); } static inline bool dma_pte_superpage(struct dma_pte *pte) { return (pte->val & DMA_PTE_LARGE_PAGE); } static inline bool first_pte_in_page(struct dma_pte *pte) { return IS_ALIGNED((unsigned long)pte, VTD_PAGE_SIZE); } static inline int nr_pte_to_next_page(struct dma_pte *pte) { return first_pte_in_page(pte) ? BIT_ULL(VTD_STRIDE_SHIFT) : (struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte; } static inline bool context_present(struct context_entry *context) { return (context->lo & 1); } #define LEVEL_STRIDE (9) #define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) #define MAX_AGAW_WIDTH (64) #define MAX_AGAW_PFN_WIDTH (MAX_AGAW_WIDTH - VTD_PAGE_SHIFT) static inline int agaw_to_level(int agaw) { return agaw + 2; } static inline int agaw_to_width(int agaw) { return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH); } static inline int width_to_agaw(int width) { return DIV_ROUND_UP(width - 30, LEVEL_STRIDE); } static inline unsigned int level_to_offset_bits(int level) { return (level - 1) * LEVEL_STRIDE; } static inline int pfn_level_offset(u64 pfn, int level) { return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; } static inline u64 level_mask(int level) { return -1ULL << level_to_offset_bits(level); } static inline u64 level_size(int level) { return 1ULL << level_to_offset_bits(level); } static inline u64 align_to_level(u64 pfn, int level) { return (pfn + level_size(level) - 1) & level_mask(level); } static inline unsigned long lvl_to_nr_pages(unsigned int lvl) { return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH); } /* VT-d pages must always be _smaller_ than MM pages. Otherwise things are never going to work. */ static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn) { return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT); } static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn) { return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1; } static inline unsigned long page_to_dma_pfn(struct page *pg) { return mm_to_dma_pfn_start(page_to_pfn(pg)); } static inline unsigned long virt_to_dma_pfn(void *p) { return page_to_dma_pfn(virt_to_page(p)); } static inline void context_set_present(struct context_entry *context) { context->lo |= 1; } static inline void context_set_fault_enable(struct context_entry *context) { context->lo &= (((u64)-1) << 2) | 1; } static inline void context_set_translation_type(struct context_entry *context, unsigned long value) { context->lo &= (((u64)-1) << 4) | 3; context->lo |= (value & 3) << 2; } static inline void context_set_address_root(struct context_entry *context, unsigned long value) { context->lo &= ~VTD_PAGE_MASK; context->lo |= value & VTD_PAGE_MASK; } static inline void context_set_address_width(struct context_entry *context, unsigned long value) { context->hi |= value & 7; } static inline void context_set_domain_id(struct context_entry *context, unsigned long value) { context->hi |= (value & ((1 << 16) - 1)) << 8; } static inline void context_set_pasid(struct context_entry *context) { context->lo |= CONTEXT_PASIDE; } static inline int context_domain_id(struct context_entry *c) { return((c->hi >> 8) & 0xffff); } static inline void context_clear_entry(struct context_entry *context) { context->lo = 0; context->hi = 0; } #ifdef CONFIG_INTEL_IOMMU static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) { if (!iommu->copied_tables) return false; return test_bit(((long)bus << 8) | devfn, iommu->copied_tables); } static inline void set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) { set_bit(((long)bus << 8) | devfn, iommu->copied_tables); } static inline void clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn) { clear_bit(((long)bus << 8) | devfn, iommu->copied_tables); } #endif /* CONFIG_INTEL_IOMMU */ /* * Set the RID_PASID field of a scalable mode context entry. The * IOMMU hardware will use the PASID value set in this field for * DMA translations of DMA requests without PASID. */ static inline void context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) { context->hi |= pasid & ((1 << 20) - 1); } /* * Set the DTE(Device-TLB Enable) field of a scalable mode context * entry. */ static inline void context_set_sm_dte(struct context_entry *context) { context->lo |= BIT_ULL(2); } /* * Set the PRE(Page Request Enable) field of a scalable mode context * entry. */ static inline void context_set_sm_pre(struct context_entry *context) { context->lo |= BIT_ULL(4); } /* * Clear the PRE(Page Request Enable) field of a scalable mode context * entry. */ static inline void context_clear_sm_pre(struct context_entry *context) { context->lo &= ~BIT_ULL(4); } /* Returns a number of VTD pages, but aligned to MM page size */ static inline unsigned long aligned_nrpages(unsigned long host_addr, size_t size) { host_addr &= ~PAGE_MASK; return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; } /* Return a size from number of VTD pages. */ static inline unsigned long nrpages_to_size(unsigned long npages) { return npages << VTD_PAGE_SHIFT; } /* Convert value to context PASID directory size field coding. */ #define context_pdts(pds) (((pds) & 0x7) << 9) struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev); int dmar_enable_qi(struct intel_iommu *iommu); void dmar_disable_qi(struct intel_iommu *iommu); int dmar_reenable_qi(struct intel_iommu *iommu); void qi_global_iec(struct intel_iommu *iommu); void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm, u64 type); void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type); void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, u16 qdep, u64 addr, unsigned mask); void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, unsigned long npages, bool ih); void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, u32 pasid, u16 qdep, u64 addr, unsigned int size_order); void quirk_extra_dev_tlb_flush(struct device_domain_info *info, unsigned long address, unsigned long pages, u32 pasid, u16 qdep); void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, u32 pasid); int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, unsigned int count, unsigned long options); /* * Options used in qi_submit_sync: * QI_OPT_WAIT_DRAIN - Wait for PRQ drain completion, spec 6.5.2.8. */ #define QI_OPT_WAIT_DRAIN BIT(0) void domain_update_iotlb(struct dmar_domain *domain); int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu); void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu); void device_block_translation(struct device *dev); int prepare_domain_attach_device(struct iommu_domain *domain, struct device *dev); void domain_update_iommu_cap(struct dmar_domain *domain); int dmar_ir_support(void); void iommu_flush_write_buffer(struct intel_iommu *iommu); struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent, const struct iommu_user_data *user_data); struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid); enum cache_tag_type { CACHE_TAG_IOTLB, CACHE_TAG_DEVTLB, CACHE_TAG_NESTING_IOTLB, CACHE_TAG_NESTING_DEVTLB, }; struct cache_tag { struct list_head node; enum cache_tag_type type; struct intel_iommu *iommu; /* * The @dev field represents the location of the cache. For IOTLB, it * resides on the IOMMU hardware. @dev stores the device pointer to * the IOMMU hardware. For DevTLB, it locates in the PCIe endpoint. * @dev stores the device pointer to that endpoint. */ struct device *dev; u16 domain_id; ioasid_t pasid; unsigned int users; }; int cache_tag_assign_domain(struct dmar_domain *domain, struct device *dev, ioasid_t pasid); void cache_tag_unassign_domain(struct dmar_domain *domain, struct device *dev, ioasid_t pasid); void cache_tag_flush_range(struct dmar_domain *domain, unsigned long start, unsigned long end, int ih); void cache_tag_flush_all(struct dmar_domain *domain); void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start, unsigned long end); void intel_context_flush_present(struct device_domain_info *info, struct context_entry *context, u16 did, bool affect_domains); #ifdef CONFIG_INTEL_IOMMU_SVM void intel_svm_check(struct intel_iommu *iommu); int intel_svm_enable_prq(struct intel_iommu *iommu); int intel_svm_finish_prq(struct intel_iommu *iommu); void intel_svm_page_response(struct device *dev, struct iopf_fault *evt, struct iommu_page_response *msg); struct iommu_domain *intel_svm_domain_alloc(struct device *dev, struct mm_struct *mm); void intel_drain_pasid_prq(struct device *dev, u32 pasid); #else static inline void intel_svm_check(struct intel_iommu *iommu) {} static inline void intel_drain_pasid_prq(struct device *dev, u32 pasid) {} static inline struct iommu_domain *intel_svm_domain_alloc(struct device *dev, struct mm_struct *mm) { return ERR_PTR(-ENODEV); } #endif #ifdef CONFIG_INTEL_IOMMU_DEBUGFS void intel_iommu_debugfs_init(void); void intel_iommu_debugfs_create_dev(struct device_domain_info *info); void intel_iommu_debugfs_remove_dev(struct device_domain_info *info); void intel_iommu_debugfs_create_dev_pasid(struct dev_pasid_info *dev_pasid); void intel_iommu_debugfs_remove_dev_pasid(struct dev_pasid_info *dev_pasid); #else static inline void intel_iommu_debugfs_init(void) {} static inline void intel_iommu_debugfs_create_dev(struct device_domain_info *info) {} static inline void intel_iommu_debugfs_remove_dev(struct device_domain_info *info) {} static inline void intel_iommu_debugfs_create_dev_pasid(struct dev_pasid_info *dev_pasid) {} static inline void intel_iommu_debugfs_remove_dev_pasid(struct dev_pasid_info *dev_pasid) {} #endif /* CONFIG_INTEL_IOMMU_DEBUGFS */ extern const struct attribute_group *intel_iommu_groups[]; struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, u8 devfn, int alloc); extern const struct iommu_ops intel_iommu_ops; #ifdef CONFIG_INTEL_IOMMU extern int intel_iommu_sm; int iommu_calculate_agaw(struct intel_iommu *iommu); int iommu_calculate_max_sagaw(struct intel_iommu *iommu); int ecmd_submit_sync(struct intel_iommu *iommu, u8 ecmd, u64 oa, u64 ob); static inline bool ecmd_has_pmu_essential(struct intel_iommu *iommu) { return (iommu->ecmdcap[DMA_ECMD_ECCAP3] & DMA_ECMD_ECCAP3_ESSENTIAL) == DMA_ECMD_ECCAP3_ESSENTIAL; } extern int dmar_disabled; extern int intel_iommu_enabled; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) { return 0; } static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) { return 0; } #define dmar_disabled (1) #define intel_iommu_enabled (0) #define intel_iommu_sm (0) #endif static inline const char *decode_prq_descriptor(char *str, size_t size, u64 dw0, u64 dw1, u64 dw2, u64 dw3) { char *buf = str; int bytes; bytes = snprintf(buf, size, "rid=0x%llx addr=0x%llx %c%c%c%c%c pasid=0x%llx index=0x%llx", FIELD_GET(GENMASK_ULL(31, 16), dw0), FIELD_GET(GENMASK_ULL(63, 12), dw1), dw1 & BIT_ULL(0) ? 'r' : '-', dw1 & BIT_ULL(1) ? 'w' : '-', dw0 & BIT_ULL(52) ? 'x' : '-', dw0 & BIT_ULL(53) ? 'p' : '-', dw1 & BIT_ULL(2) ? 'l' : '-', FIELD_GET(GENMASK_ULL(51, 32), dw0), FIELD_GET(GENMASK_ULL(11, 3), dw1)); /* Private Data */ if (dw0 & BIT_ULL(9)) { size -= bytes; buf += bytes; snprintf(buf, size, " private=0x%llx/0x%llx\n", dw2, dw3); } return str; } #endif |
| 2 3 2 1 1 3 3 9 4 2 3 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* Xtables module to match packets using a BPF filter. * Copyright 2013 Google Inc. * Written by Willem de Bruijn <willemb@google.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/syscalls.h> #include <linux/skbuff.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/netfilter/xt_bpf.h> #include <linux/netfilter/x_tables.h> MODULE_AUTHOR("Willem de Bruijn <willemb@google.com>"); MODULE_DESCRIPTION("Xtables: BPF filter match"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_bpf"); MODULE_ALIAS("ip6t_bpf"); static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len, struct bpf_prog **ret) { struct sock_fprog_kern program; if (len > XT_BPF_MAX_NUM_INSTR) return -EINVAL; program.len = len; program.filter = insns; if (bpf_prog_create(ret, &program)) { pr_info_ra |