| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | // SPDX-License-Identifier: GPL-2.0 /* * Utility functions for file contents encryption/decryption on * block device-based filesystems. * * Copyright (C) 2015, Google, Inc. * Copyright (C) 2015, Motorola Mobility */ #include <linux/pagemap.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/namei.h> #include "fscrypt_private.h" /** * fscrypt_decrypt_bio() - decrypt the contents of a bio * @bio: the bio to decrypt * * Decrypt the contents of a "read" bio following successful completion of the * underlying disk read. The bio must be reading a whole number of blocks of an * encrypted file directly into the page cache. If the bio is reading the * ciphertext into bounce pages instead of the page cache (for example, because * the file is also compressed, so decompression is required after decryption), * then this function isn't applicable. This function may sleep, so it must be * called from a workqueue rather than from the bio's bi_end_io callback. * * Return: %true on success; %false on failure. On failure, bio->bi_status is * also set to an error status. */ bool fscrypt_decrypt_bio(struct bio *bio) { struct folio_iter fi; bio_for_each_folio_all(fi, bio) { int err = fscrypt_decrypt_pagecache_blocks(fi.folio, fi.length, fi.offset); if (err) { bio->bi_status = errno_to_blk_status(err); return false; } } return true; } EXPORT_SYMBOL(fscrypt_decrypt_bio); static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { const unsigned int blockbits = inode->i_blkbits; const unsigned int blocks_per_page = 1 << (PAGE_SHIFT - blockbits); struct bio *bio; int ret, err = 0; int num_pages = 0; /* This always succeeds since __GFP_DIRECT_RECLAIM is set. */ bio = bio_alloc(inode->i_sb->s_bdev, BIO_MAX_VECS, REQ_OP_WRITE, GFP_NOFS); while (len) { unsigned int blocks_this_page = min(len, blocks_per_page); unsigned int bytes_this_page = blocks_this_page << blockbits; if (num_pages == 0) { fscrypt_set_bio_crypt_ctx(bio, inode, lblk, GFP_NOFS); bio->bi_iter.bi_sector = pblk << (blockbits - SECTOR_SHIFT); } ret = bio_add_page(bio, ZERO_PAGE(0), bytes_this_page, 0); if (WARN_ON_ONCE(ret != bytes_this_page)) { err = -EIO; goto out; } num_pages++; len -= blocks_this_page; lblk += blocks_this_page; pblk += blocks_this_page; if (num_pages == BIO_MAX_VECS || !len || !fscrypt_mergeable_bio(bio, inode, lblk)) { err = submit_bio_wait(bio); if (err) goto out; bio_reset(bio, inode->i_sb->s_bdev, REQ_OP_WRITE); num_pages = 0; } } out: bio_put(bio); return err; } /** * fscrypt_zeroout_range() - zero out a range of blocks in an encrypted file * @inode: the file's inode * @lblk: the first file logical block to zero out * @pblk: the first filesystem physical block to zero out * @len: number of blocks to zero out * * Zero out filesystem blocks in an encrypted regular file on-disk, i.e. write * ciphertext blocks which decrypt to the all-zeroes block. The blocks must be * both logically and physically contiguous. It's also assumed that the * filesystem only uses a single block device, ->s_bdev. * * Note that since each block uses a different IV, this involves writing a * different ciphertext to each block; we can't simply reuse the same one. * * Return: 0 on success; -errno on failure. */ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { const struct fscrypt_inode_info *ci = inode->i_crypt_info; const unsigned int du_bits = ci->ci_data_unit_bits; const unsigned int du_size = 1U << du_bits; const unsigned int du_per_page_bits = PAGE_SHIFT - du_bits; const unsigned int du_per_page = 1U << du_per_page_bits; u64 du_index = (u64)lblk << (inode->i_blkbits - du_bits); u64 du_remaining = (u64)len << (inode->i_blkbits - du_bits); sector_t sector = pblk << (inode->i_blkbits - SECTOR_SHIFT); struct page *pages[16]; /* write up to 16 pages at a time */ unsigned int nr_pages; unsigned int i; unsigned int offset; struct bio *bio; int ret, err; if (len == 0) return 0; if (fscrypt_inode_uses_inline_crypto(inode)) return fscrypt_zeroout_range_inline_crypt(inode, lblk, pblk, len); BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_VECS); nr_pages = min_t(u64, ARRAY_SIZE(pages), (du_remaining + du_per_page - 1) >> du_per_page_bits); /* * We need at least one page for ciphertext. Allocate the first one * from a mempool, with __GFP_DIRECT_RECLAIM set so that it can't fail. * * Any additional page allocations are allowed to fail, as they only * help performance, and waiting on the mempool for them could deadlock. */ for (i = 0; i < nr_pages; i++) { pages[i] = fscrypt_alloc_bounce_page(i == 0 ? GFP_NOFS : GFP_NOWAIT | __GFP_NOWARN); if (!pages[i]) break; } nr_pages = i; if (WARN_ON_ONCE(nr_pages <= 0)) return -EINVAL; /* This always succeeds since __GFP_DIRECT_RECLAIM is set. */ bio = bio_alloc(inode->i_sb->s_bdev, nr_pages, REQ_OP_WRITE, GFP_NOFS); do { bio->bi_iter.bi_sector = sector; i = 0; offset = 0; do { err = fscrypt_crypt_data_unit(ci, FS_ENCRYPT, du_index, ZERO_PAGE(0), pages[i], du_size, offset, GFP_NOFS); if (err) goto out; du_index++; sector += 1U << (du_bits - SECTOR_SHIFT); du_remaining--; offset += du_size; if (offset == PAGE_SIZE || du_remaining == 0) { ret = bio_add_page(bio, pages[i++], offset, 0); if (WARN_ON_ONCE(ret != offset)) { err = -EIO; goto out; } offset = 0; } } while (i != nr_pages && du_remaining != 0); err = submit_bio_wait(bio); if (err) goto out; bio_reset(bio, inode->i_sb->s_bdev, REQ_OP_WRITE); } while (du_remaining != 0); err = 0; out: bio_put(bio); for (i = 0; i < nr_pages; i++) fscrypt_free_bounce_page(pages[i]); return err; } EXPORT_SYMBOL(fscrypt_zeroout_range); |
| 66 66 1 10035 10035 2319 9561 9557 1 1 9559 9594 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> #include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_PAGE_ORDER 10 #else #define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) # define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \ get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK)) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false # define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } /* * Check whether a migratetype can be merged with another migratetype. * * It is only mergeable when it can fall back to other migratetypes for * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. */ static inline bool migratetype_is_mergeable(int mt) { return mt < MIGRATE_PCPTYPES; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) #define folio_migratetype(folio) \ get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \ MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; struct pglist_data; #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_EVENT_ITEMS }; #else #define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, #ifdef CONFIG_UNACCEPTED_MEMORY NR_UNACCEPTED, #endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the item should be printed in THPs (/proc/vmstat * currently prints number of anon, file and shmem THPs. But the item * is charged in pages). */ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || item == NR_SHMEM_PMDMAPPED || item == NR_FILE_PMDMAPPED; } /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define WORKINGSET_ANON 0 #define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { /* * An lruvec has many dirty pages backed by a congested BDI: * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. * It can be cleared by cgroup reclaim or kswapd. * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. * It can only be cleared by kswapd. * * Essentially, kswapd can unthrottle an lruvec throttled by cgroup * reclaim, but not vice versa. This only applies to the root cgroup. * The goal is to prevent cgroup reclaim on the root cgroup (e.g. * memory.reclaim) to unthrottle an unbalanced node (that was throttled * by kswapd). */ LRUVEC_CGROUP_CONGESTED, LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ /* * Evictable pages are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while * a page is on one of lrugen->folios[]. Otherwise it stores 0. * * A page is added to the youngest generation on faulting. The aging needs to * check the accessed bit at least twice before handing this page over to the * eviction. The first check takes care of the accessed bit set on the initial * fault; the second check makes sure this page hasn't been used since then. * This process, AKA second chance, requires a minimum of two generations, * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive * LRU, e.g., /proc/vmstat, these two generations are considered active; the * rest of generations, if they exist, are considered inactive. See * lru_gen_is_active(). * * PG_active is always cleared while a page is on one of lrugen->folios[] so * that the aging needs not to worry about it. And it's set again when a page * considered active is isolated for non-reclaiming purposes, e.g., migration. * See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits * in folio->flags. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* * Each generation is divided into multiple tiers. A page accessed N times * through file descriptors is in tier order_base_2(N). A page in the first tier * (N=0,1) is marked by PG_referenced unless it was faulted in through page * tables or read ahead. A page in any other tier (N>1) is marked by * PG_referenced and PG_workingset. This implies a minimum of two tiers is * supported without using additional bits in folio->flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, * comparisons of refaulted/(evicted+protected) from the first tier and the * rest infer whether pages accessed multiple times through file descriptors * are statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in * folio->flags. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H struct lruvec; struct page_vma_mapped_walk; #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) #ifdef CONFIG_LRU_GEN enum { LRU_GEN_ANON, LRU_GEN_FILE, }; enum { LRU_GEN_CORE, LRU_GEN_MM_WALK, LRU_GEN_NONLEAF_YOUNG, NR_LRU_GEN_CAPS }; #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) /* whether to keep historical stats from evicted generations */ #ifdef CONFIG_LRU_GEN_STATS #define NR_HIST_GENS MAX_NR_GENS #else #define NR_HIST_GENS 1U #endif /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are * stored in min_seq[] separately for anon and file types as clean file pages * can be evicted regardless of swap constraints. * * Normally anon and file min_seq are in sync. But if swapping is constrained, * e.g., out of swap space, file min_seq is allowed to advance and leave anon * min_seq behind. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; /* the first tier doesn't need protection, hence the minus one */ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; /* the memcg generation this lru_gen_folio belongs to */ u8 gen; /* the list segment this lru_gen_folio belongs to */ u8 seg; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_node list; }; enum { MM_LEAF_TOTAL, /* total leaf entries */ MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS }; /* double-buffering Bloom filters */ #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; /* where the last iteration ended before */ struct list_head *tail; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; /* max_seq from lru_gen_folio: can be out of date */ unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* to batch the mm stats */ int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; bool can_swap; bool force_scan; }; /* * For each node, memcgs are divided into two generations: the old and the * young. For each generation, memcgs are randomly sharded into multiple bins * to improve scalability. For each bin, the hlist_nulls is virtually divided * into three segments: the head, the tail and the default. * * An onlining memcg is added to the tail of a random bin in the old generation. * The eviction starts at the head of a random bin in the old generation. The * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes * the old generation, is incremented when all its bins become empty. * * There are four operations: * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; * 3. The first attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_TAIL; * 4. The second attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * * Notes: * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing * of their max_seq counters ensures the eventual fairness to all eligible * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). * 2. There are only two valid generations: old (seq) and young (seq+1). * MEMCG_NR_GENS is set to three so that when reading the generation counter * locklessly, a stale value (seq-1) does not wraparound to young. */ #define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { /* the per-node memcg generation counter */ unsigned long seq; /* each memcg has one lru_gen_folio per node */ unsigned long nr_memcgs[MEMCG_NR_GENS]; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; /* protects the above */ spinlock_t lock; }; void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); #else /* !CONFIG_LRU_GEN */ static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) { } static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } #endif /* CONFIG_LRU_GEN */ struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_folio lrugen; #ifdef CONFIG_LRU_GEN_WALKS_MMU /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, WMARK_PROMO, NR_WMARK }; /* * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) /* * Flags used in pcp->flags field. * * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the * previous page freeing. To avoid to drain PCP for an accident * high-order page freeing. * * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before * draining PCP for consecutive high-order pages freeing without * allocation if data cache slice of CPU is large enough. To reduce * zone lock contention and keep cache-hot pages reusing. */ #define PCPF_PREV_FREE_HIGH_ORDER BIT(0) #define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int high_min; /* min high watermark */ int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ u8 flags; /* protected by pcp->lock */ u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA u8 expire; /* When 0, remote pagesets are drained */ #endif short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; } ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; s8 stat_threshold; #endif #ifdef CONFIG_NUMA /* * Low priority inaccurate counters that are only folded * on demand. Use a large type to avoid the overhead of * folding during refresh_cpu_vm_stats. */ unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Therefore, we do not allow * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and * faulted, they come from the right zone right away. However, it is * still possible that address space already has pages in * ZONE_MOVABLE at the time when pages are pinned (i.e. user has * touches that memory before pinning). In such case we migrate them * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. * 7. Memory-hotplug: when using memmap_on_memory and onlining the * memory to the MOVABLE zone, the vmemmap pages are also placed in * such zone. Such pages cannot be really moved around as they are * self-stored in the range, but they are treated as movable when * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pages __percpu *per_cpu_pageset; struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access */ int pageset_high_min; int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * present_early_pages is present pages existing within the zone * located on memory available since early boot, excluding hotplugged * memory. * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * cma pages is present pages that are assigned for CMA use * (MIGRATE_CMA). * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/done(). Any reader who can't tolerant drift of * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; #if defined(CONFIG_MEMORY_HOTPLUG) unsigned long present_early_pages; #endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[NR_PAGE_ORDERS]; #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; #endif /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_cma_pages(struct zone *zone) { #ifdef CONFIG_CMA return zone->cma_pages; #else return 0; #endif } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } #ifndef BUILD_VDSO32_64 /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) #define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) #define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } static inline enum zone_type folio_zonenum(const struct folio *folio) { return page_zonenum(&folio->page); } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different * pgmaps. Otherwise getting the pgmap of a given segment is not possible * without scanning the entire segment. This helper returns true either if * both pages are not zone device pages or both pages are zone device pages * with the same pgmap. */ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { if (is_zone_device_page(a) != is_zone_device_page(b)) return false; if (!is_zone_device_page(a)) return true; return a->pgmap == b->pgmap; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { return true; } #endif static inline bool folio_is_zone_device(const struct folio *folio) { return is_zone_device_page(&folio->page); } static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } static inline bool folio_is_zone_movable(const struct folio *folio) { return folio_zonenum(folio) == ZONE_MOVABLE; } #endif /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; /* * The array of struct pages for flatmem. * It must be declared for SPARSEMEM as well because there are configurations * that rely on that. */ extern struct page *mem_map; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. */ struct memory_failure_stats { /* * Number of raw pages poisoned. * Cases not accounted: memory outside kernel control, offline page, * arch-specific memory_failure (SGX), hwpoison_filter() filtered * error events, and unpoison actions from hwpoison_unpoison. */ unsigned long total; /* * Recovery results of poisoned raw pages handled by memory_failure, * in sync with mf_result. * total = ignored + failed + delayed + recovered. * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. */ unsigned long ignored; unsigned long failed; unsigned long delayed; unsigned long recovered; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; /* workqueues for throttling reclaim for different reasons. */ wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ #ifdef CONFIG_MEMORY_HOTPLUG struct mutex kswapd_lock; #endif struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; /* promote threshold in ms */ unsigned int nbp_threshold; /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif #ifdef CONFIG_MEMORY_FAILURE struct memory_failure_stats mf_stats; #endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE static inline bool zone_is_zone_device(struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else static inline bool zone_is_zone_device(struct zone *zone) { return false; } #endif /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } #else /* CONFIG_NUMA */ #include <asm/mmzone.h> #endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z: The cursor used as a starting point for the search * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. * * Return: the next zone at or below highest_zoneidx within the allowed * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist: The zonelist to search for a suitable zone * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. * * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone: The current zone in the iterator * @z: The current pointer within zonelist->_zonerefs being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = z->zone; \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone: The current zone in the iterator * @z: The current pointer within zonelist->zones being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!z->zone) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available on all architectures. * However, we can exceed 6 bits on some other architectures except * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available * with the worst case of 64K pages on arm64) if we make sure the * exceeded bit is not applicable to powerpc. */ enum { SECTION_MARKED_PRESENT_BIT, SECTION_HAS_MEM_MAP_BIT, SECTION_IS_ONLINE_BIT, SECTION_IS_EARLY_BIT, #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif SECTION_MAP_LAST_BIT, }; #define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) #define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) #define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) #define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else static inline int online_device_section(struct mem_section *section) { return 0; } #endif static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN * @pfn: the page frame number to check * * Check if there is a valid memory map entry aka struct page for the @pfn. * Note, that availability of the memory map entry does not imply that * there is actual usable memory at that @pfn. The struct page may * represent a hole or an unusable page frame. * * Return: 1 for PFNs that have memory map entries and 0 otherwise */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the * pfn. Else it might lead to false positives when * some of the upper bits are set, but the lower bits * match a valid pfn. */ if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) return 0; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 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 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"); |
| 825 825 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SHA-256, as specified in * http://csrc.nist.gov/groups/STM/cavp/documents/shs/sha256-384-512.pdf * * SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>. * * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com> * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk> * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2014 Red Hat Inc. */ #include <asm/unaligned.h> #include <crypto/sha256_base.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/string.h> static const u32 SHA256_K[] = { 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da, 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070, 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2, }; static inline u32 Ch(u32 x, u32 y, u32 z) { return z ^ (x & (y ^ z)); } static inline u32 Maj(u32 x, u32 y, u32 z) { return (x & y) | (z & (x | y)); } #define e0(x) (ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22)) #define e1(x) (ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25)) #define s0(x) (ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3)) #define s1(x) (ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10)) static inline void LOAD_OP(int I, u32 *W, const u8 *input) { W[I] = get_unaligned_be32((__u32 *)input + I); } static inline void BLEND_OP(int I, u32 *W) { W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16]; } #define SHA256_ROUND(i, a, b, c, d, e, f, g, h) do { \ u32 t1, t2; \ t1 = h + e1(e) + Ch(e, f, g) + SHA256_K[i] + W[i]; \ t2 = e0(a) + Maj(a, b, c); \ d += t1; \ h = t1 + t2; \ } while (0) static void sha256_transform(u32 *state, const u8 *input, u32 *W) { u32 a, b, c, d, e, f, g, h; int i; /* load the input */ for (i = 0; i < 16; i += 8) { LOAD_OP(i + 0, W, input); LOAD_OP(i + 1, W, input); LOAD_OP(i + 2, W, input); LOAD_OP(i + 3, W, input); LOAD_OP(i + 4, W, input); LOAD_OP(i + 5, W, input); LOAD_OP(i + 6, W, input); LOAD_OP(i + 7, W, input); } /* now blend */ for (i = 16; i < 64; i += 8) { BLEND_OP(i + 0, W); BLEND_OP(i + 1, W); BLEND_OP(i + 2, W); BLEND_OP(i + 3, W); BLEND_OP(i + 4, W); BLEND_OP(i + 5, W); BLEND_OP(i + 6, W); BLEND_OP(i + 7, W); } /* load the state into our registers */ a = state[0]; b = state[1]; c = state[2]; d = state[3]; e = state[4]; f = state[5]; g = state[6]; h = state[7]; /* now iterate */ for (i = 0; i < 64; i += 8) { SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h); SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g); SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f); SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e); SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d); SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c); SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b); SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a); } state[0] += a; state[1] += b; state[2] += c; state[3] += d; state[4] += e; state[5] += f; state[6] += g; state[7] += h; } static void sha256_transform_blocks(struct sha256_state *sctx, const u8 *input, int blocks) { u32 W[64]; do { sha256_transform(sctx->state, input, W); input += SHA256_BLOCK_SIZE; } while (--blocks); memzero_explicit(W, sizeof(W)); } void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len) { lib_sha256_base_do_update(sctx, data, len, sha256_transform_blocks); } EXPORT_SYMBOL(sha256_update); static void __sha256_final(struct sha256_state *sctx, u8 *out, int digest_size) { lib_sha256_base_do_finalize(sctx, sha256_transform_blocks); lib_sha256_base_finish(sctx, out, digest_size); } void sha256_final(struct sha256_state *sctx, u8 *out) { __sha256_final(sctx, out, 32); } EXPORT_SYMBOL(sha256_final); void sha224_final(struct sha256_state *sctx, u8 *out) { __sha256_final(sctx, out, 28); } EXPORT_SYMBOL(sha224_final); void sha256(const u8 *data, unsigned int len, u8 *out) { struct sha256_state sctx; sha256_init(&sctx); sha256_update(&sctx, data, len); sha256_final(&sctx, out); } EXPORT_SYMBOL(sha256); MODULE_DESCRIPTION("SHA-256 Algorithm"); MODULE_LICENSE("GPL"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ #include <linux/netlink.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> struct sk_buff; struct nlmsghdr; struct sock; struct sock_diag_handler { struct module *owner; __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh); }; int sock_diag_register(const struct sock_diag_handler *h); void sock_diag_unregister(const struct sock_diag_handler *h); struct sock_diag_inet_compat { struct module *owner; int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh); }; void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr); void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr); u64 __sock_gen_cookie(struct sock *sk); static inline u64 sock_gen_cookie(struct sock *sk) { u64 cookie; preempt_disable(); cookie = __sock_gen_cookie(sk); preempt_enable(); return cookie; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); static inline enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) { switch (sk->sk_family) { case AF_INET: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET_UDP_DESTROY; default: return SKNLGRP_NONE; } case AF_INET6: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET6_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET6_UDP_DESTROY; default: return SKNLGRP_NONE; } default: return SKNLGRP_NONE; } } static inline bool sock_diag_has_destroy_listeners(const struct sock *sk) { const struct net *n = sock_net(sk); const enum sknetlink_groups group = sock_diag_destroy_group(sk); return group != SKNLGRP_NONE && n->diag_nlsk && netlink_has_listeners(n->diag_nlsk, group); } void sock_diag_broadcast_destroy(struct sock *sk); int sock_diag_destroy(struct sock *sk, int err); #endif |
| 558 560 128 560 561 426 426 555 557 382 382 5 381 379 383 117 117 117 10 10 10 416 417 416 2 13 13 13 2 2 2 2 109 410 413 413 413 386 127 125 127 127 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * Copyright (c) 2018 Red Hat, Inc. * All rights reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_btree.h" #include "xfs_alloc_btree.h" #include "xfs_rmap_btree.h" #include "xfs_alloc.h" #include "xfs_ialloc.h" #include "xfs_rmap.h" #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_health.h" #include "xfs_error.h" #include "xfs_bmap.h" #include "xfs_defer.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_trace.h" #include "xfs_inode.h" #include "xfs_icache.h" /* * Passive reference counting access wrappers to the perag structures. If the * per-ag structure is to be freed, the freeing code is responsible for cleaning * up objects with passive references before freeing the structure. This is * things like cached buffers. */ struct xfs_perag * xfs_perag_get( struct xfs_mount *mp, xfs_agnumber_t agno) { struct xfs_perag *pag; rcu_read_lock(); pag = radix_tree_lookup(&mp->m_perag_tree, agno); if (pag) { trace_xfs_perag_get(pag, _RET_IP_); ASSERT(atomic_read(&pag->pag_ref) >= 0); atomic_inc(&pag->pag_ref); } rcu_read_unlock(); return pag; } /* * search from @first to find the next perag with the given tag set. */ struct xfs_perag * xfs_perag_get_tag( struct xfs_mount *mp, xfs_agnumber_t first, unsigned int tag) { struct xfs_perag *pag; int found; rcu_read_lock(); found = radix_tree_gang_lookup_tag(&mp->m_perag_tree, (void **)&pag, first, 1, tag); if (found <= 0) { rcu_read_unlock(); return NULL; } trace_xfs_perag_get_tag(pag, _RET_IP_); atomic_inc(&pag->pag_ref); rcu_read_unlock(); return pag; } /* Get a passive reference to the given perag. */ struct xfs_perag * xfs_perag_hold( struct xfs_perag *pag) { ASSERT(atomic_read(&pag->pag_ref) > 0 || atomic_read(&pag->pag_active_ref) > 0); trace_xfs_perag_hold(pag, _RET_IP_); atomic_inc(&pag->pag_ref); return pag; } void xfs_perag_put( struct xfs_perag *pag) { trace_xfs_perag_put(pag, _RET_IP_); ASSERT(atomic_read(&pag->pag_ref) > 0); atomic_dec(&pag->pag_ref); } /* * Active references for perag structures. This is for short term access to the * per ag structures for walking trees or accessing state. If an AG is being * shrunk or is offline, then this will fail to find that AG and return NULL * instead. */ struct xfs_perag * xfs_perag_grab( struct xfs_mount *mp, xfs_agnumber_t agno) { struct xfs_perag *pag; rcu_read_lock(); pag = radix_tree_lookup(&mp->m_perag_tree, agno); if (pag) { trace_xfs_perag_grab(pag, _RET_IP_); if (!atomic_inc_not_zero(&pag->pag_active_ref)) pag = NULL; } rcu_read_unlock(); return pag; } /* * search from @first to find the next perag with the given tag set. */ struct xfs_perag * xfs_perag_grab_tag( struct xfs_mount *mp, xfs_agnumber_t first, int tag) { struct xfs_perag *pag; int found; rcu_read_lock(); found = radix_tree_gang_lookup_tag(&mp->m_perag_tree, (void **)&pag, first, 1, tag); if (found <= 0) { rcu_read_unlock(); return NULL; } trace_xfs_perag_grab_tag(pag, _RET_IP_); if (!atomic_inc_not_zero(&pag->pag_active_ref)) pag = NULL; rcu_read_unlock(); return pag; } void xfs_perag_rele( struct xfs_perag *pag) { trace_xfs_perag_rele(pag, _RET_IP_); if (atomic_dec_and_test(&pag->pag_active_ref)) wake_up(&pag->pag_active_wq); } /* * xfs_initialize_perag_data * * Read in each per-ag structure so we can count up the number of * allocated inodes, free inodes and used filesystem blocks as this * information is no longer persistent in the superblock. Once we have * this information, write it into the in-core superblock structure. */ int xfs_initialize_perag_data( struct xfs_mount *mp, xfs_agnumber_t agcount) { xfs_agnumber_t index; struct xfs_perag *pag; struct xfs_sb *sbp = &mp->m_sb; uint64_t ifree = 0; uint64_t ialloc = 0; uint64_t bfree = 0; uint64_t bfreelst = 0; uint64_t btree = 0; uint64_t fdblocks; int error = 0; for (index = 0; index < agcount; index++) { /* * Read the AGF and AGI buffers to populate the per-ag * structures for us. */ pag = xfs_perag_get(mp, index); error = xfs_alloc_read_agf(pag, NULL, 0, NULL); if (!error) error = xfs_ialloc_read_agi(pag, NULL, 0, NULL); if (error) { xfs_perag_put(pag); return error; } ifree += pag->pagi_freecount; ialloc += pag->pagi_count; bfree += pag->pagf_freeblks; bfreelst += pag->pagf_flcount; btree += pag->pagf_btreeblks; xfs_perag_put(pag); } fdblocks = bfree + bfreelst + btree; /* * If the new summary counts are obviously incorrect, fail the * mount operation because that implies the AGFs are also corrupt. * Clear FS_COUNTERS so that we don't unmount with a dirty log, which * will prevent xfs_repair from fixing anything. */ if (fdblocks > sbp->sb_dblocks || ifree > ialloc) { xfs_alert(mp, "AGF corruption. Please run xfs_repair."); xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS); error = -EFSCORRUPTED; goto out; } /* Overwrite incore superblock counters with just-read data */ spin_lock(&mp->m_sb_lock); sbp->sb_ifree = ifree; sbp->sb_icount = ialloc; sbp->sb_fdblocks = fdblocks; spin_unlock(&mp->m_sb_lock); xfs_reinit_percpu_counters(mp); out: xfs_fs_mark_healthy(mp, XFS_SICK_FS_COUNTERS); return error; } STATIC void __xfs_free_perag( struct rcu_head *head) { struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head); ASSERT(!delayed_work_pending(&pag->pag_blockgc_work)); kfree(pag); } /* * Free up the per-ag resources associated with the mount structure. */ void xfs_free_perag( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t agno; for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { spin_lock(&mp->m_perag_lock); pag = radix_tree_delete(&mp->m_perag_tree, agno); spin_unlock(&mp->m_perag_lock); ASSERT(pag); XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0); xfs_defer_drain_free(&pag->pag_intents_drain); cancel_delayed_work_sync(&pag->pag_blockgc_work); xfs_buf_cache_destroy(&pag->pag_bcache); /* drop the mount's active reference */ xfs_perag_rele(pag); XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_active_ref) != 0); call_rcu(&pag->rcu_head, __xfs_free_perag); } } /* Find the size of the AG, in blocks. */ static xfs_agblock_t __xfs_ag_block_count( struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agnumber_t agcount, xfs_rfsblock_t dblocks) { ASSERT(agno < agcount); if (agno < agcount - 1) return mp->m_sb.sb_agblocks; return dblocks - (agno * mp->m_sb.sb_agblocks); } xfs_agblock_t xfs_ag_block_count( struct xfs_mount *mp, xfs_agnumber_t agno) { return __xfs_ag_block_count(mp, agno, mp->m_sb.sb_agcount, mp->m_sb.sb_dblocks); } /* Calculate the first and last possible inode number in an AG. */ static void __xfs_agino_range( struct xfs_mount *mp, xfs_agblock_t eoag, xfs_agino_t *first, xfs_agino_t *last) { xfs_agblock_t bno; /* * Calculate the first inode, which will be in the first * cluster-aligned block after the AGFL. */ bno = round_up(XFS_AGFL_BLOCK(mp) + 1, M_IGEO(mp)->cluster_align); *first = XFS_AGB_TO_AGINO(mp, bno); /* * Calculate the last inode, which will be at the end of the * last (aligned) cluster that can be allocated in the AG. */ bno = round_down(eoag, M_IGEO(mp)->cluster_align); *last = XFS_AGB_TO_AGINO(mp, bno) - 1; } void xfs_agino_range( struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agino_t *first, xfs_agino_t *last) { return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last); } /* * Free perag within the specified AG range, it is only used to free unused * perags under the error handling path. */ void xfs_free_unused_perag_range( struct xfs_mount *mp, xfs_agnumber_t agstart, xfs_agnumber_t agend) { struct xfs_perag *pag; xfs_agnumber_t index; for (index = agstart; index < agend; index++) { spin_lock(&mp->m_perag_lock); pag = radix_tree_delete(&mp->m_perag_tree, index); spin_unlock(&mp->m_perag_lock); if (!pag) break; xfs_buf_cache_destroy(&pag->pag_bcache); xfs_defer_drain_free(&pag->pag_intents_drain); kfree(pag); } } int xfs_initialize_perag( struct xfs_mount *mp, xfs_agnumber_t agcount, xfs_rfsblock_t dblocks, xfs_agnumber_t *maxagi) { struct xfs_perag *pag; xfs_agnumber_t index; xfs_agnumber_t first_initialised = NULLAGNUMBER; int error; /* * Walk the current per-ag tree so we don't try to initialise AGs * that already exist (growfs case). Allocate and insert all the * AGs we don't find ready for initialisation. */ for (index = 0; index < agcount; index++) { pag = xfs_perag_get(mp, index); if (pag) { xfs_perag_put(pag); continue; } pag = kzalloc(sizeof(*pag), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!pag) { error = -ENOMEM; goto out_unwind_new_pags; } pag->pag_agno = index; pag->pag_mount = mp; error = radix_tree_preload(GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (error) goto out_free_pag; spin_lock(&mp->m_perag_lock); if (radix_tree_insert(&mp->m_perag_tree, index, pag)) { WARN_ON_ONCE(1); spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); error = -EEXIST; goto out_free_pag; } spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); #ifdef __KERNEL__ /* Place kernel structure only init below this point. */ spin_lock_init(&pag->pag_ici_lock); spin_lock_init(&pag->pagb_lock); spin_lock_init(&pag->pag_state_lock); INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); xfs_defer_drain_init(&pag->pag_intents_drain); init_waitqueue_head(&pag->pagb_wait); init_waitqueue_head(&pag->pag_active_wq); pag->pagb_count = 0; pag->pagb_tree = RB_ROOT; xfs_hooks_init(&pag->pag_rmap_update_hooks); #endif /* __KERNEL__ */ error = xfs_buf_cache_init(&pag->pag_bcache); if (error) goto out_remove_pag; /* Active ref owned by mount indicates AG is online. */ atomic_set(&pag->pag_active_ref, 1); /* first new pag is fully initialized */ if (first_initialised == NULLAGNUMBER) first_initialised = index; /* * Pre-calculated geometry */ pag->block_count = __xfs_ag_block_count(mp, index, agcount, dblocks); pag->min_block = XFS_AGFL_BLOCK(mp); __xfs_agino_range(mp, pag->block_count, &pag->agino_min, &pag->agino_max); } index = xfs_set_inode_alloc(mp, agcount); if (maxagi) *maxagi = index; mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp); return 0; out_remove_pag: xfs_defer_drain_free(&pag->pag_intents_drain); spin_lock(&mp->m_perag_lock); radix_tree_delete(&mp->m_perag_tree, index); spin_unlock(&mp->m_perag_lock); out_free_pag: kfree(pag); out_unwind_new_pags: /* unwind any prior newly initialized pags */ xfs_free_unused_perag_range(mp, first_initialised, agcount); return error; } static int xfs_get_aghdr_buf( struct xfs_mount *mp, xfs_daddr_t blkno, size_t numblks, struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { struct xfs_buf *bp; int error; error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0, &bp); if (error) return error; bp->b_maps[0].bm_bn = blkno; bp->b_ops = ops; *bpp = bp; return 0; } /* * Generic btree root block init function */ static void xfs_btroot_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno); } /* Finish initializing a free space btree. */ static void xfs_freesp_init_recs( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { struct xfs_alloc_rec *arec; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); if (xfs_ag_contains_log(mp, id->agno)) { struct xfs_alloc_rec *nrec; xfs_agblock_t start = XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart); ASSERT(start >= mp->m_ag_prealloc_blocks); if (start != mp->m_ag_prealloc_blocks) { /* * Modify first record to pad stripe align of log and * bump the record count. */ arec->ar_blockcount = cpu_to_be32(start - mp->m_ag_prealloc_blocks); be16_add_cpu(&block->bb_numrecs, 1); nrec = arec + 1; /* * Insert second record at start of internal log * which then gets trimmed. */ nrec->ar_startblock = cpu_to_be32( be32_to_cpu(arec->ar_startblock) + be32_to_cpu(arec->ar_blockcount)); arec = nrec; } /* * Change record start to after the internal log */ be32_add_cpu(&arec->ar_startblock, mp->m_sb.sb_logblocks); } /* * Calculate the block count of this record; if it is nonzero, * increment the record count. */ arec->ar_blockcount = cpu_to_be32(id->agsize - be32_to_cpu(arec->ar_startblock)); if (arec->ar_blockcount) be16_add_cpu(&block->bb_numrecs, 1); } /* * bnobt/cntbt btree root block init functions */ static void xfs_bnoroot_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno); xfs_freesp_init_recs(mp, bp, id); } /* * Reverse map root block init */ static void xfs_rmaproot_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_rmap_rec *rrec; xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno); /* * mark the AG header regions as static metadata The BNO * btree block is the first block after the headers, so * it's location defines the size of region the static * metadata consumes. * * Note: unlike mkfs, we never have to account for log * space when growing the data regions */ rrec = XFS_RMAP_REC_ADDR(block, 1); rrec->rm_startblock = 0; rrec->rm_blockcount = cpu_to_be32(XFS_BNO_BLOCK(mp)); rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_FS); rrec->rm_offset = 0; /* account freespace btree root blocks */ rrec = XFS_RMAP_REC_ADDR(block, 2); rrec->rm_startblock = cpu_to_be32(XFS_BNO_BLOCK(mp)); rrec->rm_blockcount = cpu_to_be32(2); rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG); rrec->rm_offset = 0; /* account inode btree root blocks */ rrec = XFS_RMAP_REC_ADDR(block, 3); rrec->rm_startblock = cpu_to_be32(XFS_IBT_BLOCK(mp)); rrec->rm_blockcount = cpu_to_be32(XFS_RMAP_BLOCK(mp) - XFS_IBT_BLOCK(mp)); rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_INOBT); rrec->rm_offset = 0; /* account for rmap btree root */ rrec = XFS_RMAP_REC_ADDR(block, 4); rrec->rm_startblock = cpu_to_be32(XFS_RMAP_BLOCK(mp)); rrec->rm_blockcount = cpu_to_be32(1); rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_AG); rrec->rm_offset = 0; /* account for refc btree root */ if (xfs_has_reflink(mp)) { rrec = XFS_RMAP_REC_ADDR(block, 5); rrec->rm_startblock = cpu_to_be32(xfs_refc_block(mp)); rrec->rm_blockcount = cpu_to_be32(1); rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_REFC); rrec->rm_offset = 0; be16_add_cpu(&block->bb_numrecs, 1); } /* account for the log space */ if (xfs_ag_contains_log(mp, id->agno)) { rrec = XFS_RMAP_REC_ADDR(block, be16_to_cpu(block->bb_numrecs) + 1); rrec->rm_startblock = cpu_to_be32( XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart)); rrec->rm_blockcount = cpu_to_be32(mp->m_sb.sb_logblocks); rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_LOG); rrec->rm_offset = 0; be16_add_cpu(&block->bb_numrecs, 1); } } /* * Initialise new secondary superblocks with the pre-grow geometry, but mark * them as "in progress" so we know they haven't yet been activated. This will * get cleared when the update with the new geometry information is done after * changes to the primary are committed. This isn't strictly necessary, but we * get it for free with the delayed buffer write lists and it means we can tell * if a grow operation didn't complete properly after the fact. */ static void xfs_sbblock_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { struct xfs_dsb *dsb = bp->b_addr; xfs_sb_to_disk(dsb, &mp->m_sb); dsb->sb_inprogress = 1; } static void xfs_agfblock_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { struct xfs_agf *agf = bp->b_addr; xfs_extlen_t tmpsize; agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC); agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION); agf->agf_seqno = cpu_to_be32(id->agno); agf->agf_length = cpu_to_be32(id->agsize); agf->agf_bno_root = cpu_to_be32(XFS_BNO_BLOCK(mp)); agf->agf_cnt_root = cpu_to_be32(XFS_CNT_BLOCK(mp)); agf->agf_bno_level = cpu_to_be32(1); agf->agf_cnt_level = cpu_to_be32(1); if (xfs_has_rmapbt(mp)) { agf->agf_rmap_root = cpu_to_be32(XFS_RMAP_BLOCK(mp)); agf->agf_rmap_level = cpu_to_be32(1); agf->agf_rmap_blocks = cpu_to_be32(1); } agf->agf_flfirst = cpu_to_be32(1); agf->agf_fllast = 0; agf->agf_flcount = 0; tmpsize = id->agsize - mp->m_ag_prealloc_blocks; agf->agf_freeblks = cpu_to_be32(tmpsize); agf->agf_longest = cpu_to_be32(tmpsize); if (xfs_has_crc(mp)) uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid); if (xfs_has_reflink(mp)) { agf->agf_refcount_root = cpu_to_be32( xfs_refc_block(mp)); agf->agf_refcount_level = cpu_to_be32(1); agf->agf_refcount_blocks = cpu_to_be32(1); } if (xfs_ag_contains_log(mp, id->agno)) { int64_t logblocks = mp->m_sb.sb_logblocks; be32_add_cpu(&agf->agf_freeblks, -logblocks); agf->agf_longest = cpu_to_be32(id->agsize - XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart) - logblocks); } } static void xfs_agflblock_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { struct xfs_agfl *agfl = XFS_BUF_TO_AGFL(bp); __be32 *agfl_bno; int bucket; if (xfs_has_crc(mp)) { agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC); agfl->agfl_seqno = cpu_to_be32(id->agno); uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid); } agfl_bno = xfs_buf_to_agfl_bno(bp); for (bucket = 0; bucket < xfs_agfl_size(mp); bucket++) agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK); } static void xfs_agiblock_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { struct xfs_agi *agi = bp->b_addr; int bucket; agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC); agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION); agi->agi_seqno = cpu_to_be32(id->agno); agi->agi_length = cpu_to_be32(id->agsize); agi->agi_count = 0; agi->agi_root = cpu_to_be32(XFS_IBT_BLOCK(mp)); agi->agi_level = cpu_to_be32(1); agi->agi_freecount = 0; agi->agi_newino = cpu_to_be32(NULLAGINO); agi->agi_dirino = cpu_to_be32(NULLAGINO); if (xfs_has_crc(mp)) uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid); if (xfs_has_finobt(mp)) { agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp)); agi->agi_free_level = cpu_to_be32(1); } for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO); if (xfs_has_inobtcounts(mp)) { agi->agi_iblocks = cpu_to_be32(1); if (xfs_has_finobt(mp)) agi->agi_fblocks = cpu_to_be32(1); } } typedef void (*aghdr_init_work_f)(struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id); static int xfs_ag_init_hdr( struct xfs_mount *mp, struct aghdr_init_data *id, aghdr_init_work_f work, const struct xfs_buf_ops *ops) { struct xfs_buf *bp; int error; error = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, &bp, ops); if (error) return error; (*work)(mp, bp, id); xfs_buf_delwri_queue(bp, &id->buffer_list); xfs_buf_relse(bp); return 0; } struct xfs_aghdr_grow_data { xfs_daddr_t daddr; size_t numblks; const struct xfs_buf_ops *ops; aghdr_init_work_f work; const struct xfs_btree_ops *bc_ops; bool need_init; }; /* * Prepare new AG headers to be written to disk. We use uncached buffers here, * as it is assumed these new AG headers are currently beyond the currently * valid filesystem address space. Using cached buffers would trip over EOFS * corruption detection alogrithms in the buffer cache lookup routines. * * This is a non-transactional function, but the prepared buffers are added to a * delayed write buffer list supplied by the caller so they can submit them to * disk and wait on them as required. */ int xfs_ag_init_headers( struct xfs_mount *mp, struct aghdr_init_data *id) { struct xfs_aghdr_grow_data aghdr_data[] = { { /* SB */ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_SB_DADDR), .numblks = XFS_FSS_TO_BB(mp, 1), .ops = &xfs_sb_buf_ops, .work = &xfs_sbblock_init, .need_init = true }, { /* AGF */ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGF_DADDR(mp)), .numblks = XFS_FSS_TO_BB(mp, 1), .ops = &xfs_agf_buf_ops, .work = &xfs_agfblock_init, .need_init = true }, { /* AGFL */ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGFL_DADDR(mp)), .numblks = XFS_FSS_TO_BB(mp, 1), .ops = &xfs_agfl_buf_ops, .work = &xfs_agflblock_init, .need_init = true }, { /* AGI */ .daddr = XFS_AG_DADDR(mp, id->agno, XFS_AGI_DADDR(mp)), .numblks = XFS_FSS_TO_BB(mp, 1), .ops = &xfs_agi_buf_ops, .work = &xfs_agiblock_init, .need_init = true }, { /* BNO root block */ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_BNO_BLOCK(mp)), .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_bnobt_buf_ops, .work = &xfs_bnoroot_init, .bc_ops = &xfs_bnobt_ops, .need_init = true }, { /* CNT root block */ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)), .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_cntbt_buf_ops, .work = &xfs_bnoroot_init, .bc_ops = &xfs_cntbt_ops, .need_init = true }, { /* INO root block */ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_IBT_BLOCK(mp)), .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_inobt_buf_ops, .work = &xfs_btroot_init, .bc_ops = &xfs_inobt_ops, .need_init = true }, { /* FINO root block */ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_FIBT_BLOCK(mp)), .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_finobt_buf_ops, .work = &xfs_btroot_init, .bc_ops = &xfs_finobt_ops, .need_init = xfs_has_finobt(mp) }, { /* RMAP root block */ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_RMAP_BLOCK(mp)), .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_rmapbt_buf_ops, .work = &xfs_rmaproot_init, .bc_ops = &xfs_rmapbt_ops, .need_init = xfs_has_rmapbt(mp) }, { /* REFC root block */ .daddr = XFS_AGB_TO_DADDR(mp, id->agno, xfs_refc_block(mp)), .numblks = BTOBB(mp->m_sb.sb_blocksize), .ops = &xfs_refcountbt_buf_ops, .work = &xfs_btroot_init, .bc_ops = &xfs_refcountbt_ops, .need_init = xfs_has_reflink(mp) }, { /* NULL terminating block */ .daddr = XFS_BUF_DADDR_NULL, } }; struct xfs_aghdr_grow_data *dp; int error = 0; /* Account for AG free space in new AG */ id->nfree += id->agsize - mp->m_ag_prealloc_blocks; for (dp = &aghdr_data[0]; dp->daddr != XFS_BUF_DADDR_NULL; dp++) { if (!dp->need_init) continue; id->daddr = dp->daddr; id->numblks = dp->numblks; id->bc_ops = dp->bc_ops; error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops); if (error) break; } return error; } int xfs_ag_shrink_space( struct xfs_perag *pag, struct xfs_trans **tpp, xfs_extlen_t delta) { struct xfs_mount *mp = pag->pag_mount; struct xfs_alloc_arg args = { .tp = *tpp, .mp = mp, .pag = pag, .minlen = delta, .maxlen = delta, .oinfo = XFS_RMAP_OINFO_SKIP_UPDATE, .resv = XFS_AG_RESV_NONE, .prod = 1 }; struct xfs_buf *agibp, *agfbp; struct xfs_agi *agi; struct xfs_agf *agf; xfs_agblock_t aglen; int error, err2; ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1); error = xfs_ialloc_read_agi(pag, *tpp, 0, &agibp); if (error) return error; agi = agibp->b_addr; error = xfs_alloc_read_agf(pag, *tpp, 0, &agfbp); if (error) return error; agf = agfbp->b_addr; aglen = be32_to_cpu(agi->agi_length); /* some extra paranoid checks before we shrink the ag */ if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length)) { xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF); return -EFSCORRUPTED; } if (delta >= aglen) return -EINVAL; /* * Make sure that the last inode cluster cannot overlap with the new * end of the AG, even if it's sparse. */ error = xfs_ialloc_check_shrink(pag, *tpp, agibp, aglen - delta); if (error) return error; /* * Disable perag reservations so it doesn't cause the allocation request * to fail. We'll reestablish reservation before we return. */ xfs_ag_resv_free(pag); /* internal log shouldn't also show up in the free space btrees */ error = xfs_alloc_vextent_exact_bno(&args, XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta)); if (!error && args.agbno == NULLAGBLOCK) error = -ENOSPC; if (error) { /* * If extent allocation fails, need to roll the transaction to * ensure that the AGFL fixup has been committed anyway. * * We need to hold the AGF across the roll to ensure nothing can * access the AG for allocation until the shrink is fully * cleaned up. And due to the resetting of the AG block * reservation space needing to lock the AGI, we also have to * hold that so we don't get AGI/AGF lock order inversions in * the error handling path. */ xfs_trans_bhold(*tpp, agfbp); xfs_trans_bhold(*tpp, agibp); err2 = xfs_trans_roll(tpp); if (err2) return err2; xfs_trans_bjoin(*tpp, agfbp); xfs_trans_bjoin(*tpp, agibp); goto resv_init_out; } /* * if successfully deleted from freespace btrees, need to confirm * per-AG reservation works as expected. */ be32_add_cpu(&agi->agi_length, -delta); be32_add_cpu(&agf->agf_length, -delta); err2 = xfs_ag_resv_init(pag, *tpp); if (err2) { be32_add_cpu(&agi->agi_length, delta); be32_add_cpu(&agf->agf_length, delta); if (err2 != -ENOSPC) goto resv_err; err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, XFS_AG_RESV_NONE, XFS_FREE_EXTENT_SKIP_DISCARD); if (err2) goto resv_err; /* * Roll the transaction before trying to re-init the per-ag * reservation. The new transaction is clean so it will cancel * without any side effects. */ error = xfs_defer_finish(tpp); if (error) return error; error = -ENOSPC; goto resv_init_out; } /* Update perag geometry */ pag->block_count -= delta; __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min, &pag->agino_max); xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH); xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH); return 0; resv_init_out: err2 = xfs_ag_resv_init(pag, *tpp); if (!err2) return error; resv_err: xfs_warn(mp, "Error %d reserving per-AG metadata reserve pool.", err2); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return err2; } /* * Extent the AG indicated by the @id by the length passed in */ int xfs_ag_extend_space( struct xfs_perag *pag, struct xfs_trans *tp, xfs_extlen_t len) { struct xfs_buf *bp; struct xfs_agi *agi; struct xfs_agf *agf; int error; ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1); error = xfs_ialloc_read_agi(pag, tp, 0, &bp); if (error) return error; agi = bp->b_addr; be32_add_cpu(&agi->agi_length, len); xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH); /* * Change agf length. */ error = xfs_alloc_read_agf(pag, tp, 0, &bp); if (error) return error; agf = bp->b_addr; be32_add_cpu(&agf->agf_length, len); ASSERT(agf->agf_length == agi->agi_length); xfs_alloc_log_agf(tp, bp, XFS_AGF_LENGTH); /* * Free the new space. * * XFS_RMAP_OINFO_SKIP_UPDATE is used here to tell the rmap btree that * this doesn't actually exist in the rmap btree. */ error = xfs_rmap_free(tp, bp, pag, be32_to_cpu(agf->agf_length) - len, len, &XFS_RMAP_OINFO_SKIP_UPDATE); if (error) return error; error = xfs_free_extent(tp, pag, be32_to_cpu(agf->agf_length) - len, len, &XFS_RMAP_OINFO_SKIP_UPDATE, XFS_AG_RESV_NONE); if (error) return error; /* Update perag geometry */ pag->block_count = be32_to_cpu(agf->agf_length); __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min, &pag->agino_max); return 0; } /* Retrieve AG geometry. */ int xfs_ag_get_geometry( struct xfs_perag *pag, struct xfs_ag_geometry *ageo) { struct xfs_buf *agi_bp; struct xfs_buf *agf_bp; struct xfs_agi *agi; struct xfs_agf *agf; unsigned int freeblks; int error; /* Lock the AG headers. */ error = xfs_ialloc_read_agi(pag, NULL, 0, &agi_bp); if (error) return error; error = xfs_alloc_read_agf(pag, NULL, 0, &agf_bp); if (error) goto out_agi; /* Fill out form. */ memset(ageo, 0, sizeof(*ageo)); ageo->ag_number = pag->pag_agno; agi = agi_bp->b_addr; ageo->ag_icount = be32_to_cpu(agi->agi_count); ageo->ag_ifree = be32_to_cpu(agi->agi_freecount); agf = agf_bp->b_addr; ageo->ag_length = be32_to_cpu(agf->agf_length); freeblks = pag->pagf_freeblks + pag->pagf_flcount + pag->pagf_btreeblks - xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE); ageo->ag_freeblks = freeblks; xfs_ag_geom_health(pag, ageo); /* Release resources. */ xfs_buf_relse(agf_bp); out_agi: xfs_buf_relse(agi_bp); return error; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ocfs2.h * * Defines macros and structures used in OCFS2 * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #ifndef OCFS2_H #define OCFS2_H #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/rbtree.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/mutex.h> #include <linux/lockdep.h> #include <linux/jbd2.h> /* For union ocfs2_dlm_lksb */ #include "stackglue.h" #include "ocfs2_fs.h" #include "ocfs2_lockid.h" #include "ocfs2_ioctl.h" /* For struct ocfs2_blockcheck_stats */ #include "blockcheck.h" #include "reservations.h" #include "filecheck.h" /* Caching of metadata buffers */ /* Most user visible OCFS2 inodes will have very few pieces of * metadata, but larger files (including bitmaps, etc) must be taken * into account when designing an access scheme. We allow a small * amount of inlined blocks to be stored on an array and grow the * structure into a rb tree when necessary. */ #define OCFS2_CACHE_INFO_MAX_ARRAY 2 /* Flags for ocfs2_caching_info */ enum ocfs2_caching_info_flags { /* Indicates that the metadata cache is using the inline array */ OCFS2_CACHE_FL_INLINE = 1<<1, }; struct ocfs2_caching_operations; struct ocfs2_caching_info { /* * The parent structure provides the locks, but because the * parent structure can differ, it provides locking operations * to struct ocfs2_caching_info. */ const struct ocfs2_caching_operations *ci_ops; /* next two are protected by trans_inc_lock */ /* which transaction were we created on? Zero if none. */ unsigned long ci_created_trans; /* last transaction we were a part of. */ unsigned long ci_last_trans; /* Cache structures */ unsigned int ci_flags; unsigned int ci_num_cached; union { sector_t ci_array[OCFS2_CACHE_INFO_MAX_ARRAY]; struct rb_root ci_tree; } ci_cache; }; /* * Need this prototype here instead of in uptodate.h because journal.h * uses it. */ struct super_block *ocfs2_metadata_cache_get_super(struct ocfs2_caching_info *ci); /* this limits us to 256 nodes * if we need more, we can do a kmalloc for the map */ #define OCFS2_NODE_MAP_MAX_NODES 256 struct ocfs2_node_map { u16 num_nodes; unsigned long map[BITS_TO_LONGS(OCFS2_NODE_MAP_MAX_NODES)]; }; enum ocfs2_ast_action { OCFS2_AST_INVALID = 0, OCFS2_AST_ATTACH, OCFS2_AST_CONVERT, OCFS2_AST_DOWNCONVERT, }; /* actions for an unlockast function to take. */ enum ocfs2_unlock_action { OCFS2_UNLOCK_INVALID = 0, OCFS2_UNLOCK_CANCEL_CONVERT, OCFS2_UNLOCK_DROP_LOCK, }; /* ocfs2_lock_res->l_flags flags. */ #define OCFS2_LOCK_ATTACHED (0x00000001) /* we have initialized * the lvb */ #define OCFS2_LOCK_BUSY (0x00000002) /* we are currently in * dlm_lock */ #define OCFS2_LOCK_BLOCKED (0x00000004) /* blocked waiting to * downconvert*/ #define OCFS2_LOCK_LOCAL (0x00000008) /* newly created inode */ #define OCFS2_LOCK_NEEDS_REFRESH (0x00000010) #define OCFS2_LOCK_REFRESHING (0x00000020) #define OCFS2_LOCK_INITIALIZED (0x00000040) /* track initialization * for shutdown paths */ #define OCFS2_LOCK_FREEING (0x00000080) /* help dlmglue track * when to skip queueing * a lock because it's * about to be * dropped. */ #define OCFS2_LOCK_QUEUED (0x00000100) /* queued for downconvert */ #define OCFS2_LOCK_NOCACHE (0x00000200) /* don't use a holder count */ #define OCFS2_LOCK_PENDING (0x00000400) /* This lockres is pending a call to dlm_lock. Only exists with BUSY set. */ #define OCFS2_LOCK_UPCONVERT_FINISHING (0x00000800) /* blocks the dc thread * from downconverting * before the upconvert * has completed */ #define OCFS2_LOCK_NONBLOCK_FINISHED (0x00001000) /* NONBLOCK cluster * lock has already * returned, do not block * dc thread from * downconverting */ struct ocfs2_lock_res_ops; typedef void (*ocfs2_lock_callback)(int status, unsigned long data); #ifdef CONFIG_OCFS2_FS_STATS struct ocfs2_lock_stats { u64 ls_total; /* Total wait in NSEC */ u32 ls_gets; /* Num acquires */ u32 ls_fail; /* Num failed acquires */ /* Storing max wait in usecs saves 24 bytes per inode */ u32 ls_max; /* Max wait in USEC */ u64 ls_last; /* Last unlock time in USEC */ }; #endif struct ocfs2_lock_res { void *l_priv; const struct ocfs2_lock_res_ops *l_ops; struct list_head l_blocked_list; struct list_head l_mask_waiters; struct list_head l_holders; unsigned long l_flags; char l_name[OCFS2_LOCK_ID_MAX_LEN]; unsigned int l_ro_holders; unsigned int l_ex_holders; signed char l_level; signed char l_requested; signed char l_blocking; /* Data packed - type enum ocfs2_lock_type */ unsigned char l_type; /* used from AST/BAST funcs. */ /* Data packed - enum type ocfs2_ast_action */ unsigned char l_action; /* Data packed - enum type ocfs2_unlock_action */ unsigned char l_unlock_action; unsigned int l_pending_gen; spinlock_t l_lock; struct ocfs2_dlm_lksb l_lksb; wait_queue_head_t l_event; struct list_head l_debug_list; #ifdef CONFIG_OCFS2_FS_STATS struct ocfs2_lock_stats l_lock_prmode; /* PR mode stats */ u32 l_lock_refresh; /* Disk refreshes */ u64 l_lock_wait; /* First lock wait time */ struct ocfs2_lock_stats l_lock_exmode; /* EX mode stats */ #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map l_lockdep_map; #endif }; enum ocfs2_orphan_reco_type { ORPHAN_NO_NEED_TRUNCATE = 0, ORPHAN_NEED_TRUNCATE, }; enum ocfs2_orphan_scan_state { ORPHAN_SCAN_ACTIVE, ORPHAN_SCAN_INACTIVE }; struct ocfs2_orphan_scan { struct mutex os_lock; struct ocfs2_super *os_osb; struct ocfs2_lock_res os_lockres; /* lock to synchronize scans */ struct delayed_work os_orphan_scan_work; time64_t os_scantime; /* time this node ran the scan */ u32 os_count; /* tracks node specific scans */ u32 os_seqno; /* tracks cluster wide scans */ atomic_t os_state; /* ACTIVE or INACTIVE */ }; struct ocfs2_dlm_debug { struct kref d_refcnt; u32 d_filter_secs; struct list_head d_lockres_tracking; }; enum ocfs2_vol_state { VOLUME_INIT = 0, VOLUME_MOUNTED, VOLUME_MOUNTED_QUOTAS, VOLUME_DISMOUNTED, VOLUME_DISABLED }; struct ocfs2_alloc_stats { atomic_t moves; atomic_t local_data; atomic_t bitmap_data; atomic_t bg_allocs; atomic_t bg_extends; }; enum ocfs2_local_alloc_state { OCFS2_LA_UNUSED = 0, /* Local alloc will never be used for * this mountpoint. */ OCFS2_LA_ENABLED, /* Local alloc is in use. */ OCFS2_LA_THROTTLED, /* Local alloc is in use, but number * of bits has been reduced. */ OCFS2_LA_DISABLED /* Local alloc has temporarily been * disabled. */ }; enum ocfs2_mount_options { OCFS2_MOUNT_HB_LOCAL = 1 << 0, /* Local heartbeat */ OCFS2_MOUNT_BARRIER = 1 << 1, /* Use block barriers */ OCFS2_MOUNT_NOINTR = 1 << 2, /* Don't catch signals */ OCFS2_MOUNT_ERRORS_PANIC = 1 << 3, /* Panic on errors */ OCFS2_MOUNT_DATA_WRITEBACK = 1 << 4, /* No data ordering */ OCFS2_MOUNT_LOCALFLOCKS = 1 << 5, /* No cluster aware user file locks */ OCFS2_MOUNT_NOUSERXATTR = 1 << 6, /* No user xattr */ OCFS2_MOUNT_INODE64 = 1 << 7, /* Allow inode numbers > 2^32 */ OCFS2_MOUNT_POSIX_ACL = 1 << 8, /* Force POSIX access control lists */ OCFS2_MOUNT_NO_POSIX_ACL = 1 << 9, /* Disable POSIX access control lists */ OCFS2_MOUNT_USRQUOTA = 1 << 10, /* We support user quotas */ OCFS2_MOUNT_GRPQUOTA = 1 << 11, /* We support group quotas */ OCFS2_MOUNT_COHERENCY_BUFFERED = 1 << 12, /* Allow concurrent O_DIRECT writes */ OCFS2_MOUNT_HB_NONE = 1 << 13, /* No heartbeat */ OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */ OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */ OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */ OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */ }; #define OCFS2_OSB_SOFT_RO 0x0001 #define OCFS2_OSB_HARD_RO 0x0002 #define OCFS2_OSB_ERROR_FS 0x0004 #define OCFS2_DEFAULT_ATIME_QUANTUM 60 struct ocfs2_triggers { struct jbd2_buffer_trigger_type ot_triggers; int ot_offset; struct super_block *sb; }; enum ocfs2_journal_trigger_type { OCFS2_JTR_DI, OCFS2_JTR_EB, OCFS2_JTR_RB, OCFS2_JTR_GD, OCFS2_JTR_DB, OCFS2_JTR_XB, OCFS2_JTR_DQ, OCFS2_JTR_DR, OCFS2_JTR_DL, OCFS2_JTR_NONE /* This must be the last entry */ }; #define OCFS2_JOURNAL_TRIGGER_COUNT OCFS2_JTR_NONE void ocfs2_initialize_journal_triggers(struct super_block *sb, struct ocfs2_triggers triggers[]); struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; struct ocfs2_replay_map; struct ocfs2_quota_recovery; struct ocfs2_super { struct task_struct *commit_task; struct super_block *sb; struct inode *root_inode; struct inode *sys_root_inode; struct inode *global_system_inodes[NUM_GLOBAL_SYSTEM_INODES]; struct inode **local_system_inodes; struct ocfs2_slot_info *slot_info; u32 *slot_recovery_generations; spinlock_t node_map_lock; u64 root_blkno; u64 system_dir_blkno; u64 bitmap_blkno; u32 bitmap_cpg; char *uuid_str; u32 uuid_hash; u8 *vol_label; u64 first_cluster_group_blkno; u32 fs_generation; u32 s_feature_compat; u32 s_feature_incompat; u32 s_feature_ro_compat; /* Protects s_next_generation, osb_flags and s_inode_steal_slot. * Could protect more on osb as it's very short lived. */ spinlock_t osb_lock; u32 s_next_generation; unsigned long osb_flags; u16 s_inode_steal_slot; u16 s_meta_steal_slot; atomic_t s_num_inodes_stolen; atomic_t s_num_meta_stolen; unsigned long s_mount_opt; unsigned int s_atime_quantum; unsigned int max_slots; unsigned int node_num; int slot_num; int preferred_slot; int s_sectsize_bits; int s_clustersize; int s_clustersize_bits; unsigned int s_xattr_inline_size; atomic_t vol_state; struct mutex recovery_lock; struct ocfs2_recovery_map *recovery_map; struct ocfs2_replay_map *replay_map; struct task_struct *recovery_thread_task; int disable_recovery; wait_queue_head_t checkpoint_event; struct ocfs2_journal *journal; unsigned long osb_commit_interval; /* Journal triggers for checksum */ struct ocfs2_triggers s_journal_triggers[OCFS2_JOURNAL_TRIGGER_COUNT]; struct delayed_work la_enable_wq; /* * Must hold local alloc i_rwsem and osb->osb_lock to change * local_alloc_bits. Reads can be done under either lock. */ unsigned int local_alloc_bits; unsigned int local_alloc_default_bits; /* osb_clusters_at_boot can become stale! Do not trust it to * be up to date. */ unsigned int osb_clusters_at_boot; enum ocfs2_local_alloc_state local_alloc_state; /* protected * by osb_lock */ struct buffer_head *local_alloc_bh; u64 la_last_gd; struct ocfs2_reservation_map osb_la_resmap; unsigned int osb_resv_level; unsigned int osb_dir_resv_level; /* Next two fields are for local node slot recovery during * mount. */ struct ocfs2_dinode *local_alloc_copy; struct ocfs2_quota_recovery *quota_rec; struct ocfs2_blockcheck_stats osb_ecc_stats; struct ocfs2_alloc_stats alloc_stats; char dev_str[20]; /* "major,minor" of the device */ u8 osb_stackflags; char osb_cluster_stack[OCFS2_STACK_LABEL_LEN + 1]; char osb_cluster_name[OCFS2_CLUSTER_NAME_LEN + 1]; struct ocfs2_cluster_connection *cconn; struct ocfs2_lock_res osb_super_lockres; struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; struct rw_semaphore nfs_sync_rwlock; struct ocfs2_lock_res osb_trim_fs_lockres; struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; struct dentry *osb_debug_root; wait_queue_head_t recovery_event; spinlock_t dc_task_lock; struct task_struct *dc_task; wait_queue_head_t dc_event; unsigned long dc_wake_sequence; unsigned long dc_work_sequence; /* * Any thread can add locks to the list, but the downconvert * thread is the only one allowed to remove locks. Any change * to this rule requires updating * ocfs2_downconvert_thread_do_work(). */ struct list_head blocked_lock_list; unsigned long blocked_lock_count; /* List of dquot structures to drop last reference to */ struct llist_head dquot_drop_list; struct work_struct dquot_drop_work; wait_queue_head_t osb_mount_event; /* Truncate log info */ struct inode *osb_tl_inode; struct buffer_head *osb_tl_bh; struct delayed_work osb_truncate_log_wq; atomic_t osb_tl_disable; /* * How many clusters in our truncate log. * It must be protected by osb_tl_inode->i_rwsem. */ unsigned int truncated_clusters; struct ocfs2_node_map osb_recovering_orphan_dirs; unsigned int *osb_orphan_wipes; wait_queue_head_t osb_wipe_event; struct ocfs2_orphan_scan osb_orphan_scan; /* used to protect metaecc calculation check of xattr. */ spinlock_t osb_xattr_lock; unsigned int osb_dx_mask; u32 osb_dx_seed[4]; /* the group we used to allocate inodes. */ u64 osb_inode_alloc_group; /* rb tree root for refcount lock. */ struct rb_root osb_rf_lock_tree; struct ocfs2_refcount_tree *osb_ref_tree_lru; struct mutex system_file_mutex; /* * OCFS2 needs to schedule several different types of work which * require cluster locking, disk I/O, recovery waits, etc. Since these * types of work tend to be heavy we avoid using the kernel events * workqueue and schedule on our own. */ struct workqueue_struct *ocfs2_wq; /* sysfs directory per partition */ struct kset *osb_dev_kset; /* file check related stuff */ struct ocfs2_filecheck_sysfs_entry osb_fc_ent; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) /* Useful typedef for passing around journal access functions */ typedef int (*ocfs2_journal_access_func)(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type); static inline int ocfs2_should_order_data(struct inode *inode) { if (!S_ISREG(inode->i_mode)) return 0; if (OCFS2_SB(inode->i_sb)->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK) return 0; return 1; } static inline int ocfs2_sparse_alloc(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC) return 1; return 0; } static inline int ocfs2_writes_unwritten_extents(struct ocfs2_super *osb) { /* * Support for sparse files is a pre-requisite */ if (!ocfs2_sparse_alloc(osb)) return 0; if (osb->s_feature_ro_compat & OCFS2_FEATURE_RO_COMPAT_UNWRITTEN) return 1; return 0; } static inline int ocfs2_supports_append_dio(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_APPEND_DIO) return 1; return 0; } static inline int ocfs2_supports_inline_data(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INLINE_DATA) return 1; return 0; } static inline int ocfs2_supports_xattr(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_XATTR) return 1; return 0; } static inline int ocfs2_meta_ecc(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_META_ECC) return 1; return 0; } static inline int ocfs2_supports_indexed_dirs(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS) return 1; return 0; } static inline int ocfs2_supports_discontig_bg(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG) return 1; return 0; } static inline unsigned int ocfs2_link_max(struct ocfs2_super *osb) { if (ocfs2_supports_indexed_dirs(osb)) return OCFS2_DX_LINK_MAX; return OCFS2_LINK_MAX; } static inline unsigned int ocfs2_read_links_count(struct ocfs2_dinode *di) { u32 nlink = le16_to_cpu(di->i_links_count); u32 hi = le16_to_cpu(di->i_links_count_hi); nlink |= (hi << OCFS2_LINKS_HI_SHIFT); return nlink; } static inline void ocfs2_set_links_count(struct ocfs2_dinode *di, u32 nlink) { u16 lo, hi; lo = nlink; hi = nlink >> OCFS2_LINKS_HI_SHIFT; di->i_links_count = cpu_to_le16(lo); di->i_links_count_hi = cpu_to_le16(hi); } static inline void ocfs2_add_links_count(struct ocfs2_dinode *di, int n) { u32 links = ocfs2_read_links_count(di); links += n; ocfs2_set_links_count(di, links); } static inline int ocfs2_refcount_tree(struct ocfs2_super *osb) { if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE) return 1; return 0; } /* set / clear functions because cluster events can make these happen * in parallel so we want the transitions to be atomic. this also * means that any future flags osb_flags must be protected by spinlock * too! */ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb, unsigned long flag) { spin_lock(&osb->osb_lock); osb->osb_flags |= flag; spin_unlock(&osb->osb_lock); } static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb, int hard) { spin_lock(&osb->osb_lock); osb->osb_flags &= ~(OCFS2_OSB_SOFT_RO|OCFS2_OSB_HARD_RO); if (hard) osb->osb_flags |= OCFS2_OSB_HARD_RO; else osb->osb_flags |= OCFS2_OSB_SOFT_RO; spin_unlock(&osb->osb_lock); } static inline int ocfs2_is_hard_readonly(struct ocfs2_super *osb) { int ret; spin_lock(&osb->osb_lock); ret = osb->osb_flags & OCFS2_OSB_HARD_RO; spin_unlock(&osb->osb_lock); return ret; } static inline int ocfs2_is_soft_readonly(struct ocfs2_super *osb) { int ret; spin_lock(&osb->osb_lock); ret = osb->osb_flags & OCFS2_OSB_SOFT_RO; spin_unlock(&osb->osb_lock); return ret; } static inline int ocfs2_clusterinfo_valid(struct ocfs2_super *osb) { return (osb->s_feature_incompat & (OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK | OCFS2_FEATURE_INCOMPAT_CLUSTERINFO)); } static inline int ocfs2_userspace_stack(struct ocfs2_super *osb) { if (ocfs2_clusterinfo_valid(osb) && memcmp(osb->osb_cluster_stack, OCFS2_CLASSIC_CLUSTER_STACK, OCFS2_STACK_LABEL_LEN)) return 1; return 0; } static inline int ocfs2_o2cb_stack(struct ocfs2_super *osb) { if (ocfs2_clusterinfo_valid(osb) && !memcmp(osb->osb_cluster_stack, OCFS2_CLASSIC_CLUSTER_STACK, OCFS2_STACK_LABEL_LEN)) return 1; return 0; } static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb) { return ocfs2_o2cb_stack(osb) && (osb->osb_stackflags & OCFS2_CLUSTER_O2CB_GLOBAL_HEARTBEAT); } static inline int ocfs2_mount_local(struct ocfs2_super *osb) { return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT); } static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb) { return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP); } #define OCFS2_IS_VALID_DINODE(ptr) \ (!strcmp((ptr)->i_signature, OCFS2_INODE_SIGNATURE)) #define OCFS2_IS_VALID_EXTENT_BLOCK(ptr) \ (!strcmp((ptr)->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE)) #define OCFS2_IS_VALID_GROUP_DESC(ptr) \ (!strcmp((ptr)->bg_signature, OCFS2_GROUP_DESC_SIGNATURE)) #define OCFS2_IS_VALID_XATTR_BLOCK(ptr) \ (!strcmp((ptr)->xb_signature, OCFS2_XATTR_BLOCK_SIGNATURE)) #define OCFS2_IS_VALID_DIR_TRAILER(ptr) \ (!strcmp((ptr)->db_signature, OCFS2_DIR_TRAILER_SIGNATURE)) #define OCFS2_IS_VALID_DX_ROOT(ptr) \ (!strcmp((ptr)->dr_signature, OCFS2_DX_ROOT_SIGNATURE)) #define OCFS2_IS_VALID_DX_LEAF(ptr) \ (!strcmp((ptr)->dl_signature, OCFS2_DX_LEAF_SIGNATURE)) #define OCFS2_IS_VALID_REFCOUNT_BLOCK(ptr) \ (!strcmp((ptr)->rf_signature, OCFS2_REFCOUNT_BLOCK_SIGNATURE)) static inline unsigned long ino_from_blkno(struct super_block *sb, u64 blkno) { return (unsigned long)(blkno & (u64)ULONG_MAX); } static inline u64 ocfs2_clusters_to_blocks(struct super_block *sb, u32 clusters) { int c_to_b_bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; return (u64)clusters << c_to_b_bits; } static inline u32 ocfs2_clusters_for_blocks(struct super_block *sb, u64 blocks) { int b_to_c_bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; blocks += (1 << b_to_c_bits) - 1; return (u32)(blocks >> b_to_c_bits); } static inline u32 ocfs2_blocks_to_clusters(struct super_block *sb, u64 blocks) { int b_to_c_bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; return (u32)(blocks >> b_to_c_bits); } static inline unsigned int ocfs2_clusters_for_bytes(struct super_block *sb, u64 bytes) { int cl_bits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int clusters; bytes += OCFS2_SB(sb)->s_clustersize - 1; /* OCFS2 just cannot have enough clusters to overflow this */ clusters = (unsigned int)(bytes >> cl_bits); return clusters; } static inline unsigned int ocfs2_bytes_to_clusters(struct super_block *sb, u64 bytes) { int cl_bits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int clusters; clusters = (unsigned int)(bytes >> cl_bits); return clusters; } static inline u64 ocfs2_blocks_for_bytes(struct super_block *sb, u64 bytes) { bytes += sb->s_blocksize - 1; return bytes >> sb->s_blocksize_bits; } static inline u64 ocfs2_clusters_to_bytes(struct super_block *sb, u32 clusters) { return (u64)clusters << OCFS2_SB(sb)->s_clustersize_bits; } static inline u64 ocfs2_block_to_cluster_start(struct super_block *sb, u64 blocks) { int bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits; unsigned int clusters; clusters = ocfs2_blocks_to_clusters(sb, blocks); return (u64)clusters << bits; } static inline u64 ocfs2_align_bytes_to_clusters(struct super_block *sb, u64 bytes) { int cl_bits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int clusters; clusters = ocfs2_clusters_for_bytes(sb, bytes); return (u64)clusters << cl_bits; } static inline u64 ocfs2_align_bytes_to_blocks(struct super_block *sb, u64 bytes) { u64 blocks; blocks = ocfs2_blocks_for_bytes(sb, bytes); return blocks << sb->s_blocksize_bits; } static inline unsigned long ocfs2_align_bytes_to_sectors(u64 bytes) { return (unsigned long)((bytes + 511) >> 9); } static inline unsigned int ocfs2_page_index_to_clusters(struct super_block *sb, unsigned long pg_index) { u32 clusters = pg_index; unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; if (unlikely(PAGE_SHIFT > cbits)) clusters = pg_index << (PAGE_SHIFT - cbits); else if (PAGE_SHIFT < cbits) clusters = pg_index >> (cbits - PAGE_SHIFT); return clusters; } /* * Find the 1st page index which covers the given clusters. */ static inline pgoff_t ocfs2_align_clusters_to_page_index(struct super_block *sb, u32 clusters) { unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; pgoff_t index = clusters; if (PAGE_SHIFT > cbits) { index = (pgoff_t)clusters >> (PAGE_SHIFT - cbits); } else if (PAGE_SHIFT < cbits) { index = (pgoff_t)clusters << (cbits - PAGE_SHIFT); } return index; } static inline unsigned int ocfs2_pages_per_cluster(struct super_block *sb) { unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits; unsigned int pages_per_cluster = 1; if (PAGE_SHIFT < cbits) pages_per_cluster = 1 << (cbits - PAGE_SHIFT); return pages_per_cluster; } static inline unsigned int ocfs2_megabytes_to_clusters(struct super_block *sb, unsigned int megs) { BUILD_BUG_ON(OCFS2_MAX_CLUSTERSIZE > 1048576); return megs << (20 - OCFS2_SB(sb)->s_clustersize_bits); } static inline unsigned int ocfs2_clusters_to_megabytes(struct super_block *sb, unsigned int clusters) { return clusters >> (20 - OCFS2_SB(sb)->s_clustersize_bits); } static inline void _ocfs2_set_bit(unsigned int bit, unsigned long *bitmap) { __set_bit_le(bit, bitmap); } #define ocfs2_set_bit(bit, addr) _ocfs2_set_bit((bit), (unsigned long *)(addr)) static inline void _ocfs2_clear_bit(unsigned int bit, unsigned long *bitmap) { __clear_bit_le(bit, bitmap); } #define ocfs2_clear_bit(bit, addr) _ocfs2_clear_bit((bit), (unsigned long *)(addr)) #define ocfs2_test_bit test_bit_le #define ocfs2_find_next_zero_bit find_next_zero_bit_le #define ocfs2_find_next_bit find_next_bit_le static inline void *correct_addr_and_bit_unaligned(int *bit, void *addr) { #if BITS_PER_LONG == 64 *bit += ((unsigned long) addr & 7UL) << 3; addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 *bit += ((unsigned long) addr & 3UL) << 3; addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif return addr; } static inline void ocfs2_set_bit_unaligned(int bit, void *bitmap) { bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); ocfs2_set_bit(bit, bitmap); } static inline void ocfs2_clear_bit_unaligned(int bit, void *bitmap) { bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); ocfs2_clear_bit(bit, bitmap); } static inline int ocfs2_test_bit_unaligned(int bit, void *bitmap) { bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); return ocfs2_test_bit(bit, bitmap); } static inline int ocfs2_find_next_zero_bit_unaligned(void *bitmap, int max, int start) { int fix = 0, ret, tmpmax; bitmap = correct_addr_and_bit_unaligned(&fix, bitmap); tmpmax = max + fix; start += fix; ret = ocfs2_find_next_zero_bit(bitmap, tmpmax, start) - fix; if (ret > max) return max; return ret; } #endif /* OCFS2_H */ |
| 1 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_EXTENTS_H #define _BCACHEFS_EXTENTS_H #include "bcachefs.h" #include "bkey.h" #include "extents_types.h" struct bch_fs; struct btree_trans; enum bch_validate_flags; /* extent entries: */ #define extent_entry_last(_e) \ ((typeof(&(_e).v->start[0])) bkey_val_end(_e)) #define entry_to_ptr(_entry) \ ({ \ EBUG_ON((_entry) && !extent_entry_is_ptr(_entry)); \ \ __builtin_choose_expr( \ type_is_exact(_entry, const union bch_extent_entry *), \ (const struct bch_extent_ptr *) (_entry), \ (struct bch_extent_ptr *) (_entry)); \ }) /* downcast, preserves const */ #define to_entry(_entry) \ ({ \ BUILD_BUG_ON(!type_is(_entry, union bch_extent_crc *) && \ !type_is(_entry, struct bch_extent_ptr *) && \ !type_is(_entry, struct bch_extent_stripe_ptr *)); \ \ __builtin_choose_expr( \ (type_is_exact(_entry, const union bch_extent_crc *) || \ type_is_exact(_entry, const struct bch_extent_ptr *) ||\ type_is_exact(_entry, const struct bch_extent_stripe_ptr *)),\ (const union bch_extent_entry *) (_entry), \ (union bch_extent_entry *) (_entry)); \ }) #define extent_entry_next(_entry) \ ((typeof(_entry)) ((void *) (_entry) + extent_entry_bytes(_entry))) #define extent_entry_next_safe(_entry, _end) \ (likely(__extent_entry_type(_entry) < BCH_EXTENT_ENTRY_MAX) \ ? extent_entry_next(_entry) \ : _end) static inline unsigned __extent_entry_type(const union bch_extent_entry *e) { return e->type ? __ffs(e->type) : BCH_EXTENT_ENTRY_MAX; } static inline enum bch_extent_entry_type extent_entry_type(const union bch_extent_entry *e) { int ret = __ffs(e->type); EBUG_ON(ret < 0 || ret >= BCH_EXTENT_ENTRY_MAX); return ret; } static inline size_t extent_entry_bytes(const union bch_extent_entry *entry) { switch (extent_entry_type(entry)) { #define x(f, n) \ case BCH_EXTENT_ENTRY_##f: \ return sizeof(struct bch_extent_##f); BCH_EXTENT_ENTRY_TYPES() #undef x default: BUG(); } } static inline size_t extent_entry_u64s(const union bch_extent_entry *entry) { return extent_entry_bytes(entry) / sizeof(u64); } static inline void __extent_entry_insert(struct bkey_i *k, union bch_extent_entry *dst, union bch_extent_entry *new) { union bch_extent_entry *end = bkey_val_end(bkey_i_to_s(k)); memmove_u64s_up_small((u64 *) dst + extent_entry_u64s(new), dst, (u64 *) end - (u64 *) dst); k->k.u64s += extent_entry_u64s(new); memcpy_u64s_small(dst, new, extent_entry_u64s(new)); } static inline void extent_entry_drop(struct bkey_s k, union bch_extent_entry *entry) { union bch_extent_entry *next = extent_entry_next(entry); /* stripes have ptrs, but their layout doesn't work with this code */ BUG_ON(k.k->type == KEY_TYPE_stripe); memmove_u64s_down(entry, next, (u64 *) bkey_val_end(k) - (u64 *) next); k.k->u64s -= (u64 *) next - (u64 *) entry; } static inline bool extent_entry_is_ptr(const union bch_extent_entry *e) { return __extent_entry_type(e) == BCH_EXTENT_ENTRY_ptr; } static inline bool extent_entry_is_stripe_ptr(const union bch_extent_entry *e) { return __extent_entry_type(e) == BCH_EXTENT_ENTRY_stripe_ptr; } static inline bool extent_entry_is_crc(const union bch_extent_entry *e) { switch (__extent_entry_type(e)) { case BCH_EXTENT_ENTRY_crc32: case BCH_EXTENT_ENTRY_crc64: case BCH_EXTENT_ENTRY_crc128: return true; default: return false; } } union bch_extent_crc { u8 type; struct bch_extent_crc32 crc32; struct bch_extent_crc64 crc64; struct bch_extent_crc128 crc128; }; #define __entry_to_crc(_entry) \ __builtin_choose_expr( \ type_is_exact(_entry, const union bch_extent_entry *), \ (const union bch_extent_crc *) (_entry), \ (union bch_extent_crc *) (_entry)) #define entry_to_crc(_entry) \ ({ \ EBUG_ON((_entry) && !extent_entry_is_crc(_entry)); \ \ __entry_to_crc(_entry); \ }) static inline struct bch_extent_crc_unpacked bch2_extent_crc_unpack(const struct bkey *k, const union bch_extent_crc *crc) { #define common_fields(_crc) \ .csum_type = _crc.csum_type, \ .compression_type = _crc.compression_type, \ .compressed_size = _crc._compressed_size + 1, \ .uncompressed_size = _crc._uncompressed_size + 1, \ .offset = _crc.offset, \ .live_size = k->size if (!crc) return (struct bch_extent_crc_unpacked) { .compressed_size = k->size, .uncompressed_size = k->size, .live_size = k->size, }; switch (extent_entry_type(to_entry(crc))) { case BCH_EXTENT_ENTRY_crc32: { struct bch_extent_crc_unpacked ret = (struct bch_extent_crc_unpacked) { common_fields(crc->crc32), }; *((__le32 *) &ret.csum.lo) = (__le32 __force) crc->crc32.csum; return ret; } case BCH_EXTENT_ENTRY_crc64: { struct bch_extent_crc_unpacked ret = (struct bch_extent_crc_unpacked) { common_fields(crc->crc64), .nonce = crc->crc64.nonce, .csum.lo = (__force __le64) crc->crc64.csum_lo, }; *((__le16 *) &ret.csum.hi) = (__le16 __force) crc->crc64.csum_hi; return ret; } case BCH_EXTENT_ENTRY_crc128: { struct bch_extent_crc_unpacked ret = (struct bch_extent_crc_unpacked) { common_fields(crc->crc128), .nonce = crc->crc128.nonce, .csum = crc->crc128.csum, }; return ret; } default: BUG(); } #undef common_fields } static inline bool crc_is_compressed(struct bch_extent_crc_unpacked crc) { return (crc.compression_type != BCH_COMPRESSION_TYPE_none && crc.compression_type != BCH_COMPRESSION_TYPE_incompressible); } static inline bool crc_is_encoded(struct bch_extent_crc_unpacked crc) { return crc.csum_type != BCH_CSUM_none || crc_is_compressed(crc); } void bch2_extent_crc_unpacked_to_text(struct printbuf *, struct bch_extent_crc_unpacked *); /* bkey_ptrs: generically over any key type that has ptrs */ struct bkey_ptrs_c { const union bch_extent_entry *start; const union bch_extent_entry *end; }; struct bkey_ptrs { union bch_extent_entry *start; union bch_extent_entry *end; }; static inline struct bkey_ptrs_c bch2_bkey_ptrs_c(struct bkey_s_c k) { switch (k.k->type) { case KEY_TYPE_btree_ptr: { struct bkey_s_c_btree_ptr e = bkey_s_c_to_btree_ptr(k); return (struct bkey_ptrs_c) { to_entry(&e.v->start[0]), to_entry(extent_entry_last(e)) }; } case KEY_TYPE_extent: { struct bkey_s_c_extent e = bkey_s_c_to_extent(k); return (struct bkey_ptrs_c) { e.v->start, extent_entry_last(e) }; } case KEY_TYPE_stripe: { struct bkey_s_c_stripe s = bkey_s_c_to_stripe(k); return (struct bkey_ptrs_c) { to_entry(&s.v->ptrs[0]), to_entry(&s.v->ptrs[s.v->nr_blocks]), }; } case KEY_TYPE_reflink_v: { struct bkey_s_c_reflink_v r = bkey_s_c_to_reflink_v(k); return (struct bkey_ptrs_c) { r.v->start, bkey_val_end(r), }; } case KEY_TYPE_btree_ptr_v2: { struct bkey_s_c_btree_ptr_v2 e = bkey_s_c_to_btree_ptr_v2(k); return (struct bkey_ptrs_c) { to_entry(&e.v->start[0]), to_entry(extent_entry_last(e)) }; } default: return (struct bkey_ptrs_c) { NULL, NULL }; } } static inline struct bkey_ptrs bch2_bkey_ptrs(struct bkey_s k) { struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k.s_c); return (struct bkey_ptrs) { (void *) p.start, (void *) p.end }; } #define __bkey_extent_entry_for_each_from(_start, _end, _entry) \ for ((_entry) = (_start); \ (_entry) < (_end); \ (_entry) = extent_entry_next_safe(_entry, _end)) #define __bkey_ptr_next(_ptr, _end) \ ({ \ typeof(_end) _entry; \ \ __bkey_extent_entry_for_each_from(to_entry(_ptr), _end, _entry) \ if (extent_entry_is_ptr(_entry)) \ break; \ \ _entry < (_end) ? entry_to_ptr(_entry) : NULL; \ }) #define bkey_extent_entry_for_each_from(_p, _entry, _start) \ __bkey_extent_entry_for_each_from(_start, (_p).end, _entry) #define bkey_extent_entry_for_each(_p, _entry) \ bkey_extent_entry_for_each_from(_p, _entry, _p.start) #define __bkey_for_each_ptr(_start, _end, _ptr) \ for (typeof(_start) (_ptr) = (_start); \ ((_ptr) = __bkey_ptr_next(_ptr, _end)); \ (_ptr)++) #define bkey_ptr_next(_p, _ptr) \ __bkey_ptr_next(_ptr, (_p).end) #define bkey_for_each_ptr(_p, _ptr) \ __bkey_for_each_ptr(&(_p).start->ptr, (_p).end, _ptr) #define __bkey_ptr_next_decode(_k, _end, _ptr, _entry) \ ({ \ __label__ out; \ \ (_ptr).idx = 0; \ (_ptr).has_ec = false; \ \ __bkey_extent_entry_for_each_from(_entry, _end, _entry) \ switch (__extent_entry_type(_entry)) { \ case BCH_EXTENT_ENTRY_ptr: \ (_ptr).ptr = _entry->ptr; \ goto out; \ case BCH_EXTENT_ENTRY_crc32: \ case BCH_EXTENT_ENTRY_crc64: \ case BCH_EXTENT_ENTRY_crc128: \ (_ptr).crc = bch2_extent_crc_unpack(_k, \ entry_to_crc(_entry)); \ break; \ case BCH_EXTENT_ENTRY_stripe_ptr: \ (_ptr).ec = _entry->stripe_ptr; \ (_ptr).has_ec = true; \ break; \ default: \ /* nothing */ \ break; \ } \ out: \ _entry < (_end); \ }) #define __bkey_for_each_ptr_decode(_k, _start, _end, _ptr, _entry) \ for ((_ptr).crc = bch2_extent_crc_unpack(_k, NULL), \ (_entry) = _start; \ __bkey_ptr_next_decode(_k, _end, _ptr, _entry); \ (_entry) = extent_entry_next_safe(_entry, _end)) #define bkey_for_each_ptr_decode(_k, _p, _ptr, _entry) \ __bkey_for_each_ptr_decode(_k, (_p).start, (_p).end, \ _ptr, _entry) #define bkey_crc_next(_k, _start, _end, _crc, _iter) \ ({ \ __bkey_extent_entry_for_each_from(_iter, _end, _iter) \ if (extent_entry_is_crc(_iter)) { \ (_crc) = bch2_extent_crc_unpack(_k, \ entry_to_crc(_iter)); \ break; \ } \ \ (_iter) < (_end); \ }) #define __bkey_for_each_crc(_k, _start, _end, _crc, _iter) \ for ((_crc) = bch2_extent_crc_unpack(_k, NULL), \ (_iter) = (_start); \ bkey_crc_next(_k, _start, _end, _crc, _iter); \ (_iter) = extent_entry_next(_iter)) #define bkey_for_each_crc(_k, _p, _crc, _iter) \ __bkey_for_each_crc(_k, (_p).start, (_p).end, _crc, _iter) /* Iterate over pointers in KEY_TYPE_extent: */ #define extent_for_each_entry_from(_e, _entry, _start) \ __bkey_extent_entry_for_each_from(_start, \ extent_entry_last(_e), _entry) #define extent_for_each_entry(_e, _entry) \ extent_for_each_entry_from(_e, _entry, (_e).v->start) #define extent_ptr_next(_e, _ptr) \ __bkey_ptr_next(_ptr, extent_entry_last(_e)) #define extent_for_each_ptr(_e, _ptr) \ __bkey_for_each_ptr(&(_e).v->start->ptr, extent_entry_last(_e), _ptr) #define extent_for_each_ptr_decode(_e, _ptr, _entry) \ __bkey_for_each_ptr_decode((_e).k, (_e).v->start, \ extent_entry_last(_e), _ptr, _entry) /* utility code common to all keys with pointers: */ struct bch_dev_io_failures *bch2_dev_io_failures(struct bch_io_failures *, unsigned); void bch2_mark_io_failure(struct bch_io_failures *, struct extent_ptr_decoded *); int bch2_bkey_pick_read_device(struct bch_fs *, struct bkey_s_c, struct bch_io_failures *, struct extent_ptr_decoded *); /* KEY_TYPE_btree_ptr: */ int bch2_btree_ptr_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_btree_ptr_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_btree_ptr_v2_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_btree_ptr_v2_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); void bch2_btree_ptr_v2_compat(enum btree_id, unsigned, unsigned, int, struct bkey_s); #define bch2_bkey_ops_btree_ptr ((struct bkey_ops) { \ .key_validate = bch2_btree_ptr_validate, \ .val_to_text = bch2_btree_ptr_to_text, \ .swab = bch2_ptr_swab, \ .trigger = bch2_trigger_extent, \ }) #define bch2_bkey_ops_btree_ptr_v2 ((struct bkey_ops) { \ .key_validate = bch2_btree_ptr_v2_validate, \ .val_to_text = bch2_btree_ptr_v2_to_text, \ .swab = bch2_ptr_swab, \ .compat = bch2_btree_ptr_v2_compat, \ .trigger = bch2_trigger_extent, \ .min_val_size = 40, \ }) /* KEY_TYPE_extent: */ bool bch2_extent_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); #define bch2_bkey_ops_extent ((struct bkey_ops) { \ .key_validate = bch2_bkey_ptrs_validate, \ .val_to_text = bch2_bkey_ptrs_to_text, \ .swab = bch2_ptr_swab, \ .key_normalize = bch2_extent_normalize, \ .key_merge = bch2_extent_merge, \ .trigger = bch2_trigger_extent, \ }) /* KEY_TYPE_reservation: */ int bch2_reservation_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_reservation_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); bool bch2_reservation_merge(struct bch_fs *, struct bkey_s, struct bkey_s_c); #define bch2_bkey_ops_reservation ((struct bkey_ops) { \ .key_validate = bch2_reservation_validate, \ .val_to_text = bch2_reservation_to_text, \ .key_merge = bch2_reservation_merge, \ .trigger = bch2_trigger_reservation, \ .min_val_size = 8, \ }) /* Extent checksum entries: */ bool bch2_can_narrow_extent_crcs(struct bkey_s_c, struct bch_extent_crc_unpacked); bool bch2_bkey_narrow_crcs(struct bkey_i *, struct bch_extent_crc_unpacked); void bch2_extent_crc_append(struct bkey_i *, struct bch_extent_crc_unpacked); /* Generic code for keys with pointers: */ static inline bool bkey_is_btree_ptr(const struct bkey *k) { switch (k->type) { case KEY_TYPE_btree_ptr: case KEY_TYPE_btree_ptr_v2: return true; default: return false; } } static inline bool bkey_extent_is_direct_data(const struct bkey *k) { switch (k->type) { case KEY_TYPE_btree_ptr: case KEY_TYPE_btree_ptr_v2: case KEY_TYPE_extent: case KEY_TYPE_reflink_v: return true; default: return false; } } static inline bool bkey_extent_is_inline_data(const struct bkey *k) { return k->type == KEY_TYPE_inline_data || k->type == KEY_TYPE_indirect_inline_data; } static inline unsigned bkey_inline_data_offset(const struct bkey *k) { switch (k->type) { case KEY_TYPE_inline_data: return sizeof(struct bch_inline_data); case KEY_TYPE_indirect_inline_data: return sizeof(struct bch_indirect_inline_data); default: BUG(); } } static inline unsigned bkey_inline_data_bytes(const struct bkey *k) { return bkey_val_bytes(k) - bkey_inline_data_offset(k); } #define bkey_inline_data_p(_k) (((void *) (_k).v) + bkey_inline_data_offset((_k).k)) static inline bool bkey_extent_is_data(const struct bkey *k) { return bkey_extent_is_direct_data(k) || bkey_extent_is_inline_data(k) || k->type == KEY_TYPE_reflink_p; } /* * Should extent be counted under inode->i_sectors? */ static inline bool bkey_extent_is_allocation(const struct bkey *k) { switch (k->type) { case KEY_TYPE_extent: case KEY_TYPE_reservation: case KEY_TYPE_reflink_p: case KEY_TYPE_reflink_v: case KEY_TYPE_inline_data: case KEY_TYPE_indirect_inline_data: case KEY_TYPE_error: return true; default: return false; } } static inline bool bkey_extent_is_unwritten(struct bkey_s_c k) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(ptrs, ptr) if (ptr->unwritten) return true; return false; } static inline bool bkey_extent_is_reservation(struct bkey_s_c k) { return k.k->type == KEY_TYPE_reservation || bkey_extent_is_unwritten(k); } static inline struct bch_devs_list bch2_bkey_devs(struct bkey_s_c k) { struct bch_devs_list ret = (struct bch_devs_list) { 0 }; struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(p, ptr) ret.data[ret.nr++] = ptr->dev; return ret; } static inline struct bch_devs_list bch2_bkey_dirty_devs(struct bkey_s_c k) { struct bch_devs_list ret = (struct bch_devs_list) { 0 }; struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(p, ptr) if (!ptr->cached) ret.data[ret.nr++] = ptr->dev; return ret; } static inline struct bch_devs_list bch2_bkey_cached_devs(struct bkey_s_c k) { struct bch_devs_list ret = (struct bch_devs_list) { 0 }; struct bkey_ptrs_c p = bch2_bkey_ptrs_c(k); bkey_for_each_ptr(p, ptr) if (ptr->cached) ret.data[ret.nr++] = ptr->dev; return ret; } unsigned bch2_bkey_nr_ptrs(struct bkey_s_c); unsigned bch2_bkey_nr_ptrs_allocated(struct bkey_s_c); unsigned bch2_bkey_nr_ptrs_fully_allocated(struct bkey_s_c); bool bch2_bkey_is_incompressible(struct bkey_s_c); unsigned bch2_bkey_sectors_compressed(struct bkey_s_c); unsigned bch2_bkey_replicas(struct bch_fs *, struct bkey_s_c); unsigned bch2_extent_ptr_desired_durability(struct bch_fs *, struct extent_ptr_decoded *); unsigned bch2_extent_ptr_durability(struct bch_fs *, struct extent_ptr_decoded *); unsigned bch2_bkey_durability(struct bch_fs *, struct bkey_s_c); void bch2_bkey_drop_device(struct bkey_s, unsigned); void bch2_bkey_drop_device_noerror(struct bkey_s, unsigned); const struct bch_extent_ptr *bch2_bkey_has_device_c(struct bkey_s_c, unsigned); static inline struct bch_extent_ptr *bch2_bkey_has_device(struct bkey_s k, unsigned dev) { return (void *) bch2_bkey_has_device_c(k.s_c, dev); } bool bch2_bkey_has_target(struct bch_fs *, struct bkey_s_c, unsigned); void bch2_bkey_extent_entry_drop(struct bkey_i *, union bch_extent_entry *); static inline void bch2_bkey_append_ptr(struct bkey_i *k, struct bch_extent_ptr ptr) { struct bch_extent_ptr *dest; EBUG_ON(bch2_bkey_has_device(bkey_i_to_s(k), ptr.dev)); switch (k->k.type) { case KEY_TYPE_btree_ptr: case KEY_TYPE_btree_ptr_v2: case KEY_TYPE_extent: EBUG_ON(bkey_val_u64s(&k->k) >= BKEY_EXTENT_VAL_U64s_MAX); ptr.type = 1 << BCH_EXTENT_ENTRY_ptr; dest = (struct bch_extent_ptr *)((void *) &k->v + bkey_val_bytes(&k->k)); *dest = ptr; k->k.u64s++; break; default: BUG(); } } void bch2_extent_ptr_decoded_append(struct bkey_i *, struct extent_ptr_decoded *); void bch2_bkey_drop_ptr_noerror(struct bkey_s, struct bch_extent_ptr *); void bch2_bkey_drop_ptr(struct bkey_s, struct bch_extent_ptr *); #define bch2_bkey_drop_ptrs(_k, _ptr, _cond) \ do { \ __label__ _again; \ struct bkey_ptrs _ptrs; \ _again: \ _ptrs = bch2_bkey_ptrs(_k); \ \ bkey_for_each_ptr(_ptrs, _ptr) \ if (_cond) { \ bch2_bkey_drop_ptr(_k, _ptr); \ goto _again; \ } \ } while (0) bool bch2_bkey_matches_ptr(struct bch_fs *, struct bkey_s_c, struct bch_extent_ptr, u64); bool bch2_extents_match(struct bkey_s_c, struct bkey_s_c); struct bch_extent_ptr * bch2_extent_has_ptr(struct bkey_s_c, struct extent_ptr_decoded, struct bkey_s); void bch2_extent_ptr_set_cached(struct bkey_s, struct bch_extent_ptr *); bool bch2_extent_normalize(struct bch_fs *, struct bkey_s); void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *); void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); int bch2_bkey_ptrs_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags); void bch2_ptr_swab(struct bkey_s); const struct bch_extent_rebalance *bch2_bkey_rebalance_opts(struct bkey_s_c); unsigned bch2_bkey_ptrs_need_rebalance(struct bch_fs *, struct bkey_s_c, unsigned, unsigned); bool bch2_bkey_needs_rebalance(struct bch_fs *, struct bkey_s_c); u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c); int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bkey_i *, struct bch_io_opts *); /* Generic extent code: */ enum bch_extent_overlap { BCH_EXTENT_OVERLAP_ALL = 0, BCH_EXTENT_OVERLAP_BACK = 1, BCH_EXTENT_OVERLAP_FRONT = 2, BCH_EXTENT_OVERLAP_MIDDLE = 3, }; /* Returns how k overlaps with m */ static inline enum bch_extent_overlap bch2_extent_overlap(const struct bkey *k, const struct bkey *m) { int cmp1 = bkey_lt(k->p, m->p); int cmp2 = bkey_gt(bkey_start_pos(k), bkey_start_pos(m)); return (cmp1 << 1) + cmp2; } int bch2_cut_front_s(struct bpos, struct bkey_s); int bch2_cut_back_s(struct bpos, struct bkey_s); static inline void bch2_cut_front(struct bpos where, struct bkey_i *k) { bch2_cut_front_s(where, bkey_i_to_s(k)); } static inline void bch2_cut_back(struct bpos where, struct bkey_i *k) { bch2_cut_back_s(where, bkey_i_to_s(k)); } /** * bch_key_resize - adjust size of @k * * bkey_start_offset(k) will be preserved, modifies where the extent ends */ static inline void bch2_key_resize(struct bkey *k, unsigned new_size) { k->p.offset -= k->size; k->p.offset += new_size; k->size = new_size; } #endif /* _BCACHEFS_EXTENTS_H */ |
| 30 30 2 208 208 | 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 | /* * Module for handling utf8 just like any other charset. * By Urban Widmark 2000 */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static unsigned char identity[256]; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { int n; if (boundlen <= 0) return -ENAMETOOLONG; n = utf32_to_utf8(uni, out, boundlen); if (n < 0) { *out = '?'; return -EINVAL; } return n; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { int n; unicode_t u; n = utf8_to_utf32(rawstring, boundlen, &u); if (n < 0 || u > MAX_WCHAR_T) { *uni = 0x003f; /* ? */ return -EINVAL; } *uni = (wchar_t) u; return n; } static struct nls_table table = { .charset = "utf8", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = identity, /* no conversion */ .charset2upper = identity, }; static int __init init_nls_utf8(void) { int i; for (i=0; i<256; i++) identity[i] = i; return register_nls(&table); } static void __exit exit_nls_utf8(void) { unregister_nls(&table); } module_init(init_nls_utf8) module_exit(exit_nls_utf8) MODULE_DESCRIPTION("NLS UTF-8"); MODULE_LICENSE("Dual BSD/GPL"); |
| 12 2 12 224 4 206 189 206 7 172 211 167 3 34 166 1 181 1 13 181 181 182 1 4 1 139 2 163 138 163 163 181 182 182 147 163 171 212 168 2 167 31 10 163 1 160 30 203 1 4 147 168 1 9 2 7 10 18 7 22 8 3 12 189 195 197 170 33 195 7 7 5 1 1 1 212 212 92 78 16 73 21 92 91 32 61 189 188 1 137 51 1 52 51 1 49 3 183 5 186 2 184 2 2 176 4 4 3 1 10 1 168 9 3 1 1 7 14 14 14 2 12 13 1 14 5 14 2 12 14 12 2 14 13 1 12 2 13 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fs.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/posix_acl_xattr.h> #include <linux/seq_file.h> #include <linux/xattr.h> #include "overlayfs.h" #include "params.h" static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR); module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); MODULE_PARM_DESC(redirect_dir, "Default to on or off for the redirect_dir feature"); static bool ovl_redirect_always_follow = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW); module_param_named(redirect_always_follow, ovl_redirect_always_follow, bool, 0644); MODULE_PARM_DESC(redirect_always_follow, "Follow redirects even if redirect_dir feature is turned off"); static bool ovl_xino_auto_def = IS_ENABLED(CONFIG_OVERLAY_FS_XINO_AUTO); module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644); MODULE_PARM_DESC(xino_auto, "Auto enable xino feature"); static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX); module_param_named(index, ovl_index_def, bool, 0644); MODULE_PARM_DESC(index, "Default to on or off for the inodes index feature"); static bool ovl_nfs_export_def = IS_ENABLED(CONFIG_OVERLAY_FS_NFS_EXPORT); module_param_named(nfs_export, ovl_nfs_export_def, bool, 0644); MODULE_PARM_DESC(nfs_export, "Default to on or off for the NFS export feature"); static bool ovl_metacopy_def = IS_ENABLED(CONFIG_OVERLAY_FS_METACOPY); module_param_named(metacopy, ovl_metacopy_def, bool, 0644); MODULE_PARM_DESC(metacopy, "Default to on or off for the metadata only copy up feature"); enum ovl_opt { Opt_lowerdir, Opt_lowerdir_add, Opt_datadir_add, Opt_upperdir, Opt_workdir, Opt_default_permissions, Opt_redirect_dir, Opt_index, Opt_uuid, Opt_nfs_export, Opt_userxattr, Opt_xino, Opt_metacopy, Opt_verity, Opt_volatile, }; static const struct constant_table ovl_parameter_bool[] = { { "on", true }, { "off", false }, {} }; static const struct constant_table ovl_parameter_uuid[] = { { "off", OVL_UUID_OFF }, { "null", OVL_UUID_NULL }, { "auto", OVL_UUID_AUTO }, { "on", OVL_UUID_ON }, {} }; static const char *ovl_uuid_mode(struct ovl_config *config) { return ovl_parameter_uuid[config->uuid].name; } static int ovl_uuid_def(void) { return OVL_UUID_AUTO; } static const struct constant_table ovl_parameter_xino[] = { { "off", OVL_XINO_OFF }, { "auto", OVL_XINO_AUTO }, { "on", OVL_XINO_ON }, {} }; const char *ovl_xino_mode(struct ovl_config *config) { return ovl_parameter_xino[config->xino].name; } static int ovl_xino_def(void) { return ovl_xino_auto_def ? OVL_XINO_AUTO : OVL_XINO_OFF; } const struct constant_table ovl_parameter_redirect_dir[] = { { "off", OVL_REDIRECT_OFF }, { "follow", OVL_REDIRECT_FOLLOW }, { "nofollow", OVL_REDIRECT_NOFOLLOW }, { "on", OVL_REDIRECT_ON }, {} }; static const char *ovl_redirect_mode(struct ovl_config *config) { return ovl_parameter_redirect_dir[config->redirect_mode].name; } static int ovl_redirect_mode_def(void) { return ovl_redirect_dir_def ? OVL_REDIRECT_ON : ovl_redirect_always_follow ? OVL_REDIRECT_FOLLOW : OVL_REDIRECT_NOFOLLOW; } static const struct constant_table ovl_parameter_verity[] = { { "off", OVL_VERITY_OFF }, { "on", OVL_VERITY_ON }, { "require", OVL_VERITY_REQUIRE }, {} }; static const char *ovl_verity_mode(struct ovl_config *config) { return ovl_parameter_verity[config->verity_mode].name; } static int ovl_verity_mode_def(void) { return OVL_VERITY_OFF; } const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_string_empty("lowerdir", Opt_lowerdir), fsparam_string("lowerdir+", Opt_lowerdir_add), fsparam_string("datadir+", Opt_datadir_add), fsparam_string("upperdir", Opt_upperdir), fsparam_string("workdir", Opt_workdir), fsparam_flag("default_permissions", Opt_default_permissions), fsparam_enum("redirect_dir", Opt_redirect_dir, ovl_parameter_redirect_dir), fsparam_enum("index", Opt_index, ovl_parameter_bool), fsparam_enum("uuid", Opt_uuid, ovl_parameter_uuid), fsparam_enum("nfs_export", Opt_nfs_export, ovl_parameter_bool), fsparam_flag("userxattr", Opt_userxattr), fsparam_enum("xino", Opt_xino, ovl_parameter_xino), fsparam_enum("metacopy", Opt_metacopy, ovl_parameter_bool), fsparam_enum("verity", Opt_verity, ovl_parameter_verity), fsparam_flag("volatile", Opt_volatile), {} }; static char *ovl_next_opt(char **s) { char *sbegin = *s; char *p; if (sbegin == NULL) return NULL; for (p = sbegin; *p; p++) { if (*p == '\\') { p++; if (!*p) break; } else if (*p == ',') { *p = '\0'; *s = p + 1; return sbegin; } } *s = NULL; return sbegin; } static int ovl_parse_monolithic(struct fs_context *fc, void *data) { return vfs_parse_monolithic_sep(fc, data, ovl_next_opt); } static ssize_t ovl_parse_param_split_lowerdirs(char *str) { ssize_t nr_layers = 1, nr_colons = 0; char *s, *d; for (s = d = str;; s++, d++) { if (*s == '\\') { /* keep esc chars in split lowerdir */ *d++ = *s++; } else if (*s == ':') { bool next_colon = (*(s + 1) == ':'); nr_colons++; if (nr_colons == 2 && next_colon) { pr_err("only single ':' or double '::' sequences of unescaped colons in lowerdir mount option allowed.\n"); return -EINVAL; } /* count layers, not colons */ if (!next_colon) nr_layers++; *d = '\0'; continue; } *d = *s; if (!*s) { /* trailing colons */ if (nr_colons) { pr_err("unescaped trailing colons in lowerdir mount option.\n"); return -EINVAL; } break; } nr_colons = 0; } return nr_layers; } static int ovl_mount_dir_noesc(const char *name, struct path *path) { int err = -EINVAL; if (!*name) { pr_err("empty lowerdir\n"); goto out; } err = kern_path(name, LOOKUP_FOLLOW, path); if (err) { pr_err("failed to resolve '%s': %i\n", name, err); goto out; } return 0; out: return err; } static void ovl_unescape(char *s) { char *d = s; for (;; s++, d++) { if (*s == '\\') s++; *d = *s; if (!*s) break; } } static int ovl_mount_dir(const char *name, struct path *path) { int err = -ENOMEM; char *tmp = kstrdup(name, GFP_KERNEL); if (tmp) { ovl_unescape(tmp); err = ovl_mount_dir_noesc(tmp, path); kfree(tmp); } return err; } static int ovl_mount_dir_check(struct fs_context *fc, const struct path *path, enum ovl_opt layer, const char *name, bool upper) { struct ovl_fs_context *ctx = fc->fs_private; if (!d_is_dir(path->dentry)) return invalfc(fc, "%s is not a directory", name); /* * Root dentries of case-insensitive capable filesystems might * not have the dentry operations set, but still be incompatible * with overlayfs. Check explicitly to prevent post-mount * failures. */ if (sb_has_encoding(path->mnt->mnt_sb)) return invalfc(fc, "case-insensitive capable filesystem on %s not supported", name); if (ovl_dentry_weird(path->dentry)) return invalfc(fc, "filesystem on %s not supported", name); /* * Check whether upper path is read-only here to report failures * early. Don't forget to recheck when the superblock is created * as the mount attributes could change. */ if (upper) { if (path->dentry->d_flags & DCACHE_OP_REAL) return invalfc(fc, "filesystem on %s not supported as upperdir", name); if (__mnt_is_readonly(path->mnt)) return invalfc(fc, "filesystem on %s is read-only", name); } else { if (ctx->lowerdir_all && layer != Opt_lowerdir) return invalfc(fc, "lowerdir+ and datadir+ cannot follow lowerdir"); if (ctx->nr_data && layer == Opt_lowerdir_add) return invalfc(fc, "regular lower layers cannot follow data layers"); if (ctx->nr == OVL_MAX_STACK) return invalfc(fc, "too many lower directories, limit is %d", OVL_MAX_STACK); } return 0; } static int ovl_ctx_realloc_lower(struct fs_context *fc) { struct ovl_fs_context *ctx = fc->fs_private; struct ovl_fs_context_layer *l; size_t nr; if (ctx->nr < ctx->capacity) return 0; nr = min_t(size_t, max(4096 / sizeof(*l), ctx->capacity * 2), OVL_MAX_STACK); l = krealloc_array(ctx->lower, nr, sizeof(*l), GFP_KERNEL_ACCOUNT); if (!l) return -ENOMEM; ctx->lower = l; ctx->capacity = nr; return 0; } static void ovl_add_layer(struct fs_context *fc, enum ovl_opt layer, struct path *path, char **pname) { struct ovl_fs *ofs = fc->s_fs_info; struct ovl_config *config = &ofs->config; struct ovl_fs_context *ctx = fc->fs_private; struct ovl_fs_context_layer *l; switch (layer) { case Opt_workdir: swap(config->workdir, *pname); swap(ctx->work, *path); break; case Opt_upperdir: swap(config->upperdir, *pname); swap(ctx->upper, *path); break; case Opt_datadir_add: ctx->nr_data++; fallthrough; case Opt_lowerdir: fallthrough; case Opt_lowerdir_add: WARN_ON(ctx->nr >= ctx->capacity); l = &ctx->lower[ctx->nr++]; memset(l, 0, sizeof(*l)); swap(l->name, *pname); swap(l->path, *path); break; default: WARN_ON(1); } } static int ovl_parse_layer(struct fs_context *fc, const char *layer_name, enum ovl_opt layer) { char *name = kstrdup(layer_name, GFP_KERNEL); bool upper = (layer == Opt_upperdir || layer == Opt_workdir); struct path path; int err; if (!name) return -ENOMEM; if (upper || layer == Opt_lowerdir) err = ovl_mount_dir(name, &path); else err = ovl_mount_dir_noesc(name, &path); if (err) goto out_free; err = ovl_mount_dir_check(fc, &path, layer, name, upper); if (err) goto out_put; if (!upper) { err = ovl_ctx_realloc_lower(fc); if (err) goto out_put; } /* Store the user provided path string in ctx to show in mountinfo */ ovl_add_layer(fc, layer, &path, &name); out_put: path_put(&path); out_free: kfree(name); return err; } static void ovl_reset_lowerdirs(struct ovl_fs_context *ctx) { struct ovl_fs_context_layer *l = ctx->lower; // Reset old user provided lowerdir string kfree(ctx->lowerdir_all); ctx->lowerdir_all = NULL; for (size_t nr = 0; nr < ctx->nr; nr++, l++) { path_put(&l->path); kfree(l->name); l->name = NULL; } ctx->nr = 0; ctx->nr_data = 0; } /* * Parse lowerdir= mount option: * * e.g.: lowerdir=/lower1:/lower2:/lower3::/data1::/data2 * Set "/lower1", "/lower2", and "/lower3" as lower layers and * "/data1" and "/data2" as data lower layers. Any existing lower * layers are replaced. */ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) { int err; struct ovl_fs_context *ctx = fc->fs_private; char *dup = NULL, *iter; ssize_t nr_lower, nr; bool data_layer = false; /* * Ensure we're backwards compatible with mount(2) * by allowing relative paths. */ /* drop all existing lower layers */ ovl_reset_lowerdirs(ctx); if (!*name) return 0; if (*name == ':') { pr_err("cannot append lower layer\n"); return -EINVAL; } // Store user provided lowerdir string to show in mount options ctx->lowerdir_all = kstrdup(name, GFP_KERNEL); if (!ctx->lowerdir_all) return -ENOMEM; dup = kstrdup(name, GFP_KERNEL); if (!dup) return -ENOMEM; err = -EINVAL; nr_lower = ovl_parse_param_split_lowerdirs(dup); if (nr_lower < 0) goto out_err; if (nr_lower > OVL_MAX_STACK) { pr_err("too many lower directories, limit is %d\n", OVL_MAX_STACK); goto out_err; } iter = dup; for (nr = 0; nr < nr_lower; nr++) { err = ovl_parse_layer(fc, iter, Opt_lowerdir); if (err) goto out_err; if (data_layer) ctx->nr_data++; /* Calling strchr() again would overrun. */ if (ctx->nr == nr_lower) break; err = -EINVAL; iter = strchr(iter, '\0') + 1; if (*iter) { /* * This is a regular layer so we require that * there are no data layers. */ if (ctx->nr_data > 0) { pr_err("regular lower layers cannot follow data lower layers\n"); goto out_err; } data_layer = false; continue; } /* This is a data lower layer. */ data_layer = true; iter++; } kfree(dup); return 0; out_err: kfree(dup); /* Intentionally don't realloc to a smaller size. */ return err; } static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param) { int err = 0; struct fs_parse_result result; struct ovl_fs *ofs = fc->s_fs_info; struct ovl_config *config = &ofs->config; struct ovl_fs_context *ctx = fc->fs_private; int opt; if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { /* * On remount overlayfs has always ignored all mount * options no matter if malformed or not so for * backwards compatibility we do the same here. */ if (fc->oldapi) return 0; /* * Give us the freedom to allow changing mount options * with the new mount api in the future. So instead of * silently ignoring everything we report a proper * error. This is only visible for users of the new * mount api. */ return invalfc(fc, "No changes allowed in reconfigure"); } opt = fs_parse(fc, ovl_parameter_spec, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_lowerdir: err = ovl_parse_param_lowerdir(param->string, fc); break; case Opt_lowerdir_add: case Opt_datadir_add: case Opt_upperdir: case Opt_workdir: err = ovl_parse_layer(fc, param->string, opt); break; case Opt_default_permissions: config->default_permissions = true; break; case Opt_redirect_dir: config->redirect_mode = result.uint_32; if (config->redirect_mode == OVL_REDIRECT_OFF) { config->redirect_mode = ovl_redirect_always_follow ? OVL_REDIRECT_FOLLOW : OVL_REDIRECT_NOFOLLOW; } ctx->set.redirect = true; break; case Opt_index: config->index = result.uint_32; ctx->set.index = true; break; case Opt_uuid: config->uuid = result.uint_32; break; case Opt_nfs_export: config->nfs_export = result.uint_32; ctx->set.nfs_export = true; break; case Opt_xino: config->xino = result.uint_32; break; case Opt_metacopy: config->metacopy = result.uint_32; ctx->set.metacopy = true; break; case Opt_verity: config->verity_mode = result.uint_32; break; case Opt_volatile: config->ovl_volatile = true; break; case Opt_userxattr: config->userxattr = true; break; default: pr_err("unrecognized mount option \"%s\" or missing value\n", param->key); return -EINVAL; } return err; } static int ovl_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, ovl_fill_super); } static inline void ovl_fs_context_free(struct ovl_fs_context *ctx) { ovl_reset_lowerdirs(ctx); path_put(&ctx->upper); path_put(&ctx->work); kfree(ctx->lower); kfree(ctx); } static void ovl_free(struct fs_context *fc) { struct ovl_fs *ofs = fc->s_fs_info; struct ovl_fs_context *ctx = fc->fs_private; /* * ofs is stored in the fs_context when it is initialized. * ofs is transferred to the superblock on a successful mount, * but if an error occurs before the transfer we have to free * it here. */ if (ofs) ovl_free_fs(ofs); if (ctx) ovl_fs_context_free(ctx); } static int ovl_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct ovl_fs *ofs = OVL_FS(sb); struct super_block *upper_sb; int ret = 0; if (!(fc->sb_flags & SB_RDONLY) && ovl_force_readonly(ofs)) return -EROFS; if (fc->sb_flags & SB_RDONLY && !sb_rdonly(sb)) { upper_sb = ovl_upper_mnt(ofs)->mnt_sb; if (ovl_should_sync(ofs)) { down_read(&upper_sb->s_umount); ret = sync_filesystem(upper_sb); up_read(&upper_sb->s_umount); } } return ret; } static const struct fs_context_operations ovl_context_ops = { .parse_monolithic = ovl_parse_monolithic, .parse_param = ovl_parse_param, .get_tree = ovl_get_tree, .reconfigure = ovl_reconfigure, .free = ovl_free, }; /* * This is called during fsopen() and will record the user namespace of * the caller in fc->user_ns since we've raised FS_USERNS_MOUNT. We'll * need it when we actually create the superblock to verify that the * process creating the superblock is in the same user namespace as * process that called fsopen(). */ int ovl_init_fs_context(struct fs_context *fc) { struct ovl_fs_context *ctx; struct ovl_fs *ofs; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (!ctx) return -ENOMEM; /* * By default we allocate for three lower layers. It's likely * that it'll cover most users. */ ctx->lower = kmalloc_array(3, sizeof(*ctx->lower), GFP_KERNEL_ACCOUNT); if (!ctx->lower) goto out_err; ctx->capacity = 3; ofs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL); if (!ofs) goto out_err; ofs->config.redirect_mode = ovl_redirect_mode_def(); ofs->config.index = ovl_index_def; ofs->config.uuid = ovl_uuid_def(); ofs->config.nfs_export = ovl_nfs_export_def; ofs->config.xino = ovl_xino_def(); ofs->config.metacopy = ovl_metacopy_def; fc->s_fs_info = ofs; fc->fs_private = ctx; fc->ops = &ovl_context_ops; return 0; out_err: ovl_fs_context_free(ctx); return -ENOMEM; } void ovl_free_fs(struct ovl_fs *ofs) { struct vfsmount **mounts; unsigned i; iput(ofs->workbasedir_trap); iput(ofs->workdir_trap); dput(ofs->whiteout); dput(ofs->workdir); if (ofs->workdir_locked) ovl_inuse_unlock(ofs->workbasedir); dput(ofs->workbasedir); if (ofs->upperdir_locked) ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root); /* Reuse ofs->config.lowerdirs as a vfsmount array before freeing it */ mounts = (struct vfsmount **) ofs->config.lowerdirs; for (i = 0; i < ofs->numlayer; i++) { iput(ofs->layers[i].trap); kfree(ofs->config.lowerdirs[i]); mounts[i] = ofs->layers[i].mnt; } kern_unmount_array(mounts, ofs->numlayer); kfree(ofs->layers); for (i = 0; i < ofs->numfs; i++) free_anon_bdev(ofs->fs[i].pseudo_dev); kfree(ofs->fs); kfree(ofs->config.lowerdirs); kfree(ofs->config.upperdir); kfree(ofs->config.workdir); if (ofs->creator_cred) put_cred(ofs->creator_cred); kfree(ofs); } int ovl_fs_params_verify(const struct ovl_fs_context *ctx, struct ovl_config *config) { struct ovl_opt_set set = ctx->set; if (ctx->nr_data > 0 && !config->metacopy) { pr_err("lower data-only dirs require metacopy support.\n"); return -EINVAL; } /* Workdir/index are useless in non-upper mount */ if (!config->upperdir) { if (config->workdir) { pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n", config->workdir); kfree(config->workdir); config->workdir = NULL; } if (config->index && set.index) { pr_info("option \"index=on\" is useless in a non-upper mount, ignore\n"); set.index = false; } config->index = false; } if (!config->upperdir && config->ovl_volatile) { pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n"); config->ovl_volatile = false; } if (!config->upperdir && config->uuid == OVL_UUID_ON) { pr_info("option \"uuid=on\" requires an upper fs, falling back to uuid=null.\n"); config->uuid = OVL_UUID_NULL; } /* Resolve verity -> metacopy dependency */ if (config->verity_mode && !config->metacopy) { /* Don't allow explicit specified conflicting combinations */ if (set.metacopy) { pr_err("conflicting options: metacopy=off,verity=%s\n", ovl_verity_mode(config)); return -EINVAL; } /* Otherwise automatically enable metacopy. */ config->metacopy = true; } /* * This is to make the logic below simpler. It doesn't make any other * difference, since redirect_dir=on is only used for upper. */ if (!config->upperdir && config->redirect_mode == OVL_REDIRECT_FOLLOW) config->redirect_mode = OVL_REDIRECT_ON; /* Resolve verity -> metacopy -> redirect_dir dependency */ if (config->metacopy && config->redirect_mode != OVL_REDIRECT_ON) { if (set.metacopy && set.redirect) { pr_err("conflicting options: metacopy=on,redirect_dir=%s\n", ovl_redirect_mode(config)); return -EINVAL; } if (config->verity_mode && set.redirect) { pr_err("conflicting options: verity=%s,redirect_dir=%s\n", ovl_verity_mode(config), ovl_redirect_mode(config)); return -EINVAL; } if (set.redirect) { /* * There was an explicit redirect_dir=... that resulted * in this conflict. */ pr_info("disabling metacopy due to redirect_dir=%s\n", ovl_redirect_mode(config)); config->metacopy = false; } else { /* Automatically enable redirect otherwise. */ config->redirect_mode = OVL_REDIRECT_ON; } } /* Resolve nfs_export -> index dependency */ if (config->nfs_export && !config->index) { if (!config->upperdir && config->redirect_mode != OVL_REDIRECT_NOFOLLOW) { pr_info("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n"); config->nfs_export = false; } else if (set.nfs_export && set.index) { pr_err("conflicting options: nfs_export=on,index=off\n"); return -EINVAL; } else if (set.index) { /* * There was an explicit index=off that resulted * in this conflict. */ pr_info("disabling nfs_export due to index=off\n"); config->nfs_export = false; } else { /* Automatically enable index otherwise. */ config->index = true; } } /* Resolve nfs_export -> !metacopy && !verity dependency */ if (config->nfs_export && config->metacopy) { if (set.nfs_export && set.metacopy) { pr_err("conflicting options: nfs_export=on,metacopy=on\n"); return -EINVAL; } if (set.metacopy) { /* * There was an explicit metacopy=on that resulted * in this conflict. */ pr_info("disabling nfs_export due to metacopy=on\n"); config->nfs_export = false; } else if (config->verity_mode) { /* * There was an explicit verity=.. that resulted * in this conflict. */ pr_info("disabling nfs_export due to verity=%s\n", ovl_verity_mode(config)); config->nfs_export = false; } else { /* * There was an explicit nfs_export=on that resulted * in this conflict. */ pr_info("disabling metacopy due to nfs_export=on\n"); config->metacopy = false; } } /* Resolve userxattr -> !redirect && !metacopy && !verity dependency */ if (config->userxattr) { if (set.redirect && config->redirect_mode != OVL_REDIRECT_NOFOLLOW) { pr_err("conflicting options: userxattr,redirect_dir=%s\n", ovl_redirect_mode(config)); return -EINVAL; } if (config->metacopy && set.metacopy) { pr_err("conflicting options: userxattr,metacopy=on\n"); return -EINVAL; } if (config->verity_mode) { pr_err("conflicting options: userxattr,verity=%s\n", ovl_verity_mode(config)); return -EINVAL; } /* * Silently disable default setting of redirect and metacopy. * This shall be the default in the future as well: these * options must be explicitly enabled if used together with * userxattr. */ config->redirect_mode = OVL_REDIRECT_NOFOLLOW; config->metacopy = false; } return 0; } /** * ovl_show_options * @m: the seq_file handle * @dentry: The dentry to query * * Prints the mount options for a given superblock. * Returns zero; does not fail. */ int ovl_show_options(struct seq_file *m, struct dentry *dentry) { struct super_block *sb = dentry->d_sb; struct ovl_fs *ofs = OVL_FS(sb); size_t nr, nr_merged_lower, nr_lower = 0; char **lowerdirs = ofs->config.lowerdirs; /* * lowerdirs[0] holds the colon separated list that user provided * with lowerdir mount option. * lowerdirs[1..numlayer] hold the lowerdir paths that were added * using the lowerdir+ and datadir+ mount options. * For now, we do not allow mixing the legacy lowerdir mount option * with the new lowerdir+ and datadir+ mount options. */ if (lowerdirs[0]) { seq_show_option(m, "lowerdir", lowerdirs[0]); } else { nr_lower = ofs->numlayer; nr_merged_lower = nr_lower - ofs->numdatalayer; } for (nr = 1; nr < nr_lower; nr++) { if (nr < nr_merged_lower) seq_show_option(m, "lowerdir+", lowerdirs[nr]); else seq_show_option(m, "datadir+", lowerdirs[nr]); } if (ofs->config.upperdir) { seq_show_option(m, "upperdir", ofs->config.upperdir); seq_show_option(m, "workdir", ofs->config.workdir); } if (ofs->config.default_permissions) seq_puts(m, ",default_permissions"); if (ofs->config.redirect_mode != ovl_redirect_mode_def()) seq_printf(m, ",redirect_dir=%s", ovl_redirect_mode(&ofs->config)); if (ofs->config.index != ovl_index_def) seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off"); if (ofs->config.uuid != ovl_uuid_def()) seq_printf(m, ",uuid=%s", ovl_uuid_mode(&ofs->config)); if (ofs->config.nfs_export != ovl_nfs_export_def) seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ? "on" : "off"); if (ofs->config.xino != ovl_xino_def() && !ovl_same_fs(ofs)) seq_printf(m, ",xino=%s", ovl_xino_mode(&ofs->config)); if (ofs->config.metacopy != ovl_metacopy_def) seq_printf(m, ",metacopy=%s", ofs->config.metacopy ? "on" : "off"); if (ofs->config.ovl_volatile) seq_puts(m, ",volatile"); if (ofs->config.userxattr) seq_puts(m, ",userxattr"); if (ofs->config.verity_mode != ovl_verity_mode_def()) seq_printf(m, ",verity=%s", ovl_verity_mode(&ofs->config)); return 0; } |
| 510 1695 1654 48 | 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 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix - mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitrary value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitrary value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * mac80211 <-> driver interface * * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH * Copyright (C) 2018 - 2024 Intel Corporation */ #ifndef MAC80211_H #define MAC80211_H #include <linux/bug.h> #include <linux/kernel.h> #include <linux/if_ether.h> #include <linux/skbuff.h> #include <linux/ieee80211.h> #include <linux/lockdep.h> #include <net/cfg80211.h> #include <net/codel.h> #include <net/ieee80211_radiotap.h> #include <asm/unaligned.h> /** * DOC: Introduction * * mac80211 is the Linux stack for 802.11 hardware that implements * only partial functionality in hard- or firmware. This document * defines the interface between mac80211 and low-level hardware * drivers. */ /** * DOC: Calling mac80211 from interrupts * * Only ieee80211_tx_status_irqsafe() and ieee80211_rx_irqsafe() can be * called in hardware interrupt context. The low-level driver must not call any * other functions in hardware interrupt context. If there is a need for such * call, the low-level driver should first ACK the interrupt and perform the * IEEE 802.11 code call after this, e.g. from a scheduled workqueue or even * tasklet function. * * NOTE: If the driver opts to use the _irqsafe() functions, it may not also * use the non-IRQ-safe functions! */ /** * DOC: Warning * * If you're reading this document and not the header file itself, it will * be incomplete because not all documentation has been converted yet. */ /** * DOC: Frame format * * As a general rule, when frames are passed between mac80211 and the driver, * they start with the IEEE 802.11 header and include the same octets that are * sent over the air except for the FCS which should be calculated by the * hardware. * * There are, however, various exceptions to this rule for advanced features: * * The first exception is for hardware encryption and decryption offload * where the IV/ICV may or may not be generated in hardware. * * Secondly, when the hardware handles fragmentation, the frame handed to * the driver from mac80211 is the MSDU, not the MPDU. */ /** * DOC: mac80211 workqueue * * mac80211 provides its own workqueue for drivers and internal mac80211 use. * The workqueue is a single threaded workqueue and can only be accessed by * helpers for sanity checking. Drivers must ensure all work added onto the * mac80211 workqueue should be cancelled on the driver stop() callback. * * mac80211 will flush the workqueue upon interface removal and during * suspend. * * All work performed on the mac80211 workqueue must not acquire the RTNL lock. * */ /** * DOC: mac80211 software tx queueing * * mac80211 uses an intermediate queueing implementation, designed to allow the * driver to keep hardware queues short and to provide some fairness between * different stations/interfaces. * * Drivers must provide the .wake_tx_queue driver operation by either * linking it to ieee80211_handle_wake_tx_queue() or implementing a custom * handler. * * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with * another per-sta for non-data/non-mgmt and bufferable management frames, and * a single per-vif queue for multicast data frames. * * The driver is expected to initialize its private per-queue data for stations * and interfaces in the .add_interface and .sta_add ops. * * The driver can't access the internal TX queues (iTXQs) directly. * Whenever mac80211 adds a new frame to a queue, it calls the .wake_tx_queue * driver op. * Drivers implementing a custom .wake_tx_queue op can get them by calling * ieee80211_tx_dequeue(). Drivers using ieee80211_handle_wake_tx_queue() will * simply get the individual frames pushed via the .tx driver operation. * * Drivers can optionally delegate responsibility for scheduling queues to * mac80211, to take advantage of airtime fairness accounting. In this case, to * obtain the next queue to pull frames from, the driver calls * ieee80211_next_txq(). The driver is then expected to return the txq using * ieee80211_return_txq(). * * For AP powersave TIM handling, the driver only needs to indicate if it has * buffered packets in the driver specific data structures by calling * ieee80211_sta_set_buffered(). For frames buffered in the ieee80211_txq * struct, mac80211 sets the appropriate TIM PVB bits and calls * .release_buffered_frames(). * In that callback the driver is therefore expected to release its own * buffered frames and afterwards also frames from the ieee80211_txq (obtained * via the usual ieee80211_tx_dequeue). */ /** * DOC: HW timestamping * * Timing Measurement and Fine Timing Measurement require accurate timestamps * of the action frames TX/RX and their respective acks. * * To report hardware timestamps for Timing Measurement or Fine Timing * Measurement frame RX, the low level driver should set the SKB's hwtstamp * field to the frame RX timestamp and report the ack TX timestamp in the * ieee80211_rx_status struct. * * Similarly, to report hardware timestamps for Timing Measurement or Fine * Timing Measurement frame TX, the driver should set the SKB's hwtstamp field * to the frame TX timestamp and report the ack RX timestamp in the * ieee80211_tx_status struct. */ struct device; /** * enum ieee80211_max_queues - maximum number of queues * * @IEEE80211_MAX_QUEUES: Maximum number of regular device queues. * @IEEE80211_MAX_QUEUE_MAP: bitmap with maximum queues set */ enum ieee80211_max_queues { IEEE80211_MAX_QUEUES = 16, IEEE80211_MAX_QUEUE_MAP = BIT(IEEE80211_MAX_QUEUES) - 1, }; #define IEEE80211_INVAL_HW_QUEUE 0xff /** * enum ieee80211_ac_numbers - AC numbers as used in mac80211 * @IEEE80211_AC_VO: voice * @IEEE80211_AC_VI: video * @IEEE80211_AC_BE: best effort * @IEEE80211_AC_BK: background */ enum ieee80211_ac_numbers { IEEE80211_AC_VO = 0, IEEE80211_AC_VI = 1, IEEE80211_AC_BE = 2, IEEE80211_AC_BK = 3, }; /** * struct ieee80211_tx_queue_params - transmit queue configuration * * The information provided in this structure is required for QoS * transmit queue configuration. Cf. IEEE 802.11 7.3.2.29. * * @aifs: arbitration interframe space [0..255] * @cw_min: minimum contention window [a value of the form * 2^n-1 in the range 1..32767] * @cw_max: maximum contention window [like @cw_min] * @txop: maximum burst time in units of 32 usecs, 0 meaning disabled * @acm: is mandatory admission control required for the access category * @uapsd: is U-APSD mode enabled for the queue * @mu_edca: is the MU EDCA configured * @mu_edca_param_rec: MU EDCA Parameter Record for HE */ struct ieee80211_tx_queue_params { u16 txop; u16 cw_min; u16 cw_max; u8 aifs; bool acm; bool uapsd; bool mu_edca; struct ieee80211_he_mu_edca_param_ac_rec mu_edca_param_rec; }; struct ieee80211_low_level_stats { unsigned int dot11ACKFailureCount; unsigned int dot11RTSFailureCount; unsigned int dot11FCSErrorCount; unsigned int dot11RTSSuccessCount; }; /** * enum ieee80211_chanctx_change - change flag for channel context * @IEEE80211_CHANCTX_CHANGE_WIDTH: The channel width changed * @IEEE80211_CHANCTX_CHANGE_RX_CHAINS: The number of RX chains changed * @IEEE80211_CHANCTX_CHANGE_RADAR: radar detection flag changed * @IEEE80211_CHANCTX_CHANGE_CHANNEL: switched to another operating channel, * this is used only with channel switching with CSA * @IEEE80211_CHANCTX_CHANGE_MIN_WIDTH: The min required channel width changed * @IEEE80211_CHANCTX_CHANGE_AP: The AP channel definition changed, so (wider * bandwidth) OFDMA settings need to be changed * @IEEE80211_CHANCTX_CHANGE_PUNCTURING: The punctured channel(s) bitmap * was changed. */ enum ieee80211_chanctx_change { IEEE80211_CHANCTX_CHANGE_WIDTH = BIT(0), IEEE80211_CHANCTX_CHANGE_RX_CHAINS = BIT(1), IEEE80211_CHANCTX_CHANGE_RADAR = BIT(2), IEEE80211_CHANCTX_CHANGE_CHANNEL = BIT(3), IEEE80211_CHANCTX_CHANGE_MIN_WIDTH = BIT(4), IEEE80211_CHANCTX_CHANGE_AP = BIT(5), IEEE80211_CHANCTX_CHANGE_PUNCTURING = BIT(6), }; /** * struct ieee80211_chan_req - A channel "request" * @oper: channel definition to use for operation * @ap: the channel definition of the AP, if any * (otherwise the chan member is %NULL) */ struct ieee80211_chan_req { struct cfg80211_chan_def oper; struct cfg80211_chan_def ap; }; /** * struct ieee80211_chanctx_conf - channel context that vifs may be tuned to * * This is the driver-visible part. The ieee80211_chanctx * that contains it is visible in mac80211 only. * * @def: the channel definition * @min_def: the minimum channel definition currently required. * @ap: the channel definition the AP actually is operating as, * for use with (wider bandwidth) OFDMA * @radio_idx: index of the wiphy radio used used for this channel * @rx_chains_static: The number of RX chains that must always be * active on the channel to receive MIMO transmissions * @rx_chains_dynamic: The number of RX chains that must be enabled * after RTS/CTS handshake to receive SMPS MIMO transmissions; * this will always be >= @rx_chains_static. * @radar_enabled: whether radar detection is enabled on this channel. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *), size is determined in hw information. */ struct ieee80211_chanctx_conf { struct cfg80211_chan_def def; struct cfg80211_chan_def min_def; struct cfg80211_chan_def ap; int radio_idx; u8 rx_chains_static, rx_chains_dynamic; bool radar_enabled; u8 drv_priv[] __aligned(sizeof(void *)); }; /** * enum ieee80211_chanctx_switch_mode - channel context switch mode * @CHANCTX_SWMODE_REASSIGN_VIF: Both old and new contexts already * exist (and will continue to exist), but the virtual interface * needs to be switched from one to the other. * @CHANCTX_SWMODE_SWAP_CONTEXTS: The old context exists but will stop * to exist with this call, the new context doesn't exist but * will be active after this call, the virtual interface switches * from the old to the new (note that the driver may of course * implement this as an on-the-fly chandef switch of the existing * hardware context, but the mac80211 pointer for the old context * will cease to exist and only the new one will later be used * for changes/removal.) */ enum ieee80211_chanctx_switch_mode { CHANCTX_SWMODE_REASSIGN_VIF, CHANCTX_SWMODE_SWAP_CONTEXTS, }; /** * struct ieee80211_vif_chanctx_switch - vif chanctx switch information * * This is structure is used to pass information about a vif that * needs to switch from one chanctx to another. The * &ieee80211_chanctx_switch_mode defines how the switch should be * done. * * @vif: the vif that should be switched from old_ctx to new_ctx * @link_conf: the link conf that's switching * @old_ctx: the old context to which the vif was assigned * @new_ctx: the new context to which the vif must be assigned */ struct ieee80211_vif_chanctx_switch { struct ieee80211_vif *vif; struct ieee80211_bss_conf *link_conf; struct ieee80211_chanctx_conf *old_ctx; struct ieee80211_chanctx_conf *new_ctx; }; /** * enum ieee80211_bss_change - BSS change notification flags * * These flags are used with the bss_info_changed(), link_info_changed() * and vif_cfg_changed() callbacks to indicate which parameter(s) changed. * * @BSS_CHANGED_ASSOC: association status changed (associated/disassociated), * also implies a change in the AID. * @BSS_CHANGED_ERP_CTS_PROT: CTS protection changed * @BSS_CHANGED_ERP_PREAMBLE: preamble changed * @BSS_CHANGED_ERP_SLOT: slot timing changed * @BSS_CHANGED_HT: 802.11n parameters changed * @BSS_CHANGED_BASIC_RATES: Basic rateset changed * @BSS_CHANGED_BEACON_INT: Beacon interval changed * @BSS_CHANGED_BSSID: BSSID changed, for whatever * reason (IBSS and managed mode) * @BSS_CHANGED_BEACON: Beacon data changed, retrieve * new beacon (beaconing modes) * @BSS_CHANGED_BEACON_ENABLED: Beaconing should be * enabled/disabled (beaconing modes) * @BSS_CHANGED_CQM: Connection quality monitor config changed * @BSS_CHANGED_IBSS: IBSS join status changed * @BSS_CHANGED_ARP_FILTER: Hardware ARP filter address list or state changed. * @BSS_CHANGED_QOS: QoS for this association was enabled/disabled. Note * that it is only ever disabled for station mode. * @BSS_CHANGED_IDLE: Idle changed for this BSS/interface. * @BSS_CHANGED_SSID: SSID changed for this BSS (AP and IBSS mode) * @BSS_CHANGED_AP_PROBE_RESP: Probe Response changed for this BSS (AP mode) * @BSS_CHANGED_PS: PS changed for this BSS (STA mode) * @BSS_CHANGED_TXPOWER: TX power setting changed for this interface * @BSS_CHANGED_P2P_PS: P2P powersave settings (CTWindow, opportunistic PS) * changed * @BSS_CHANGED_BEACON_INFO: Data from the AP's beacon became available: * currently dtim_period only is under consideration. * @BSS_CHANGED_BANDWIDTH: The bandwidth used by this interface changed, * note that this is only called when it changes after the channel * context had been assigned. * @BSS_CHANGED_OCB: OCB join status changed * @BSS_CHANGED_MU_GROUPS: VHT MU-MIMO group id or user position changed * @BSS_CHANGED_KEEP_ALIVE: keep alive options (idle period or protected * keep alive) changed. * @BSS_CHANGED_MCAST_RATE: Multicast Rate setting changed for this interface * @BSS_CHANGED_FTM_RESPONDER: fine timing measurement request responder * functionality changed for this BSS (AP mode). * @BSS_CHANGED_TWT: TWT status changed * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed. * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response * status changed. * @BSS_CHANGED_MLD_VALID_LINKS: MLD valid links status changed. * @BSS_CHANGED_MLD_TTLM: negotiated TID to link mapping was changed * @BSS_CHANGED_TPE: transmit power envelope changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, BSS_CHANGED_ERP_CTS_PROT = 1<<1, BSS_CHANGED_ERP_PREAMBLE = 1<<2, BSS_CHANGED_ERP_SLOT = 1<<3, BSS_CHANGED_HT = 1<<4, BSS_CHANGED_BASIC_RATES = 1<<5, BSS_CHANGED_BEACON_INT = 1<<6, BSS_CHANGED_BSSID = 1<<7, BSS_CHANGED_BEACON = 1<<8, BSS_CHANGED_BEACON_ENABLED = 1<<9, BSS_CHANGED_CQM = 1<<10, BSS_CHANGED_IBSS = 1<<11, BSS_CHANGED_ARP_FILTER = 1<<12, BSS_CHANGED_QOS = 1<<13, BSS_CHANGED_IDLE = 1<<14, BSS_CHANGED_SSID = 1<<15, BSS_CHANGED_AP_PROBE_RESP = 1<<16, BSS_CHANGED_PS = 1<<17, BSS_CHANGED_TXPOWER = 1<<18, BSS_CHANGED_P2P_PS = 1<<19, BSS_CHANGED_BEACON_INFO = 1<<20, BSS_CHANGED_BANDWIDTH = 1<<21, BSS_CHANGED_OCB = 1<<22, BSS_CHANGED_MU_GROUPS = 1<<23, BSS_CHANGED_KEEP_ALIVE = 1<<24, BSS_CHANGED_MCAST_RATE = 1<<25, BSS_CHANGED_FTM_RESPONDER = 1<<26, BSS_CHANGED_TWT = 1<<27, BSS_CHANGED_HE_OBSS_PD = 1<<28, BSS_CHANGED_HE_BSS_COLOR = 1<<29, BSS_CHANGED_FILS_DISCOVERY = 1<<30, BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = BIT_ULL(31), BSS_CHANGED_MLD_VALID_LINKS = BIT_ULL(33), BSS_CHANGED_MLD_TTLM = BIT_ULL(34), BSS_CHANGED_TPE = BIT_ULL(35), /* when adding here, make sure to change ieee80211_reconfig */ }; /* * The maximum number of IPv4 addresses listed for ARP filtering. If the number * of addresses for an interface increase beyond this value, hardware ARP * filtering will be disabled. */ #define IEEE80211_BSS_ARP_ADDR_LIST_LEN 4 /** * enum ieee80211_event_type - event to be notified to the low level driver * @RSSI_EVENT: AP's rssi crossed the a threshold set by the driver. * @MLME_EVENT: event related to MLME * @BAR_RX_EVENT: a BAR was received * @BA_FRAME_TIMEOUT: Frames were released from the reordering buffer because * they timed out. This won't be called for each frame released, but only * once each time the timeout triggers. */ enum ieee80211_event_type { RSSI_EVENT, MLME_EVENT, BAR_RX_EVENT, BA_FRAME_TIMEOUT, }; /** * enum ieee80211_rssi_event_data - relevant when event type is %RSSI_EVENT * @RSSI_EVENT_HIGH: AP's rssi went below the threshold set by the driver. * @RSSI_EVENT_LOW: AP's rssi went above the threshold set by the driver. */ enum ieee80211_rssi_event_data { RSSI_EVENT_HIGH, RSSI_EVENT_LOW, }; /** * struct ieee80211_rssi_event - data attached to an %RSSI_EVENT * @data: See &enum ieee80211_rssi_event_data */ struct ieee80211_rssi_event { enum ieee80211_rssi_event_data data; }; /** * enum ieee80211_mlme_event_data - relevant when event type is %MLME_EVENT * @AUTH_EVENT: the MLME operation is authentication * @ASSOC_EVENT: the MLME operation is association * @DEAUTH_RX_EVENT: deauth received.. * @DEAUTH_TX_EVENT: deauth sent. */ enum ieee80211_mlme_event_data { AUTH_EVENT, ASSOC_EVENT, DEAUTH_RX_EVENT, DEAUTH_TX_EVENT, }; /** * enum ieee80211_mlme_event_status - relevant when event type is %MLME_EVENT * @MLME_SUCCESS: the MLME operation completed successfully. * @MLME_DENIED: the MLME operation was denied by the peer. * @MLME_TIMEOUT: the MLME operation timed out. */ enum ieee80211_mlme_event_status { MLME_SUCCESS, MLME_DENIED, MLME_TIMEOUT, }; /** * struct ieee80211_mlme_event - data attached to an %MLME_EVENT * @data: See &enum ieee80211_mlme_event_data * @status: See &enum ieee80211_mlme_event_status * @reason: the reason code if applicable */ struct ieee80211_mlme_event { enum ieee80211_mlme_event_data data; enum ieee80211_mlme_event_status status; u16 reason; }; /** * struct ieee80211_ba_event - data attached for BlockAck related events * @sta: pointer to the &ieee80211_sta to which this event relates * @tid: the tid * @ssn: the starting sequence number (for %BAR_RX_EVENT) */ struct ieee80211_ba_event { struct ieee80211_sta *sta; u16 tid; u16 ssn; }; /** * struct ieee80211_event - event to be sent to the driver * @type: The event itself. See &enum ieee80211_event_type. * @u.rssi: relevant if &type is %RSSI_EVENT * @u.mlme: relevant if &type is %AUTH_EVENT * @u.ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT * @u:union holding the fields above */ struct ieee80211_event { enum ieee80211_event_type type; union { struct ieee80211_rssi_event rssi; struct ieee80211_mlme_event mlme; struct ieee80211_ba_event ba; } u; }; /** * struct ieee80211_mu_group_data - STA's VHT MU-MIMO group data * * This structure describes the group id data of VHT MU-MIMO * * @membership: 64 bits array - a bit is set if station is member of the group * @position: 2 bits per group id indicating the position in the group */ struct ieee80211_mu_group_data { u8 membership[WLAN_MEMBERSHIP_LEN]; u8 position[WLAN_USER_POSITION_LEN]; }; /** * struct ieee80211_ftm_responder_params - FTM responder parameters * * @lci: LCI subelement content * @civicloc: CIVIC location subelement content * @lci_len: LCI data length * @civicloc_len: Civic data length */ struct ieee80211_ftm_responder_params { const u8 *lci; const u8 *civicloc; size_t lci_len; size_t civicloc_len; }; /** * struct ieee80211_fils_discovery - FILS discovery parameters from * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. * * @min_interval: Minimum packet interval in TUs (0 - 10000) * @max_interval: Maximum packet interval in TUs (0 - 10000) */ struct ieee80211_fils_discovery { u32 min_interval; u32 max_interval; }; #define IEEE80211_TPE_EIRP_ENTRIES_320MHZ 5 struct ieee80211_parsed_tpe_eirp { bool valid; s8 power[IEEE80211_TPE_EIRP_ENTRIES_320MHZ]; u8 count; }; #define IEEE80211_TPE_PSD_ENTRIES_320MHZ 16 struct ieee80211_parsed_tpe_psd { bool valid; s8 power[IEEE80211_TPE_PSD_ENTRIES_320MHZ]; u8 count, n; }; /** * struct ieee80211_parsed_tpe - parsed transmit power envelope information * @max_local: maximum local EIRP, one value for 20, 40, 80, 160, 320 MHz each * (indexed by TX power category) * @max_reg_client: maximum regulatory client EIRP, one value for 20, 40, 80, * 160, 320 MHz each * (indexed by TX power category) * @psd_local: maximum local power spectral density, one value for each 20 MHz * subchannel per bss_conf's chanreq.oper * (indexed by TX power category) * @psd_reg_client: maximum regulatory power spectral density, one value for * each 20 MHz subchannel per bss_conf's chanreq.oper * (indexed by TX power category) */ struct ieee80211_parsed_tpe { struct ieee80211_parsed_tpe_eirp max_local[2], max_reg_client[2]; struct ieee80211_parsed_tpe_psd psd_local[2], psd_reg_client[2]; }; /** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association * to that BSS) that can change during the lifetime of the BSS. * * @vif: reference to owning VIF * @bss: the cfg80211 bss descriptor. Valid only for a station, and only * when associated. Note: This contains information which is not * necessarily authenticated. For example, information coming from probe * responses. * @addr: (link) address used locally * @link_id: link ID, or 0 for non-MLO * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE * @uora_exists: is the UORA element advertised by AP * @uora_ocw_range: UORA element's OCW Range field * @frame_time_rts_th: HE duration RTS threshold, in units of 32us * @he_support: does this BSS support HE * @twt_requester: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) * @twt_responder: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) * @twt_protected: does this BSS support protected TWT frames * @twt_broadcast: does this BSS support broadcast TWT * @use_cts_prot: use CTS protection * @use_short_preamble: use 802.11b short preamble * @use_short_slot: use short slot time (only relevant for ERP) * @dtim_period: num of beacons before the next DTIM, for beaconing, * valid in station mode only if after the driver was notified * with the %BSS_CHANGED_BEACON_INFO flag, will be non-zero then. * @sync_tsf: last beacon's/probe response's TSF timestamp (could be old * as it may have been received during scanning long ago). If the * HW flag %IEEE80211_HW_TIMING_BEACON_ONLY is set, then this can * only come from a beacon, but might not become valid until after * association when a beacon is received (which is notified with the * %BSS_CHANGED_DTIM flag.). See also sync_dtim_count important notice. * @sync_device_ts: the device timestamp corresponding to the sync_tsf, * the driver/device can use this to calculate synchronisation * (see @sync_tsf). See also sync_dtim_count important notice. * @sync_dtim_count: Only valid when %IEEE80211_HW_TIMING_BEACON_ONLY * is requested, see @sync_tsf/@sync_device_ts. * IMPORTANT: These three sync_* parameters would possibly be out of sync * by the time the driver will use them. The synchronized view is currently * guaranteed only in certain callbacks. * Note also that this is not used with MLD associations, mac80211 doesn't * know how to track beacons for all of the links for this. * @beacon_int: beacon interval * @assoc_capability: capabilities taken from assoc resp * @basic_rates: bitmap of basic rates, each bit stands for an * index into the rate table configured by the driver in * the current band. * @beacon_rate: associated AP's beacon TX rate * @mcast_rate: per-band multicast rate index + 1 (0: disabled) * @bssid: The BSSID for this BSS * @enable_beacon: whether beaconing should be enabled or not * @chanreq: Channel request for this BSS -- the hardware might be * configured a higher bandwidth than this BSS uses, for example. * @mu_group: VHT MU-MIMO group membership data * @ht_operation_mode: HT operation mode like in &struct ieee80211_ht_operation. * This field is only valid when the channel is a wide HT/VHT channel. * Note that with TDLS this can be the case (channel is HT, protection must * be used from this field) even when the BSS association isn't using HT. * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value * implies disabled. As with the cfg80211 callback, a change here should * cause an event to be sent indicating where the current value is in * relation to the newly configured threshold. * @cqm_rssi_low: Connection quality monitor RSSI lower threshold, a zero value * implies disabled. This is an alternative mechanism to the single * threshold event and can't be enabled simultaneously with it. * @cqm_rssi_high: Connection quality monitor RSSI upper threshold. * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis * @qos: This is a QoS-enabled BSS. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. * @txpower: TX power in dBm. INT_MIN means not configured. * @txpower_type: TX power adjustment used to control per packet Transmit * Power Control (TPC) in lower driver for the current vif. In particular * TPC is enabled if value passed in %txpower_type is * NL80211_TX_POWER_LIMITED (allow using less than specified from * userspace), whereas TPC is disabled if %txpower_type is set to * NL80211_TX_POWER_FIXED (use value configured from userspace) * @p2p_noa_attr: P2P NoA attribute for P2P powersave * @allow_p2p_go_ps: indication for AP or P2P GO interface, whether it's allowed * to use P2P PS mechanism or not. AP/P2P GO is not allowed to use P2P PS * if it has associated clients without P2P PS support. * @max_idle_period: the time period during which the station can refrain from * transmitting frames to its associated AP without being disassociated. * In units of 1000 TUs. Zero value indicates that the AP did not include * a (valid) BSS Max Idle Period Element. * @protected_keep_alive: if set, indicates that the station should send an RSN * protected frame to the AP to reset the idle timer at the AP for the * station. * @ftm_responder: whether to enable or disable fine timing measurement FTM * responder functionality. * @ftmr_params: configurable lci/civic parameter when enabling FTM responder. * @nontransmitted: this BSS is a nontransmitted BSS profile * @transmitter_bssid: the address of transmitter AP * @bssid_index: index inside the multiple BSSID set * @bssid_indicator: 2^bssid_indicator is the maximum number of APs in set * @ema_ap: AP supports enhancements of discovery and advertisement of * nontransmitted BSSIDs * @profile_periodicity: the least number of beacon frames need to be received * in order to discover all the nontransmitted BSSIDs in the set. * @he_oper: HE operation information of the BSS (AP/Mesh) or of the AP we are * connected to (STA) * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE * @fils_discovery: FILS discovery configuration * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response * interval. * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed * to driver when rate control is offloaded to firmware. * @power_type: power type of BSS for 6 GHz * @tpe: transmit power envelope information * @pwr_reduction: power constraint of BSS. * @eht_support: does this BSS support EHT * @csa_active: marks whether a channel switch is going on. * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @chanctx_conf: The channel context this interface is assigned to, or %NULL * when it is not assigned. This pointer is RCU-protected due to the TX * path needing to access it; even though the netdev carrier will always * be off when it is %NULL there can still be races and packets could be * processed after it switches back to %NULL. * @color_change_active: marks whether a color change is ongoing. * @color_change_color: the bss color that will be used after the change. * @ht_ldpc: in AP mode, indicates interface has HT LDPC capability. * @vht_ldpc: in AP mode, indicates interface has VHT LDPC capability. * @he_ldpc: in AP mode, indicates interface has HE LDPC capability. * @vht_su_beamformer: in AP mode, does this BSS support operation as an VHT SU * beamformer * @vht_su_beamformee: in AP mode, does this BSS support operation as an VHT SU * beamformee * @vht_mu_beamformer: in AP mode, does this BSS support operation as an VHT MU * beamformer * @vht_mu_beamformee: in AP mode, does this BSS support operation as an VHT MU * beamformee * @he_su_beamformer: in AP-mode, does this BSS support operation as an HE SU * beamformer * @he_su_beamformee: in AP-mode, does this BSS support operation as an HE SU * beamformee * @he_mu_beamformer: in AP-mode, does this BSS support operation as an HE MU * beamformer * @he_full_ul_mumimo: does this BSS support the reception (AP) or transmission * (non-AP STA) of an HE TB PPDU on an RU that spans the entire PPDU * bandwidth * @eht_su_beamformer: in AP-mode, does this BSS enable operation as an EHT SU * beamformer * @eht_su_beamformee: in AP-mode, does this BSS enable operation as an EHT SU * beamformee * @eht_mu_beamformer: in AP-mode, does this BSS enable operation as an EHT MU * beamformer * @eht_80mhz_full_bw_ul_mumimo: in AP-mode, does this BSS support the * reception of an EHT TB PPDU on an RU that spans the entire PPDU * bandwidth */ struct ieee80211_bss_conf { struct ieee80211_vif *vif; struct cfg80211_bss *bss; const u8 *bssid; unsigned int link_id; u8 addr[ETH_ALEN] __aligned(2); u8 htc_trig_based_pkt_ext; bool uora_exists; u8 uora_ocw_range; u16 frame_time_rts_th; bool he_support; bool twt_requester; bool twt_responder; bool twt_protected; bool twt_broadcast; /* erp related data */ bool use_cts_prot; bool use_short_preamble; bool use_short_slot; bool enable_beacon; u8 dtim_period; u16 beacon_int; u16 assoc_capability; u64 sync_tsf; u32 sync_device_ts; u8 sync_dtim_count; u32 basic_rates; struct ieee80211_rate *beacon_rate; int mcast_rate[NUM_NL80211_BANDS]; u16 ht_operation_mode; s32 cqm_rssi_thold; u32 cqm_rssi_hyst; s32 cqm_rssi_low; s32 cqm_rssi_high; struct ieee80211_chan_req chanreq; struct ieee80211_mu_group_data mu_group; bool qos; bool hidden_ssid; int txpower; enum nl80211_tx_power_setting txpower_type; struct ieee80211_p2p_noa_attr p2p_noa_attr; bool allow_p2p_go_ps; u16 max_idle_period; bool protected_keep_alive; bool ftm_responder; struct ieee80211_ftm_responder_params *ftmr_params; /* Multiple BSSID data */ bool nontransmitted; u8 transmitter_bssid[ETH_ALEN]; u8 bssid_index; u8 bssid_indicator; bool ema_ap; u8 profile_periodicity; struct { u32 params; u16 nss_set; } he_oper; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; struct ieee80211_fils_discovery fils_discovery; u32 unsol_bcast_probe_resp_interval; struct cfg80211_bitrate_mask beacon_tx_rate; enum ieee80211_ap_reg_power power_type; struct ieee80211_parsed_tpe tpe; u8 pwr_reduction; bool eht_support; bool csa_active; bool mu_mimo_owner; struct ieee80211_chanctx_conf __rcu *chanctx_conf; bool color_change_active; u8 color_change_color; bool ht_ldpc; bool vht_ldpc; bool he_ldpc; bool vht_su_beamformer; bool vht_su_beamformee; bool vht_mu_beamformer; bool vht_mu_beamformee; bool he_su_beamformer; bool he_su_beamformee; bool he_mu_beamformer; bool he_full_ul_mumimo; bool eht_su_beamformer; bool eht_su_beamformee; bool eht_mu_beamformer; bool eht_80mhz_full_bw_ul_mumimo; }; /** * enum mac80211_tx_info_flags - flags to describe transmission information/status * * These flags are used with the @flags member of &ieee80211_tx_info. * * @IEEE80211_TX_CTL_REQ_TX_STATUS: require TX status callback for this frame. * @IEEE80211_TX_CTL_ASSIGN_SEQ: The driver has to assign a sequence * number to this frame, taking care of not overwriting the fragment * number and increasing the sequence number only when the * IEEE80211_TX_CTL_FIRST_FRAGMENT flag is set. mac80211 will properly * assign sequence numbers to QoS-data frames but cannot do so correctly * for non-QoS-data and management frames because beacons need them from * that counter as well and mac80211 cannot guarantee proper sequencing. * If this flag is set, the driver should instruct the hardware to * assign a sequence number to the frame or assign one itself. Cf. IEEE * 802.11-2007 7.1.3.4.1 paragraph 3. This flag will always be set for * beacons and always be clear for frames without a sequence number field. * @IEEE80211_TX_CTL_NO_ACK: tell the low level not to wait for an ack * @IEEE80211_TX_CTL_CLEAR_PS_FILT: clear powersave filter for destination * station * @IEEE80211_TX_CTL_FIRST_FRAGMENT: this is a first fragment of the frame * @IEEE80211_TX_CTL_SEND_AFTER_DTIM: send this frame after DTIM beacon * @IEEE80211_TX_CTL_AMPDU: this frame should be sent as part of an A-MPDU * @IEEE80211_TX_CTL_INJECTED: Frame was injected, internal to mac80211. * @IEEE80211_TX_STAT_TX_FILTERED: The frame was not transmitted * because the destination STA was in powersave mode. Note that to * avoid race conditions, the filter must be set by the hardware or * firmware upon receiving a frame that indicates that the station * went to sleep (must be done on device to filter frames already on * the queue) and may only be unset after mac80211 gives the OK for * that by setting the IEEE80211_TX_CTL_CLEAR_PS_FILT (see above), * since only then is it guaranteed that no more frames are in the * hardware queue. * @IEEE80211_TX_STAT_ACK: Frame was acknowledged * @IEEE80211_TX_STAT_AMPDU: The frame was aggregated, so status * is for the whole aggregation. * @IEEE80211_TX_STAT_AMPDU_NO_BACK: no block ack was returned, * so consider using block ack request (BAR). * @IEEE80211_TX_CTL_RATE_CTRL_PROBE: internal to mac80211, can be * set by rate control algorithms to indicate probe rate, will * be cleared for fragmented frames (except on the last fragment) * @IEEE80211_TX_INTFL_OFFCHAN_TX_OK: Internal to mac80211. Used to indicate * that a frame can be transmitted while the queues are stopped for * off-channel operation. * @IEEE80211_TX_CTL_HW_80211_ENCAP: This frame uses hardware encapsulation * (header conversion) * @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211, * used to indicate that a frame was already retried due to PS * @IEEE80211_TX_INTFL_DONT_ENCRYPT: completely internal to mac80211, * used to indicate frame should not be encrypted * @IEEE80211_TX_CTL_NO_PS_BUFFER: This frame is a response to a poll * frame (PS-Poll or uAPSD) or a non-bufferable MMPDU and must * be sent although the station is in powersave mode. * @IEEE80211_TX_CTL_MORE_FRAMES: More frames will be passed to the * transmit function after the current frame, this can be used * by drivers to kick the DMA queue only if unset or when the * queue gets full. * @IEEE80211_TX_INTFL_RETRANSMISSION: This frame is being retransmitted * after TX status because the destination was asleep, it must not * be modified again (no seqno assignment, crypto, etc.) * @IEEE80211_TX_INTFL_MLME_CONN_TX: This frame was transmitted by the MLME * code for connection establishment, this indicates that its status * should kick the MLME state machine. * @IEEE80211_TX_INTFL_NL80211_FRAME_TX: Frame was requested through nl80211 * MLME command (internal to mac80211 to figure out whether to send TX * status to user space) * @IEEE80211_TX_CTL_LDPC: tells the driver to use LDPC for this frame * @IEEE80211_TX_CTL_STBC: Enables Space-Time Block Coding (STBC) for this * frame and selects the maximum number of streams that it can use. * @IEEE80211_TX_CTL_TX_OFFCHAN: Marks this packet to be transmitted on * the off-channel channel when a remain-on-channel offload is done * in hardware -- normal packets still flow and are expected to be * handled properly by the device. * @IEEE80211_TX_INTFL_TKIP_MIC_FAILURE: Marks this packet to be used for TKIP * testing. It will be sent out with incorrect Michael MIC key to allow * TKIP countermeasures to be tested. * @IEEE80211_TX_CTL_NO_CCK_RATE: This frame will be sent at non CCK rate. * This flag is actually used for management frame especially for P2P * frames not being sent at CCK rate in 2GHz band. * @IEEE80211_TX_STATUS_EOSP: This packet marks the end of service period, * when its status is reported the service period ends. For frames in * an SP that mac80211 transmits, it is already set; for driver frames * the driver may set this flag. It is also used to do the same for * PS-Poll responses. * @IEEE80211_TX_CTL_USE_MINRATE: This frame will be sent at lowest rate. * This flag is used to send nullfunc frame at minimum rate when * the nullfunc is used for connection monitoring purpose. * @IEEE80211_TX_CTL_DONTFRAG: Don't fragment this packet even if it * would be fragmented by size (this is optional, only used for * monitor injection). * @IEEE80211_TX_STAT_NOACK_TRANSMITTED: A frame that was marked with * IEEE80211_TX_CTL_NO_ACK has been successfully transmitted without * any errors (like issues specific to the driver/HW). * This flag must not be set for frames that don't request no-ack * behaviour with IEEE80211_TX_CTL_NO_ACK. * * Note: If you have to add new flags to the enumeration, then don't * forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary. */ enum mac80211_tx_info_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), IEEE80211_TX_CTL_ASSIGN_SEQ = BIT(1), IEEE80211_TX_CTL_NO_ACK = BIT(2), IEEE80211_TX_CTL_CLEAR_PS_FILT = BIT(3), IEEE80211_TX_CTL_FIRST_FRAGMENT = BIT(4), IEEE80211_TX_CTL_SEND_AFTER_DTIM = BIT(5), IEEE80211_TX_CTL_AMPDU = BIT(6), IEEE80211_TX_CTL_INJECTED = BIT(7), IEEE80211_TX_STAT_TX_FILTERED = BIT(8), IEEE80211_TX_STAT_ACK = BIT(9), IEEE80211_TX_STAT_AMPDU = BIT(10), IEEE80211_TX_STAT_AMPDU_NO_BACK = BIT(11), IEEE80211_TX_CTL_RATE_CTRL_PROBE = BIT(12), IEEE80211_TX_INTFL_OFFCHAN_TX_OK = BIT(13), IEEE80211_TX_CTL_HW_80211_ENCAP = BIT(14), IEEE80211_TX_INTFL_RETRIED = BIT(15), IEEE80211_TX_INTFL_DONT_ENCRYPT = BIT(16), IEEE80211_TX_CTL_NO_PS_BUFFER = BIT(17), IEEE80211_TX_CTL_MORE_FRAMES = BIT(18), IEEE80211_TX_INTFL_RETRANSMISSION = BIT(19), IEEE80211_TX_INTFL_MLME_CONN_TX = BIT(20), IEEE80211_TX_INTFL_NL80211_FRAME_TX = BIT(21), IEEE80211_TX_CTL_LDPC = BIT(22), IEEE80211_TX_CTL_STBC = BIT(23) | BIT(24), IEEE80211_TX_CTL_TX_OFFCHAN = BIT(25), IEEE80211_TX_INTFL_TKIP_MIC_FAILURE = BIT(26), IEEE80211_TX_CTL_NO_CCK_RATE = BIT(27), IEEE80211_TX_STATUS_EOSP = BIT(28), IEEE80211_TX_CTL_USE_MINRATE = BIT(29), IEEE80211_TX_CTL_DONTFRAG = BIT(30), IEEE80211_TX_STAT_NOACK_TRANSMITTED = BIT(31), }; #define IEEE80211_TX_CTL_STBC_SHIFT 23 #define IEEE80211_TX_RC_S1G_MCS IEEE80211_TX_RC_VHT_MCS /** * enum mac80211_tx_control_flags - flags to describe transmit control * * @IEEE80211_TX_CTRL_PORT_CTRL_PROTO: this frame is a port control * protocol frame (e.g. EAP) * @IEEE80211_TX_CTRL_PS_RESPONSE: This frame is a response to a poll * frame (PS-Poll or uAPSD). * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup * @IEEE80211_TX_INTCFL_NEED_TXPROCESSING: completely internal to mac80211, * used to indicate that a pending frame requires TX processing before * it can be sent out. * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that * has already been assigned to this frame. * @IEEE80211_TX_CTRL_DONT_REORDER: This frame should not be reordered * relative to other frames that have this flag set, independent * of their QoS TID or other priority field values. * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally * for sequence number assignment * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted * due to scanning, not in normal operation on the interface. * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this * frame should be transmitted on the specific link. This really is * only relevant for frames that do not have data present, and is * also not used for 802.3 format frames. Note that even if the frame * is on a specific link, address translation might still apply if * it's intended for an MLD. * * These flags are used in tx_info->control.flags. */ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_PORT_CTRL_PROTO = BIT(0), IEEE80211_TX_CTRL_PS_RESPONSE = BIT(1), IEEE80211_TX_CTRL_RATE_INJECT = BIT(2), IEEE80211_TX_CTRL_AMSDU = BIT(3), IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9), IEEE80211_TX_CTRL_SCAN_TX = BIT(10), IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; #define IEEE80211_LINK_UNSPECIFIED 0xf #define IEEE80211_TX_CTRL_MLO_LINK_UNSPEC \ u32_encode_bits(IEEE80211_LINK_UNSPECIFIED, \ IEEE80211_TX_CTRL_MLO_LINK) /** * enum mac80211_tx_status_flags - flags to describe transmit status * * @IEEE80211_TX_STATUS_ACK_SIGNAL_VALID: ACK signal is valid * * These flags are used in tx_info->status.flags. */ enum mac80211_tx_status_flags { IEEE80211_TX_STATUS_ACK_SIGNAL_VALID = BIT(0), }; /* * This definition is used as a mask to clear all temporary flags, which are * set by the tx handlers for each transmission attempt by the mac80211 stack. */ #define IEEE80211_TX_TEMPORARY_FLAGS (IEEE80211_TX_CTL_NO_ACK | \ IEEE80211_TX_CTL_CLEAR_PS_FILT | IEEE80211_TX_CTL_FIRST_FRAGMENT | \ IEEE80211_TX_CTL_SEND_AFTER_DTIM | IEEE80211_TX_CTL_AMPDU | \ IEEE80211_TX_STAT_TX_FILTERED | IEEE80211_TX_STAT_ACK | \ IEEE80211_TX_STAT_AMPDU | IEEE80211_TX_STAT_AMPDU_NO_BACK | \ IEEE80211_TX_CTL_RATE_CTRL_PROBE | IEEE80211_TX_CTL_NO_PS_BUFFER | \ IEEE80211_TX_CTL_MORE_FRAMES | IEEE80211_TX_CTL_LDPC | \ IEEE80211_TX_CTL_STBC | IEEE80211_TX_STATUS_EOSP) /** * enum mac80211_rate_control_flags - per-rate flags set by the * Rate Control algorithm. * * These flags are set by the Rate control algorithm for each rate during tx, * in the @flags member of struct ieee80211_tx_rate. * * @IEEE80211_TX_RC_USE_RTS_CTS: Use RTS/CTS exchange for this rate. * @IEEE80211_TX_RC_USE_CTS_PROTECT: CTS-to-self protection is required. * This is set if the current BSS requires ERP protection. * @IEEE80211_TX_RC_USE_SHORT_PREAMBLE: Use short preamble. * @IEEE80211_TX_RC_MCS: HT rate. * @IEEE80211_TX_RC_VHT_MCS: VHT MCS rate, in this case the idx field is split * into a higher 4 bits (Nss) and lower 4 bits (MCS number) * @IEEE80211_TX_RC_GREEN_FIELD: Indicates whether this rate should be used in * Greenfield mode. * @IEEE80211_TX_RC_40_MHZ_WIDTH: Indicates if the Channel Width should be 40 MHz. * @IEEE80211_TX_RC_80_MHZ_WIDTH: Indicates 80 MHz transmission * @IEEE80211_TX_RC_160_MHZ_WIDTH: Indicates 160 MHz transmission * (80+80 isn't supported yet) * @IEEE80211_TX_RC_DUP_DATA: The frame should be transmitted on both of the * adjacent 20 MHz channels, if the current channel type is * NL80211_CHAN_HT40MINUS or NL80211_CHAN_HT40PLUS. * @IEEE80211_TX_RC_SHORT_GI: Short Guard interval should be used for this rate. */ enum mac80211_rate_control_flags { IEEE80211_TX_RC_USE_RTS_CTS = BIT(0), IEEE80211_TX_RC_USE_CTS_PROTECT = BIT(1), IEEE80211_TX_RC_USE_SHORT_PREAMBLE = BIT(2), /* rate index is an HT/VHT MCS instead of an index */ IEEE80211_TX_RC_MCS = BIT(3), IEEE80211_TX_RC_GREEN_FIELD = BIT(4), IEEE80211_TX_RC_40_MHZ_WIDTH = BIT(5), IEEE80211_TX_RC_DUP_DATA = BIT(6), IEEE80211_TX_RC_SHORT_GI = BIT(7), IEEE80211_TX_RC_VHT_MCS = BIT(8), IEEE80211_TX_RC_80_MHZ_WIDTH = BIT(9), IEEE80211_TX_RC_160_MHZ_WIDTH = BIT(10), }; /* there are 40 bytes if you don't need the rateset to be kept */ #define IEEE80211_TX_INFO_DRIVER_DATA_SIZE 40 /* if you do need the rateset, then you have less space */ #define IEEE80211_TX_INFO_RATE_DRIVER_DATA_SIZE 24 /* maximum number of rate stages */ #define IEEE80211_TX_MAX_RATES 4 /* maximum number of rate table entries */ #define IEEE80211_TX_RATE_TABLE_SIZE 4 /** * struct ieee80211_tx_rate - rate selection/status * * @idx: rate index to attempt to send with * @flags: rate control flags (&enum mac80211_rate_control_flags) * @count: number of tries in this rate before going to the next rate * * A value of -1 for @idx indicates an invalid rate and, if used * in an array of retry rates, that no more rates should be tried. * * When used for transmit status reporting, the driver should * always report the rate along with the flags it used. * * &struct ieee80211_tx_info contains an array of these structs * in the control information, and it will be filled by the rate * control algorithm according to what should be sent. For example, * if this array contains, in the format { <idx>, <count> } the * information:: * * { 3, 2 }, { 2, 2 }, { 1, 4 }, { -1, 0 }, { -1, 0 } * * then this means that the frame should be transmitted * up to twice at rate 3, up to twice at rate 2, and up to four * times at rate 1 if it doesn't get acknowledged. Say it gets * acknowledged by the peer after the fifth attempt, the status * information should then contain:: * * { 3, 2 }, { 2, 2 }, { 1, 1 }, { -1, 0 } ... * * since it was transmitted twice at rate 3, twice at rate 2 * and once at rate 1 after which we received an acknowledgement. */ struct ieee80211_tx_rate { s8 idx; u16 count:5, flags:11; } __packed; #define IEEE80211_MAX_TX_RETRY 31 static inline bool ieee80211_rate_valid(struct ieee80211_tx_rate *rate) { return rate->idx >= 0 && rate->count > 0; } static inline void ieee80211_rate_set_vht(struct ieee80211_tx_rate *rate, u8 mcs, u8 nss) { WARN_ON(mcs & ~0xF); WARN_ON((nss - 1) & ~0x7); rate->idx = ((nss - 1) << 4) | mcs; } static inline u8 ieee80211_rate_get_vht_mcs(const struct ieee80211_tx_rate *rate) { return rate->idx & 0xF; } static inline u8 ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) { return (rate->idx >> 4) + 1; } /** * struct ieee80211_tx_info - skb transmit information * * This structure is placed in skb->cb for three uses: * (1) mac80211 TX control - mac80211 tells the driver what to do * (2) driver internal use (if applicable) * (3) TX status information - driver tells mac80211 what happened * * @flags: transmit info flags, defined above * @band: the band to transmit on (use e.g. for checking for races), * not valid if the interface is an MLD since we won't know which * link the frame will be transmitted on * @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC * @status_data: internal data for TX status handling, assigned privately, * see also &enum ieee80211_status_data for the internal documentation * @status_data_idr: indicates status data is IDR allocated ID for ack frame * @tx_time_est: TX time estimate in units of 4us, used internally * @control: union part for control data * @control.rates: TX rates array to try * @control.rts_cts_rate_idx: rate for RTS or CTS * @control.use_rts: use RTS * @control.use_cts_prot: use RTS/CTS * @control.short_preamble: use short preamble (CCK only) * @control.skip_table: skip externally configured rate table * @control.jiffies: timestamp for expiry on powersave clients * @control.vif: virtual interface (may be NULL) * @control.hw_key: key to encrypt with (may be NULL) * @control.flags: control flags, see &enum mac80211_tx_control_flags * @control.enqueue_time: enqueue time (for iTXQs) * @driver_rates: alias to @control.rates to reserve space * @pad: padding * @rate_driver_data: driver use area if driver needs @control.rates * @status: union part for status data * @status.rates: attempted rates * @status.ack_signal: ACK signal * @status.ampdu_ack_len: AMPDU ack length * @status.ampdu_len: AMPDU length * @status.antenna: (legacy, kept only for iwlegacy) * @status.tx_time: airtime consumed for transmission; note this is only * used for WMM AC, not for airtime fairness * @status.flags: status flags, see &enum mac80211_tx_status_flags * @status.status_driver_data: driver use area * @ack: union part for pure ACK data * @ack.cookie: cookie for the ACK * @driver_data: array of driver_data pointers */ struct ieee80211_tx_info { /* common information */ u32 flags; u32 band:3, status_data_idr:1, status_data:13, hw_queue:4, tx_time_est:10; /* 1 free bit */ union { struct { union { /* rate control */ struct { struct ieee80211_tx_rate rates[ IEEE80211_TX_MAX_RATES]; s8 rts_cts_rate_idx; u8 use_rts:1; u8 use_cts_prot:1; u8 short_preamble:1; u8 skip_table:1; /* for injection only (bitmap) */ u8 antennas:2; /* 14 bits free */ }; /* only needed before rate control */ unsigned long jiffies; }; /* NB: vif can be NULL for injected frames */ struct ieee80211_vif *vif; struct ieee80211_key_conf *hw_key; u32 flags; codel_time_t enqueue_time; } control; struct { u64 cookie; } ack; struct { struct ieee80211_tx_rate rates[IEEE80211_TX_MAX_RATES]; s32 ack_signal; u8 ampdu_ack_len; u8 ampdu_len; u8 antenna; u8 pad; u16 tx_time; u8 flags; u8 pad2; void *status_driver_data[16 / sizeof(void *)]; } status; struct { struct ieee80211_tx_rate driver_rates[ IEEE80211_TX_MAX_RATES]; u8 pad[4]; void *rate_driver_data[ IEEE80211_TX_INFO_RATE_DRIVER_DATA_SIZE / sizeof(void *)]; }; void *driver_data[ IEEE80211_TX_INFO_DRIVER_DATA_SIZE / sizeof(void *)]; }; }; static inline u16 ieee80211_info_set_tx_time_est(struct ieee80211_tx_info *info, u16 tx_time_est) { /* We only have 10 bits in tx_time_est, so store airtime * in increments of 4us and clamp the maximum to 2**12-1 */ info->tx_time_est = min_t(u16, tx_time_est, 4095) >> 2; return info->tx_time_est << 2; } static inline u16 ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) { return info->tx_time_est << 2; } /*** * struct ieee80211_rate_status - mrr stage for status path * * This struct is used in struct ieee80211_tx_status to provide drivers a * dynamic way to report about used rates and power levels per packet. * * @rate_idx The actual used rate. * @try_count How often the rate was tried. * @tx_power_idx An idx into the ieee80211_hw->tx_power_levels list of the * corresponding wifi hardware. The idx shall point to the power level * that was used when sending the packet. */ struct ieee80211_rate_status { struct rate_info rate_idx; u8 try_count; u8 tx_power_idx; }; /** * struct ieee80211_tx_status - extended tx status info for rate control * * @sta: Station that the packet was transmitted for * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) * @rates: Mrr stages that were used when sending the packet * @n_rates: Number of mrr stages (count of instances for @rates) * @free_list: list where processed skbs are stored to be free'd by the driver * @ack_hwtstamp: Hardware timestamp of the received ack in nanoseconds * Only needed for Timing measurement and Fine timing measurement action * frames. Only reported by devices that have timestamping enabled. */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; struct ieee80211_rate_status *rates; ktime_t ack_hwtstamp; u8 n_rates; struct list_head *free_list; }; /** * struct ieee80211_scan_ies - descriptors for different blocks of IEs * * This structure is used to point to different blocks of IEs in HW scan * and scheduled scan. These blocks contain the IEs passed by userspace * and the ones generated by mac80211. * * @ies: pointers to band specific IEs. * @len: lengths of band_specific IEs. * @common_ies: IEs for all bands (especially vendor specific ones) * @common_ie_len: length of the common_ies */ struct ieee80211_scan_ies { const u8 *ies[NUM_NL80211_BANDS]; size_t len[NUM_NL80211_BANDS]; const u8 *common_ies; size_t common_ie_len; }; static inline struct ieee80211_tx_info *IEEE80211_SKB_CB(struct sk_buff *skb) { return (struct ieee80211_tx_info *)skb->cb; } static inline struct ieee80211_rx_status *IEEE80211_SKB_RXCB(struct sk_buff *skb) { return (struct ieee80211_rx_status *)skb->cb; } /** * ieee80211_tx_info_clear_status - clear TX status * * @info: The &struct ieee80211_tx_info to be cleared. * * When the driver passes an skb back to mac80211, it must report * a number of things in TX status. This function clears everything * in the TX status but the rate control information (it does clear * the count since you need to fill that in anyway). * * NOTE: While the rates array is kept intact, this will wipe all of the * driver_data fields in info, so it's up to the driver to restore * any fields it needs after calling this helper. */ static inline void ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) { int i; BUILD_BUG_ON(offsetof(struct ieee80211_tx_info, status.rates) != offsetof(struct ieee80211_tx_info, control.rates)); BUILD_BUG_ON(offsetof(struct ieee80211_tx_info, status.rates) != offsetof(struct ieee80211_tx_info, driver_rates)); BUILD_BUG_ON(offsetof(struct ieee80211_tx_info, status.rates) != 8); /* clear the rate counts */ for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) info->status.rates[i].count = 0; memset_after(&info->status, 0, rates); } /** * enum mac80211_rx_flags - receive flags * * These flags are used with the @flag member of &struct ieee80211_rx_status. * @RX_FLAG_MMIC_ERROR: Michael MIC error was reported on this frame. * Use together with %RX_FLAG_MMIC_STRIPPED. * @RX_FLAG_DECRYPTED: This frame was decrypted in hardware. * @RX_FLAG_MMIC_STRIPPED: the Michael MIC is stripped off this frame, * verification has been done by the hardware. * @RX_FLAG_IV_STRIPPED: The IV and ICV are stripped from this frame. * If this flag is set, the stack cannot do any replay detection * hence the driver or hardware will have to do that. * @RX_FLAG_PN_VALIDATED: Currently only valid for CCMP/GCMP frames, this * flag indicates that the PN was verified for replay protection. * Note that this flag is also currently only supported when a frame * is also decrypted (ie. @RX_FLAG_DECRYPTED must be set) * @RX_FLAG_DUP_VALIDATED: The driver should set this flag if it did * de-duplication by itself. * @RX_FLAG_FAILED_FCS_CRC: Set this flag if the FCS check failed on * the frame. * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on * the frame. * @RX_FLAG_MACTIME: The timestamp passed in the RX status (@mactime * field) is valid if this field is non-zero, and the position * where the timestamp was sampled depends on the value. * @RX_FLAG_MACTIME_START: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the first symbol of the MPDU * was received. This is useful in monitor mode and for proper IBSS * merging. * @RX_FLAG_MACTIME_END: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the last symbol of the MPDU * (including FCS) was received. * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the SYNC preamble was received. * @RX_FLAG_MACTIME_IS_RTAP_TS64: The timestamp passed in the RX status @mactime * is only for use in the radiotap timestamp header, not otherwise a valid * @mactime value. Note this is a separate flag so that we continue to see * %RX_FLAG_MACTIME as unset. Also note that in this case the timestamp is * reported to be 64 bits wide, not just 32. * @RX_FLAG_NO_SIGNAL_VAL: The signal strength value is not present. * Valid only for data frames (mainly A-MPDU) * @RX_FLAG_AMPDU_DETAILS: A-MPDU details are known, in particular the reference * number (@ampdu_reference) must be populated and be a distinct number for * each A-MPDU * @RX_FLAG_AMPDU_LAST_KNOWN: last subframe is known, should be set on all * subframes of a single A-MPDU * @RX_FLAG_AMPDU_IS_LAST: this subframe is the last subframe of the A-MPDU * @RX_FLAG_AMPDU_DELIM_CRC_ERROR: A delimiter CRC error has been detected * on this subframe * @RX_FLAG_AMPDU_DELIM_CRC_KNOWN: The delimiter CRC field is known (the CRC * is stored in the @ampdu_delimiter_crc field) * @RX_FLAG_MIC_STRIPPED: The mic was stripped of this packet. Decryption was * done by the hardware * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without * processing it in any regular way. * This is useful if drivers offload some frames but still want to report * them for sniffing purposes. * @RX_FLAG_SKIP_MONITOR: Process and report frame to all interfaces except * monitor interfaces. * This is useful if drivers offload some frames but still want to report * them for sniffing purposes. * @RX_FLAG_AMSDU_MORE: Some drivers may prefer to report separate A-MSDU * subframes instead of a one huge frame for performance reasons. * All, but the last MSDU from an A-MSDU should have this flag set. E.g. * if an A-MSDU has 3 frames, the first 2 must have the flag set, while * the 3rd (last) one must not have this flag set. The flag is used to * deal with retransmission/duplication recovery properly since A-MSDU * subframes share the same sequence number. Reported subframes can be * either regular MSDU or singly A-MSDUs. Subframes must not be * interleaved with other frames. * @RX_FLAG_RADIOTAP_TLV_AT_END: This frame contains radiotap TLVs in the * skb->data (before the 802.11 header). * If used, the SKB's mac_header pointer must be set to point * to the 802.11 header after the TLVs, and any padding added after TLV * data to align to 4 must be cleared by the driver putting the TLVs * in the skb. * @RX_FLAG_ALLOW_SAME_PN: Allow the same PN as same packet before. * This is used for AMSDU subframes which can have the same PN as * the first subframe. * @RX_FLAG_ICV_STRIPPED: The ICV is stripped from this frame. CRC checking must * be done in the hardware. * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this * frame * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present * (&struct ieee80211_radiotap_he, mac80211 will fill in * * - DATA3_DATA_MCS * - DATA3_DATA_DCM * - DATA3_CODING * - DATA5_GI * - DATA5_DATA_BW_RU_ALLOC * - DATA6_NSTS * - DATA3_STBC * * from the RX info data, so leave those zeroed when building this data) * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present * (&struct ieee80211_radiotap_he_mu) * @RX_FLAG_RADIOTAP_LSIG: L-SIG radiotap data is present * @RX_FLAG_NO_PSDU: use the frame only for radiotap reporting, with * the "0-length PSDU" field included there. The value for it is * in &struct ieee80211_rx_status. Note that if this value isn't * known the frame shouldn't be reported. * @RX_FLAG_8023: the frame has an 802.3 header (decap offload performed by * hardware or driver) */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), RX_FLAG_DECRYPTED = BIT(1), RX_FLAG_ONLY_MONITOR = BIT(2), RX_FLAG_MMIC_STRIPPED = BIT(3), RX_FLAG_IV_STRIPPED = BIT(4), RX_FLAG_FAILED_FCS_CRC = BIT(5), RX_FLAG_FAILED_PLCP_CRC = BIT(6), RX_FLAG_MACTIME_IS_RTAP_TS64 = BIT(7), RX_FLAG_NO_SIGNAL_VAL = BIT(8), RX_FLAG_AMPDU_DETAILS = BIT(9), RX_FLAG_PN_VALIDATED = BIT(10), RX_FLAG_DUP_VALIDATED = BIT(11), RX_FLAG_AMPDU_LAST_KNOWN = BIT(12), RX_FLAG_AMPDU_IS_LAST = BIT(13), RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(14), RX_FLAG_AMPDU_DELIM_CRC_KNOWN = BIT(15), RX_FLAG_MACTIME = BIT(16) | BIT(17), RX_FLAG_MACTIME_PLCP_START = 1 << 16, RX_FLAG_MACTIME_START = 2 << 16, RX_FLAG_MACTIME_END = 3 << 16, RX_FLAG_SKIP_MONITOR = BIT(18), RX_FLAG_AMSDU_MORE = BIT(19), RX_FLAG_RADIOTAP_TLV_AT_END = BIT(20), RX_FLAG_MIC_STRIPPED = BIT(21), RX_FLAG_ALLOW_SAME_PN = BIT(22), RX_FLAG_ICV_STRIPPED = BIT(23), RX_FLAG_AMPDU_EOF_BIT = BIT(24), RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), RX_FLAG_RADIOTAP_HE = BIT(26), RX_FLAG_RADIOTAP_HE_MU = BIT(27), RX_FLAG_RADIOTAP_LSIG = BIT(28), RX_FLAG_NO_PSDU = BIT(29), RX_FLAG_8023 = BIT(30), }; /** * enum mac80211_rx_encoding_flags - MCS & bandwidth flags * * @RX_ENC_FLAG_SHORTPRE: Short preamble was used for this frame * @RX_ENC_FLAG_SHORT_GI: Short guard interval was used * @RX_ENC_FLAG_HT_GF: This frame was received in a HT-greenfield transmission, * if the driver fills this value it should add * %IEEE80211_RADIOTAP_MCS_HAVE_FMT * to @hw.radiotap_mcs_details to advertise that fact. * @RX_ENC_FLAG_LDPC: LDPC was used * @RX_ENC_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3 * @RX_ENC_FLAG_BF: packet was beamformed */ enum mac80211_rx_encoding_flags { RX_ENC_FLAG_SHORTPRE = BIT(0), RX_ENC_FLAG_SHORT_GI = BIT(2), RX_ENC_FLAG_HT_GF = BIT(3), RX_ENC_FLAG_STBC_MASK = BIT(4) | BIT(5), RX_ENC_FLAG_LDPC = BIT(6), RX_ENC_FLAG_BF = BIT(7), }; #define RX_ENC_FLAG_STBC_SHIFT 4 enum mac80211_rx_encoding { RX_ENC_LEGACY = 0, RX_ENC_HT, RX_ENC_VHT, RX_ENC_HE, RX_ENC_EHT, }; /** * struct ieee80211_rx_status - receive status * * The low-level driver should provide this information (the subset * supported by hardware) to the 802.11 code with each received * frame, in the skb's control buffer (cb). * * @mactime: value in microseconds of the 64-bit Time Synchronization Function * (TSF) timer when the first data symbol (MPDU) arrived at the hardware. * @boottime_ns: CLOCK_BOOTTIME timestamp the frame was received at, this is * needed only for beacons and probe responses that update the scan cache. * @ack_tx_hwtstamp: Hardware timestamp for the ack TX in nanoseconds. Only * needed for Timing measurement and Fine timing measurement action frames. * Only reported by devices that have timestamping enabled. * @device_timestamp: arbitrary timestamp for the device, mac80211 doesn't use * it but can store it and pass it back to the driver for synchronisation * @band: the active band when this frame was received * @freq: frequency the radio was tuned to when receiving this frame, in MHz * This field must be set for management frames, but isn't strictly needed * for data (other) frames - for those it only affects radiotap reporting. * @freq_offset: @freq has a positive offset of 500Khz. * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* * @chains: bitmask of receive chains for which separate signal strength * values were filled. * @chain_signal: per-chain signal strength, in dBm (unlike @signal, doesn't * support dB or unspecified units) * @antenna: antenna used * @rate_idx: index of data rate into band's supported rates or MCS index if * HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT) * @nss: number of streams (VHT, HE and EHT only) * @flag: %RX_FLAG_\* * @encoding: &enum mac80211_rx_encoding * @bw: &enum rate_info_bw * @enc_flags: uses bits from &enum mac80211_rx_encoding_flags * @he_ru: HE RU, from &enum nl80211_he_ru_alloc * @he_gi: HE GI, from &enum nl80211_he_gi * @he_dcm: HE DCM value * @eht: EHT specific rate information * @eht.ru: EHT RU, from &enum nl80211_eht_ru_alloc * @eht.gi: EHT GI, from &enum nl80211_eht_gi * @rx_flags: internal RX flags for mac80211 * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU * @ampdu_delimiter_crc: A-MPDU delimiter CRC * @zero_length_psdu_type: radiotap type of the 0-length PSDU * @link_valid: if the link which is identified by @link_id is valid. This flag * is set only when connection is MLO. * @link_id: id of the link used to receive the packet. This is used along with * @link_valid. */ struct ieee80211_rx_status { u64 mactime; union { u64 boottime_ns; ktime_t ack_tx_hwtstamp; }; u32 device_timestamp; u32 ampdu_reference; u32 flag; u16 freq: 13, freq_offset: 1; u8 enc_flags; u8 encoding:3, bw:4; union { struct { u8 he_ru:3; u8 he_gi:2; u8 he_dcm:1; }; struct { u8 ru:4; u8 gi:2; } eht; }; u8 rate_idx; u8 nss; u8 rx_flags; u8 band; u8 antenna; s8 signal; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 ampdu_delimiter_crc; u8 zero_length_psdu_type; u8 link_valid:1, link_id:4; }; static inline u32 ieee80211_rx_status_to_khz(struct ieee80211_rx_status *rx_status) { return MHZ_TO_KHZ(rx_status->freq) + (rx_status->freq_offset ? 500 : 0); } /** * enum ieee80211_conf_flags - configuration flags * * Flags to define PHY configuration options * * @IEEE80211_CONF_MONITOR: there's a monitor interface present -- use this * to determine for example whether to calculate timestamps for packets * or not, do not use instead of filter flags! * @IEEE80211_CONF_PS: Enable 802.11 power save mode (managed mode only). * This is the power save mode defined by IEEE 802.11-2007 section 11.2, * meaning that the hardware still wakes up for beacons, is able to * transmit frames and receive the possible acknowledgment frames. * Not to be confused with hardware specific wakeup/sleep states, * driver is responsible for that. See the section "Powersave support" * for more. * @IEEE80211_CONF_IDLE: The device is running, but idle; if the flag is set * the driver should be prepared to handle configuration requests but * may turn the device off as much as possible. Typically, this flag will * be set when an interface is set UP but not associated or scanning, but * it can also be unset in that case when monitor interfaces are active. * @IEEE80211_CONF_OFFCHANNEL: The device is currently not on its main * operating channel. */ enum ieee80211_conf_flags { IEEE80211_CONF_MONITOR = (1<<0), IEEE80211_CONF_PS = (1<<1), IEEE80211_CONF_IDLE = (1<<2), IEEE80211_CONF_OFFCHANNEL = (1<<3), }; /** * enum ieee80211_conf_changed - denotes which configuration changed * * @IEEE80211_CONF_CHANGE_LISTEN_INTERVAL: the listen interval changed * @IEEE80211_CONF_CHANGE_MONITOR: the monitor flag changed * @IEEE80211_CONF_CHANGE_PS: the PS flag or dynamic PS timeout changed * @IEEE80211_CONF_CHANGE_POWER: the TX power changed * @IEEE80211_CONF_CHANGE_CHANNEL: the channel/channel_type changed * @IEEE80211_CONF_CHANGE_RETRY_LIMITS: retry limits changed * @IEEE80211_CONF_CHANGE_IDLE: Idle flag changed * @IEEE80211_CONF_CHANGE_SMPS: Spatial multiplexing powersave mode changed * Note that this is only valid if channel contexts are not used, * otherwise each channel context has the number of chains listed. */ enum ieee80211_conf_changed { IEEE80211_CONF_CHANGE_SMPS = BIT(1), IEEE80211_CONF_CHANGE_LISTEN_INTERVAL = BIT(2), IEEE80211_CONF_CHANGE_MONITOR = BIT(3), IEEE80211_CONF_CHANGE_PS = BIT(4), IEEE80211_CONF_CHANGE_POWER = BIT(5), IEEE80211_CONF_CHANGE_CHANNEL = BIT(6), IEEE80211_CONF_CHANGE_RETRY_LIMITS = BIT(7), IEEE80211_CONF_CHANGE_IDLE = BIT(8), }; /** * enum ieee80211_smps_mode - spatial multiplexing power save mode * * @IEEE80211_SMPS_AUTOMATIC: automatic * @IEEE80211_SMPS_OFF: off * @IEEE80211_SMPS_STATIC: static * @IEEE80211_SMPS_DYNAMIC: dynamic * @IEEE80211_SMPS_NUM_MODES: internal, don't use */ enum ieee80211_smps_mode { IEEE80211_SMPS_AUTOMATIC, IEEE80211_SMPS_OFF, IEEE80211_SMPS_STATIC, IEEE80211_SMPS_DYNAMIC, /* keep last */ IEEE80211_SMPS_NUM_MODES, }; /** * struct ieee80211_conf - configuration of the device * * This struct indicates how the driver shall configure the hardware. * * @flags: configuration flags defined above * * @listen_interval: listen interval in units of beacon interval * @ps_dtim_period: The DTIM period of the AP we're connected to, for use * in power saving. Power saving will not be enabled until a beacon * has been received and the DTIM period is known. * @dynamic_ps_timeout: The dynamic powersave timeout (in ms), see the * powersave documentation below. This variable is valid only when * the CONF_PS flag is set. * * @power_level: requested transmit power (in dBm), backward compatibility * value only that is set to the minimum of all interfaces * * @chandef: the channel definition to tune to * @radar_enabled: whether radar detection is enabled * * @long_frame_max_tx_count: Maximum number of transmissions for a "long" frame * (a frame not RTS protected), called "dot11LongRetryLimit" in 802.11, * but actually means the number of transmissions not the number of retries * @short_frame_max_tx_count: Maximum number of transmissions for a "short" * frame, called "dot11ShortRetryLimit" in 802.11, but actually means the * number of transmissions not the number of retries * * @smps_mode: spatial multiplexing powersave mode; note that * %IEEE80211_SMPS_STATIC is used when the device is not * configured for an HT channel. * Note that this is only valid if channel contexts are not used, * otherwise each channel context has the number of chains listed. */ struct ieee80211_conf { u32 flags; int power_level, dynamic_ps_timeout; u16 listen_interval; u8 ps_dtim_period; u8 long_frame_max_tx_count, short_frame_max_tx_count; struct cfg80211_chan_def chandef; bool radar_enabled; enum ieee80211_smps_mode smps_mode; }; /** * struct ieee80211_channel_switch - holds the channel switch data * * The information provided in this structure is required for channel switch * operation. * * @timestamp: value in microseconds of the 64-bit Time Synchronization * Function (TSF) timer when the frame containing the channel switch * announcement was received. This is simply the rx.mactime parameter * the driver passed into mac80211. * @device_timestamp: arbitrary timestamp for the device, this is the * rx.device_timestamp parameter the driver passed to mac80211. * @block_tx: Indicates whether transmission must be blocked before the * scheduled channel switch, as indicated by the AP. * @chandef: the new channel to switch to * @count: the number of TBTT's until the channel switch event * @delay: maximum delay between the time the AP transmitted the last beacon in * current channel and the expected time of the first beacon in the new * channel, expressed in TU. * @link_id: the link ID of the link doing the channel switch, 0 for non-MLO */ struct ieee80211_channel_switch { u64 timestamp; u32 device_timestamp; bool block_tx; struct cfg80211_chan_def chandef; u8 count; u8 link_id; u32 delay; }; /** * enum ieee80211_vif_flags - virtual interface flags * * @IEEE80211_VIF_BEACON_FILTER: the device performs beacon filtering * on this virtual interface to avoid unnecessary CPU wakeups * @IEEE80211_VIF_SUPPORTS_CQM_RSSI: the device can do connection quality * monitoring on this virtual interface -- i.e. it can monitor * connection quality related parameters, such as the RSSI level and * provide notifications if configured trigger levels are reached. * @IEEE80211_VIF_SUPPORTS_UAPSD: The device can do U-APSD for this * interface. This flag should be set during interface addition, * but may be set/cleared as late as authentication to an AP. It is * only valid for managed/station mode interfaces. * @IEEE80211_VIF_GET_NOA_UPDATE: request to handle NOA attributes * and send P2P_PS notification to the driver if NOA changed, even * this is not pure P2P vif. * @IEEE80211_VIF_EML_ACTIVE: The driver indicates that EML operation is * enabled for the interface. * @IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW: Ignore wider bandwidth OFDMA * operation on this interface and request a channel context without * the AP definition. Use this e.g. because the device is able to * handle OFDMA (downlink and trigger for uplink) on a per-AP basis. */ enum ieee80211_vif_flags { IEEE80211_VIF_BEACON_FILTER = BIT(0), IEEE80211_VIF_SUPPORTS_CQM_RSSI = BIT(1), IEEE80211_VIF_SUPPORTS_UAPSD = BIT(2), IEEE80211_VIF_GET_NOA_UPDATE = BIT(3), IEEE80211_VIF_EML_ACTIVE = BIT(4), IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW = BIT(5), }; /** * enum ieee80211_offload_flags - virtual interface offload flags * * @IEEE80211_OFFLOAD_ENCAP_ENABLED: tx encapsulation offload is enabled * The driver supports sending frames passed as 802.3 frames by mac80211. * It must also support sending 802.11 packets for the same interface. * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload * @IEEE80211_OFFLOAD_DECAP_ENABLED: rx encapsulation offload is enabled * The driver supports passing received 802.11 frames as 802.3 frames to * mac80211. */ enum ieee80211_offload_flags { IEEE80211_OFFLOAD_ENCAP_ENABLED = BIT(0), IEEE80211_OFFLOAD_ENCAP_4ADDR = BIT(1), IEEE80211_OFFLOAD_DECAP_ENABLED = BIT(2), }; /** * struct ieee80211_vif_cfg - interface configuration * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS or not * @ibss_creator: indicates if a new IBSS network is being created * @ps: power-save mode (STA only). This flag is NOT affected by * offchannel/dynamic_ps operations. * @aid: association ID number, valid only when @assoc is true * @eml_cap: EML capabilities as described in P802.11be_D4.1 Figure 9-1001j. * @eml_med_sync_delay: Medium Synchronization delay as described in * P802.11be_D4.1 Figure 9-1001i. * @mld_capa_op: MLD Capabilities and Operations per P802.11be_D4.1 * Figure 9-1001k * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The * may filter ARP queries targeted for other addresses than listed here. * The driver must allow ARP queries targeted for all address listed here * to pass through. An empty list implies no ARP queries need to pass. * @arp_addr_cnt: Number of addresses currently on the list. Note that this * may be larger than %IEEE80211_BSS_ARP_ADDR_LIST_LEN (the arp_addr_list * array size), it's up to the driver what to do in that case. * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. * @ssid_len: Length of SSID given in @ssid. * @s1g: BSS is S1G BSS (affects Association Request format). * @idle: This interface is idle. There's also a global idle flag in the * hardware config which may be more appropriate depending on what * your driver/device needs to do. * @ap_addr: AP MLD address, or BSSID for non-MLO connections * (station mode only) */ struct ieee80211_vif_cfg { /* association related data */ bool assoc, ibss_joined; bool ibss_creator; bool ps; u16 aid; u16 eml_cap; u16 eml_med_sync_delay; u16 mld_capa_op; __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; int arp_addr_cnt; u8 ssid[IEEE80211_MAX_SSID_LEN]; size_t ssid_len; bool s1g; bool idle; u8 ap_addr[ETH_ALEN] __aligned(2); }; #define IEEE80211_TTLM_NUM_TIDS 8 /** * struct ieee80211_neg_ttlm - negotiated TID to link map info * * @downlink: bitmap of active links per TID for downlink, or 0 if mapping for * this TID is not included. * @uplink: bitmap of active links per TID for uplink, or 0 if mapping for this * TID is not included. * @valid: info is valid or not. */ struct ieee80211_neg_ttlm { u16 downlink[IEEE80211_TTLM_NUM_TIDS]; u16 uplink[IEEE80211_TTLM_NUM_TIDS]; bool valid; }; /** * enum ieee80211_neg_ttlm_res - return value for negotiated TTLM handling * @NEG_TTLM_RES_ACCEPT: accept the request * @NEG_TTLM_RES_REJECT: reject the request * @NEG_TTLM_RES_SUGGEST_PREFERRED: reject and suggest a new mapping */ enum ieee80211_neg_ttlm_res { NEG_TTLM_RES_ACCEPT, NEG_TTLM_RES_REJECT, NEG_TTLM_RES_SUGGEST_PREFERRED }; /** * struct ieee80211_vif - per-interface data * * Data in this structure is continually present for driver * use during the life of a virtual interface. * * @type: type of this virtual interface * @cfg: vif configuration, see &struct ieee80211_vif_cfg * @bss_conf: BSS configuration for this interface, either our own * or the BSS we're associated to * @link_conf: in case of MLD, the per-link BSS configuration, * indexed by link ID * @valid_links: bitmap of valid links, or 0 for non-MLO. * @active_links: The bitmap of active links, or 0 for non-MLO. * The driver shouldn't change this directly, but use the * API calls meant for that purpose. * @dormant_links: subset of the valid links that are disabled/suspended * due to advertised or negotiated TTLM respectively. * 0 for non-MLO. * @suspended_links: subset of dormant_links representing links that are * suspended due to negotiated TTLM, and could be activated in the * future by tearing down the TTLM negotiation. * 0 for non-MLO. * @neg_ttlm: negotiated TID to link mapping info. * see &struct ieee80211_neg_ttlm. * @addr: address of this interface * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively * @netdev_features: tx netdev features supported by the hardware for this * vif. mac80211 initializes this to hw->netdev_features, and the driver * can mask out specific tx features. mac80211 will handle software fixup * for masked offloads (GSO, CSUM) * @driver_flags: flags/capabilities the driver has for this interface, * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field * @offload_flags: hardware offload capabilities/flags for this interface. * These are initialized by mac80211 before calling .add_interface, * .change_interface or .update_vif_offload and updated by the driver * within these ops, based on supported features or runtime change * restrictions. * @hw_queue: hardware queue for each AC * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only * @debugfs_dir: debugfs dentry, can be used by drivers to create own per * interface debug files. Note that it will be NULL for the virtual * monitor interface (if that is requested.) * @probe_req_reg: probe requests should be reported to mac80211 for this * interface. * @rx_mcast_action_reg: multicast Action frames should be reported to mac80211 * for this interface. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*). * @txq: the multicast data TX queue * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see * &enum ieee80211_offload_flags. * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. */ struct ieee80211_vif { enum nl80211_iftype type; struct ieee80211_vif_cfg cfg; struct ieee80211_bss_conf bss_conf; struct ieee80211_bss_conf __rcu *link_conf[IEEE80211_MLD_MAX_NUM_LINKS]; u16 valid_links, active_links, dormant_links, suspended_links; struct ieee80211_neg_ttlm neg_ttlm; u8 addr[ETH_ALEN] __aligned(2); bool p2p; u8 cab_queue; u8 hw_queue[IEEE80211_NUM_ACS]; struct ieee80211_txq *txq; netdev_features_t netdev_features; u32 driver_flags; u32 offload_flags; #ifdef CONFIG_MAC80211_DEBUGFS struct dentry *debugfs_dir; #endif bool probe_req_reg; bool rx_mcast_action_reg; struct ieee80211_vif *mbssid_tx_vif; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; /** * ieee80211_vif_usable_links - Return the usable links for the vif * @vif: the vif for which the usable links are requested * Return: the usable link bitmap */ static inline u16 ieee80211_vif_usable_links(const struct ieee80211_vif *vif) { return vif->valid_links & ~vif->dormant_links; } /** * ieee80211_vif_is_mld - Returns true iff the vif is an MLD one * @vif: the vif * Return: %true if the vif is an MLD, %false otherwise. */ static inline bool ieee80211_vif_is_mld(const struct ieee80211_vif *vif) { /* valid_links != 0 indicates this vif is an MLD */ return vif->valid_links != 0; } /** * ieee80211_vif_link_active - check if a given link is active * @vif: the vif * @link_id: the link ID to check * Return: %true if the vif is an MLD and the link is active, or if * the vif is not an MLD and the link ID is 0; %false otherwise. */ static inline bool ieee80211_vif_link_active(const struct ieee80211_vif *vif, unsigned int link_id) { if (!ieee80211_vif_is_mld(vif)) return link_id == 0; return vif->active_links & BIT(link_id); } #define for_each_vif_active_link(vif, link, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((vif)->link_conf); link_id++) \ if ((!(vif)->active_links || \ (vif)->active_links & BIT(link_id)) && \ (link = link_conf_dereference_check(vif, link_id))) static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) { #ifdef CONFIG_MAC80211_MESH return vif->type == NL80211_IFTYPE_MESH_POINT; #endif return false; } /** * wdev_to_ieee80211_vif - return a vif struct from a wdev * @wdev: the wdev to get the vif for * * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that get a wdev. * * Return: pointer to the wdev, or %NULL if the given wdev isn't * associated with a vif that the driver knows about (e.g. monitor * or AP_VLAN interfaces.) */ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); /** * ieee80211_vif_to_wdev - return a wdev struct from a vif * @vif: the vif to get the wdev for * * This can be used by mac80211 drivers with direct cfg80211 APIs * (like the vendor commands) that needs to get the wdev for a vif. * This can also be useful to get the netdev associated to a vif. * * Return: pointer to the wdev */ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); static inline bool lockdep_vif_wiphy_mutex_held(struct ieee80211_vif *vif) { return lockdep_is_held(&ieee80211_vif_to_wdev(vif)->wiphy->mtx); } #define link_conf_dereference_protected(vif, link_id) \ rcu_dereference_protected((vif)->link_conf[link_id], \ lockdep_vif_wiphy_mutex_held(vif)) #define link_conf_dereference_check(vif, link_id) \ rcu_dereference_check((vif)->link_conf[link_id], \ lockdep_vif_wiphy_mutex_held(vif)) /** * enum ieee80211_key_flags - key flags * * These flags are used for communication about keys between the driver * and mac80211, with the @flags parameter of &struct ieee80211_key_conf. * * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the * driver to indicate that it requires IV generation for this * particular key. Setting this flag does not necessarily mean that SKBs * will have sufficient tailroom for ICV or MIC. * @IEEE80211_KEY_FLAG_GENERATE_MMIC: This flag should be set by * the driver for a TKIP key if it requires Michael MIC * generation in software. * @IEEE80211_KEY_FLAG_PAIRWISE: Set by mac80211, this flag indicates * that the key is pairwise rather then a shared key. * @IEEE80211_KEY_FLAG_SW_MGMT_TX: This flag should be set by the driver for a * CCMP/GCMP key if it requires CCMP/GCMP encryption of management frames * (MFP) to be done in software. * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver * if space should be prepared for the IV, but the IV * itself should not be generated. Do not set together with * @IEEE80211_KEY_FLAG_GENERATE_IV on the same key. Setting this flag does * not necessarily mean that SKBs will have sufficient tailroom for ICV or * MIC. * @IEEE80211_KEY_FLAG_RX_MGMT: This key will be used to decrypt received * management frames. The flag can help drivers that have a hardware * crypto implementation that doesn't deal with management frames * properly by allowing them to not upload the keys to hardware and * fall back to software crypto. Note that this flag deals only with * RX, if your crypto engine can't deal with TX you can also set the * %IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW. * @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the * driver for a CCMP/GCMP key to indicate that is requires IV generation * only for management frames (MFP). * @IEEE80211_KEY_FLAG_RESERVE_TAILROOM: This flag should be set by the * driver for a key to indicate that sufficient tailroom must always * be reserved for ICV or MIC, even when HW encryption is enabled. * @IEEE80211_KEY_FLAG_PUT_MIC_SPACE: This flag should be set by the driver for * a TKIP key if it only requires MIC space. Do not set together with * @IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key. * @IEEE80211_KEY_FLAG_NO_AUTO_TX: Key needs explicit Tx activation. * @IEEE80211_KEY_FLAG_GENERATE_MMIE: This flag should be set by the driver * for a AES_CMAC or a AES_GMAC key to indicate that it requires sequence * number generation only * @IEEE80211_KEY_FLAG_SPP_AMSDU: SPP A-MSDUs can be used with this key * (set by mac80211 from the sta->spp_amsdu flag) */ enum ieee80211_key_flags { IEEE80211_KEY_FLAG_GENERATE_IV_MGMT = BIT(0), IEEE80211_KEY_FLAG_GENERATE_IV = BIT(1), IEEE80211_KEY_FLAG_GENERATE_MMIC = BIT(2), IEEE80211_KEY_FLAG_PAIRWISE = BIT(3), IEEE80211_KEY_FLAG_SW_MGMT_TX = BIT(4), IEEE80211_KEY_FLAG_PUT_IV_SPACE = BIT(5), IEEE80211_KEY_FLAG_RX_MGMT = BIT(6), IEEE80211_KEY_FLAG_RESERVE_TAILROOM = BIT(7), IEEE80211_KEY_FLAG_PUT_MIC_SPACE = BIT(8), IEEE80211_KEY_FLAG_NO_AUTO_TX = BIT(9), IEEE80211_KEY_FLAG_GENERATE_MMIE = BIT(10), IEEE80211_KEY_FLAG_SPP_AMSDU = BIT(11), }; /** * struct ieee80211_key_conf - key information * * This key information is given by mac80211 to the driver by * the set_key() callback in &struct ieee80211_ops. * * @hw_key_idx: To be set by the driver, this is the key index the driver * wants to be given when a frame is transmitted and needs to be * encrypted in hardware. * @cipher: The key's cipher suite selector. * @tx_pn: PN used for TX keys, may be used by the driver as well if it * needs to do software PN assignment by itself (e.g. due to TSO) * @flags: key flags, see &enum ieee80211_key_flags. * @keyidx: the key index (0-3) * @keylen: key material length * @key: key material. For ALG_TKIP the key is encoded as a 256-bit (32 byte) * data block: * - Temporal Encryption Key (128 bits) * - Temporal Authenticator Tx MIC Key (64 bits) * - Temporal Authenticator Rx MIC Key (64 bits) * @icv_len: The ICV length for this key type * @iv_len: The IV length for this key type * @link_id: the link ID for MLO, or -1 for non-MLO or pairwise keys */ struct ieee80211_key_conf { atomic64_t tx_pn; u32 cipher; u8 icv_len; u8 iv_len; u8 hw_key_idx; s8 keyidx; u16 flags; s8 link_id; u8 keylen; u8 key[]; }; #define IEEE80211_MAX_PN_LEN 16 #define TKIP_PN_TO_IV16(pn) ((u16)(pn & 0xffff)) #define TKIP_PN_TO_IV32(pn) ((u32)((pn >> 16) & 0xffffffff)) /** * struct ieee80211_key_seq - key sequence counter * * @tkip: TKIP data, containing IV32 and IV16 in host byte order * @ccmp: PN data, most significant byte first (big endian, * reverse order than in packet) * @aes_cmac: PN data, most significant byte first (big endian, * reverse order than in packet) * @aes_gmac: PN data, most significant byte first (big endian, * reverse order than in packet) * @gcmp: PN data, most significant byte first (big endian, * reverse order than in packet) * @hw: data for HW-only (e.g. cipher scheme) keys */ struct ieee80211_key_seq { union { struct { u32 iv32; u16 iv16; } tkip; struct { u8 pn[6]; } ccmp; struct { u8 pn[6]; } aes_cmac; struct { u8 pn[6]; } aes_gmac; struct { u8 pn[6]; } gcmp; struct { u8 seq[IEEE80211_MAX_PN_LEN]; u8 seq_len; } hw; }; }; /** * enum set_key_cmd - key command * * Used with the set_key() callback in &struct ieee80211_ops, this * indicates whether a key is being removed or added. * * @SET_KEY: a key is set * @DISABLE_KEY: a key must be disabled */ enum set_key_cmd { SET_KEY, DISABLE_KEY, }; /** * enum ieee80211_sta_state - station state * * @IEEE80211_STA_NOTEXIST: station doesn't exist at all, * this is a special state for add/remove transitions * @IEEE80211_STA_NONE: station exists without special state * @IEEE80211_STA_AUTH: station is authenticated * @IEEE80211_STA_ASSOC: station is associated * @IEEE80211_STA_AUTHORIZED: station is authorized (802.1X) */ enum ieee80211_sta_state { /* NOTE: These need to be ordered correctly! */ IEEE80211_STA_NOTEXIST, IEEE80211_STA_NONE, IEEE80211_STA_AUTH, IEEE80211_STA_ASSOC, IEEE80211_STA_AUTHORIZED, }; /** * enum ieee80211_sta_rx_bandwidth - station RX bandwidth * @IEEE80211_STA_RX_BW_20: station can only receive 20 MHz * @IEEE80211_STA_RX_BW_40: station can receive up to 40 MHz * @IEEE80211_STA_RX_BW_80: station can receive up to 80 MHz * @IEEE80211_STA_RX_BW_160: station can receive up to 160 MHz * (including 80+80 MHz) * @IEEE80211_STA_RX_BW_320: station can receive up to 320 MHz * * Implementation note: 20 must be zero to be initialized * correctly, the values must be sorted. */ enum ieee80211_sta_rx_bandwidth { IEEE80211_STA_RX_BW_20 = 0, IEEE80211_STA_RX_BW_40, IEEE80211_STA_RX_BW_80, IEEE80211_STA_RX_BW_160, IEEE80211_STA_RX_BW_320, }; /** * struct ieee80211_sta_rates - station rate selection table * * @rcu_head: RCU head used for freeing the table on update * @rate: transmit rates/flags to be used by default. * Overriding entries per-packet is possible by using cb tx control. */ struct ieee80211_sta_rates { struct rcu_head rcu_head; struct { s8 idx; u8 count; u8 count_cts; u8 count_rts; u16 flags; } rate[IEEE80211_TX_RATE_TABLE_SIZE]; }; /** * struct ieee80211_sta_txpwr - station txpower configuration * * Used to configure txpower for station. * * @power: indicates the tx power, in dBm, to be used when sending data frames * to the STA. * @type: In particular if TPC %type is NL80211_TX_POWER_LIMITED then tx power * will be less than or equal to specified from userspace, whereas if TPC * %type is NL80211_TX_POWER_AUTOMATIC then it indicates default tx power. * NL80211_TX_POWER_FIXED is not a valid configuration option for * per peer TPC. */ struct ieee80211_sta_txpwr { s16 power; enum nl80211_tx_power_setting type; }; /** * struct ieee80211_sta_aggregates - info that is aggregated from active links * * Used for any per-link data that needs to be aggregated and updated in the * main &struct ieee80211_sta when updated or the active links change. * * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. * This field is always valid for packets with a VHT preamble. * For packets with a HT preamble, additional limits apply: * * * If the skb is transmitted as part of a BA agreement, the * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. * * If the skb is not part of a BA agreement, the A-MSDU maximal * size is min(max_amsdu_len, 7935) bytes. * * Both additional HT limits must be enforced by the low level * driver. This is defined by the spec (IEEE 802.11-2012 section * 8.3.2.2 NOTE 2). * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID */ struct ieee80211_sta_aggregates { u16 max_amsdu_len; u16 max_rc_amsdu_len; u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; }; /** * struct ieee80211_link_sta - station Link specific info * All link specific info for a STA link for a non MLD STA(single) * or a MLD STA(multiple entries) are stored here. * * @sta: reference to owning STA * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr * in ieee80211_sta. For MLO Link STA this addr can be same or different * from addr in ieee80211_sta (representing MLD STA addr) * @link_id: the link ID for this link STA (0 for deflink) * @smps_mode: current SMPS mode (off, static or dynamic) * @supp_rates: Bitmap of supported rates * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities * @he_cap: HE capabilities of this STA * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities * @eht_cap: EHT capabilities of this STA * @agg: per-link data for multi-link aggregation * @bandwidth: current bandwidth the station can receive with * @rx_nss: in HT/VHT, the maximum number of spatial streams the * station can receive at the moment, changed by operating mode * notifications and capabilities. The value is only valid after * the station moves to associated state. * @txpwr: the station tx power configuration * */ struct ieee80211_link_sta { struct ieee80211_sta *sta; u8 addr[ETH_ALEN]; u8 link_id; enum ieee80211_smps_mode smps_mode; u32 supp_rates[NUM_NL80211_BANDS]; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; struct ieee80211_sta_eht_cap eht_cap; struct ieee80211_sta_aggregates agg; u8 rx_nss; enum ieee80211_sta_rx_bandwidth bandwidth; struct ieee80211_sta_txpwr txpwr; }; /** * struct ieee80211_sta - station table entry * * A station table entry represents a station we are possibly * communicating with. Since stations are RCU-managed in * mac80211, any ieee80211_sta pointer you get access to must * either be protected by rcu_read_lock() explicitly or implicitly, * or you must take good care to not use such a pointer after a * call to your sta_remove callback that removed it. * This also represents the MLD STA in case of MLO association * and holds pointers to various link STA's * * @addr: MAC address * @aid: AID we assigned to the station if we're an AP * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. * @wme: indicates whether the STA supports QoS/WME (if local devices does, * otherwise always false) * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*), size is determined in hw information. * @uapsd_queues: bitmap of queues configured for uapsd. Only valid * if wme is supported. The bits order is like in * IEEE80211_WMM_IE_STA_QOSINFO_AC_*. * @max_sp: max Service Period. Only valid if wme is supported. * @rates: rate control selection table * @tdls: indicates whether the STA is a TDLS peer * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. * @mfp: indicates whether the STA uses management frame protection or not. * @mlo: indicates whether the STA is MLO station. * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single * A-MSDU. Taken from the Extended Capabilities element. 0 means * unlimited. * @cur: currently valid data as aggregated from the active links * For non MLO STA it will point to the deflink data. For MLO STA * ieee80211_sta_recalc_aggregates() must be called to update it. * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. * @txq: per-TID data TX queues; note that the last entry (%IEEE80211_NUM_TIDS) * is used for non-data frames * @deflink: This holds the default link STA information, for non MLO STA all link * specific STA information is accessed through @deflink or through * link[0] which points to address of @deflink. For MLO Link STA * the first added link STA will point to deflink. * @link: reference to Link Sta entries. For Non MLO STA, except 1st link, * i.e link[0] all links would be assigned to NULL by default and * would access link information via @deflink or link[0]. For MLO * STA, first link STA being added will point its link pointer to * @deflink address and remaining would be allocated and the address * would be assigned to link[link_id] where link_id is the id assigned * by the AP. * @valid_links: bitmap of valid links, or 0 for non-MLO * @spp_amsdu: indicates whether the STA uses SPP A-MSDU or not. */ struct ieee80211_sta { u8 addr[ETH_ALEN]; u16 aid; u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; bool mfp; bool mlo; bool spp_amsdu; u8 max_amsdu_subframes; struct ieee80211_sta_aggregates *cur; bool support_p2p_ps; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; u16 valid_links; struct ieee80211_link_sta deflink; struct ieee80211_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; #ifdef CONFIG_LOCKDEP bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta); #else static inline bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta) { return true; } #endif #define link_sta_dereference_protected(sta, link_id) \ rcu_dereference_protected((sta)->link[link_id], \ lockdep_sta_mutex_held(sta)) #define link_sta_dereference_check(sta, link_id) \ rcu_dereference_check((sta)->link[link_id], \ lockdep_sta_mutex_held(sta)) #define for_each_sta_active_link(vif, sta, link_sta, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) \ if ((!(vif)->active_links || \ (vif)->active_links & BIT(link_id)) && \ ((link_sta) = link_sta_dereference_check(sta, link_id))) /** * enum sta_notify_cmd - sta notify command * * Used with the sta_notify() callback in &struct ieee80211_ops, this * indicates if an associated station made a power state transition. * * @STA_NOTIFY_SLEEP: a station is now sleeping * @STA_NOTIFY_AWAKE: a sleeping station woke up */ enum sta_notify_cmd { STA_NOTIFY_SLEEP, STA_NOTIFY_AWAKE, }; /** * struct ieee80211_tx_control - TX control data * * @sta: station table entry, this sta pointer may be NULL and * it is not allowed to copy the pointer, due to RCU. */ struct ieee80211_tx_control { struct ieee80211_sta *sta; }; /** * struct ieee80211_txq - Software intermediate tx queue * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @sta: station table entry, %NULL for per-vif queue * @tid: the TID for this queue (unused for per-vif queue), * %IEEE80211_NUM_TIDS for non-data (if enabled) * @ac: the AC for this queue * @drv_priv: driver private area, sized by hw->txq_data_size * * The driver can obtain packets from this queue by calling * ieee80211_tx_dequeue(). */ struct ieee80211_txq { struct ieee80211_vif *vif; struct ieee80211_sta *sta; u8 tid; u8 ac; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; /** * enum ieee80211_hw_flags - hardware flags * * These flags are used to indicate hardware capabilities to * the stack. Generally, flags here should have their meaning * done in a way that the simplest hardware doesn't need setting * any particular flags. There are some exceptions to this rule, * however, so you are advised to review these flags carefully. * * @IEEE80211_HW_HAS_RATE_CONTROL: * The hardware or firmware includes rate control, and cannot be * controlled by the stack. As such, no rate control algorithm * should be instantiated, and the TX rate reported to userspace * will be taken from the TX status instead of the rate control * algorithm. * Note that this requires that the driver implement a number of * callbacks so it has the correct information, it needs to have * the @set_rts_threshold callback and must look at the BSS config * @use_cts_prot for G/N protection, @use_short_slot for slot * timing in 2.4 GHz and @use_short_preamble for preambles for * CCK frames. * * @IEEE80211_HW_RX_INCLUDES_FCS: * Indicates that received frames passed to the stack include * the FCS at the end. * * @IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING: * Some wireless LAN chipsets buffer broadcast/multicast frames * for power saving stations in the hardware/firmware and others * rely on the host system for such buffering. This option is used * to configure the IEEE 802.11 upper layer to buffer broadcast and * multicast frames when there are power saving stations so that * the driver can fetch them with ieee80211_get_buffered_bc(). * * @IEEE80211_HW_SIGNAL_UNSPEC: * Hardware can provide signal values but we don't know its units. We * expect values between 0 and @max_signal. * If possible please provide dB or dBm instead. * * @IEEE80211_HW_SIGNAL_DBM: * Hardware gives signal values in dBm, decibel difference from * one milliwatt. This is the preferred method since it is standardized * between different devices. @max_signal does not need to be set. * * @IEEE80211_HW_SPECTRUM_MGMT: * Hardware supports spectrum management defined in 802.11h * Measurement, Channel Switch, Quieting, TPC * * @IEEE80211_HW_AMPDU_AGGREGATION: * Hardware supports 11n A-MPDU aggregation. * * @IEEE80211_HW_SUPPORTS_PS: * Hardware has power save support (i.e. can go to sleep). * * @IEEE80211_HW_PS_NULLFUNC_STACK: * Hardware requires nullfunc frame handling in stack, implies * stack support for dynamic PS. * * @IEEE80211_HW_SUPPORTS_DYNAMIC_PS: * Hardware has support for dynamic PS. * * @IEEE80211_HW_MFP_CAPABLE: * Hardware supports management frame protection (MFP, IEEE 802.11w). * * @IEEE80211_HW_REPORTS_TX_ACK_STATUS: * Hardware can provide ack status reports of Tx frames to * the stack. * * @IEEE80211_HW_CONNECTION_MONITOR: * The hardware performs its own connection monitoring, including * periodic keep-alives to the AP and probing the AP on beacon loss. * * @IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC: * This device needs to get data from beacon before association (i.e. * dtim_period). * * @IEEE80211_HW_SUPPORTS_PER_STA_GTK: The device's crypto engine supports * per-station GTKs as used by IBSS RSN or during fast transition. If * the device doesn't support per-station GTKs, but can be asked not * to decrypt group addressed frames, then IBSS RSN support is still * possible but software crypto will be used. Advertise the wiphy flag * only in that case. * * @IEEE80211_HW_AP_LINK_PS: When operating in AP mode the device * autonomously manages the PS status of connected stations. When * this flag is set mac80211 will not trigger PS mode for connected * stations based on the PM bit of incoming frames. * Use ieee80211_start_ps()/ieee8021_end_ps() to manually configure * the PS mode of connected stations. * * @IEEE80211_HW_TX_AMPDU_SETUP_IN_HW: The device handles TX A-MPDU session * setup strictly in HW. mac80211 should not attempt to do this in * software. * * @IEEE80211_HW_WANT_MONITOR_VIF: The driver would like to be informed of * a virtual monitor interface when monitor interfaces are the only * active interfaces. * * @IEEE80211_HW_NO_AUTO_VIF: The driver would like for no wlanX to * be created. It is expected user-space will create vifs as * desired (and thus have them named as desired). * * @IEEE80211_HW_SW_CRYPTO_CONTROL: The driver wants to control which of the * crypto algorithms can be done in software - so don't automatically * try to fall back to it if hardware crypto fails, but do so only if * the driver returns 1. This also forces the driver to advertise its * supported cipher suites. * * @IEEE80211_HW_SUPPORT_FAST_XMIT: The driver/hardware supports fast-xmit, * this currently requires only the ability to calculate the duration * for frames. * * @IEEE80211_HW_QUEUE_CONTROL: The driver wants to control per-interface * queue mapping in order to use different queues (not just one per AC) * for different virtual interfaces. See the doc section on HW queue * control for more details. * * @IEEE80211_HW_SUPPORTS_RC_TABLE: The driver supports using a rate * selection table provided by the rate control algorithm. * * @IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF: Use the P2P Device address for any * P2P Interface. This will be honoured even if more than one interface * is supported. * * @IEEE80211_HW_TIMING_BEACON_ONLY: Use sync timing from beacon frames * only, to allow getting TBTT of a DTIM beacon. * * @IEEE80211_HW_SUPPORTS_HT_CCK_RATES: Hardware supports mixing HT/CCK rates * and can cope with CCK rates in an aggregation session (e.g. by not * using aggregation for such frames.) * * @IEEE80211_HW_CHANCTX_STA_CSA: Support 802.11h based channel-switch (CSA) * for a single active channel while using channel contexts. When support * is not enabled the default action is to disconnect when getting the * CSA frame. * * @IEEE80211_HW_SUPPORTS_CLONED_SKBS: The driver will never modify the payload * or tailroom of TX skbs without copying them first. * * @IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS: The HW supports scanning on all bands * in one command, mac80211 doesn't have to run separate scans per band. * * @IEEE80211_HW_TDLS_WIDER_BW: The device/driver supports wider bandwidth * than then BSS bandwidth for a TDLS link on the base channel. * * @IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU: The driver supports receiving A-MSDUs * within A-MPDU. * * @IEEE80211_HW_BEACON_TX_STATUS: The device/driver provides TX status * for sent beacons. * * @IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR: Hardware (or driver) requires that each * station has a unique address, i.e. each station entry can be identified * by just its MAC address; this prevents, for example, the same station * from connecting to two virtual AP interfaces at the same time. * * @IEEE80211_HW_SUPPORTS_REORDERING_BUFFER: Hardware (or driver) manages the * reordering buffer internally, guaranteeing mac80211 receives frames in * order and does not need to manage its own reorder buffer or BA session * timeout. * * @IEEE80211_HW_USES_RSS: The device uses RSS and thus requires parallel RX, * which implies using per-CPU station statistics. * * @IEEE80211_HW_TX_AMSDU: Hardware (or driver) supports software aggregated * A-MSDU frames. Requires software tx queueing and fast-xmit support. * When not using minstrel/minstrel_ht rate control, the driver must * limit the maximum A-MSDU size based on the current tx rate by setting * max_rc_amsdu_len in struct ieee80211_sta. * * @IEEE80211_HW_TX_FRAG_LIST: Hardware (or driver) supports sending frag_list * skbs, needed for zero-copy software A-MSDU. * * @IEEE80211_HW_REPORTS_LOW_ACK: The driver (or firmware) reports low ack event * by ieee80211_report_low_ack() based on its own algorithm. For such * drivers, mac80211 packet loss mechanism will not be triggered and driver * is completely depending on firmware event for station kickout. * * @IEEE80211_HW_SUPPORTS_TX_FRAG: Hardware does fragmentation by itself. * The stack will not do fragmentation. * The callback for @set_frag_threshold should be set as well. * * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on * TDLS links. * * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't * support QoS NDP for AP probing - that's most likely a driver bug. * * @IEEE80211_HW_BUFF_MMPDU_TXQ: use the TXQ for bufferable MMPDUs, this of * course requires the driver to use TXQs to start with. * * @IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW: (Hardware) rate control supports VHT * extended NSS BW (dot11VHTExtendedNSSBWCapable). This flag will be set if * the selected rate control algorithm sets %RATE_CTRL_CAPA_VHT_EXT_NSS_BW * but if the rate control is built-in then it must be set by the driver. * See also the documentation for that flag. * * @IEEE80211_HW_STA_MMPDU_TXQ: use the extra non-TID per-station TXQ for all * MMPDUs on station interfaces. This of course requires the driver to use * TXQs to start with. * * @IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN: Driver does not report accurate A-MPDU * length in tx status information * * @IEEE80211_HW_SUPPORTS_MULTI_BSSID: Hardware supports multi BSSID * * @IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID: Hardware supports multi BSSID * only for HE APs. Applies if @IEEE80211_HW_SUPPORTS_MULTI_BSSID is set. * * @IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT: The card and driver is only * aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx * A-MPDU sessions active while rekeying with Extended Key ID. * * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation * offload * * @IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD: Hardware supports rx decapsulation * offload * * @IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP: Hardware supports concurrent rx * decapsulation offload and passing raw 802.11 frames for monitor iface. * If this is supported, the driver must pass both 802.3 frames for real * usage and 802.11 frames with %RX_FLAG_ONLY_MONITOR set for monitor to * the stack. * * @IEEE80211_HW_DETECTS_COLOR_COLLISION: HW/driver has support for BSS color * collision detection and doesn't need it in software. * * @IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX: Hardware/driver handles transmitting * multicast frames on all links, mac80211 should not do that. * * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT * and connecting with a lower bandwidth instead * @IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ: HW requires disabling puncturing in * EHT in 5 GHz and connecting with a lower bandwidth instead * * @IEEE80211_HW_HANDLES_QUIET_CSA: HW/driver handles quieting for CSA, so * no need to stop queues. This really should be set by a driver that * implements MLO, so operation can continue on other links when one * link is switching. * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL, IEEE80211_HW_RX_INCLUDES_FCS, IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING, IEEE80211_HW_SIGNAL_UNSPEC, IEEE80211_HW_SIGNAL_DBM, IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC, IEEE80211_HW_SPECTRUM_MGMT, IEEE80211_HW_AMPDU_AGGREGATION, IEEE80211_HW_SUPPORTS_PS, IEEE80211_HW_PS_NULLFUNC_STACK, IEEE80211_HW_SUPPORTS_DYNAMIC_PS, IEEE80211_HW_MFP_CAPABLE, IEEE80211_HW_WANT_MONITOR_VIF, IEEE80211_HW_NO_AUTO_VIF, IEEE80211_HW_SW_CRYPTO_CONTROL, IEEE80211_HW_SUPPORT_FAST_XMIT, IEEE80211_HW_REPORTS_TX_ACK_STATUS, IEEE80211_HW_CONNECTION_MONITOR, IEEE80211_HW_QUEUE_CONTROL, IEEE80211_HW_SUPPORTS_PER_STA_GTK, IEEE80211_HW_AP_LINK_PS, IEEE80211_HW_TX_AMPDU_SETUP_IN_HW, IEEE80211_HW_SUPPORTS_RC_TABLE, IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF, IEEE80211_HW_TIMING_BEACON_ONLY, IEEE80211_HW_SUPPORTS_HT_CCK_RATES, IEEE80211_HW_CHANCTX_STA_CSA, IEEE80211_HW_SUPPORTS_CLONED_SKBS, IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS, IEEE80211_HW_TDLS_WIDER_BW, IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, IEEE80211_HW_BEACON_TX_STATUS, IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR, IEEE80211_HW_SUPPORTS_REORDERING_BUFFER, IEEE80211_HW_USES_RSS, IEEE80211_HW_TX_AMSDU, IEEE80211_HW_TX_FRAG_LIST, IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, IEEE80211_HW_BUFF_MMPDU_TXQ, IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, IEEE80211_HW_STA_MMPDU_TXQ, IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN, IEEE80211_HW_SUPPORTS_MULTI_BSSID, IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID, IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT, IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD, IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP, IEEE80211_HW_DETECTS_COLOR_COLLISION, IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX, IEEE80211_HW_DISALLOW_PUNCTURING, IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ, IEEE80211_HW_HANDLES_QUIET_CSA, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS }; /** * struct ieee80211_hw - hardware information and state * * This structure contains the configuration and hardware * information for an 802.11 PHY. * * @wiphy: This points to the &struct wiphy allocated for this * 802.11 PHY. You must fill in the @perm_addr and @dev * members of this structure using SET_IEEE80211_DEV() * and SET_IEEE80211_PERM_ADDR(). Additionally, all supported * bands (with channels, bitrates) are registered here. * * @conf: &struct ieee80211_conf, device configuration, don't use. * * @priv: pointer to private area that was allocated for driver use * along with this structure. * * @flags: hardware flags, see &enum ieee80211_hw_flags. * * @extra_tx_headroom: headroom to reserve in each transmit skb * for use by the driver (e.g. for transmit headers.) * * @extra_beacon_tailroom: tailroom to reserve in each beacon tx skb. * Can be used by drivers to add extra IEs. * * @max_signal: Maximum value for signal (rssi) in RX information, used * only when @IEEE80211_HW_SIGNAL_UNSPEC or @IEEE80211_HW_SIGNAL_DB * * @max_listen_interval: max listen interval in units of beacon interval * that HW supports * * @queues: number of available hardware transmit queues for * data packets. WMM/QoS requires at least four, these * queues need to have configurable access parameters. * * @rate_control_algorithm: rate control algorithm for this hardware. * If unset (NULL), the default algorithm will be used. Must be * set before calling ieee80211_register_hw(). * * @vif_data_size: size (in bytes) of the drv_priv data area * within &struct ieee80211_vif. * @sta_data_size: size (in bytes) of the drv_priv data area * within &struct ieee80211_sta. * @chanctx_data_size: size (in bytes) of the drv_priv data area * within &struct ieee80211_chanctx_conf. * @txq_data_size: size (in bytes) of the drv_priv data area * within @struct ieee80211_txq. * * @max_rates: maximum number of alternate rate retry stages the hw * can handle. * @max_report_rates: maximum number of alternate rate retry stages * the hw can report back. * @max_rate_tries: maximum number of tries for each stage * * @max_rx_aggregation_subframes: maximum buffer size (number of * sub-frames) to be used for A-MPDU block ack receiver * aggregation. * This is only relevant if the device has restrictions on the * number of subframes, if it relies on mac80211 to do reordering * it shouldn't be set. * * @max_tx_aggregation_subframes: maximum number of subframes in an * aggregate an HT/HE device will transmit. In HT AddBA we'll * advertise a constant value of 64 as some older APs crash if * the window size is smaller (an example is LinkSys WRT120N * with FW v1.0.07 build 002 Jun 18 2012). * For AddBA to HE capable peers this value will be used. * * @max_tx_fragments: maximum number of tx buffers per (A)-MSDU, sum * of 1 + skb_shinfo(skb)->nr_frags for each skb in the frag_list. * * @offchannel_tx_hw_queue: HW queue ID to use for offchannel TX * (if %IEEE80211_HW_QUEUE_CONTROL is set) * * @radiotap_mcs_details: lists which MCS information can the HW * reports, by default it is set to _MCS, _GI and _BW but doesn't * include _FMT. Use %IEEE80211_RADIOTAP_MCS_HAVE_\* values, only * adding _BW is supported today. * * @radiotap_vht_details: lists which VHT MCS information the HW reports, * the default is _GI | _BANDWIDTH. * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values. * * @radiotap_timestamp: Information for the radiotap timestamp field; if the * @units_pos member is set to a non-negative value then the timestamp * field will be added and populated from the &struct ieee80211_rx_status * device_timestamp. * @radiotap_timestamp.units_pos: Must be set to a combination of a * IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a * IEEE80211_RADIOTAP_TIMESTAMP_SPOS_* value. * @radiotap_timestamp.accuracy: If non-negative, fills the accuracy in the * radiotap field and the accuracy known flag will be set. * * @netdev_features: netdev features to be set in each netdev created * from this HW. Note that not all features are usable with mac80211, * other features will be rejected during HW registration. * * @uapsd_queues: This bitmap is included in (re)association frame to indicate * for each access category if it is uAPSD trigger-enabled and delivery- * enabled. Use IEEE80211_WMM_IE_STA_QOSINFO_AC_* to set this bitmap. * Each bit corresponds to different AC. Value '1' in specific bit means * that corresponding AC is both trigger- and delivery-enabled. '0' means * neither enabled. * * @uapsd_max_sp_len: maximum number of total buffered frames the WMM AP may * deliver to a WMM STA during any Service Period triggered by the WMM STA. * Use IEEE80211_WMM_IE_STA_QOSINFO_SP_* for correct values. * * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. * * @tx_sk_pacing_shift: Pacing shift to set on TCP sockets when frames from * them are encountered. The default should typically not be changed, * unless the driver has good reasons for needing more buffers. * * @weight_multiplier: Driver specific airtime weight multiplier used while * refilling deficit of each TXQ. * * @max_mtu: the max mtu could be set. * * @tx_power_levels: a list of power levels supported by the wifi hardware. * The power levels can be specified either as integer or fractions. * The power level at idx 0 shall be the maximum positive power level. * * @max_txpwr_levels_idx: the maximum valid idx of 'tx_power_levels' list. */ struct ieee80211_hw { struct ieee80211_conf conf; struct wiphy *wiphy; const char *rate_control_algorithm; void *priv; unsigned long flags[BITS_TO_LONGS(NUM_IEEE80211_HW_FLAGS)]; unsigned int extra_tx_headroom; unsigned int extra_beacon_tailroom; int vif_data_size; int sta_data_size; int chanctx_data_size; int txq_data_size; u16 queues; u16 max_listen_interval; s8 max_signal; u8 max_rates; u8 max_report_rates; u8 max_rate_tries; u16 max_rx_aggregation_subframes; u16 max_tx_aggregation_subframes; u8 max_tx_fragments; u8 offchannel_tx_hw_queue; u8 radiotap_mcs_details; u16 radiotap_vht_details; struct { int units_pos; s16 accuracy; } radiotap_timestamp; netdev_features_t netdev_features; u8 uapsd_queues; u8 uapsd_max_sp_len; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; u8 weight_multiplier; u32 max_mtu; const s8 *tx_power_levels; u8 max_txpwr_levels_idx; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, enum ieee80211_hw_flags flg) { return test_bit(flg, hw->flags); } #define ieee80211_hw_check(hw, flg) _ieee80211_hw_check(hw, IEEE80211_HW_##flg) static inline void _ieee80211_hw_set(struct ieee80211_hw *hw, enum ieee80211_hw_flags flg) { return __set_bit(flg, hw->flags); } #define ieee80211_hw_set(hw, flg) _ieee80211_hw_set(hw, IEEE80211_HW_##flg) /** * struct ieee80211_scan_request - hw scan request * * @ies: pointers different parts of IEs (in req.ie) * @req: cfg80211 request. */ struct ieee80211_scan_request { struct ieee80211_scan_ies ies; /* Keep last */ struct cfg80211_scan_request req; }; /** * struct ieee80211_tdls_ch_sw_params - TDLS channel switch parameters * * @sta: peer this TDLS channel-switch request/response came from * @chandef: channel referenced in a TDLS channel-switch request * @action_code: see &enum ieee80211_tdls_actioncode * @status: channel-switch response status * @timestamp: time at which the frame was received * @switch_time: switch-timing parameter received in the frame * @switch_timeout: switch-timing parameter received in the frame * @tmpl_skb: TDLS switch-channel response template * @ch_sw_tm_ie: offset of the channel-switch timing IE inside @tmpl_skb */ struct ieee80211_tdls_ch_sw_params { struct ieee80211_sta *sta; struct cfg80211_chan_def *chandef; u8 action_code; u32 status; u32 timestamp; u16 switch_time; u16 switch_timeout; struct sk_buff *tmpl_skb; u32 ch_sw_tm_ie; }; /** * wiphy_to_ieee80211_hw - return a mac80211 driver hw struct from a wiphy * * @wiphy: the &struct wiphy which we want to query * * mac80211 drivers can use this to get to their respective * &struct ieee80211_hw. Drivers wishing to get to their own private * structure can then access it via hw->priv. Note that mac802111 drivers should * not use wiphy_priv() to try to get their private driver structure as this * is already used internally by mac80211. * * Return: The mac80211 driver hw struct of @wiphy. */ struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy); /** * SET_IEEE80211_DEV - set device for 802.11 hardware * * @hw: the &struct ieee80211_hw to set the device for * @dev: the &struct device of this 802.11 device */ static inline void SET_IEEE80211_DEV(struct ieee80211_hw *hw, struct device *dev) { set_wiphy_dev(hw->wiphy, dev); } /** * SET_IEEE80211_PERM_ADDR - set the permanent MAC address for 802.11 hardware * * @hw: the &struct ieee80211_hw to set the MAC address for * @addr: the address to set */ static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, const u8 *addr) { memcpy(hw->wiphy->perm_addr, addr, ETH_ALEN); } static inline struct ieee80211_rate * ieee80211_get_tx_rate(const struct ieee80211_hw *hw, const struct ieee80211_tx_info *c) { if (WARN_ON_ONCE(c->control.rates[0].idx < 0)) return NULL; return &hw->wiphy->bands[c->band]->bitrates[c->control.rates[0].idx]; } static inline struct ieee80211_rate * ieee80211_get_rts_cts_rate(const struct ieee80211_hw *hw, const struct ieee80211_tx_info *c) { if (c->control.rts_cts_rate_idx < 0) return NULL; return &hw->wiphy->bands[c->band]->bitrates[c->control.rts_cts_rate_idx]; } static inline struct ieee80211_rate * ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, const struct ieee80211_tx_info *c, int idx) { if (c->control.rates[idx + 1].idx < 0) return NULL; return &hw->wiphy->bands[c->band]->bitrates[c->control.rates[idx + 1].idx]; } /** * ieee80211_free_txskb - free TX skb * @hw: the hardware * @skb: the skb * * Free a transmit skb. Use this function when some failure * to transmit happened and thus status cannot be reported. */ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); /** * DOC: Hardware crypto acceleration * * mac80211 is capable of taking advantage of many hardware * acceleration designs for encryption and decryption operations. * * The set_key() callback in the &struct ieee80211_ops for a given * device is called to enable hardware acceleration of encryption and * decryption. The callback takes a @sta parameter that will be NULL * for default keys or keys used for transmission only, or point to * the station information for the peer for individual keys. * Multiple transmission keys with the same key index may be used when * VLANs are configured for an access point. * * When transmitting, the TX control data will use the @hw_key_idx * selected by the driver by modifying the &struct ieee80211_key_conf * pointed to by the @key parameter to the set_key() function. * * The set_key() call for the %SET_KEY command should return 0 if * the key is now in use, -%EOPNOTSUPP or -%ENOSPC if it couldn't be * added; if you return 0 then hw_key_idx must be assigned to the * hardware key index. You are free to use the full u8 range. * * Note that in the case that the @IEEE80211_HW_SW_CRYPTO_CONTROL flag is * set, mac80211 will not automatically fall back to software crypto if * enabling hardware crypto failed. The set_key() call may also return the * value 1 to permit this specific key/algorithm to be done in software. * * When the cmd is %DISABLE_KEY then it must succeed. * * Note that it is permissible to not decrypt a frame even if a key * for it has been uploaded to hardware. The stack will not make any * decision based on whether a key has been uploaded or not but rather * based on the receive flags. * * The &struct ieee80211_key_conf structure pointed to by the @key * parameter is guaranteed to be valid until another call to set_key() * removes it, but it can only be used as a cookie to differentiate * keys. * * In TKIP some HW need to be provided a phase 1 key, for RX decryption * acceleration (i.e. iwlwifi). Those drivers should provide update_tkip_key * handler. * The update_tkip_key() call updates the driver with the new phase 1 key. * This happens every time the iv16 wraps around (every 65536 packets). The * set_key() call will happen only once for each key (unless the AP did * rekeying); it will not include a valid phase 1 key. The valid phase 1 key is * provided by update_tkip_key only. The trigger that makes mac80211 call this * handler is software decryption with wrap around of iv16. * * The set_default_unicast_key() call updates the default WEP key index * configured to the hardware for WEP encryption type. This is required * for devices that support offload of data packets (e.g. ARP responses). * * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag * when they are able to replace in-use PTK keys according to the following * requirements: * 1) They do not hand over frames decrypted with the old key to mac80211 once the call to set_key() with command %DISABLE_KEY has been completed, 2) either drop or continue to use the old key for any outgoing frames queued at the time of the key deletion (including re-transmits), 3) never send out a frame queued prior to the set_key() %SET_KEY command encrypted with the new key when also needing @IEEE80211_KEY_FLAG_GENERATE_IV and 4) never send out a frame unencrypted when it should be encrypted. Mac80211 will not queue any new frames for a deleted key to the driver. */ /** * DOC: Powersave support * * mac80211 has support for various powersave implementations. * * First, it can support hardware that handles all powersaving by itself; * such hardware should simply set the %IEEE80211_HW_SUPPORTS_PS hardware * flag. In that case, it will be told about the desired powersave mode * with the %IEEE80211_CONF_PS flag depending on the association status. * The hardware must take care of sending nullfunc frames when necessary, * i.e. when entering and leaving powersave mode. The hardware is required * to look at the AID in beacons and signal to the AP that it woke up when * it finds traffic directed to it. * * %IEEE80211_CONF_PS flag enabled means that the powersave mode defined in * IEEE 802.11-2007 section 11.2 is enabled. This is not to be confused * with hardware wakeup and sleep states. Driver is responsible for waking * up the hardware before issuing commands to the hardware and putting it * back to sleep at appropriate times. * * When PS is enabled, hardware needs to wakeup for beacons and receive the * buffered multicast/broadcast frames after the beacon. Also it must be * possible to send frames and receive the acknowledment frame. * * Other hardware designs cannot send nullfunc frames by themselves and also * need software support for parsing the TIM bitmap. This is also supported * by mac80211 by combining the %IEEE80211_HW_SUPPORTS_PS and * %IEEE80211_HW_PS_NULLFUNC_STACK flags. The hardware is of course still * required to pass up beacons. The hardware is still required to handle * waking up for multicast traffic; if it cannot the driver must handle that * as best as it can; mac80211 is too slow to do that. * * Dynamic powersave is an extension to normal powersave in which the * hardware stays awake for a user-specified period of time after sending a * frame so that reply frames need not be buffered and therefore delayed to * the next wakeup. It's a compromise of getting good enough latency when * there's data traffic and still saving significantly power in idle * periods. * * Dynamic powersave is simply supported by mac80211 enabling and disabling * PS based on traffic. Driver needs to only set %IEEE80211_HW_SUPPORTS_PS * flag and mac80211 will handle everything automatically. Additionally, * hardware having support for the dynamic PS feature may set the * %IEEE80211_HW_SUPPORTS_DYNAMIC_PS flag to indicate that it can support * dynamic PS mode itself. The driver needs to look at the * @dynamic_ps_timeout hardware configuration value and use it that value * whenever %IEEE80211_CONF_PS is set. In this case mac80211 will disable * dynamic PS feature in stack and will just keep %IEEE80211_CONF_PS * enabled whenever user has enabled powersave. * * Driver informs U-APSD client support by enabling * %IEEE80211_VIF_SUPPORTS_UAPSD flag. The mode is configured through the * uapsd parameter in conf_tx() operation. Hardware needs to send the QoS * Nullfunc frames and stay awake until the service period has ended. To * utilize U-APSD, dynamic powersave is disabled for voip AC and all frames * from that AC are transmitted with powersave enabled. * * Note: U-APSD client mode is not yet supported with * %IEEE80211_HW_PS_NULLFUNC_STACK. */ /** * DOC: Beacon filter support * * Some hardware have beacon filter support to reduce host cpu wakeups * which will reduce system power consumption. It usually works so that * the firmware creates a checksum of the beacon but omits all constantly * changing elements (TSF, TIM etc). Whenever the checksum changes the * beacon is forwarded to the host, otherwise it will be just dropped. That * way the host will only receive beacons where some relevant information * (for example ERP protection or WMM settings) have changed. * * Beacon filter support is advertised with the %IEEE80211_VIF_BEACON_FILTER * interface capability. The driver needs to enable beacon filter support * whenever power save is enabled, that is %IEEE80211_CONF_PS is set. When * power save is enabled, the stack will not check for beacon loss and the * driver needs to notify about loss of beacons with ieee80211_beacon_loss(). * * The time (or number of beacons missed) until the firmware notifies the * driver of a beacon loss event (which in turn causes the driver to call * ieee80211_beacon_loss()) should be configurable and will be controlled * by mac80211 and the roaming algorithm in the future. * * Since there may be constantly changing information elements that nothing * in the software stack cares about, we will, in the future, have mac80211 * tell the driver which information elements are interesting in the sense * that we want to see changes in them. This will include * * - a list of information element IDs * - a list of OUIs for the vendor information element * * Ideally, the hardware would filter out any beacons without changes in the * requested elements, but if it cannot support that it may, at the expense * of some efficiency, filter out only a subset. For example, if the device * doesn't support checking for OUIs it should pass up all changes in all * vendor information elements. * * Note that change, for the sake of simplification, also includes information * elements appearing or disappearing from the beacon. * * Some hardware supports an "ignore list" instead. Just make sure nothing * that was requested is on the ignore list, and include commonly changing * information element IDs in the ignore list, for example 11 (BSS load) and * the various vendor-assigned IEs with unknown contents (128, 129, 133-136, * 149, 150, 155, 156, 173, 176, 178, 179, 219); for forward compatibility * it could also include some currently unused IDs. * * * In addition to these capabilities, hardware should support notifying the * host of changes in the beacon RSSI. This is relevant to implement roaming * when no traffic is flowing (when traffic is flowing we see the RSSI of * the received data packets). This can consist of notifying the host when * the RSSI changes significantly or when it drops below or rises above * configurable thresholds. In the future these thresholds will also be * configured by mac80211 (which gets them from userspace) to implement * them as the roaming algorithm requires. * * If the hardware cannot implement this, the driver should ask it to * periodically pass beacon frames to the host so that software can do the * signal strength threshold checking. */ /** * DOC: Spatial multiplexing power save * * SMPS (Spatial multiplexing power save) is a mechanism to conserve * power in an 802.11n implementation. For details on the mechanism * and rationale, please refer to 802.11 (as amended by 802.11n-2009) * "11.2.3 SM power save". * * The mac80211 implementation is capable of sending action frames * to update the AP about the station's SMPS mode, and will instruct * the driver to enter the specific mode. It will also announce the * requested SMPS mode during the association handshake. Hardware * support for this feature is required, and can be indicated by * hardware flags. * * The default mode will be "automatic", which nl80211/cfg80211 * defines to be dynamic SMPS in (regular) powersave, and SMPS * turned off otherwise. * * To support this feature, the driver must set the appropriate * hardware support flags, and handle the SMPS flag to the config() * operation. It will then with this mechanism be instructed to * enter the requested SMPS mode while associated to an HT AP. */ /** * DOC: Frame filtering * * mac80211 requires to see many management frames for proper * operation, and users may want to see many more frames when * in monitor mode. However, for best CPU usage and power consumption, * having as few frames as possible percolate through the stack is * desirable. Hence, the hardware should filter as much as possible. * * To achieve this, mac80211 uses filter flags (see below) to tell * the driver's configure_filter() function which frames should be * passed to mac80211 and which should be filtered out. * * Before configure_filter() is invoked, the prepare_multicast() * callback is invoked with the parameters @mc_count and @mc_list * for the combined multicast address list of all virtual interfaces. * It's use is optional, and it returns a u64 that is passed to * configure_filter(). Additionally, configure_filter() has the * arguments @changed_flags telling which flags were changed and * @total_flags with the new flag states. * * If your device has no multicast address filters your driver will * need to check both the %FIF_ALLMULTI flag and the @mc_count * parameter to see whether multicast frames should be accepted * or dropped. * * All unsupported flags in @total_flags must be cleared. * Hardware does not support a flag if it is incapable of _passing_ * the frame to the stack. Otherwise the driver must ignore * the flag, but not clear it. * You must _only_ clear the flag (announce no support for the * flag to mac80211) if you are not able to pass the packet type * to the stack (so the hardware always filters it). * So for example, you should clear @FIF_CONTROL, if your hardware * always filters control frames. If your hardware always passes * control frames to the kernel and is incapable of filtering them, * you do _not_ clear the @FIF_CONTROL flag. * This rule applies to all other FIF flags as well. */ /** * DOC: AP support for powersaving clients * * In order to implement AP and P2P GO modes, mac80211 has support for * client powersaving, both "legacy" PS (PS-Poll/null data) and uAPSD. * There currently is no support for sAPSD. * * There is one assumption that mac80211 makes, namely that a client * will not poll with PS-Poll and trigger with uAPSD at the same time. * Both are supported, and both can be used by the same client, but * they can't be used concurrently by the same client. This simplifies * the driver code. * * The first thing to keep in mind is that there is a flag for complete * driver implementation: %IEEE80211_HW_AP_LINK_PS. If this flag is set, * mac80211 expects the driver to handle most of the state machine for * powersaving clients and will ignore the PM bit in incoming frames. * Drivers then use ieee80211_sta_ps_transition() to inform mac80211 of * stations' powersave transitions. In this mode, mac80211 also doesn't * handle PS-Poll/uAPSD. * * In the mode without %IEEE80211_HW_AP_LINK_PS, mac80211 will check the * PM bit in incoming frames for client powersave transitions. When a * station goes to sleep, we will stop transmitting to it. There is, * however, a race condition: a station might go to sleep while there is * data buffered on hardware queues. If the device has support for this * it will reject frames, and the driver should give the frames back to * mac80211 with the %IEEE80211_TX_STAT_TX_FILTERED flag set which will * cause mac80211 to retry the frame when the station wakes up. The * driver is also notified of powersave transitions by calling its * @sta_notify callback. * * When the station is asleep, it has three choices: it can wake up, * it can PS-Poll, or it can possibly start a uAPSD service period. * Waking up is implemented by simply transmitting all buffered (and * filtered) frames to the station. This is the easiest case. When * the station sends a PS-Poll or a uAPSD trigger frame, mac80211 * will inform the driver of this with the @allow_buffered_frames * callback; this callback is optional. mac80211 will then transmit * the frames as usual and set the %IEEE80211_TX_CTL_NO_PS_BUFFER * on each frame. The last frame in the service period (or the only * response to a PS-Poll) also has %IEEE80211_TX_STATUS_EOSP set to * indicate that it ends the service period; as this frame must have * TX status report it also sets %IEEE80211_TX_CTL_REQ_TX_STATUS. * When TX status is reported for this frame, the service period is * marked has having ended and a new one can be started by the peer. * * Additionally, non-bufferable MMPDUs can also be transmitted by * mac80211 with the %IEEE80211_TX_CTL_NO_PS_BUFFER set in them. * * Another race condition can happen on some devices like iwlwifi * when there are frames queued for the station and it wakes up * or polls; the frames that are already queued could end up being * transmitted first instead, causing reordering and/or wrong * processing of the EOSP. The cause is that allowing frames to be * transmitted to a certain station is out-of-band communication to * the device. To allow this problem to be solved, the driver can * call ieee80211_sta_block_awake() if frames are buffered when it * is notified that the station went to sleep. When all these frames * have been filtered (see above), it must call the function again * to indicate that the station is no longer blocked. * * If the driver buffers frames in the driver for aggregation in any * way, it must use the ieee80211_sta_set_buffered() call when it is * notified of the station going to sleep to inform mac80211 of any * TIDs that have frames buffered. Note that when a station wakes up * this information is reset (hence the requirement to call it when * informed of the station going to sleep). Then, when a service * period starts for any reason, @release_buffered_frames is called * with the number of frames to be released and which TIDs they are * to come from. In this case, the driver is responsible for setting * the EOSP (for uAPSD) and MORE_DATA bits in the released frames. * To help the @more_data parameter is passed to tell the driver if * there is more data on other TIDs -- the TIDs to release frames * from are ignored since mac80211 doesn't know how many frames the * buffers for those TIDs contain. * * If the driver also implement GO mode, where absence periods may * shorten service periods (or abort PS-Poll responses), it must * filter those response frames except in the case of frames that * are buffered in the driver -- those must remain buffered to avoid * reordering. Because it is possible that no frames are released * in this case, the driver must call ieee80211_sta_eosp() * to indicate to mac80211 that the service period ended anyway. * * Finally, if frames from multiple TIDs are released from mac80211 * but the driver might reorder them, it must clear & set the flags * appropriately (only the last frame may have %IEEE80211_TX_STATUS_EOSP) * and also take care of the EOSP and MORE_DATA bits in the frame. * The driver may also use ieee80211_sta_eosp() in this case. * * Note that if the driver ever buffers frames other than QoS-data * frames, it must take care to never send a non-QoS-data frame as * the last frame in a service period, adding a QoS-nulldata frame * after a non-QoS-data frame if needed. */ /** * DOC: HW queue control * * Before HW queue control was introduced, mac80211 only had a single static * assignment of per-interface AC software queues to hardware queues. This * was problematic for a few reasons: * 1) off-channel transmissions might get stuck behind other frames * 2) multiple virtual interfaces couldn't be handled correctly * 3) after-DTIM frames could get stuck behind other frames * * To solve this, hardware typically uses multiple different queues for all * the different usages, and this needs to be propagated into mac80211 so it * won't have the same problem with the software queues. * * Therefore, mac80211 now offers the %IEEE80211_HW_QUEUE_CONTROL capability * flag that tells it that the driver implements its own queue control. To do * so, the driver will set up the various queues in each &struct ieee80211_vif * and the offchannel queue in &struct ieee80211_hw. In response, mac80211 will * use those queue IDs in the hw_queue field of &struct ieee80211_tx_info and * if necessary will queue the frame on the right software queue that mirrors * the hardware queue. * Additionally, the driver has to then use these HW queue IDs for the queue * management functions (ieee80211_stop_queue() et al.) * * The driver is free to set up the queue mappings as needed; multiple virtual * interfaces may map to the same hardware queues if needed. The setup has to * happen during add_interface or change_interface callbacks. For example, a * driver supporting station+station and station+AP modes might decide to have * 10 hardware queues to handle different scenarios: * * 4 AC HW queues for 1st vif: 0, 1, 2, 3 * 4 AC HW queues for 2nd vif: 4, 5, 6, 7 * after-DTIM queue for AP: 8 * off-channel queue: 9 * * It would then set up the hardware like this: * hw.offchannel_tx_hw_queue = 9 * * and the first virtual interface that is added as follows: * vif.hw_queue[IEEE80211_AC_VO] = 0 * vif.hw_queue[IEEE80211_AC_VI] = 1 * vif.hw_queue[IEEE80211_AC_BE] = 2 * vif.hw_queue[IEEE80211_AC_BK] = 3 * vif.cab_queue = 8 // if AP mode, otherwise %IEEE80211_INVAL_HW_QUEUE * and the second virtual interface with 4-7. * * If queue 6 gets full, for example, mac80211 would only stop the second * virtual interface's BE queue since virtual interface queues are per AC. * * Note that the vif.cab_queue value should be set to %IEEE80211_INVAL_HW_QUEUE * whenever the queue is not used (i.e. the interface is not in AP mode) if the * queue could potentially be shared since mac80211 will look at cab_queue when * a queue is stopped/woken even if the interface is not in AP mode. */ /** * enum ieee80211_filter_flags - hardware filter flags * * These flags determine what the filter in hardware should be * programmed to let through and what should not be passed to the * stack. It is always safe to pass more frames than requested, * but this has negative impact on power consumption. * * @FIF_ALLMULTI: pass all multicast frames, this is used if requested * by the user or if the hardware is not capable of filtering by * multicast address. * * @FIF_FCSFAIL: pass frames with failed FCS (but you need to set the * %RX_FLAG_FAILED_FCS_CRC for them) * * @FIF_PLCPFAIL: pass frames with failed PLCP CRC (but you need to set * the %RX_FLAG_FAILED_PLCP_CRC for them * * @FIF_BCN_PRBRESP_PROMISC: This flag is set during scanning to indicate * to the hardware that it should not filter beacons or probe responses * by BSSID. Filtering them can greatly reduce the amount of processing * mac80211 needs to do and the amount of CPU wakeups, so you should * honour this flag if possible. * * @FIF_CONTROL: pass control frames (except for PS Poll) addressed to this * station * * @FIF_OTHER_BSS: pass frames destined to other BSSes * * @FIF_PSPOLL: pass PS Poll frames * * @FIF_PROBE_REQ: pass probe request frames * * @FIF_MCAST_ACTION: pass multicast Action frames */ enum ieee80211_filter_flags { FIF_ALLMULTI = 1<<1, FIF_FCSFAIL = 1<<2, FIF_PLCPFAIL = 1<<3, FIF_BCN_PRBRESP_PROMISC = 1<<4, FIF_CONTROL = 1<<5, FIF_OTHER_BSS = 1<<6, FIF_PSPOLL = 1<<7, FIF_PROBE_REQ = 1<<8, FIF_MCAST_ACTION = 1<<9, }; /** * enum ieee80211_ampdu_mlme_action - A-MPDU actions * * These flags are used with the ampdu_action() callback in * &struct ieee80211_ops to indicate which action is needed. * * Note that drivers MUST be able to deal with a TX aggregation * session being stopped even before they OK'ed starting it by * calling ieee80211_start_tx_ba_cb_irqsafe, because the peer * might receive the addBA frame and send a delBA right away! * * @IEEE80211_AMPDU_RX_START: start RX aggregation * @IEEE80211_AMPDU_RX_STOP: stop RX aggregation * @IEEE80211_AMPDU_TX_START: start TX aggregation, the driver must either * call ieee80211_start_tx_ba_cb_irqsafe() or * call ieee80211_start_tx_ba_cb_irqsafe() with status * %IEEE80211_AMPDU_TX_START_DELAY_ADDBA to delay addba after * ieee80211_start_tx_ba_cb_irqsafe is called, or just return the special * status %IEEE80211_AMPDU_TX_START_IMMEDIATE. * @IEEE80211_AMPDU_TX_OPERATIONAL: TX aggregation has become operational * @IEEE80211_AMPDU_TX_STOP_CONT: stop TX aggregation but continue transmitting * queued packets, now unaggregated. After all packets are transmitted the * driver has to call ieee80211_stop_tx_ba_cb_irqsafe(). * @IEEE80211_AMPDU_TX_STOP_FLUSH: stop TX aggregation and flush all packets, * called when the station is removed. There's no need or reason to call * ieee80211_stop_tx_ba_cb_irqsafe() in this case as mac80211 assumes the * session is gone and removes the station. * @IEEE80211_AMPDU_TX_STOP_FLUSH_CONT: called when TX aggregation is stopped * but the driver hasn't called ieee80211_stop_tx_ba_cb_irqsafe() yet and * now the connection is dropped and the station will be removed. Drivers * should clean up and drop remaining packets when this is called. */ enum ieee80211_ampdu_mlme_action { IEEE80211_AMPDU_RX_START, IEEE80211_AMPDU_RX_STOP, IEEE80211_AMPDU_TX_START, IEEE80211_AMPDU_TX_STOP_CONT, IEEE80211_AMPDU_TX_STOP_FLUSH, IEEE80211_AMPDU_TX_STOP_FLUSH_CONT, IEEE80211_AMPDU_TX_OPERATIONAL, }; #define IEEE80211_AMPDU_TX_START_IMMEDIATE 1 #define IEEE80211_AMPDU_TX_START_DELAY_ADDBA 2 /** * struct ieee80211_ampdu_params - AMPDU action parameters * * @action: the ampdu action, value from %ieee80211_ampdu_mlme_action. * @sta: peer of this AMPDU session * @tid: tid of the BA session * @ssn: start sequence number of the session. TX/RX_STOP can pass 0. When * action is set to %IEEE80211_AMPDU_RX_START the driver passes back the * actual ssn value used to start the session and writes the value here. * @buf_size: reorder buffer size (number of subframes). Valid only when the * action is set to %IEEE80211_AMPDU_RX_START or * %IEEE80211_AMPDU_TX_OPERATIONAL * @amsdu: indicates the peer's ability to receive A-MSDU within A-MPDU. * valid when the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL * @timeout: BA session timeout. Valid only when the action is set to * %IEEE80211_AMPDU_RX_START */ struct ieee80211_ampdu_params { enum ieee80211_ampdu_mlme_action action; struct ieee80211_sta *sta; u16 tid; u16 ssn; u16 buf_size; bool amsdu; u16 timeout; }; /** * enum ieee80211_frame_release_type - frame release reason * @IEEE80211_FRAME_RELEASE_PSPOLL: frame released for PS-Poll * @IEEE80211_FRAME_RELEASE_UAPSD: frame(s) released due to * frame received on trigger-enabled AC */ enum ieee80211_frame_release_type { IEEE80211_FRAME_RELEASE_PSPOLL, IEEE80211_FRAME_RELEASE_UAPSD, }; /** * enum ieee80211_rate_control_changed - flags to indicate what changed * * @IEEE80211_RC_BW_CHANGED: The bandwidth that can be used to transmit * to this station changed. The actual bandwidth is in the station * information -- for HT20/40 the IEEE80211_HT_CAP_SUP_WIDTH_20_40 * flag changes, for HT and VHT the bandwidth field changes. * @IEEE80211_RC_SMPS_CHANGED: The SMPS state of the station changed. * @IEEE80211_RC_SUPP_RATES_CHANGED: The supported rate set of this peer * changed (in IBSS mode) due to discovering more information about * the peer. * @IEEE80211_RC_NSS_CHANGED: N_SS (number of spatial streams) was changed * by the peer */ enum ieee80211_rate_control_changed { IEEE80211_RC_BW_CHANGED = BIT(0), IEEE80211_RC_SMPS_CHANGED = BIT(1), IEEE80211_RC_SUPP_RATES_CHANGED = BIT(2), IEEE80211_RC_NSS_CHANGED = BIT(3), }; /** * enum ieee80211_roc_type - remain on channel type * * With the support for multi channel contexts and multi channel operations, * remain on channel operations might be limited/deferred/aborted by other * flows/operations which have higher priority (and vice versa). * Specifying the ROC type can be used by devices to prioritize the ROC * operations compared to other operations/flows. * * @IEEE80211_ROC_TYPE_NORMAL: There are no special requirements for this ROC. * @IEEE80211_ROC_TYPE_MGMT_TX: The remain on channel request is required * for sending management frames offchannel. */ enum ieee80211_roc_type { IEEE80211_ROC_TYPE_NORMAL = 0, IEEE80211_ROC_TYPE_MGMT_TX, }; /** * enum ieee80211_reconfig_type - reconfig type * * This enum is used by the reconfig_complete() callback to indicate what * reconfiguration type was completed. * * @IEEE80211_RECONFIG_TYPE_RESTART: hw restart type * (also due to resume() callback returning 1) * @IEEE80211_RECONFIG_TYPE_SUSPEND: suspend type (regardless * of wowlan configuration) */ enum ieee80211_reconfig_type { IEEE80211_RECONFIG_TYPE_RESTART, IEEE80211_RECONFIG_TYPE_SUSPEND, }; /** * struct ieee80211_prep_tx_info - prepare TX information * @duration: if non-zero, hint about the required duration, * only used with the mgd_prepare_tx() method. * @subtype: frame subtype (auth, (re)assoc, deauth, disassoc) * @success: whether the frame exchange was successful, only * used with the mgd_complete_tx() method, and then only * valid for auth and (re)assoc. * @was_assoc: set if this call is due to deauth/disassoc * while just having been associated * @link_id: the link id on which the frame will be TX'ed. * Only used with the mgd_prepare_tx() method. */ struct ieee80211_prep_tx_info { u16 duration; u16 subtype; u8 success:1, was_assoc:1; int link_id; }; /** * struct ieee80211_ops - callbacks from mac80211 to the driver * * This structure contains various callbacks that the driver may * handle or, in some cases, must handle, for example to configure * the hardware to a new channel or to transmit a frame. * * @tx: Handler that 802.11 module calls for each transmitted frame. * skb contains the buffer starting from the IEEE 802.11 header. * The low-level driver should send the frame out based on * configuration in the TX control data. This handler should, * preferably, never fail and stop queues appropriately. * Must be atomic. * * @start: Called before the first netdevice attached to the hardware * is enabled. This should turn on the hardware and must turn on * frame reception (for possibly enabled monitor interfaces.) * Returns negative error codes, these may be seen in userspace, * or zero. * When the device is started it should not have a MAC address * to avoid acknowledging frames before a non-monitor device * is added. * Must be implemented and can sleep. * * @stop: Called after last netdevice attached to the hardware * is disabled. This should turn off the hardware (at least * it must turn off frame reception.) * May be called right after add_interface if that rejects * an interface. If you added any work onto the mac80211 workqueue * you should ensure to cancel it on this callback. * Must be implemented and can sleep. * * @suspend: Suspend the device; mac80211 itself will quiesce before and * stop transmitting and doing any other configuration, and then * ask the device to suspend. This is only invoked when WoWLAN is * configured, otherwise the device is deconfigured completely and * reconfigured at resume time. * The driver may also impose special conditions under which it * wants to use the "normal" suspend (deconfigure), say if it only * supports WoWLAN when the device is associated. In this case, it * must return 1 from this function. * * @resume: If WoWLAN was configured, this indicates that mac80211 is * now resuming its operation, after this the device must be fully * functional again. If this returns an error, the only way out is * to also unregister the device. If it returns 1, then mac80211 * will also go through the regular complete restart on resume. * * @set_wakeup: Enable or disable wakeup when WoWLAN configuration is * modified. The reason is that device_set_wakeup_enable() is * supposed to be called when the configuration changes, not only * in suspend(). * * @add_interface: Called when a netdevice attached to the hardware is * enabled. Because it is not called for monitor mode devices, @start * and @stop must be implemented. * The driver should perform any initialization it needs before * the device can be enabled. The initial configuration for the * interface is given in the conf parameter. * The callback may refuse to add an interface by returning a * negative error code (which will be seen in userspace.) * Must be implemented and can sleep. * * @change_interface: Called when a netdevice changes type. This callback * is optional, but only if it is supported can interface types be * switched while the interface is UP. The callback may sleep. * Note that while an interface is being switched, it will not be * found by the interface iteration callbacks. * * @remove_interface: Notifies a driver that an interface is going down. * The @stop callback is called after this if it is the last interface * and no monitor interfaces are present. * When all interfaces are removed, the MAC address in the hardware * must be cleared so the device no longer acknowledges packets, * the mac_addr member of the conf structure is, however, set to the * MAC address of the device going away. * Hence, this callback must be implemented. It can sleep. * * @config: Handler for configuration requests. IEEE 802.11 code calls this * function to change hardware configuration, e.g., channel. * This function should never fail but returns a negative error code * if it does. The callback can sleep. * * @bss_info_changed: Handler for configuration requests related to BSS * parameters that may vary during BSS's lifespan, and may affect low * level driver (e.g. assoc/disassoc status, erp parameters). * This function should not be used if no BSS has been set, unless * for association indication. The @changed parameter indicates which * of the bss parameters has changed when a call is made. The callback * can sleep. * Note: this callback is called if @vif_cfg_changed or @link_info_changed * are not implemented. * * @vif_cfg_changed: Handler for configuration requests related to interface * (MLD) parameters from &struct ieee80211_vif_cfg that vary during the * lifetime of the interface (e.g. assoc status, IP addresses, etc.) * The @changed parameter indicates which value changed. * The callback can sleep. * * @link_info_changed: Handler for configuration requests related to link * parameters from &struct ieee80211_bss_conf that are related to an * individual link. e.g. legacy/HT/VHT/... rate information. * The @changed parameter indicates which value changed, and the @link_id * parameter indicates the link ID. Note that the @link_id will be 0 for * non-MLO connections. * The callback can sleep. * * @prepare_multicast: Prepare for multicast filter configuration. * This callback is optional, and its return value is passed * to configure_filter(). This callback must be atomic. * * @configure_filter: Configure the device's RX filter. * See the section "Frame filtering" for more information. * This callback must be implemented and can sleep. * * @config_iface_filter: Configure the interface's RX filter. * This callback is optional and is used to configure which frames * should be passed to mac80211. The filter_flags is the combination * of FIF_* flags. The changed_flags is a bit mask that indicates * which flags are changed. * This callback can sleep. * * @set_tim: Set TIM bit. mac80211 calls this function when a TIM bit * must be set or cleared for a given STA. Must be atomic. * * @set_key: See the section "Hardware crypto acceleration" * This callback is only called between add_interface and * remove_interface calls, i.e. while the given virtual interface * is enabled. * Returns a negative error code if the key can't be added. * The callback can sleep. * * @update_tkip_key: See the section "Hardware crypto acceleration" * This callback will be called in the context of Rx. Called for drivers * which set IEEE80211_KEY_FLAG_TKIP_REQ_RX_P1_KEY. * The callback must be atomic. * * @set_rekey_data: If the device supports GTK rekeying, for example while the * host is suspended, it can assign this callback to retrieve the data * necessary to do GTK rekeying, this is the KEK, KCK and replay counter. * After rekeying was done it should (for example during resume) notify * userspace of the new replay counter using ieee80211_gtk_rekey_notify(). * * @set_default_unicast_key: Set the default (unicast) key index, useful for * WEP when the device sends data packets autonomously, e.g. for ARP * offloading. The index can be 0-3, or -1 for unsetting it. * * @hw_scan: Ask the hardware to service the scan request, no need to start * the scan state machine in stack. The scan must honour the channel * configuration done by the regulatory agent in the wiphy's * registered bands. The hardware (or the driver) needs to make sure * that power save is disabled. * The @req ie/ie_len members are rewritten by mac80211 to contain the * entire IEs after the SSID, so that drivers need not look at these * at all but just send them after the SSID -- mac80211 includes the * (extended) supported rates and HT information (where applicable). * When the scan finishes, ieee80211_scan_completed() must be called; * note that it also must be called when the scan cannot finish due to * any error unless this callback returned a negative error code. * This callback is also allowed to return the special return value 1, * this indicates that hardware scan isn't desirable right now and a * software scan should be done instead. A driver wishing to use this * capability must ensure its (hardware) scan capabilities aren't * advertised as more capable than mac80211's software scan is. * The callback can sleep. * * @cancel_hw_scan: Ask the low-level tp cancel the active hw scan. * The driver should ask the hardware to cancel the scan (if possible), * but the scan will be completed only after the driver will call * ieee80211_scan_completed(). * This callback is needed for wowlan, to prevent enqueueing a new * scan_work after the low-level driver was already suspended. * The callback can sleep. * * @sched_scan_start: Ask the hardware to start scanning repeatedly at * specific intervals. The driver must call the * ieee80211_sched_scan_results() function whenever it finds results. * This process will continue until sched_scan_stop is called. * * @sched_scan_stop: Tell the hardware to stop an ongoing scheduled scan. * In this case, ieee80211_sched_scan_stopped() must not be called. * * @sw_scan_start: Notifier function that is called just before a software scan * is started. Can be NULL, if the driver doesn't need this notification. * The mac_addr parameter allows supporting NL80211_SCAN_FLAG_RANDOM_ADDR, * the driver may set the NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR flag if it * can use this parameter. The callback can sleep. * * @sw_scan_complete: Notifier function that is called just after a * software scan finished. Can be NULL, if the driver doesn't need * this notification. * The callback can sleep. * * @get_stats: Return low-level statistics. * Returns zero if statistics are available. * The callback can sleep. * * @get_key_seq: If your device implements encryption in hardware and does * IV/PN assignment then this callback should be provided to read the * IV/PN for the given key from hardware. * The callback must be atomic. * * @set_frag_threshold: Configuration of fragmentation threshold. Assign this * if the device does fragmentation by itself. Note that to prevent the * stack from doing fragmentation IEEE80211_HW_SUPPORTS_TX_FRAG * should be set as well. * The callback can sleep. * * @set_rts_threshold: Configuration of RTS threshold (if device needs it) * The callback can sleep. * * @sta_add: Notifies low level driver about addition of an associated station, * AP, IBSS/WDS/mesh peer etc. This callback can sleep. * * @sta_remove: Notifies low level driver about removal of an associated * station, AP, IBSS/WDS/mesh peer etc. Note that after the callback * returns it isn't safe to use the pointer, not even RCU protected; * no RCU grace period is guaranteed between returning here and freeing * the station. See @sta_pre_rcu_remove if needed. * This callback can sleep. * * @vif_add_debugfs: Drivers can use this callback to add a debugfs vif * directory with its files. This callback should be within a * CONFIG_MAC80211_DEBUGFS conditional. This callback can sleep. * * @link_add_debugfs: Drivers can use this callback to add debugfs files * when a link is added to a mac80211 vif. This callback should be within * a CONFIG_MAC80211_DEBUGFS conditional. This callback can sleep. * For non-MLO the callback will be called once for the default bss_conf * with the vif's directory rather than a separate subdirectory. * * @sta_add_debugfs: Drivers can use this callback to add debugfs files * when a station is added to mac80211's station list. This callback * should be within a CONFIG_MAC80211_DEBUGFS conditional. This * callback can sleep. * * @link_sta_add_debugfs: Drivers can use this callback to add debugfs files * when a link is added to a mac80211 station. This callback * should be within a CONFIG_MAC80211_DEBUGFS conditional. This * callback can sleep. * For non-MLO the callback will be called once for the deflink with the * station's directory rather than a separate subdirectory. * * @sta_notify: Notifies low level driver about power state transition of an * associated station, AP, IBSS/WDS/mesh peer etc. For a VIF operating * in AP mode, this callback will not be called when the flag * %IEEE80211_HW_AP_LINK_PS is set. Must be atomic. * * @sta_set_txpwr: Configure the station tx power. This callback set the tx * power for the station. * This callback can sleep. * * @sta_state: Notifies low level driver about state transition of a * station (which can be the AP, a client, IBSS/WDS/mesh peer etc.) * This callback is mutually exclusive with @sta_add/@sta_remove. * It must not fail for down transitions but may fail for transitions * up the list of states. Also note that after the callback returns it * isn't safe to use the pointer, not even RCU protected - no RCU grace * period is guaranteed between returning here and freeing the station. * See @sta_pre_rcu_remove if needed. * The callback can sleep. * * @sta_pre_rcu_remove: Notify driver about station removal before RCU * synchronisation. This is useful if a driver needs to have station * pointers protected using RCU, it can then use this call to clear * the pointers instead of waiting for an RCU grace period to elapse * in @sta_state. * The callback can sleep. * * @sta_rc_update: Notifies the driver of changes to the bitrates that can be * used to transmit to the station. The changes are advertised with bits * from &enum ieee80211_rate_control_changed and the values are reflected * in the station data. This callback should only be used when the driver * uses hardware rate control (%IEEE80211_HW_HAS_RATE_CONTROL) since * otherwise the rate control algorithm is notified directly. * Must be atomic. * @sta_rate_tbl_update: Notifies the driver that the rate table changed. This * is only used if the configured rate control algorithm actually uses * the new rate table API, and is therefore optional. Must be atomic. * * @sta_statistics: Get statistics for this station. For example with beacon * filtering, the statistics kept by mac80211 might not be accurate, so * let the driver pre-fill the statistics. The driver can fill most of * the values (indicating which by setting the filled bitmap), but not * all of them make sense - see the source for which ones are possible. * Statistics that the driver doesn't fill will be filled by mac80211. * The callback can sleep. * * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max), * bursting) for a hardware TX queue. * Returns a negative error code on failure. * The callback can sleep. * * @get_tsf: Get the current TSF timer value from firmware/hardware. Currently, * this is only used for IBSS mode BSSID merging and debugging. Is not a * required function. * The callback can sleep. * * @set_tsf: Set the TSF timer to the specified value in the firmware/hardware. * Currently, this is only used for IBSS mode debugging. Is not a * required function. * The callback can sleep. * * @offset_tsf: Offset the TSF timer by the specified value in the * firmware/hardware. Preferred to set_tsf as it avoids delay between * calling set_tsf() and hardware getting programmed, which will show up * as TSF delay. Is not a required function. * The callback can sleep. * * @reset_tsf: Reset the TSF timer and allow firmware/hardware to synchronize * with other STAs in the IBSS. This is only used in IBSS mode. This * function is optional if the firmware/hardware takes full care of * TSF synchronization. * The callback can sleep. * * @tx_last_beacon: Determine whether the last IBSS beacon was sent by us. * This is needed only for IBSS mode and the result of this function is * used to determine whether to reply to Probe Requests. * Returns non-zero if this device sent the last beacon. * The callback can sleep. * * @get_survey: Return per-channel survey information * * @rfkill_poll: Poll rfkill hardware state. If you need this, you also * need to set wiphy->rfkill_poll to %true before registration, * and need to call wiphy_rfkill_set_hw_state() in the callback. * The callback can sleep. * * @set_coverage_class: Set slot time for given coverage class as specified * in IEEE 802.11-2007 section 17.3.8.6 and modify ACK timeout * accordingly; coverage class equals to -1 to enable ACK timeout * estimation algorithm (dynack). To disable dynack set valid value for * coverage class. This callback is not required and may sleep. * * @testmode_cmd: Implement a cfg80211 test mode command. The passed @vif may * be %NULL. The callback can sleep. * @testmode_dump: Implement a cfg80211 test mode dump. The callback can sleep. * * @flush: Flush all pending frames from the hardware queue, making sure * that the hardware queues are empty. The @queues parameter is a bitmap * of queues to flush, which is useful if different virtual interfaces * use different hardware queues; it may also indicate all queues. * If the parameter @drop is set to %true, pending frames may be dropped. * Note that vif can be NULL. * The callback can sleep. * * @flush_sta: Flush or drop all pending frames from the hardware queue(s) for * the given station, as it's about to be removed. * The callback can sleep. * * @channel_switch: Drivers that need (or want) to offload the channel * switch operation for CSAs received from the AP may implement this * callback. They must then call ieee80211_chswitch_done() to indicate * completion of the channel switch. * * @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device. * Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may * reject TX/RX mask combinations they cannot support by returning -EINVAL * (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX). * * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant). * * @remain_on_channel: Starts an off-channel period on the given channel, must * call back to ieee80211_ready_on_channel() when on that channel. Note * that normal channel traffic is not stopped as this is intended for hw * offload. Frames to transmit on the off-channel channel are transmitted * normally except for the %IEEE80211_TX_CTL_TX_OFFCHAN flag. When the * duration (which will always be non-zero) expires, the driver must call * ieee80211_remain_on_channel_expired(). * Note that this callback may be called while the device is in IDLE and * must be accepted in this case. * This callback may sleep. * @cancel_remain_on_channel: Requests that an ongoing off-channel period is * aborted before it expires. This callback may sleep. * * @set_ringparam: Set tx and rx ring sizes. * * @get_ringparam: Get tx and rx ring current and maximum sizes. * * @tx_frames_pending: Check if there is any pending frame in the hardware * queues before entering power save. * * @set_bitrate_mask: Set a mask of rates to be used for rate control selection * when transmitting a frame. Currently only legacy rates are handled. * The callback can sleep. * @event_callback: Notify driver about any event in mac80211. See * &enum ieee80211_event_type for the different types. * The callback must be atomic. * * @release_buffered_frames: Release buffered frames according to the given * parameters. In the case where the driver buffers some frames for * sleeping stations mac80211 will use this callback to tell the driver * to release some frames, either for PS-poll or uAPSD. * Note that if the @more_data parameter is %false the driver must check * if there are more frames on the given TIDs, and if there are more than * the frames being released then it must still set the more-data bit in * the frame. If the @more_data parameter is %true, then of course the * more-data bit must always be set. * The @tids parameter tells the driver which TIDs to release frames * from, for PS-poll it will always have only a single bit set. * In the case this is used for a PS-poll initiated release, the * @num_frames parameter will always be 1 so code can be shared. In * this case the driver must also set %IEEE80211_TX_STATUS_EOSP flag * on the TX status (and must report TX status) so that the PS-poll * period is properly ended. This is used to avoid sending multiple * responses for a retried PS-poll frame. * In the case this is used for uAPSD, the @num_frames parameter may be * bigger than one, but the driver may send fewer frames (it must send * at least one, however). In this case it is also responsible for * setting the EOSP flag in the QoS header of the frames. Also, when the * service period ends, the driver must set %IEEE80211_TX_STATUS_EOSP * on the last frame in the SP. Alternatively, it may call the function * ieee80211_sta_eosp() to inform mac80211 of the end of the SP. * This callback must be atomic. * @allow_buffered_frames: Prepare device to allow the given number of frames * to go out to the given station. The frames will be sent by mac80211 * via the usual TX path after this call. The TX information for frames * released will also have the %IEEE80211_TX_CTL_NO_PS_BUFFER flag set * and the last one will also have %IEEE80211_TX_STATUS_EOSP set. In case * frames from multiple TIDs are released and the driver might reorder * them between the TIDs, it must set the %IEEE80211_TX_STATUS_EOSP flag * on the last frame and clear it on all others and also handle the EOSP * bit in the QoS header correctly. Alternatively, it can also call the * ieee80211_sta_eosp() function. * The @tids parameter is a bitmap and tells the driver which TIDs the * frames will be on; it will at most have two bits set. * This callback must be atomic. * * @get_et_sset_count: Ethtool API to get string-set count. * Note that the wiphy mutex is not held for this callback since it's * expected to return a static value. * * @get_et_stats: Ethtool API to get a set of u64 stats. * * @get_et_strings: Ethtool API to get a set of strings to describe stats * and perhaps other supported types of ethtool data-sets. * Note that the wiphy mutex is not held for this callback since it's * expected to return a static value. * * @mgd_prepare_tx: Prepare for transmitting a management frame for association * before associated. In multi-channel scenarios, a virtual interface is * bound to a channel before it is associated, but as it isn't associated * yet it need not necessarily be given airtime, in particular since any * transmission to a P2P GO needs to be synchronized against the GO's * powersave state. mac80211 will call this function before transmitting a * management frame prior to transmitting that frame to allow the driver * to give it channel time for the transmission, to get a response and be * able to synchronize with the GO. * The callback will be called before each transmission and upon return * mac80211 will transmit the frame right away. * Additional information is passed in the &struct ieee80211_prep_tx_info * data. If duration there is greater than zero, mac80211 hints to the * driver the duration for which the operation is requested. * The callback is optional and can (should!) sleep. * @mgd_complete_tx: Notify the driver that the response frame for a previously * transmitted frame announced with @mgd_prepare_tx was received, the data * is filled similarly to @mgd_prepare_tx though the duration is not used. * * @mgd_protect_tdls_discover: Protect a TDLS discovery session. After sending * a TDLS discovery-request, we expect a reply to arrive on the AP's * channel. We must stay on the channel (no PSM, scan, etc.), since a TDLS * setup-response is a direct packet not buffered by the AP. * mac80211 will call this function just before the transmission of a TDLS * discovery-request. The recommended period of protection is at least * 2 * (DTIM period). * The callback is optional and can sleep. * * @add_chanctx: Notifies device driver about new channel context creation. * This callback may sleep. * @remove_chanctx: Notifies device driver about channel context destruction. * This callback may sleep. * @change_chanctx: Notifies device driver about channel context changes that * may happen when combining different virtual interfaces on the same * channel context with different settings * This callback may sleep. * @assign_vif_chanctx: Notifies device driver about channel context being bound * to vif. Possible use is for hw queue remapping. * This callback may sleep. * @unassign_vif_chanctx: Notifies device driver about channel context being * unbound from vif. * This callback may sleep. * @switch_vif_chanctx: switch a number of vifs from one chanctx to * another, as specified in the list of * @ieee80211_vif_chanctx_switch passed to the driver, according * to the mode defined in &ieee80211_chanctx_switch_mode. * This callback may sleep. * * @start_ap: Start operation on the AP interface, this is called after all the * information in bss_conf is set and beacon can be retrieved. A channel * context is bound before this is called. Note that if the driver uses * software scan or ROC, this (and @stop_ap) isn't called when the AP is * just "paused" for scanning/ROC, which is indicated by the beacon being * disabled/enabled via @bss_info_changed. * @stop_ap: Stop operation on the AP interface. * * @reconfig_complete: Called after a call to ieee80211_restart_hw() and * during resume, when the reconfiguration has completed. * This can help the driver implement the reconfiguration step (and * indicate mac80211 is ready to receive frames). * This callback may sleep. * * @ipv6_addr_change: IPv6 address assignment on the given interface changed. * Currently, this is only called for managed or P2P client interfaces. * This callback is optional; it must not sleep. * * @channel_switch_beacon: Starts a channel switch to a new channel. * Beacons are modified to include CSA or ECSA IEs before calling this * function. The corresponding count fields in these IEs must be * decremented, and when they reach 1 the driver must call * ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get() * get the csa counter decremented by mac80211, but must check if it is * 1 using ieee80211_beacon_counter_is_complete() after the beacon has been * transmitted and then call ieee80211_csa_finish(). * If the CSA count starts as zero or 1, this function will not be called, * since there won't be any time to beacon before the switch anyway. * @pre_channel_switch: This is an optional callback that is called * before a channel switch procedure is started (ie. when a STA * gets a CSA or a userspace initiated channel-switch), allowing * the driver to prepare for the channel switch. * @post_channel_switch: This is an optional callback that is called * after a channel switch procedure is completed, allowing the * driver to go back to a normal configuration. * @abort_channel_switch: This is an optional callback that is called * when channel switch procedure was aborted, allowing the * driver to go back to a normal configuration. * @channel_switch_rx_beacon: This is an optional callback that is called * when channel switch procedure is in progress and additional beacon with * CSA IE was received, allowing driver to track changes in count. * @join_ibss: Join an IBSS (on an IBSS interface); this is called after all * information in bss_conf is set up and the beacon can be retrieved. A * channel context is bound before this is called. * @leave_ibss: Leave the IBSS again. * * @get_expected_throughput: extract the expected throughput towards the * specified station. The returned value is expressed in Kbps. It returns 0 * if the RC algorithm does not have proper data to provide. * * @get_txpower: get current maximum tx power (in dBm) based on configuration * and hardware limits. * * @tdls_channel_switch: Start channel-switching with a TDLS peer. The driver * is responsible for continually initiating channel-switching operations * and returning to the base channel for communication with the AP. The * driver receives a channel-switch request template and the location of * the switch-timing IE within the template as part of the invocation. * The template is valid only within the call, and the driver can * optionally copy the skb for further re-use. * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both * peers must be on the base channel when the call completes. * @tdls_recv_channel_switch: a TDLS channel-switch related frame (request or * response) has been received from a remote peer. The driver gets * parameters parsed from the incoming frame and may use them to continue * an ongoing channel-switch operation. In addition, a channel-switch * response template is provided, together with the location of the * switch-timing IE within the template. The skb can only be used within * the function call. * * @wake_tx_queue: Called when new packets have been added to the queue. * @sync_rx_queues: Process all pending frames in RSS queues. This is a * synchronization which is needed in case driver has in its RSS queues * pending frames that were received prior to the control path action * currently taken (e.g. disassociation) but are not processed yet. * * @start_nan: join an existing NAN cluster, or create a new one. * @stop_nan: leave the NAN cluster. * @nan_change_conf: change NAN configuration. The data in cfg80211_nan_conf * contains full new configuration and changes specify which parameters * are changed with respect to the last NAN config. * The driver gets both full configuration and the changed parameters since * some devices may need the full configuration while others need only the * changed parameters. * @add_nan_func: Add a NAN function. Returns 0 on success. The data in * cfg80211_nan_func must not be referenced outside the scope of * this call. * @del_nan_func: Remove a NAN function. The driver must call * ieee80211_nan_func_terminated() with * NL80211_NAN_FUNC_TERM_REASON_USER_REQUEST reason code upon removal. * @can_aggregate_in_amsdu: Called in order to determine if HW supports * aggregating two specific frames in the same A-MSDU. The relation * between the skbs should be symmetric and transitive. Note that while * skb is always a real frame, head may or may not be an A-MSDU. * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available. * Statistics should be cumulative, currently no way to reset is provided. * * @start_pmsr: start peer measurement (e.g. FTM) (this call can sleep) * @abort_pmsr: abort peer measurement (this call can sleep) * @set_tid_config: Apply TID specific configurations. This callback may sleep. * @reset_tid_config: Reset TID specific configuration for the peer. * This callback may sleep. * @update_vif_offload: Update virtual interface offload flags * This callback may sleep. * @sta_set_4addr: Called to notify the driver when a station starts/stops using * 4-address mode * @set_sar_specs: Update the SAR (TX power) settings. * @sta_set_decap_offload: Called to notify the driver when a station is allowed * to use rx decapsulation offload * @add_twt_setup: Update hw with TWT agreement parameters received from the peer. * This callback allows the hw to check if requested parameters * are supported and if there is enough room for a new agreement. * The hw is expected to set agreement result in the req_type field of * twt structure. * @twt_teardown_request: Update the hw with TWT teardown request received * from the peer. * @set_radar_background: Configure dedicated offchannel chain available for * radar/CAC detection on some hw. This chain can't be used to transmit * or receive frames and it is bounded to a running wdev. * Background radar/CAC detection allows to avoid the CAC downtime * switching to a different channel during CAC detection on the selected * radar channel. * The caller is expected to set chandef pointer to NULL in order to * disable background CAC/radar detection. * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to * resolve a path for hardware flow offloading * @can_activate_links: Checks if a specific active_links bitmap is * supported by the driver. * @change_vif_links: Change the valid links on an interface, note that while * removing the old link information is still valid (link_conf pointer), * but may immediately disappear after the function returns. The old or * new links bitmaps may be 0 if going from/to a non-MLO situation. * The @old array contains pointers to the old bss_conf structures * that were already removed, in case they're needed. * This callback can sleep. * @change_sta_links: Change the valid links of a station, similar to * @change_vif_links. This callback can sleep. * Note that a sta can also be inserted or removed with valid links, * i.e. passed to @sta_add/@sta_state with sta->valid_links not zero. * In fact, cannot change from having valid_links and not having them. * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames. This is * not restored at HW reset by mac80211 so drivers need to take care of * that. * @net_setup_tc: Called from .ndo_setup_tc in order to prepare hardware * flow offloading for flows originating from the vif. * Note that the driver must not assume that the vif driver_data is valid * at this point, since the callback can be called during netdev teardown. * @can_neg_ttlm: for managed interface, requests the driver to determine * if the requested TID-To-Link mapping can be accepted or not. * If it's not accepted the driver may suggest a preferred mapping and * modify @ttlm parameter with the suggested TID-to-Link mapping. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb); int (*start)(struct ieee80211_hw *hw); void (*stop)(struct ieee80211_hw *hw, bool suspend); #ifdef CONFIG_PM int (*suspend)(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan); int (*resume)(struct ieee80211_hw *hw); void (*set_wakeup)(struct ieee80211_hw *hw, bool enabled); #endif int (*add_interface)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*change_interface)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum nl80211_iftype new_type, bool p2p); void (*remove_interface)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*config)(struct ieee80211_hw *hw, u32 changed); void (*bss_info_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, u64 changed); void (*vif_cfg_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 changed); void (*link_info_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, u64 changed); int (*start_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*stop_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); u64 (*prepare_multicast)(struct ieee80211_hw *hw, struct netdev_hw_addr_list *mc_list); void (*configure_filter)(struct ieee80211_hw *hw, unsigned int changed_flags, unsigned int *total_flags, u64 multicast); void (*config_iface_filter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int filter_flags, unsigned int changed_flags); int (*set_tim)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set); int (*set_key)(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key); void (*update_tkip_key)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_key_conf *conf, struct ieee80211_sta *sta, u32 iv32, u16 *phase1key); void (*set_rekey_data)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_gtk_rekey_data *data); void (*set_default_unicast_key)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int idx); int (*hw_scan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_scan_request *req); void (*cancel_hw_scan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*sched_scan_start)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_sched_scan_request *req, struct ieee80211_scan_ies *ies); int (*sched_scan_stop)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*sw_scan_start)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *mac_addr); void (*sw_scan_complete)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*get_stats)(struct ieee80211_hw *hw, struct ieee80211_low_level_stats *stats); void (*get_key_seq)(struct ieee80211_hw *hw, struct ieee80211_key_conf *key, struct ieee80211_key_seq *seq); int (*set_frag_threshold)(struct ieee80211_hw *hw, u32 value); int (*set_rts_threshold)(struct ieee80211_hw *hw, u32 value); int (*sta_add)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); int (*sta_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); #ifdef CONFIG_MAC80211_DEBUGFS void (*vif_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*link_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct dentry *dir); void (*sta_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct dentry *dir); void (*link_sta_add_debugfs)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_link_sta *link_sta, struct dentry *dir); #endif void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd, struct ieee80211_sta *sta); int (*sta_set_txpwr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); int (*sta_state)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum ieee80211_sta_state old_state, enum ieee80211_sta_state new_state); void (*sta_pre_rcu_remove)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*sta_rc_update)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u32 changed); void (*sta_rate_tbl_update)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*sta_statistics)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct station_info *sinfo); int (*conf_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id, u16 ac, const struct ieee80211_tx_queue_params *params); u64 (*get_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*set_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 tsf); void (*offset_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, s64 offset); void (*reset_tsf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*tx_last_beacon)(struct ieee80211_hw *hw); /** * @ampdu_action: * Perform a certain A-MPDU action. * The RA/TID combination determines the destination and TID we want * the ampdu action to be performed for. The action is defined through * ieee80211_ampdu_mlme_action. * When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver * may neither send aggregates containing more subframes than @buf_size * nor send aggregates in a way that lost frames would exceed the * buffer size. If just limiting the aggregate size, this would be * possible with a buf_size of 8: * * - ``TX: 1.....7`` * - ``RX: 2....7`` (lost frame #1) * - ``TX: 8..1...`` * * which is invalid since #1 was now re-transmitted well past the * buffer size of 8. Correct ways to retransmit #1 would be: * * - ``TX: 1 or`` * - ``TX: 18 or`` * - ``TX: 81`` * * Even ``189`` would be wrong since 1 could be lost again. * * Returns a negative error code on failure. The driver may return * %IEEE80211_AMPDU_TX_START_IMMEDIATE for %IEEE80211_AMPDU_TX_START * if the session can start immediately. * * The callback can sleep. */ int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); void (*set_coverage_class)(struct ieee80211_hw *hw, s16 coverage_class); #ifdef CONFIG_NL80211_TESTMODE int (*testmode_cmd)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void *data, int len); int (*testmode_dump)(struct ieee80211_hw *hw, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len); #endif void (*flush)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 queues, bool drop); void (*flush_sta)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); int (*set_antenna)(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant); int (*get_antenna)(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant); int (*remain_on_channel)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel *chan, int duration, enum ieee80211_roc_type type); int (*cancel_remain_on_channel)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx); void (*get_ringparam)(struct ieee80211_hw *hw, u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max); bool (*tx_frames_pending)(struct ieee80211_hw *hw); int (*set_bitrate_mask)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct cfg80211_bitrate_mask *mask); void (*event_callback)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct ieee80211_event *event); void (*allow_buffered_frames)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u16 tids, int num_frames, enum ieee80211_frame_release_type reason, bool more_data); void (*release_buffered_frames)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u16 tids, int num_frames, enum ieee80211_frame_release_type reason, bool more_data); int (*get_et_sset_count)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int sset); void (*get_et_stats)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ethtool_stats *stats, u64 *data); void (*get_et_strings)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 sset, u8 *data); void (*mgd_prepare_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_prep_tx_info *info); void (*mgd_complete_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_prep_tx_info *info); void (*mgd_protect_tdls_discover)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id); int (*add_chanctx)(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); void (*remove_chanctx)(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); void (*change_chanctx)(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx, u32 changed); int (*assign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx); void (*unassign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf, struct ieee80211_chanctx_conf *ctx); int (*switch_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif_chanctx_switch *vifs, int n_vifs, enum ieee80211_chanctx_switch_mode mode); void (*reconfig_complete)(struct ieee80211_hw *hw, enum ieee80211_reconfig_type reconfig_type); #if IS_ENABLED(CONFIG_IPV6) void (*ipv6_addr_change)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct inet6_dev *idev); #endif void (*channel_switch_beacon)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_chan_def *chandef); int (*pre_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); int (*post_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*abort_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*channel_switch_rx_beacon)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); u32 (*get_expected_throughput)(struct ieee80211_hw *hw, struct ieee80211_sta *sta); int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int *dbm); int (*tdls_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u8 oper_class, struct cfg80211_chan_def *chandef, struct sk_buff *tmpl_skb, u32 ch_sw_tm_ie); void (*tdls_cancel_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void (*tdls_recv_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_tdls_ch_sw_params *params); void (*wake_tx_queue)(struct ieee80211_hw *hw, struct ieee80211_txq *txq); void (*sync_rx_queues)(struct ieee80211_hw *hw); int (*start_nan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_nan_conf *conf); int (*stop_nan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); int (*nan_change_conf)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_nan_conf *conf, u32 changes); int (*add_nan_func)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct cfg80211_nan_func *nan_func); void (*del_nan_func)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u8 instance_id); bool (*can_aggregate_in_amsdu)(struct ieee80211_hw *hw, struct sk_buff *head, struct sk_buff *skb); int (*get_ftm_responder_stats)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_ftm_responder_stats *ftm_stats); int (*start_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request); void (*abort_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request); int (*set_tid_config)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct cfg80211_tid_config *tid_conf); int (*reset_tid_config)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u8 tids); void (*update_vif_offload)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*sta_set_4addr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enabled); int (*set_sar_specs)(struct ieee80211_hw *hw, const struct cfg80211_sar_specs *sar); void (*sta_set_decap_offload)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enabled); void (*add_twt_setup)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct ieee80211_twt_setup *twt); void (*twt_teardown_request)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u8 flowid); int (*set_radar_background)(struct ieee80211_hw *hw, struct cfg80211_chan_def *chandef); int (*net_fill_forward_path)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct net_device_path_ctx *ctx, struct net_device_path *path); bool (*can_activate_links)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 active_links); int (*change_vif_links)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 old_links, u16 new_links, struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]); int (*change_sta_links)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, u16 old_links, u16 new_links); int (*set_hw_timestamp)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_set_hw_timestamp *hwts); int (*net_setup_tc)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct net_device *dev, enum tc_setup_type type, void *type_data); enum ieee80211_neg_ttlm_res (*can_neg_ttlm)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_neg_ttlm *ttlm); }; /** * ieee80211_alloc_hw_nm - Allocate a new hardware device * * This must be called once for each hardware device. The returned pointer * must be used to refer to this device when calling other functions. * mac80211 allocates a private data area for the driver pointed to by * @priv in &struct ieee80211_hw, the size of this area is given as * @priv_data_len. * * @priv_data_len: length of private data * @ops: callbacks for this device * @requested_name: Requested name for this device. * NULL is valid value, and means use the default naming (phy%d) * * Return: A pointer to the new hardware device, or %NULL on error. */ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, const struct ieee80211_ops *ops, const char *requested_name); /** * ieee80211_alloc_hw - Allocate a new hardware device * * This must be called once for each hardware device. The returned pointer * must be used to refer to this device when calling other functions. * mac80211 allocates a private data area for the driver pointed to by * @priv in &struct ieee80211_hw, the size of this area is given as * @priv_data_len. * * @priv_data_len: length of private data * @ops: callbacks for this device * * Return: A pointer to the new hardware device, or %NULL on error. */ static inline struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, const struct ieee80211_ops *ops) { return ieee80211_alloc_hw_nm(priv_data_len, ops, NULL); } /** * ieee80211_register_hw - Register hardware device * * You must call this function before any other functions in * mac80211. Note that before a hardware can be registered, you * need to fill the contained wiphy's information. * * @hw: the device to register as returned by ieee80211_alloc_hw() * * Return: 0 on success. An error code otherwise. */ int ieee80211_register_hw(struct ieee80211_hw *hw); /** * struct ieee80211_tpt_blink - throughput blink description * @throughput: throughput in Kbit/sec * @blink_time: blink time in milliseconds * (full cycle, ie. one off + one on period) */ struct ieee80211_tpt_blink { int throughput; int blink_time; }; /** * enum ieee80211_tpt_led_trigger_flags - throughput trigger flags * @IEEE80211_TPT_LEDTRIG_FL_RADIO: enable blinking with radio * @IEEE80211_TPT_LEDTRIG_FL_WORK: enable blinking when working * @IEEE80211_TPT_LEDTRIG_FL_CONNECTED: enable blinking when at least one * interface is connected in some way, including being an AP */ enum ieee80211_tpt_led_trigger_flags { IEEE80211_TPT_LEDTRIG_FL_RADIO = BIT(0), IEEE80211_TPT_LEDTRIG_FL_WORK = BIT(1), IEEE80211_TPT_LEDTRIG_FL_CONNECTED = BIT(2), }; #ifdef CONFIG_MAC80211_LEDS const char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); const char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); const char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); const char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); const char * __ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, unsigned int flags, const struct ieee80211_tpt_blink *blink_table, unsigned int blink_table_len); #endif /** * ieee80211_get_tx_led_name - get name of TX LED * * mac80211 creates a transmit LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_tx_led_name(hw); #else return NULL; #endif } /** * ieee80211_get_rx_led_name - get name of RX LED * * mac80211 creates a receive LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_rx_led_name(hw); #else return NULL; #endif } /** * ieee80211_get_assoc_led_name - get name of association LED * * mac80211 creates a association LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_assoc_led_name(hw); #else return NULL; #endif } /** * ieee80211_get_radio_led_name - get name of radio LED * * mac80211 creates a radio change LED trigger for each wireless hardware * that can be used to drive LEDs if your driver registers a LED device. * This function returns the name (or %NULL if not configured for LEDs) * of the trigger so you can automatically link the LED device. * * @hw: the hardware to get the LED trigger name for * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ static inline const char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_radio_led_name(hw); #else return NULL; #endif } /** * ieee80211_create_tpt_led_trigger - create throughput LED trigger * @hw: the hardware to create the trigger for * @flags: trigger flags, see &enum ieee80211_tpt_led_trigger_flags * @blink_table: the blink table -- needs to be ordered by throughput * @blink_table_len: size of the blink table * * Return: %NULL (in case of error, or if no LED triggers are * configured) or the name of the new trigger. * * Note: This function must be called before ieee80211_register_hw(). */ static inline const char * ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, unsigned int flags, const struct ieee80211_tpt_blink *blink_table, unsigned int blink_table_len) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_create_tpt_led_trigger(hw, flags, blink_table, blink_table_len); #else return NULL; #endif } /** * ieee80211_unregister_hw - Unregister a hardware device * * This function instructs mac80211 to free allocated resources * and unregister netdevices from the networking subsystem. * * @hw: the hardware to unregister */ void ieee80211_unregister_hw(struct ieee80211_hw *hw); /** * ieee80211_free_hw - free hardware descriptor * * This function frees everything that was allocated, including the * private data for the driver. You must call ieee80211_unregister_hw() * before calling this function. * * @hw: the hardware to free */ void ieee80211_free_hw(struct ieee80211_hw *hw); /** * ieee80211_restart_hw - restart hardware completely * * Call this function when the hardware was restarted for some reason * (hardware error, ...) and the driver is unable to restore its state * by itself. mac80211 assumes that at this point the driver/hardware * is completely uninitialised and stopped, it starts the process by * calling the ->start() operation. The driver will need to reset all * internal state that it has prior to calling this function. * * @hw: the hardware to restart */ void ieee80211_restart_hw(struct ieee80211_hw *hw); /** * ieee80211_rx_list - receive frame and store processed skbs in a list * * Use this function to hand received frames to mac80211. The receive * buffer in @skb must start with an IEEE 802.11 header. In case of a * paged @skb is used, the driver is recommended to put the ieee80211 * header of the frame on the linear part of the @skb to avoid memory * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be * mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * This function must be called with BHs disabled and RCU read lock * * @hw: the hardware this frame came in on * @sta: the station the frame was received from, or %NULL * @skb: the buffer to receive, owned by mac80211 after this call * @list: the destination list */ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct sk_buff *skb, struct list_head *list); /** * ieee80211_rx_napi - receive frame from NAPI context * * Use this function to hand received frames to mac80211. The receive * buffer in @skb must start with an IEEE 802.11 header. In case of a * paged @skb is used, the driver is recommended to put the ieee80211 * header of the frame on the linear part of the @skb to avoid memory * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be * mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * This function must be called with BHs disabled. * * @hw: the hardware this frame came in on * @sta: the station the frame was received from, or %NULL * @skb: the buffer to receive, owned by mac80211 after this call * @napi: the NAPI context */ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct sk_buff *skb, struct napi_struct *napi); /** * ieee80211_rx - receive frame * * Use this function to hand received frames to mac80211. The receive * buffer in @skb must start with an IEEE 802.11 header. In case of a * paged @skb is used, the driver is recommended to put the ieee80211 * header of the frame on the linear part of the @skb to avoid memory * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to * this function, ieee80211_rx_ni() and ieee80211_rx_irqsafe() may not be * mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * In process context use instead ieee80211_rx_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call */ static inline void ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb) { ieee80211_rx_napi(hw, NULL, skb, NULL); } /** * ieee80211_rx_irqsafe - receive frame * * Like ieee80211_rx() but can be called in IRQ context * (internally defers to a tasklet.) * * Calls to this function, ieee80211_rx() or ieee80211_rx_ni() may not * be mixed for a single hardware.Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call */ void ieee80211_rx_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb); /** * ieee80211_rx_ni - receive frame (in process context) * * Like ieee80211_rx() but can be called in process context * (internally disables bottom halves). * * Calls to this function, ieee80211_rx() and ieee80211_rx_irqsafe() may * not be mixed for a single hardware. Must not run concurrently with * ieee80211_tx_status_skb() or ieee80211_tx_status_ni(). * * @hw: the hardware this frame came in on * @skb: the buffer to receive, owned by mac80211 after this call */ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, struct sk_buff *skb) { local_bh_disable(); ieee80211_rx(hw, skb); local_bh_enable(); } /** * ieee80211_sta_ps_transition - PS transition for connected sta * * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS * flag set, use this function to inform mac80211 about a connected station * entering/leaving PS mode. * * This function may not be called in IRQ context or with softirqs enabled. * * Calls to this function for a single hardware must be synchronized against * each other. * * @sta: currently connected sta * @start: start or stop PS * * Return: 0 on success. -EINVAL when the requested PS mode is already set. */ int ieee80211_sta_ps_transition(struct ieee80211_sta *sta, bool start); /** * ieee80211_sta_ps_transition_ni - PS transition for connected sta * (in process context) * * Like ieee80211_sta_ps_transition() but can be called in process context * (internally disables bottom halves). Concurrent call restriction still * applies. * * @sta: currently connected sta * @start: start or stop PS * * Return: Like ieee80211_sta_ps_transition(). */ static inline int ieee80211_sta_ps_transition_ni(struct ieee80211_sta *sta, bool start) { int ret; local_bh_disable(); ret = ieee80211_sta_ps_transition(sta, start); local_bh_enable(); return ret; } /** * ieee80211_sta_pspoll - PS-Poll frame received * @sta: currently connected station * * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS flag set, * use this function to inform mac80211 that a PS-Poll frame from a * connected station was received. * This must be used in conjunction with ieee80211_sta_ps_transition() * and possibly ieee80211_sta_uapsd_trigger(); calls to all three must * be serialized. */ void ieee80211_sta_pspoll(struct ieee80211_sta *sta); /** * ieee80211_sta_uapsd_trigger - (potential) U-APSD trigger frame received * @sta: currently connected station * @tid: TID of the received (potential) trigger frame * * When operating in AP mode with the %IEEE80211_HW_AP_LINK_PS flag set, * use this function to inform mac80211 that a (potential) trigger frame * from a connected station was received. * This must be used in conjunction with ieee80211_sta_ps_transition() * and possibly ieee80211_sta_pspoll(); calls to all three must be * serialized. * %IEEE80211_NUM_TIDS can be passed as the tid if the tid is unknown. * In this case, mac80211 will not check that this tid maps to an AC * that is trigger enabled and assume that the caller did the proper * checks. */ void ieee80211_sta_uapsd_trigger(struct ieee80211_sta *sta, u8 tid); /* * The TX headroom reserved by mac80211 for its own tx_status functions. * This is enough for the radiotap header. */ #define IEEE80211_TX_STATUS_HEADROOM ALIGN(14, 4) /** * ieee80211_sta_set_buffered - inform mac80211 about driver-buffered frames * @sta: &struct ieee80211_sta pointer for the sleeping station * @tid: the TID that has buffered frames * @buffered: indicates whether or not frames are buffered for this TID * * If a driver buffers frames for a powersave station instead of passing * them back to mac80211 for retransmission, the station may still need * to be told that there are buffered frames via the TIM bit. * * This function informs mac80211 whether or not there are frames that are * buffered in the driver for a given TID; mac80211 can then use this data * to set the TIM bit (NOTE: This may call back into the driver's set_tim * call! Beware of the locking!) * * If all frames are released to the station (due to PS-poll or uAPSD) * then the driver needs to inform mac80211 that there no longer are * frames buffered. However, when the station wakes up mac80211 assumes * that all buffered frames will be transmitted and clears this data, * drivers need to make sure they inform mac80211 about all buffered * frames on the sleep transition (sta_notify() with %STA_NOTIFY_SLEEP). * * Note that technically mac80211 only needs to know this per AC, not per * TID, but since driver buffering will inevitably happen per TID (since * it is related to aggregation) it is easier to make mac80211 map the * TID to the AC as required instead of keeping track in all drivers that * use this API. */ void ieee80211_sta_set_buffered(struct ieee80211_sta *sta, u8 tid, bool buffered); /** * ieee80211_get_tx_rates - get the selected transmit rates for a packet * * Call this function in a driver with per-packet rate selection support * to combine the rate info in the packet tx info with the most recent * rate selection table for the station entry. * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @sta: the receiver station to which this packet is sent. * @skb: the frame to be transmitted. * @dest: buffer for extracted rate/retry information * @max_rates: maximum number of rates to fetch */ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct sk_buff *skb, struct ieee80211_tx_rate *dest, int max_rates); /** * ieee80211_sta_set_expected_throughput - set the expected tpt for a station * * Call this function to notify mac80211 about a change in expected throughput * to a station. A driver for a device that does rate control in firmware can * call this function when the expected throughput estimate towards a station * changes. The information is used to tune the CoDel AQM applied to traffic * going towards that station (which can otherwise be too aggressive and cause * slow stations to starve). * * @pubsta: the station to set throughput for. * @thr: the current expected throughput in kbps. */ void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta, u32 thr); /** * ieee80211_tx_rate_update - transmit rate update callback * * Drivers should call this functions with a non-NULL pub sta * This function can be used in drivers that does not have provision * in updating the tx rate in data path. * * @hw: the hardware the frame was transmitted by * @pubsta: the station to update the tx rate for. * @info: tx status information */ void ieee80211_tx_rate_update(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, struct ieee80211_tx_info *info); /** * ieee80211_tx_status_skb - transmit status callback * * Call this function for all transmitted frames after they have been * transmitted. It is permissible to not call this function for * multicast frames but this can affect statistics. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls * to this function, ieee80211_tx_status_ni() and ieee80211_tx_status_irqsafe() * may not be mixed for a single hardware. Must not run concurrently with * ieee80211_rx() or ieee80211_rx_ni(). * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call */ void ieee80211_tx_status_skb(struct ieee80211_hw *hw, struct sk_buff *skb); /** * ieee80211_tx_status_ext - extended transmit status callback * * This function can be used as a replacement for ieee80211_tx_status_skb() * in drivers that may want to provide extra information that does not * fit into &struct ieee80211_tx_info. * * Calls to this function for a single hardware must be synchronized * against each other. Calls to this function, ieee80211_tx_status_ni() * and ieee80211_tx_status_irqsafe() may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @status: tx status information */ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_tx_status *status); /** * ieee80211_tx_status_noskb - transmit status callback without skb * * This function can be used as a replacement for ieee80211_tx_status_skb() * in drivers that cannot reliably map tx status information back to * specific skbs. * * Calls to this function for a single hardware must be synchronized * against each other. Calls to this function, ieee80211_tx_status_ni() * and ieee80211_tx_status_irqsafe() may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @sta: the receiver station to which this packet is sent * (NULL for multicast packets) * @info: tx status information */ static inline void ieee80211_tx_status_noskb(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct ieee80211_tx_info *info) { struct ieee80211_tx_status status = { .sta = sta, .info = info, }; ieee80211_tx_status_ext(hw, &status); } /** * ieee80211_tx_status_ni - transmit status callback (in process context) * * Like ieee80211_tx_status_skb() but can be called in process context. * * Calls to this function, ieee80211_tx_status_skb() and * ieee80211_tx_status_irqsafe() may not be mixed * for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call */ static inline void ieee80211_tx_status_ni(struct ieee80211_hw *hw, struct sk_buff *skb) { local_bh_disable(); ieee80211_tx_status_skb(hw, skb); local_bh_enable(); } /** * ieee80211_tx_status_irqsafe - IRQ-safe transmit status callback * * Like ieee80211_tx_status_skb() but can be called in IRQ context * (internally defers to a tasklet.) * * Calls to this function, ieee80211_tx_status_skb() and * ieee80211_tx_status_ni() may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call */ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb); /** * ieee80211_report_low_ack - report non-responding station * * When operating in AP-mode, call this function to report a non-responding * connected STA. * * @sta: the non-responding connected sta * @num_packets: number of packets sent to @sta without a response */ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets); #define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2 /** * struct ieee80211_mutable_offsets - mutable beacon offsets * @tim_offset: position of TIM element * @tim_length: size of TIM element * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets * to countdown counters. This array can contain zero values which * should be ignored. * @mbssid_off: position of the multiple bssid element */ struct ieee80211_mutable_offsets { u16 tim_offset; u16 tim_length; u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; u16 mbssid_off; }; /** * ieee80211_beacon_get_template - beacon template generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @offs: &struct ieee80211_mutable_offsets pointer to struct that will * receive the offsets that may be updated by the driver. * @link_id: the link id to which the beacon belongs (or 0 for an AP STA * that is not associated with AP MLD). * * If the driver implements beaconing modes, it must use this function to * obtain the beacon template. * * This function should be used if the beacon frames are generated by the * device, and then the driver must use the returned beacon as the template * The driver or the device are responsible to update the DTIM and, when * applicable, the CSA count. * * The driver is responsible for freeing the returned skb. * * Return: The beacon template. %NULL on error. */ struct sk_buff * ieee80211_beacon_get_template(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_mutable_offsets *offs, unsigned int link_id); /** * ieee80211_beacon_get_template_ema_index - EMA beacon template generation * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @offs: &struct ieee80211_mutable_offsets pointer to struct that will * receive the offsets that may be updated by the driver. * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP). * @ema_index: index of the beacon in the EMA set. * * This function follows the same rules as ieee80211_beacon_get_template() * but returns a beacon template which includes multiple BSSID element at the * requested index. * * Return: The beacon template. %NULL indicates the end of EMA templates. */ struct sk_buff * ieee80211_beacon_get_template_ema_index(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_mutable_offsets *offs, unsigned int link_id, u8 ema_index); /** * struct ieee80211_ema_beacons - List of EMA beacons * @cnt: count of EMA beacons. * * @bcn: array of EMA beacons. * @bcn.skb: the skb containing this specific beacon * @bcn.offs: &struct ieee80211_mutable_offsets pointer to struct that will * receive the offsets that may be updated by the driver. */ struct ieee80211_ema_beacons { u8 cnt; struct { struct sk_buff *skb; struct ieee80211_mutable_offsets offs; } bcn[]; }; /** * ieee80211_beacon_get_template_ema_list - EMA beacon template generation * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP) * * This function follows the same rules as ieee80211_beacon_get_template() * but allocates and returns a pointer to list of all beacon templates required * to cover all profiles in the multiple BSSID set. Each template includes only * one multiple BSSID element. * * Driver must call ieee80211_beacon_free_ema_list() to free the memory. * * Return: EMA beacon templates of type struct ieee80211_ema_beacons *. * %NULL on error. */ struct ieee80211_ema_beacons * ieee80211_beacon_get_template_ema_list(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id); /** * ieee80211_beacon_free_ema_list - free an EMA beacon template list * @ema_beacons: list of EMA beacons of type &struct ieee80211_ema_beacons pointers. * * This function will free a list previously acquired by calling * ieee80211_beacon_get_template_ema_list() */ void ieee80211_beacon_free_ema_list(struct ieee80211_ema_beacons *ema_beacons); /** * ieee80211_beacon_get_tim - beacon generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @tim_offset: pointer to variable that will receive the TIM IE offset. * Set to 0 if invalid (in non-AP modes). * @tim_length: pointer to variable that will receive the TIM IE length, * (including the ID and length bytes!). * Set to 0 if invalid (in non-AP modes). * @link_id: the link id to which the beacon belongs (or 0 for an AP STA * that is not associated with AP MLD). * * If the driver implements beaconing modes, it must use this function to * obtain the beacon frame. * * If the beacon frames are generated by the host system (i.e., not in * hardware/firmware), the driver uses this function to get each beacon * frame from mac80211 -- it is responsible for calling this function exactly * once before the beacon is needed (e.g. based on hardware interrupt). * * The driver is responsible for freeing the returned skb. * * Return: The beacon template. %NULL on error. */ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 *tim_offset, u16 *tim_length, unsigned int link_id); /** * ieee80211_beacon_get - beacon generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: the link id to which the beacon belongs (or 0 for an AP STA * that is not associated with AP MLD). * * See ieee80211_beacon_get_tim(). * * Return: See ieee80211_beacon_get_tim(). */ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, unsigned int link_id) { return ieee80211_beacon_get_tim(hw, vif, NULL, NULL, link_id); } /** * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: valid link_id during MLO or 0 for non-MLO * * The beacon counter should be updated after each beacon transmission. * This function is called implicitly when * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the * beacon frames are generated by the device, the driver should call this * function after each beacon transmission to sync mac80211's beacon countdown. * * Return: new countdown value */ u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif, unsigned int link_id); /** * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @counter: the new value for the counter * * The beacon countdown can be changed by the device, this API should be * used by the device driver to update csa counter in mac80211. * * It should never be used together with ieee80211_beacon_update_cntdwn(), * as it will cause a race condition around the counter value. */ void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter); /** * ieee80211_csa_finish - notify mac80211 about channel switch * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: valid link_id during MLO or 0 for non-MLO * * After a channel switch announcement was scheduled and the counter in this * announcement hits 1, this function must be called by the driver to * notify mac80211 that the channel can be changed. */ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id); /** * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1 * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: valid link_id during MLO or 0 for non-MLO * * Return: %true if the countdown reached 1, %false otherwise */ bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif, unsigned int link_id); /** * ieee80211_color_change_finish - notify mac80211 about color change * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: valid link_id during MLO or 0 for non-MLO * * After a color change announcement was scheduled and the counter in this * announcement hits 1, this function must be called by the driver to * notify mac80211 that the color can be changed */ void ieee80211_color_change_finish(struct ieee80211_vif *vif, u8 link_id); /** * ieee80211_proberesp_get - retrieve a Probe Response template * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * Creates a Probe Response template which can, for example, be uploaded to * hardware. The destination address should be set by the caller. * * Can only be called in AP mode. * * Return: The Probe Response template. %NULL on error. */ struct sk_buff *ieee80211_proberesp_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif); /** * ieee80211_pspoll_get - retrieve a PS Poll template * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * Creates a PS Poll a template which can, for example, uploaded to * hardware. The template must be updated after association so that correct * AID, BSSID and MAC address is used. * * Note: Caller (or hardware) is responsible for setting the * &IEEE80211_FCTL_PM bit. * * Return: The PS Poll template. %NULL on error. */ struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif); /** * ieee80211_nullfunc_get - retrieve a nullfunc template * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: If the vif is an MLD, get a frame with the link addresses * for the given link ID. For a link_id < 0 you get a frame with * MLD addresses, however useful that might be. * @qos_ok: QoS NDP is acceptable to the caller, this should be set * if at all possible * * Creates a Nullfunc template which can, for example, uploaded to * hardware. The template must be updated after association so that correct * BSSID and address is used. * * If @qos_ndp is set and the association is to an AP with QoS/WMM, the * returned packet will be QoS NDP. * * Note: Caller (or hardware) is responsible for setting the * &IEEE80211_FCTL_PM bit as well as Duration and Sequence Control fields. * * Return: The nullfunc template. %NULL on error. */ struct sk_buff *ieee80211_nullfunc_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int link_id, bool qos_ok); /** * ieee80211_probereq_get - retrieve a Probe Request template * @hw: pointer obtained from ieee80211_alloc_hw(). * @src_addr: source MAC address * @ssid: SSID buffer * @ssid_len: length of SSID * @tailroom: tailroom to reserve at end of SKB for IEs * * Creates a Probe Request template which can, for example, be uploaded to * hardware. * * Return: The Probe Request template. %NULL on error. */ struct sk_buff *ieee80211_probereq_get(struct ieee80211_hw *hw, const u8 *src_addr, const u8 *ssid, size_t ssid_len, size_t tailroom); /** * ieee80211_rts_get - RTS frame generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame: pointer to the frame that is going to be protected by the RTS. * @frame_len: the frame length (in octets). * @frame_txctl: &struct ieee80211_tx_info of the frame. * @rts: The buffer where to store the RTS frame. * * If the RTS frames are generated by the host system (i.e., not in * hardware/firmware), the low-level driver uses this function to receive * the next RTS frame from the 802.11 code. The low-level is responsible * for calling this function before and RTS frame is needed. */ void ieee80211_rts_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const void *frame, size_t frame_len, const struct ieee80211_tx_info *frame_txctl, struct ieee80211_rts *rts); /** * ieee80211_rts_duration - Get the duration field for an RTS frame * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame_len: the length of the frame that is going to be protected by the RTS. * @frame_txctl: &struct ieee80211_tx_info of the frame. * * If the RTS is generated in firmware, but the host system must provide * the duration field, the low-level driver uses this function to receive * the duration field value in little-endian byteorder. * * Return: The duration. */ __le16 ieee80211_rts_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, size_t frame_len, const struct ieee80211_tx_info *frame_txctl); /** * ieee80211_ctstoself_get - CTS-to-self frame generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame: pointer to the frame that is going to be protected by the CTS-to-self. * @frame_len: the frame length (in octets). * @frame_txctl: &struct ieee80211_tx_info of the frame. * @cts: The buffer where to store the CTS-to-self frame. * * If the CTS-to-self frames are generated by the host system (i.e., not in * hardware/firmware), the low-level driver uses this function to receive * the next CTS-to-self frame from the 802.11 code. The low-level is responsible * for calling this function before and CTS-to-self frame is needed. */ void ieee80211_ctstoself_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const void *frame, size_t frame_len, const struct ieee80211_tx_info *frame_txctl, struct ieee80211_cts *cts); /** * ieee80211_ctstoself_duration - Get the duration field for a CTS-to-self frame * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @frame_len: the length of the frame that is going to be protected by the CTS-to-self. * @frame_txctl: &struct ieee80211_tx_info of the frame. * * If the CTS-to-self is generated in firmware, but the host system must provide * the duration field, the low-level driver uses this function to receive * the duration field value in little-endian byteorder. * * Return: The duration. */ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, size_t frame_len, const struct ieee80211_tx_info *frame_txctl); /** * ieee80211_generic_frame_duration - Calculate the duration field for a frame * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @band: the band to calculate the frame duration on * @frame_len: the length of the frame. * @rate: the rate at which the frame is going to be transmitted. * * Calculate the duration field of some generic frame, given its * length and transmission rate (in 100kbps). * * Return: The duration. */ __le16 ieee80211_generic_frame_duration(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum nl80211_band band, size_t frame_len, struct ieee80211_rate *rate); /** * ieee80211_get_buffered_bc - accessing buffered broadcast and multicast frames * @hw: pointer as obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * Function for accessing buffered broadcast and multicast frames. If * hardware/firmware does not implement buffering of broadcast/multicast * frames when power saving is used, 802.11 code buffers them in the host * memory. The low-level driver uses this function to fetch next buffered * frame. In most cases, this is used when generating beacon frame. * * Return: A pointer to the next buffered skb or NULL if no more buffered * frames are available. * * Note: buffered frames are returned only after DTIM beacon frame was * generated with ieee80211_beacon_get() and the low-level driver must thus * call ieee80211_beacon_get() first. ieee80211_get_buffered_bc() returns * NULL if the previous generated beacon was not DTIM, so the low-level driver * does not need to check for DTIM beacons separately and should be able to * use common code for all beacons. */ struct sk_buff * ieee80211_get_buffered_bc(struct ieee80211_hw *hw, struct ieee80211_vif *vif); /** * ieee80211_get_tkip_p1k_iv - get a TKIP phase 1 key for IV32 * * This function returns the TKIP phase 1 key for the given IV32. * * @keyconf: the parameter passed with the set key * @iv32: IV32 to get the P1K for * @p1k: a buffer to which the key will be written, as 5 u16 values */ void ieee80211_get_tkip_p1k_iv(struct ieee80211_key_conf *keyconf, u32 iv32, u16 *p1k); /** * ieee80211_get_tkip_p1k - get a TKIP phase 1 key * * This function returns the TKIP phase 1 key for the IV32 taken * from the given packet. * * @keyconf: the parameter passed with the set key * @skb: the packet to take the IV32 value from that will be encrypted * with this P1K * @p1k: a buffer to which the key will be written, as 5 u16 values */ static inline void ieee80211_get_tkip_p1k(struct ieee80211_key_conf *keyconf, struct sk_buff *skb, u16 *p1k) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; const u8 *data = (u8 *)hdr + ieee80211_hdrlen(hdr->frame_control); u32 iv32 = get_unaligned_le32(&data[4]); ieee80211_get_tkip_p1k_iv(keyconf, iv32, p1k); } /** * ieee80211_get_tkip_rx_p1k - get a TKIP phase 1 key for RX * * This function returns the TKIP phase 1 key for the given IV32 * and transmitter address. * * @keyconf: the parameter passed with the set key * @ta: TA that will be used with the key * @iv32: IV32 to get the P1K for * @p1k: a buffer to which the key will be written, as 5 u16 values */ void ieee80211_get_tkip_rx_p1k(struct ieee80211_key_conf *keyconf, const u8 *ta, u32 iv32, u16 *p1k); /** * ieee80211_get_tkip_p2k - get a TKIP phase 2 key * * This function computes the TKIP RC4 key for the IV values * in the packet. * * @keyconf: the parameter passed with the set key * @skb: the packet to take the IV32/IV16 values from that will be * encrypted with this key * @p2k: a buffer to which the key will be written, 16 bytes */ void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf, struct sk_buff *skb, u8 *p2k); /** * ieee80211_tkip_add_iv - write TKIP IV and Ext. IV to pos * * @pos: start of crypto header * @keyconf: the parameter passed with the set key * @pn: PN to add * * Returns: pointer to the octet following IVs (i.e. beginning of * the packet payload) * * This function writes the tkip IV value to pos (which should * point to the crypto header) */ u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key_conf *keyconf, u64 pn); /** * ieee80211_get_key_rx_seq - get key RX sequence counter * * @keyconf: the parameter passed with the set key * @tid: The TID, or -1 for the management frame value (CCMP/GCMP only); * the value on TID 0 is also used for non-QoS frames. For * CMAC, only TID 0 is valid. * @seq: buffer to receive the sequence data * * This function allows a driver to retrieve the current RX IV/PNs * for the given key. It must not be called if IV checking is done * by the device and not by mac80211. * * Note that this function may only be called when no RX processing * can be done concurrently. */ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq); /** * ieee80211_set_key_rx_seq - set key RX sequence counter * * @keyconf: the parameter passed with the set key * @tid: The TID, or -1 for the management frame value (CCMP/GCMP only); * the value on TID 0 is also used for non-QoS frames. For * CMAC, only TID 0 is valid. * @seq: new sequence data * * This function allows a driver to set the current RX IV/PNs for the * given key. This is useful when resuming from WoWLAN sleep and GTK * rekey may have been done while suspended. It should not be called * if IV checking is done by the device and not by mac80211. * * Note that this function may only be called when no RX processing * can be done concurrently. */ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq); /** * ieee80211_remove_key - remove the given key * @keyconf: the parameter passed with the set key * * Context: Must be called with the wiphy mutex held. * * Remove the given key. If the key was uploaded to the hardware at the * time this function is called, it is not deleted in the hardware but * instead assumed to have been removed already. */ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); /** * ieee80211_gtk_rekey_add - add a GTK key from rekeying during WoWLAN * @vif: the virtual interface to add the key on * @keyconf: new key data * @link_id: the link id of the key or -1 for non-MLO * * When GTK rekeying was done while the system was suspended, (a) new * key(s) will be available. These will be needed by mac80211 for proper * RX processing, so this function allows setting them. * * Return: the newly allocated key structure, which will have * similar contents to the passed key configuration but point to * mac80211-owned memory. In case of errors, the function returns an * ERR_PTR(), use IS_ERR() etc. * * Note that this function assumes the key isn't added to hardware * acceleration, so no TX will be done with the key. Since it's a GTK * on managed (station) networks, this is true anyway. If the driver * calls this function from the resume callback and subsequently uses * the return code 1 to reconfigure the device, this key will be part * of the reconfiguration. * * Note that the driver should also call ieee80211_set_key_rx_seq() * for the new key for each TID to set up sequence counters properly. * * IMPORTANT: If this replaces a key that is present in the hardware, * then it will attempt to remove it during this call. In many cases * this isn't what you want, so call ieee80211_remove_key() first for * the key that's being replaced. */ struct ieee80211_key_conf * ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, struct ieee80211_key_conf *keyconf, int link_id); /** * ieee80211_gtk_rekey_notify - notify userspace supplicant of rekeying * @vif: virtual interface the rekeying was done on * @bssid: The BSSID of the AP, for checking association * @replay_ctr: the new replay counter after GTK rekeying * @gfp: allocation flags */ void ieee80211_gtk_rekey_notify(struct ieee80211_vif *vif, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp); /** * ieee80211_key_mic_failure - increment MIC failure counter for the key * * Note: this is really only safe if no other RX function is called * at the same time. * * @keyconf: the key in question */ void ieee80211_key_mic_failure(struct ieee80211_key_conf *keyconf); /** * ieee80211_key_replay - increment replay counter for the key * * Note: this is really only safe if no other RX function is called * at the same time. * * @keyconf: the key in question */ void ieee80211_key_replay(struct ieee80211_key_conf *keyconf); /** * ieee80211_wake_queue - wake specific queue * @hw: pointer as obtained from ieee80211_alloc_hw(). * @queue: queue number (counted from zero). * * Drivers must use this function instead of netif_wake_queue. */ void ieee80211_wake_queue(struct ieee80211_hw *hw, int queue); /** * ieee80211_stop_queue - stop specific queue * @hw: pointer as obtained from ieee80211_alloc_hw(). * @queue: queue number (counted from zero). * * Drivers must use this function instead of netif_stop_queue. */ void ieee80211_stop_queue(struct ieee80211_hw *hw, int queue); /** * ieee80211_queue_stopped - test status of the queue * @hw: pointer as obtained from ieee80211_alloc_hw(). * @queue: queue number (counted from zero). * * Drivers must use this function instead of netif_queue_stopped. * * Return: %true if the queue is stopped. %false otherwise. */ int ieee80211_queue_stopped(struct ieee80211_hw *hw, int queue); /** * ieee80211_stop_queues - stop all queues * @hw: pointer as obtained from ieee80211_alloc_hw(). * * Drivers must use this function instead of netif_tx_stop_all_queues. */ void ieee80211_stop_queues(struct ieee80211_hw *hw); /** * ieee80211_wake_queues - wake all queues * @hw: pointer as obtained from ieee80211_alloc_hw(). * * Drivers must use this function instead of netif_tx_wake_all_queues. */ void ieee80211_wake_queues(struct ieee80211_hw *hw); /** * ieee80211_scan_completed - completed hardware scan * * When hardware scan offload is used (i.e. the hw_scan() callback is * assigned) this function needs to be called by the driver to notify * mac80211 that the scan finished. This function can be called from * any context, including hardirq context. * * @hw: the hardware that finished the scan * @info: information about the completed scan */ void ieee80211_scan_completed(struct ieee80211_hw *hw, struct cfg80211_scan_info *info); /** * ieee80211_sched_scan_results - got results from scheduled scan * * When a scheduled scan is running, this function needs to be called by the * driver whenever there are new scan results available. * * @hw: the hardware that is performing scheduled scans */ void ieee80211_sched_scan_results(struct ieee80211_hw *hw); /** * ieee80211_sched_scan_stopped - inform that the scheduled scan has stopped * * When a scheduled scan is running, this function can be called by * the driver if it needs to stop the scan to perform another task. * Usual scenarios are drivers that cannot continue the scheduled scan * while associating, for instance. * * @hw: the hardware that is performing scheduled scans */ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw); /** * enum ieee80211_interface_iteration_flags - interface iteration flags * @IEEE80211_IFACE_ITER_NORMAL: Iterate over all interfaces that have * been added to the driver; However, note that during hardware * reconfiguration (after restart_hw) it will iterate over a new * interface and over all the existing interfaces even if they * haven't been re-added to the driver yet. * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all * interfaces, even if they haven't been re-added to the driver yet. * @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up). * @IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER: Skip any interfaces where SDATA * is not in the driver. This may fix crashes during firmware recovery * for instance. */ enum ieee80211_interface_iteration_flags { IEEE80211_IFACE_ITER_NORMAL = 0, IEEE80211_IFACE_ITER_RESUME_ALL = BIT(0), IEEE80211_IFACE_ITER_ACTIVE = BIT(1), IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER = BIT(2), }; /** * ieee80211_iterate_interfaces - iterate interfaces * * This function iterates over the interfaces associated with a given * hardware and calls the callback for them. This includes active as well as * inactive interfaces. This function allows the iterator function to sleep. * Will iterate over a new interface during add_interface(). * * @hw: the hardware struct of which the interfaces should be iterated over * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags * @iterator: the iterator function to call * @data: first argument of the iterator function */ void ieee80211_iterate_interfaces(struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data); /** * ieee80211_iterate_active_interfaces - iterate active interfaces * * This function iterates over the interfaces associated with a given * hardware that are currently active and calls the callback for them. * This function allows the iterator function to sleep, when the iterator * function is atomic @ieee80211_iterate_active_interfaces_atomic can * be used. * Does not iterate over a new interface during add_interface(). * * @hw: the hardware struct of which the interfaces should be iterated over * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags * @iterator: the iterator function to call * @data: first argument of the iterator function */ static inline void ieee80211_iterate_active_interfaces(struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data) { ieee80211_iterate_interfaces(hw, iter_flags | IEEE80211_IFACE_ITER_ACTIVE, iterator, data); } /** * ieee80211_iterate_active_interfaces_atomic - iterate active interfaces * * This function iterates over the interfaces associated with a given * hardware that are currently active and calls the callback for them. * This function requires the iterator callback function to be atomic, * if that is not desired, use @ieee80211_iterate_active_interfaces instead. * Does not iterate over a new interface during add_interface(). * * @hw: the hardware struct of which the interfaces should be iterated over * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags * @iterator: the iterator function to call, cannot sleep * @data: first argument of the iterator function */ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data); /** * ieee80211_iterate_active_interfaces_mtx - iterate active interfaces * * This function iterates over the interfaces associated with a given * hardware that are currently active and calls the callback for them. * This version can only be used while holding the wiphy mutex. * * @hw: the hardware struct of which the interfaces should be iterated over * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags * @iterator: the iterator function to call, cannot sleep * @data: first argument of the iterator function */ void ieee80211_iterate_active_interfaces_mtx(struct ieee80211_hw *hw, u32 iter_flags, void (*iterator)(void *data, u8 *mac, struct ieee80211_vif *vif), void *data); /** * ieee80211_iterate_stations_atomic - iterate stations * * This function iterates over all stations associated with a given * hardware that are currently uploaded to the driver and calls the callback * function for them. * This function requires the iterator callback function to be atomic, * * @hw: the hardware struct of which the interfaces should be iterated over * @iterator: the iterator function to call, cannot sleep * @data: first argument of the iterator function */ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, void (*iterator)(void *data, struct ieee80211_sta *sta), void *data); /** * ieee80211_queue_work - add work onto the mac80211 workqueue * * Drivers and mac80211 use this to add work onto the mac80211 workqueue. * This helper ensures drivers are not queueing work when they should not be. * * @hw: the hardware struct for the interface we are adding work for * @work: the work we want to add onto the mac80211 workqueue */ void ieee80211_queue_work(struct ieee80211_hw *hw, struct work_struct *work); /** * ieee80211_queue_delayed_work - add work onto the mac80211 workqueue * * Drivers and mac80211 use this to queue delayed work onto the mac80211 * workqueue. * * @hw: the hardware struct for the interface we are adding work for * @dwork: delayable work to queue onto the mac80211 workqueue * @delay: number of jiffies to wait before queueing */ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, struct delayed_work *dwork, unsigned long delay); /** * ieee80211_refresh_tx_agg_session_timer - Refresh a tx agg session timer. * @sta: the station for which to start a BA session * @tid: the TID to BA on. * * This function allows low level driver to refresh tx agg session timer * to maintain BA session, the session level will still be managed by the * mac80211. * * Note: must be called in an RCU critical section. */ void ieee80211_refresh_tx_agg_session_timer(struct ieee80211_sta *sta, u16 tid); /** * ieee80211_start_tx_ba_session - Start a tx Block Ack session. * @sta: the station for which to start a BA session * @tid: the TID to BA on. * @timeout: session timeout value (in TUs) * * Return: success if addBA request was sent, failure otherwise * * Although mac80211/low level driver/user space application can estimate * the need to start aggregation on a certain RA/TID, the session level * will be managed by the mac80211. */ int ieee80211_start_tx_ba_session(struct ieee80211_sta *sta, u16 tid, u16 timeout); /** * ieee80211_start_tx_ba_cb_irqsafe - low level driver ready to aggregate. * @vif: &struct ieee80211_vif pointer from the add_interface callback * @ra: receiver address of the BA session recipient. * @tid: the TID to BA on. * * This function must be called by low level driver once it has * finished with preparations for the BA session. It can be called * from any context. */ void ieee80211_start_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid); /** * ieee80211_stop_tx_ba_session - Stop a Block Ack session. * @sta: the station whose BA session to stop * @tid: the TID to stop BA. * * Return: negative error if the TID is invalid, or no aggregation active * * Although mac80211/low level driver/user space application can estimate * the need to stop aggregation on a certain RA/TID, the session level * will be managed by the mac80211. */ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *sta, u16 tid); /** * ieee80211_stop_tx_ba_cb_irqsafe - low level driver ready to stop aggregate. * @vif: &struct ieee80211_vif pointer from the add_interface callback * @ra: receiver address of the BA session recipient. * @tid: the desired TID to BA on. * * This function must be called by low level driver once it has * finished with preparations for the BA session tear down. It * can be called from any context. */ void ieee80211_stop_tx_ba_cb_irqsafe(struct ieee80211_vif *vif, const u8 *ra, u16 tid); /** * ieee80211_find_sta - find a station * * @vif: virtual interface to look for station on * @addr: station's address * * Return: The station, if found. %NULL otherwise. * * Note: This function must be called under RCU lock and the * resulting pointer is only valid under RCU lock as well. */ struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif, const u8 *addr); /** * ieee80211_find_sta_by_ifaddr - find a station on hardware * * @hw: pointer as obtained from ieee80211_alloc_hw() * @addr: remote station's address * @localaddr: local address (vif->sdata->vif.addr). Use NULL for 'any'. * * Return: The station, if found. %NULL otherwise. * * Note: This function must be called under RCU lock and the * resulting pointer is only valid under RCU lock as well. * * NOTE: You may pass NULL for localaddr, but then you will just get * the first STA that matches the remote address 'addr'. * We can have multiple STA associated with multiple * logical stations (e.g. consider a station connecting to another * BSSID on the same AP hardware without disconnecting first). * In this case, the result of this method with localaddr NULL * is not reliable. * * DO NOT USE THIS FUNCTION with localaddr NULL if at all possible. */ struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, const u8 *addr, const u8 *localaddr); /** * ieee80211_find_sta_by_link_addrs - find STA by link addresses * @hw: pointer as obtained from ieee80211_alloc_hw() * @addr: remote station's link address * @localaddr: local link address, use %NULL for any (but avoid that) * @link_id: pointer to obtain the link ID if the STA is found, * may be %NULL if the link ID is not needed * * Obtain the STA by link address, must use RCU protection. * * Return: pointer to STA if found, otherwise %NULL. */ struct ieee80211_sta * ieee80211_find_sta_by_link_addrs(struct ieee80211_hw *hw, const u8 *addr, const u8 *localaddr, unsigned int *link_id); /** * ieee80211_sta_block_awake - block station from waking up * @hw: the hardware * @pubsta: the station * @block: whether to block or unblock * * Some devices require that all frames that are on the queues * for a specific station that went to sleep are flushed before * a poll response or frames after the station woke up can be * delivered to that it. Note that such frames must be rejected * by the driver as filtered, with the appropriate status flag. * * This function allows implementing this mode in a race-free * manner. * * To do this, a driver must keep track of the number of frames * still enqueued for a specific station. If this number is not * zero when the station goes to sleep, the driver must call * this function to force mac80211 to consider the station to * be asleep regardless of the station's actual state. Once the * number of outstanding frames reaches zero, the driver must * call this function again to unblock the station. That will * cause mac80211 to be able to send ps-poll responses, and if * the station queried in the meantime then frames will also * be sent out as a result of this. Additionally, the driver * will be notified that the station woke up some time after * it is unblocked, regardless of whether the station actually * woke up while blocked or not. */ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, bool block); /** * ieee80211_sta_eosp - notify mac80211 about end of SP * @pubsta: the station * * When a device transmits frames in a way that it can't tell * mac80211 in the TX status about the EOSP, it must clear the * %IEEE80211_TX_STATUS_EOSP bit and call this function instead. * This applies for PS-Poll as well as uAPSD. * * Note that just like with _tx_status() and _rx() drivers must * not mix calls to irqsafe/non-irqsafe versions, this function * must not be mixed with those either. Use the all irqsafe, or * all non-irqsafe, don't mix! * * NB: the _irqsafe version of this function doesn't exist, no * driver needs it right now. Don't call this function if * you'd need the _irqsafe version, look at the git history * and restore the _irqsafe version! */ void ieee80211_sta_eosp(struct ieee80211_sta *pubsta); /** * ieee80211_send_eosp_nullfunc - ask mac80211 to send NDP with EOSP * @pubsta: the station * @tid: the tid of the NDP * * Sometimes the device understands that it needs to close * the Service Period unexpectedly. This can happen when * sending frames that are filling holes in the BA window. * In this case, the device can ask mac80211 to send a * Nullfunc frame with EOSP set. When that happens, the * driver must have called ieee80211_sta_set_buffered() to * let mac80211 know that there are no buffered frames any * more, otherwise mac80211 will get the more_data bit wrong. * The low level driver must have made sure that the frame * will be sent despite the station being in power-save. * Mac80211 won't call allow_buffered_frames(). * Note that calling this function, doesn't exempt the driver * from closing the EOSP properly, it will still have to call * ieee80211_sta_eosp when the NDP is sent. */ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); /** * ieee80211_sta_recalc_aggregates - recalculate aggregate data after a change * @pubsta: the station * * Call this function after changing a per-link aggregate data as referenced in * &struct ieee80211_sta_aggregates by accessing the agg field of * &struct ieee80211_link_sta. * * With non MLO the data in deflink will be referenced directly. In that case * there is no need to call this function. */ void ieee80211_sta_recalc_aggregates(struct ieee80211_sta *pubsta); /** * ieee80211_sta_register_airtime - register airtime usage for a sta/tid * * Register airtime usage for a given sta on a given tid. The driver must call * this function to notify mac80211 that a station used a certain amount of * airtime. This information will be used by the TXQ scheduler to schedule * stations in a way that ensures airtime fairness. * * The reported airtime should as a minimum include all time that is spent * transmitting to the remote station, including overhead and padding, but not * including time spent waiting for a TXOP. If the time is not reported by the * hardware it can in some cases be calculated from the rate and known frame * composition. When possible, the time should include any failed transmission * attempts. * * The driver can either call this function synchronously for every packet or * aggregate, or asynchronously as airtime usage information becomes available. * TX and RX airtime can be reported together, or separately by setting one of * them to 0. * * @pubsta: the station * @tid: the TID to register airtime for * @tx_airtime: airtime used during TX (in usec) * @rx_airtime: airtime used during RX (in usec) */ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, u32 tx_airtime, u32 rx_airtime); /** * ieee80211_txq_airtime_check - check if a txq can send frame to device * * @hw: pointer obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface * * Return: %true if the AQL's airtime limit has not been reached and the txq can * continue to send more packets to the device. Otherwise return %false. */ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** * ieee80211_iter_keys - iterate keys programmed into the device * @hw: pointer obtained from ieee80211_alloc_hw() * @vif: virtual interface to iterate, may be %NULL for all * @iter: iterator function that will be called for each key * @iter_data: custom data to pass to the iterator function * * Context: Must be called with wiphy mutex held; can sleep. * * This function can be used to iterate all the keys known to * mac80211, even those that weren't previously programmed into * the device. This is intended for use in WoWLAN if the device * needs reprogramming of the keys during suspend. * * The order in which the keys are iterated matches the order * in which they were originally installed and handed to the * set_key callback. */ void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data); /** * ieee80211_iter_keys_rcu - iterate keys programmed into the device * @hw: pointer obtained from ieee80211_alloc_hw() * @vif: virtual interface to iterate, may be %NULL for all * @iter: iterator function that will be called for each key * @iter_data: custom data to pass to the iterator function * * This function can be used to iterate all the keys known to * mac80211, even those that weren't previously programmed into * the device. Note that due to locking reasons, keys of station * in removal process will be skipped. * * This function requires being called in an RCU critical section, * and thus iter must be atomic. */ void ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key, void *data), void *iter_data); /** * ieee80211_iter_chan_contexts_atomic - iterate channel contexts * @hw: pointer obtained from ieee80211_alloc_hw(). * @iter: iterator function * @iter_data: data passed to iterator function * * Iterate all active channel contexts. This function is atomic and * doesn't acquire any locks internally that might be held in other * places while calling into the driver. * * The iterator will not find a context that's being added (during * the driver callback to add it) but will find it while it's being * removed. * * Note that during hardware restart, all contexts that existed * before the restart are considered already present so will be * found while iterating, whether they've been re-added already * or not. */ void ieee80211_iter_chan_contexts_atomic( struct ieee80211_hw *hw, void (*iter)(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *chanctx_conf, void *data), void *iter_data); /** * ieee80211_ap_probereq_get - retrieve a Probe Request template * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * Creates a Probe Request template which can, for example, be uploaded to * hardware. The template is filled with bssid, ssid and supported rate * information. This function must only be called from within the * .bss_info_changed callback function and only in managed mode. The function * is only useful when the interface is associated, otherwise it will return * %NULL. * * Return: The Probe Request template. %NULL on error. */ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif); /** * ieee80211_beacon_loss - inform hardware does not receive beacons * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * When beacon filtering is enabled with %IEEE80211_VIF_BEACON_FILTER and * %IEEE80211_CONF_PS is set, the driver needs to inform whenever the * hardware is not receiving beacons with this function. */ void ieee80211_beacon_loss(struct ieee80211_vif *vif); /** * ieee80211_connection_loss - inform hardware has lost connection to the AP * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * When beacon filtering is enabled with %IEEE80211_VIF_BEACON_FILTER, and * %IEEE80211_CONF_PS and %IEEE80211_HW_CONNECTION_MONITOR are set, the driver * needs to inform if the connection to the AP has been lost. * The function may also be called if the connection needs to be terminated * for some other reason, even if %IEEE80211_HW_CONNECTION_MONITOR isn't set. * * This function will cause immediate change to disassociated state, * without connection recovery attempts. */ void ieee80211_connection_loss(struct ieee80211_vif *vif); /** * ieee80211_disconnect - request disconnection * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @reconnect: immediate reconnect is desired * * Request disconnection from the current network and, if enabled, send a * hint to the higher layers that immediate reconnect is desired. */ void ieee80211_disconnect(struct ieee80211_vif *vif, bool reconnect); /** * ieee80211_resume_disconnect - disconnect from AP after resume * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * Instructs mac80211 to disconnect from the AP after resume. * Drivers can use this after WoWLAN if they know that the * connection cannot be kept up, for example because keys were * used while the device was asleep but the replay counters or * similar cannot be retrieved from the device during resume. * * Note that due to implementation issues, if the driver uses * the reconfiguration functionality during resume the interface * will still be added as associated first during resume and then * disconnect normally later. * * This function can only be called from the resume callback and * the driver must not be holding any of its own locks while it * calls this function, or at least not any locks it needs in the * key configuration paths (if it supports HW crypto). */ void ieee80211_resume_disconnect(struct ieee80211_vif *vif); /** * ieee80211_hw_restart_disconnect - disconnect from AP after * hardware restart * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * Instructs mac80211 to disconnect from the AP after * hardware restart. */ void ieee80211_hw_restart_disconnect(struct ieee80211_vif *vif); /** * ieee80211_cqm_rssi_notify - inform a configured connection quality monitoring * rssi threshold triggered * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @rssi_event: the RSSI trigger event type * @rssi_level: new RSSI level value or 0 if not available * @gfp: context flags * * When the %IEEE80211_VIF_SUPPORTS_CQM_RSSI is set, and a connection quality * monitoring is configured with an rssi threshold, the driver will inform * whenever the rssi level reaches the threshold. */ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, enum nl80211_cqm_rssi_threshold_event rssi_event, s32 rssi_level, gfp_t gfp); /** * ieee80211_cqm_beacon_loss_notify - inform CQM of beacon loss * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @gfp: context flags */ void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp); /** * ieee80211_radar_detected - inform that a radar was detected * * @hw: pointer as obtained from ieee80211_alloc_hw() */ void ieee80211_radar_detected(struct ieee80211_hw *hw); /** * ieee80211_chswitch_done - Complete channel switch process * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @success: make the channel switch successful or not * @link_id: the link_id on which the switch was done. Ignored if success is * false. * * Complete the channel switch post-process: set the new operational channel * and wake up the suspended queues. */ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, unsigned int link_id); /** * ieee80211_channel_switch_disconnect - disconnect due to channel switch error * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @block_tx: if %true, do not send deauth frame. * * Instruct mac80211 to disconnect due to a channel switch error. The channel * switch can request to block the tx and so, we need to make sure we do not send * a deauth frame in this case. */ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_tx); /** * ieee80211_request_smps - request SM PS transition * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @link_id: link ID for MLO, or 0 * @smps_mode: new SM PS mode * * This allows the driver to request an SM PS transition in managed * mode. This is useful when the driver has more information than * the stack about possible interference, for example by bluetooth. */ void ieee80211_request_smps(struct ieee80211_vif *vif, unsigned int link_id, enum ieee80211_smps_mode smps_mode); /** * ieee80211_ready_on_channel - notification of remain-on-channel start * @hw: pointer as obtained from ieee80211_alloc_hw() */ void ieee80211_ready_on_channel(struct ieee80211_hw *hw); /** * ieee80211_remain_on_channel_expired - remain_on_channel duration expired * @hw: pointer as obtained from ieee80211_alloc_hw() */ void ieee80211_remain_on_channel_expired(struct ieee80211_hw *hw); /** * ieee80211_stop_rx_ba_session - callback to stop existing BA sessions * * in order not to harm the system performance and user experience, the device * may request not to allow any rx ba session and tear down existing rx ba * sessions based on system constraints such as periodic BT activity that needs * to limit wlan activity (eg.sco or a2dp)." * in such cases, the intention is to limit the duration of the rx ppdu and * therefore prevent the peer device to use a-mpdu aggregation. * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @ba_rx_bitmap: Bit map of open rx ba per tid * @addr: & to bssid mac address */ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, const u8 *addr); /** * ieee80211_mark_rx_ba_filtered_frames - move RX BA window and mark filtered * @pubsta: station struct * @tid: the session's TID * @ssn: starting sequence number of the bitmap, all frames before this are * assumed to be out of the window after the call * @filtered: bitmap of filtered frames, BIT(0) is the @ssn entry etc. * @received_mpdus: number of received mpdus in firmware * * This function moves the BA window and releases all frames before @ssn, and * marks frames marked in the bitmap as having been filtered. Afterwards, it * checks if any frames in the window starting from @ssn can now be released * (in case they were only waiting for frames that were filtered.) * (Only work correctly if @max_rx_aggregation_subframes <= 64 frames) */ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, u16 ssn, u64 filtered, u16 received_mpdus); /** * ieee80211_send_bar - send a BlockAckReq frame * * can be used to flush pending frames from the peer's aggregation reorder * buffer. * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @ra: the peer's destination address * @tid: the TID of the aggregation session * @ssn: the new starting sequence number for the receiver */ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn); /** * ieee80211_manage_rx_ba_offl - helper to queue an RX BA work * @vif: &struct ieee80211_vif pointer from the add_interface callback * @addr: station mac address * @tid: the rx tid */ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, const u8 *addr, unsigned int tid); /** * ieee80211_start_rx_ba_session_offl - start a Rx BA session * * Some device drivers may offload part of the Rx aggregation flow including * AddBa/DelBa negotiation but may otherwise be incapable of full Rx * reordering. * * Create structures responsible for reordering so device drivers may call here * when they complete AddBa negotiation. * * @vif: &struct ieee80211_vif pointer from the add_interface callback * @addr: station mac address * @tid: the rx tid */ static inline void ieee80211_start_rx_ba_session_offl(struct ieee80211_vif *vif, const u8 *addr, u16 tid) { if (WARN_ON(tid >= IEEE80211_NUM_TIDS)) return; ieee80211_manage_rx_ba_offl(vif, addr, tid); } /** * ieee80211_stop_rx_ba_session_offl - stop a Rx BA session * * Some device drivers may offload part of the Rx aggregation flow including * AddBa/DelBa negotiation but may otherwise be incapable of full Rx * reordering. * * Destroy structures responsible for reordering so device drivers may call here * when they complete DelBa negotiation. * * @vif: &struct ieee80211_vif pointer from the add_interface callback * @addr: station mac address * @tid: the rx tid */ static inline void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif, const u8 *addr, u16 tid) { if (WARN_ON(tid >= IEEE80211_NUM_TIDS)) return; ieee80211_manage_rx_ba_offl(vif, addr, tid + IEEE80211_NUM_TIDS); } /** * ieee80211_rx_ba_timer_expired - stop a Rx BA session due to timeout * * Some device drivers do not offload AddBa/DelBa negotiation, but handle rx * buffer reording internally, and therefore also handle the session timer. * * Trigger the timeout flow, which sends a DelBa. * * @vif: &struct ieee80211_vif pointer from the add_interface callback * @addr: station mac address * @tid: the rx tid */ void ieee80211_rx_ba_timer_expired(struct ieee80211_vif *vif, const u8 *addr, unsigned int tid); /* Rate control API */ /** * struct ieee80211_tx_rate_control - rate control information for/from RC algo * * @hw: The hardware the algorithm is invoked for. * @sband: The band this frame is being transmitted on. * @bss_conf: the current BSS configuration * @skb: the skb that will be transmitted, the control information in it needs * to be filled in * @reported_rate: The rate control algorithm can fill this in to indicate * which rate should be reported to userspace as the current rate and * used for rate calculations in the mesh network. * @rts: whether RTS will be used for this frame because it is longer than the * RTS threshold * @short_preamble: whether mac80211 will request short-preamble transmission * if the selected rate supports it * @rate_idx_mask: user-requested (legacy) rate mask * @rate_idx_mcs_mask: user-requested MCS rate mask (NULL if not in use) * @bss: whether this frame is sent out in AP or IBSS mode */ struct ieee80211_tx_rate_control { struct ieee80211_hw *hw; struct ieee80211_supported_band *sband; struct ieee80211_bss_conf *bss_conf; struct sk_buff *skb; struct ieee80211_tx_rate reported_rate; bool rts, short_preamble; u32 rate_idx_mask; u8 *rate_idx_mcs_mask; bool bss; }; /** * enum rate_control_capabilities - rate control capabilities */ enum rate_control_capabilities { /** * @RATE_CTRL_CAPA_VHT_EXT_NSS_BW: * Support for extended NSS BW support (dot11VHTExtendedNSSCapable) * Note that this is only looked at if the minimum number of chains * that the AP uses is < the number of TX chains the hardware has, * otherwise the NSS difference doesn't bother us. */ RATE_CTRL_CAPA_VHT_EXT_NSS_BW = BIT(0), /** * @RATE_CTRL_CAPA_AMPDU_TRIGGER: * mac80211 should start A-MPDU sessions on tx */ RATE_CTRL_CAPA_AMPDU_TRIGGER = BIT(1), }; struct rate_control_ops { unsigned long capa; const char *name; void *(*alloc)(struct ieee80211_hw *hw); void (*add_debugfs)(struct ieee80211_hw *hw, void *priv, struct dentry *debugfsdir); void (*free)(void *priv); void *(*alloc_sta)(void *priv, struct ieee80211_sta *sta, gfp_t gfp); void (*rate_init)(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta); void (*rate_update)(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta, u32 changed); void (*free_sta)(void *priv, struct ieee80211_sta *sta, void *priv_sta); void (*tx_status_ext)(void *priv, struct ieee80211_supported_band *sband, void *priv_sta, struct ieee80211_tx_status *st); void (*tx_status)(void *priv, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, void *priv_sta, struct sk_buff *skb); void (*get_rate)(void *priv, struct ieee80211_sta *sta, void *priv_sta, struct ieee80211_tx_rate_control *txrc); void (*add_sta_debugfs)(void *priv, void *priv_sta, struct dentry *dir); u32 (*get_expected_throughput)(void *priv_sta); }; static inline int rate_supported(struct ieee80211_sta *sta, enum nl80211_band band, int index) { return (sta == NULL || sta->deflink.supp_rates[band] & BIT(index)); } static inline s8 rate_lowest_index(struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) { int i; for (i = 0; i < sband->n_bitrates; i++) if (rate_supported(sta, sband->band, i)) return i; /* warn when we cannot find a rate. */ WARN_ON_ONCE(1); /* and return 0 (the lowest index) */ return 0; } static inline bool rate_usable_index_exists(struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) { unsigned int i; for (i = 0; i < sband->n_bitrates; i++) if (rate_supported(sta, sband->band, i)) return true; return false; } /** * rate_control_set_rates - pass the sta rate selection to mac80211/driver * * When not doing a rate control probe to test rates, rate control should pass * its rate selection to mac80211. If the driver supports receiving a station * rate table, it will use it to ensure that frames are always sent based on * the most recent rate control module decision. * * @hw: pointer as obtained from ieee80211_alloc_hw() * @pubsta: &struct ieee80211_sta pointer to the target destination. * @rates: new tx rate set to be used for this station. * * Return: 0 on success. An error code otherwise. */ int rate_control_set_rates(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, struct ieee80211_sta_rates *rates); int ieee80211_rate_control_register(const struct rate_control_ops *ops); void ieee80211_rate_control_unregister(const struct rate_control_ops *ops); static inline bool conf_is_ht20(struct ieee80211_conf *conf) { return conf->chandef.width == NL80211_CHAN_WIDTH_20; } static inline bool conf_is_ht40_minus(struct ieee80211_conf *conf) { return conf->chandef.width == NL80211_CHAN_WIDTH_40 && conf->chandef.center_freq1 < conf->chandef.chan->center_freq; } static inline bool conf_is_ht40_plus(struct ieee80211_conf *conf) { return conf->chandef.width == NL80211_CHAN_WIDTH_40 && conf->chandef.center_freq1 > conf->chandef.chan->center_freq; } static inline bool conf_is_ht40(struct ieee80211_conf *conf) { return conf->chandef.width == NL80211_CHAN_WIDTH_40; } static inline bool conf_is_ht(struct ieee80211_conf *conf) { return (conf->chandef.width != NL80211_CHAN_WIDTH_5) && (conf->chandef.width != NL80211_CHAN_WIDTH_10) && (conf->chandef.width != NL80211_CHAN_WIDTH_20_NOHT); } static inline enum nl80211_iftype ieee80211_iftype_p2p(enum nl80211_iftype type, bool p2p) { if (p2p) { switch (type) { case NL80211_IFTYPE_STATION: return NL80211_IFTYPE_P2P_CLIENT; case NL80211_IFTYPE_AP: return NL80211_IFTYPE_P2P_GO; default: break; } } return type; } static inline enum nl80211_iftype ieee80211_vif_type_p2p(struct ieee80211_vif *vif) { return ieee80211_iftype_p2p(vif->type, vif->p2p); } /** * ieee80211_get_he_iftype_cap_vif - return HE capabilities for sband/vif * @sband: the sband to search for the iftype on * @vif: the vif to get the iftype from * * Return: pointer to the struct ieee80211_sta_he_cap, or %NULL is none found */ static inline const struct ieee80211_sta_he_cap * ieee80211_get_he_iftype_cap_vif(const struct ieee80211_supported_band *sband, struct ieee80211_vif *vif) { return ieee80211_get_he_iftype_cap(sband, ieee80211_vif_type_p2p(vif)); } /** * ieee80211_get_he_6ghz_capa_vif - return HE 6 GHz capabilities * @sband: the sband to search for the STA on * @vif: the vif to get the iftype from * * Return: the 6GHz capabilities */ static inline __le16 ieee80211_get_he_6ghz_capa_vif(const struct ieee80211_supported_band *sband, struct ieee80211_vif *vif) { return ieee80211_get_he_6ghz_capa(sband, ieee80211_vif_type_p2p(vif)); } /** * ieee80211_get_eht_iftype_cap_vif - return ETH capabilities for sband/vif * @sband: the sband to search for the iftype on * @vif: the vif to get the iftype from * * Return: pointer to the struct ieee80211_sta_eht_cap, or %NULL is none found */ static inline const struct ieee80211_sta_eht_cap * ieee80211_get_eht_iftype_cap_vif(const struct ieee80211_supported_band *sband, struct ieee80211_vif *vif) { return ieee80211_get_eht_iftype_cap(sband, ieee80211_vif_type_p2p(vif)); } /** * ieee80211_update_mu_groups - set the VHT MU-MIMO groud data * * @vif: the specified virtual interface * @link_id: the link ID for MLO, otherwise 0 * @membership: 64 bits array - a bit is set if station is member of the group * @position: 2 bits per group id indicating the position in the group * * Note: This function assumes that the given vif is valid and the position and * membership data is of the correct size and are in the same byte order as the * matching GroupId management frame. * Calls to this function need to be serialized with RX path. */ void ieee80211_update_mu_groups(struct ieee80211_vif *vif, unsigned int link_id, const u8 *membership, const u8 *position); void ieee80211_enable_rssi_reports(struct ieee80211_vif *vif, int rssi_min_thold, int rssi_max_thold); void ieee80211_disable_rssi_reports(struct ieee80211_vif *vif); /** * ieee80211_ave_rssi - report the average RSSI for the specified interface * * @vif: the specified virtual interface * * Note: This function assumes that the given vif is valid. * * Return: The average RSSI value for the requested interface, or 0 if not * applicable. */ int ieee80211_ave_rssi(struct ieee80211_vif *vif); /** * ieee80211_report_wowlan_wakeup - report WoWLAN wakeup * @vif: virtual interface * @wakeup: wakeup reason(s) * @gfp: allocation flags * * See cfg80211_report_wowlan_wakeup(). */ void ieee80211_report_wowlan_wakeup(struct ieee80211_vif *vif, struct cfg80211_wowlan_wakeup *wakeup, gfp_t gfp); /** * ieee80211_tx_prepare_skb - prepare an 802.11 skb for transmission * @hw: pointer as obtained from ieee80211_alloc_hw() * @vif: virtual interface * @skb: frame to be sent from within the driver * @band: the band to transmit on * @sta: optional pointer to get the station to send the frame to * * Return: %true if the skb was prepared, %false otherwise * * Note: must be called under RCU lock */ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct sk_buff *skb, int band, struct ieee80211_sta **sta); /** * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header * of injected frames. * * To accurately parse and take into account rate and retransmission fields, * you must initialize the chandef field in the ieee80211_tx_info structure * of the skb before calling this function. * * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device * * Return: %true if the radiotap header was parsed, %false otherwise */ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev); /** * struct ieee80211_noa_data - holds temporary data for tracking P2P NoA state * * @next_tsf: TSF timestamp of the next absent state change * @has_next_tsf: next absent state change event pending * * @absent: descriptor bitmask, set if GO is currently absent * * private: * * @count: count fields from the NoA descriptors * @desc: adjusted data from the NoA */ struct ieee80211_noa_data { u32 next_tsf; bool has_next_tsf; u8 absent; u8 count[IEEE80211_P2P_NOA_DESC_MAX]; struct { u32 start; u32 duration; u32 interval; } desc[IEEE80211_P2P_NOA_DESC_MAX]; }; /** * ieee80211_parse_p2p_noa - initialize NoA tracking data from P2P IE * * @attr: P2P NoA IE * @data: NoA tracking data * @tsf: current TSF timestamp * * Return: number of successfully parsed descriptors */ int ieee80211_parse_p2p_noa(const struct ieee80211_p2p_noa_attr *attr, struct ieee80211_noa_data *data, u32 tsf); /** * ieee80211_update_p2p_noa - get next pending P2P GO absent state change * * @data: NoA tracking data * @tsf: current TSF timestamp */ void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf); /** * ieee80211_tdls_oper_request - request userspace to perform a TDLS operation * @vif: virtual interface * @peer: the peer's destination address * @oper: the requested TDLS operation * @reason_code: reason code for the operation, valid for TDLS teardown * @gfp: allocation flags * * See cfg80211_tdls_oper_request(). */ void ieee80211_tdls_oper_request(struct ieee80211_vif *vif, const u8 *peer, enum nl80211_tdls_operation oper, u16 reason_code, gfp_t gfp); /** * ieee80211_reserve_tid - request to reserve a specific TID * * There is sometimes a need (such as in TDLS) for blocking the driver from * using a specific TID so that the FW can use it for certain operations such * as sending PTI requests. To make sure that the driver doesn't use that TID, * this function must be called as it flushes out packets on this TID and marks * it as blocked, so that any transmit for the station on this TID will be * redirected to the alternative TID in the same AC. * * Note that this function blocks and may call back into the driver, so it * should be called without driver locks held. Also note this function should * only be called from the driver's @sta_state callback. * * @sta: the station to reserve the TID for * @tid: the TID to reserve * * Returns: 0 on success, else on failure */ int ieee80211_reserve_tid(struct ieee80211_sta *sta, u8 tid); /** * ieee80211_unreserve_tid - request to unreserve a specific TID * * Once there is no longer any need for reserving a certain TID, this function * should be called, and no longer will packets have their TID modified for * preventing use of this TID in the driver. * * Note that this function blocks and acquires a lock, so it should be called * without driver locks held. Also note this function should only be called * from the driver's @sta_state callback. * * @sta: the station * @tid: the TID to unreserve */ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); /** * ieee80211_tx_dequeue - dequeue a packet from a software tx queue * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface, or from * ieee80211_next_txq() * * Return: the skb if successful, %NULL if no frame was available. * * Note that this must be called in an rcu_read_lock() critical section, * which can only be released after the SKB was handled. Some pointers in * skb->cb, e.g. the key pointer, are protected by RCU and thus the * critical section must persist not just for the duration of this call * but for the duration of the frame handling. * However, also note that while in the wake_tx_queue() method, * rcu_read_lock() is already held. * * softirqs must also be disabled when this function is called. * In process context, use ieee80211_tx_dequeue_ni() instead. */ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** * ieee80211_tx_dequeue_ni - dequeue a packet from a software tx queue * (in process context) * * Like ieee80211_tx_dequeue() but can be called in process context * (internally disables bottom halves). * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface, or from * ieee80211_next_txq() * * Return: the skb if successful, %NULL if no frame was available. */ static inline struct sk_buff *ieee80211_tx_dequeue_ni(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { struct sk_buff *skb; local_bh_disable(); skb = ieee80211_tx_dequeue(hw, txq); local_bh_enable(); return skb; } /** * ieee80211_handle_wake_tx_queue - mac80211 handler for wake_tx_queue callback * * @hw: pointer as obtained from wake_tx_queue() callback(). * @txq: pointer as obtained from wake_tx_queue() callback(). * * Drivers can use this function for the mandatory mac80211 wake_tx_queue * callback in struct ieee80211_ops. They should not call this function. */ void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** * ieee80211_next_txq - get next tx queue to pull packets from * * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to return packets from. * * Return: the next txq if successful, %NULL if no queue is eligible. If a txq * is returned, it should be returned with ieee80211_return_txq() after the * driver has finished scheduling it. */ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac); /** * ieee80211_txq_schedule_start - start new scheduling round for TXQs * * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to acquire locks for * * Should be called before ieee80211_next_txq() or ieee80211_return_txq(). * The driver must not call multiple TXQ scheduling rounds concurrently. */ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac); /* (deprecated) */ static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) { } void __ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, bool force); /** * ieee80211_schedule_txq - schedule a TXQ for transmission * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface * * Schedules a TXQ for transmission if it is not already scheduled, * even if mac80211 does not have any packets buffered. * * The driver may call this function if it has buffered packets for * this TXQ internally. */ static inline void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { __ieee80211_schedule_txq(hw, txq, true); } /** * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface * @force: schedule txq even if mac80211 does not have any buffered packets. * * The driver may set force=true if it has buffered packets for this TXQ * internally. */ static inline void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, bool force) { __ieee80211_schedule_txq(hw, txq, force); } /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit * * This function is used to check whether given txq is allowed to transmit by * the airtime scheduler, and can be used by drivers to access the airtime * fairness accounting without using the scheduling order enforced by * next_txq(). * * Returns %true if the airtime scheduler thinks the TXQ should be allowed to * transmit, and %false if it should be throttled. This function can also have * the side effect of rotating the TXQ in the scheduler rotation, which will * eventually bring the deficit to positive and allow the station to transmit * again. * * The API ieee80211_txq_may_transmit() also ensures that TXQ list will be * aligned against driver's own round-robin scheduler list. i.e it rotates * the TXQ list till it makes the requested node becomes the first entry * in TXQ list. Thus both the TXQ list and driver's list are in sync. If this * function returns %true, the driver is expected to schedule packets * for transmission, and then return the TXQ through ieee80211_return_txq(). * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface * * Return: %true if transmission is allowed, %false otherwise */ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** * ieee80211_txq_get_depth - get pending frame/byte count of given txq * * The values are not guaranteed to be coherent with regard to each other, i.e. * txq state can change half-way of this function and the caller may end up * with "new" frame_cnt and "old" byte_cnt or vice-versa. * * @txq: pointer obtained from station or virtual interface * @frame_cnt: pointer to store frame count * @byte_cnt: pointer to store byte count */ void ieee80211_txq_get_depth(struct ieee80211_txq *txq, unsigned long *frame_cnt, unsigned long *byte_cnt); /** * ieee80211_nan_func_terminated - notify about NAN function termination. * * This function is used to notify mac80211 about NAN function termination. * Note that this function can't be called from hard irq. * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @inst_id: the local instance id * @reason: termination reason (one of the NL80211_NAN_FUNC_TERM_REASON_*) * @gfp: allocation flags */ void ieee80211_nan_func_terminated(struct ieee80211_vif *vif, u8 inst_id, enum nl80211_nan_func_term_reason reason, gfp_t gfp); /** * ieee80211_nan_func_match - notify about NAN function match event. * * This function is used to notify mac80211 about NAN function match. The * cookie inside the match struct will be assigned by mac80211. * Note that this function can't be called from hard irq. * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @match: match event information * @gfp: allocation flags */ void ieee80211_nan_func_match(struct ieee80211_vif *vif, struct cfg80211_nan_match_params *match, gfp_t gfp); /** * ieee80211_calc_rx_airtime - calculate estimated transmission airtime for RX. * * This function calculates the estimated airtime usage of a frame based on the * rate information in the RX status struct and the frame length. * * @hw: pointer as obtained from ieee80211_alloc_hw() * @status: &struct ieee80211_rx_status containing the transmission rate * information. * @len: frame length in bytes * * Return: the airtime estimate */ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, struct ieee80211_rx_status *status, int len); /** * ieee80211_calc_tx_airtime - calculate estimated transmission airtime for TX. * * This function calculates the estimated airtime usage of a frame based on the * rate information in the TX info struct and the frame length. * * @hw: pointer as obtained from ieee80211_alloc_hw() * @info: &struct ieee80211_tx_info of the frame. * @len: frame length in bytes * * Return: the airtime estimate */ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_info *info, int len); /** * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template. * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * The driver is responsible for freeing the returned skb. * * Return: FILS discovery template. %NULL on error. */ struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, struct ieee80211_vif *vif); /** * ieee80211_get_unsol_bcast_probe_resp_tmpl - Get unsolicited broadcast * probe response template. * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. * * The driver is responsible for freeing the returned skb. * * Return: Unsolicited broadcast probe response template. %NULL on error. */ struct sk_buff * ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, struct ieee80211_vif *vif); /** * ieee80211_obss_color_collision_notify - notify userland about a BSS color * collision. * @link_id: valid link_id during MLO or 0 for non-MLO * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @color_bitmap: a 64 bit bitmap representing the colors that the local BSS is * aware of. */ void ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, u64 color_bitmap, u8 link_id); /** * ieee80211_is_tx_data - check if frame is a data frame * * The function is used to check if a frame is a data frame. Frames with * hardware encapsulation enabled are data frames. * * @skb: the frame to be transmitted. * * Return: %true if @skb is a data frame, %false otherwise */ static inline bool ieee80211_is_tx_data(struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *) skb->data; return info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP || ieee80211_is_data(hdr->frame_control); } /** * ieee80211_set_active_links - set active links in client mode * @vif: interface to set active links on * @active_links: the new active links bitmap * * Context: Must be called with wiphy mutex held; may sleep; calls * back into the driver. * * This changes the active links on an interface. The interface * must be in client mode (in AP mode, all links are always active), * and @active_links must be a subset of the vif's valid_links. * * If a link is switched off and another is switched on at the same * time (e.g. active_links going from 0x1 to 0x10) then you will get * a sequence of calls like * * - change_vif_links(0x11) * - unassign_vif_chanctx(link_id=0) * - change_sta_links(0x11) for each affected STA (the AP) * (TDLS connections on now inactive links should be torn down) * - remove group keys on the old link (link_id 0) * - add new group keys (GTK/IGTK/BIGTK) on the new link (link_id 4) * - change_sta_links(0x10) for each affected STA (the AP) * - assign_vif_chanctx(link_id=4) * - change_vif_links(0x10) * * Return: 0 on success. An error code otherwise. */ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links); /** * ieee80211_set_active_links_async - asynchronously set active links * @vif: interface to set active links on * @active_links: the new active links bitmap * * See ieee80211_set_active_links() for more information, the only * difference here is that the link change is triggered async and * can be called in any context, but the link switch will only be * completed after it returns. */ void ieee80211_set_active_links_async(struct ieee80211_vif *vif, u16 active_links); /** * ieee80211_send_teardown_neg_ttlm - tear down a negotiated TTLM request * @vif: the interface on which the tear down request should be sent. * * This function can be used to tear down a previously accepted negotiated * TTLM request. */ void ieee80211_send_teardown_neg_ttlm(struct ieee80211_vif *vif); /* for older drivers - let's not document these ... */ int ieee80211_emulate_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); void ieee80211_emulate_remove_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx); void ieee80211_emulate_change_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx, u32 changed); int ieee80211_emulate_switch_vif_chanctx(struct ieee80211_hw *hw, struct ieee80211_vif_chanctx_switch *vifs, int n_vifs, enum ieee80211_chanctx_switch_mode mode); #endif /* MAC80211_H */ |
| 6 6 5 5 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2016-present, Facebook, Inc. * All rights reserved. * * zstd_wrapper.c */ #include <linux/mutex.h> #include <linux/bio.h> #include <linux/slab.h> #include <linux/zstd.h> #include <linux/vmalloc.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" #include "page_actor.h" struct workspace { void *mem; size_t mem_size; size_t window_size; }; static void *zstd_init(struct squashfs_sb_info *msblk, void *buff) { struct workspace *wksp = kmalloc(sizeof(*wksp), GFP_KERNEL); if (wksp == NULL) goto failed; wksp->window_size = max_t(size_t, msblk->block_size, SQUASHFS_METADATA_SIZE); wksp->mem_size = zstd_dstream_workspace_bound(wksp->window_size); wksp->mem = vmalloc(wksp->mem_size); if (wksp->mem == NULL) goto failed; return wksp; failed: ERROR("Failed to allocate zstd workspace\n"); kfree(wksp); return ERR_PTR(-ENOMEM); } static void zstd_free(void *strm) { struct workspace *wksp = strm; if (wksp) vfree(wksp->mem); kfree(wksp); } static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, struct bio *bio, int offset, int length, struct squashfs_page_actor *output) { struct workspace *wksp = strm; zstd_dstream *stream; size_t total_out = 0; int error = 0; zstd_in_buffer in_buf = { NULL, 0, 0 }; zstd_out_buffer out_buf = { NULL, 0, 0 }; struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size); if (!stream) { ERROR("Failed to initialize zstd decompressor\n"); return -EIO; } out_buf.size = PAGE_SIZE; out_buf.dst = squashfs_first_page(output); if (IS_ERR(out_buf.dst)) { error = PTR_ERR(out_buf.dst); goto finish; } for (;;) { size_t zstd_err; if (in_buf.pos == in_buf.size) { const void *data; int avail; if (!bio_next_segment(bio, &iter_all)) { error = -EIO; break; } avail = min(length, ((int)bvec->bv_len) - offset); data = bvec_virt(bvec); length -= avail; in_buf.src = data + offset; in_buf.size = avail; in_buf.pos = 0; offset = 0; } if (out_buf.pos == out_buf.size) { out_buf.dst = squashfs_next_page(output); if (IS_ERR(out_buf.dst)) { error = PTR_ERR(out_buf.dst); break; } else if (out_buf.dst == NULL) { /* Shouldn't run out of pages * before stream is done. */ error = -EIO; break; } out_buf.pos = 0; out_buf.size = PAGE_SIZE; } total_out -= out_buf.pos; zstd_err = zstd_decompress_stream(stream, &out_buf, &in_buf); total_out += out_buf.pos; /* add the additional data produced */ if (zstd_err == 0) break; if (zstd_is_error(zstd_err)) { ERROR("zstd decompression error: %d\n", (int)zstd_get_error_code(zstd_err)); error = -EIO; break; } } finish: squashfs_finish_page(output); return error ? error : total_out; } const struct squashfs_decompressor squashfs_zstd_comp_ops = { .init = zstd_init, .free = zstd_free, .decompress = zstd_uncompress, .id = ZSTD_COMPRESSION, .name = "zstd", .alloc_buffer = 1, .supported = 1 }; |
| 5 6 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/namespace.c * Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc. */ #include <linux/ipc.h> #include <linux/msg.h> #include <linux/ipc_namespace.h> #include <linux/rcupdate.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/sched/task.h> #include "util.h" /* * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount. */ static void free_ipc(struct work_struct *unused); static DECLARE_WORK(free_ipc_work, free_ipc); static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES); } static void dec_ipc_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_IPC_NAMESPACES); } static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, struct ipc_namespace *old_ns) { struct ipc_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; again: ucounts = inc_ipc_namespaces(user_ns); if (!ucounts) { /* * IPC namespaces are freed asynchronously, by free_ipc_work. * If frees were pending, flush_work will wait, and * return true. Fail the allocation if no frees are pending. */ if (flush_work(&free_ipc_work)) goto again; goto fail; } err = -ENOMEM; ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT); if (ns == NULL) goto fail_dec; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free; ns->ns.ops = &ipcns_operations; refcount_set(&ns->ns.count, 1); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; err = mq_init_ns(ns); if (err) goto fail_put; err = -ENOMEM; if (!setup_mq_sysctls(ns)) goto fail_put; if (!setup_ipc_sysctls(ns)) goto fail_mq; err = msg_init_ns(ns); if (err) goto fail_put; sem_init_ns(ns); shm_init_ns(ns); return ns; fail_mq: retire_mq_sysctls(ns); fail_put: put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); fail_free: kfree(ns); fail_dec: dec_ipc_namespaces(ucounts); fail: return ERR_PTR(err); } struct ipc_namespace *copy_ipcs(unsigned long flags, struct user_namespace *user_ns, struct ipc_namespace *ns) { if (!(flags & CLONE_NEWIPC)) return get_ipc_ns(ns); return create_ipc_ns(user_ns, ns); } /* * free_ipcs - free all ipcs of one type * @ns: the namespace to remove the ipcs from * @ids: the table of ipcs to free * @free: the function called to free each individual ipc * * Called for each kind of ipc when an ipc_namespace exits. */ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)) { struct kern_ipc_perm *perm; int next_id; int total, in_use; down_write(&ids->rwsem); in_use = ids->in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { perm = idr_find(&ids->ipcs_idr, next_id); if (perm == NULL) continue; rcu_read_lock(); ipc_lock_object(perm); free(ns, perm); total++; } up_write(&ids->rwsem); } static void free_ipc_ns(struct ipc_namespace *ns) { /* * Caller needs to wait for an RCU grace period to have passed * after making the mount point inaccessible to new accesses. */ mntput(ns->mq_mnt); sem_exit_ns(ns); msg_exit_ns(ns); shm_exit_ns(ns); retire_mq_sysctls(ns); retire_ipc_sysctls(ns); dec_ipc_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kfree(ns); } static LLIST_HEAD(free_ipc_list); static void free_ipc(struct work_struct *unused) { struct llist_node *node = llist_del_all(&free_ipc_list); struct ipc_namespace *n, *t; llist_for_each_entry_safe(n, t, node, mnt_llist) mnt_make_shortterm(n->mq_mnt); /* Wait for any last users to have gone away. */ synchronize_rcu(); llist_for_each_entry_safe(n, t, node, mnt_llist) free_ipc_ns(n); } /* * put_ipc_ns - drop a reference to an ipc namespace. * @ns: the namespace to put * * If this is the last task in the namespace exiting, and * it is dropping the refcount to 0, then it can race with * a task in another ipc namespace but in a mounts namespace * which has this ipcns's mqueuefs mounted, doing some action * with one of the mqueuefs files. That can raise the refcount. * So dropping the refcount, and raising the refcount when * accessing it through the VFS, are protected with mq_lock. * * (Clearly, a task raising the refcount on its own ipc_ns * needn't take mq_lock since it can't race with the last task * in the ipcns exiting). */ void put_ipc_ns(struct ipc_namespace *ns) { if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) { mq_clear_sbinfo(ns); spin_unlock(&mq_lock); if (llist_add(&ns->mnt_llist, &free_ipc_list)) schedule_work(&free_ipc_work); } } static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns) { return container_of(ns, struct ipc_namespace, ns); } static struct ns_common *ipcns_get(struct task_struct *task) { struct ipc_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) ns = get_ipc_ns(nsproxy->ipc_ns); task_unlock(task); return ns ? &ns->ns : NULL; } static void ipcns_put(struct ns_common *ns) { return put_ipc_ns(to_ipc_ns(ns)); } static int ipcns_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct ipc_namespace *ns = to_ipc_ns(new); if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; put_ipc_ns(nsproxy->ipc_ns); nsproxy->ipc_ns = get_ipc_ns(ns); return 0; } static struct user_namespace *ipcns_owner(struct ns_common *ns) { return to_ipc_ns(ns)->user_ns; } const struct proc_ns_operations ipcns_operations = { .name = "ipc", .type = CLONE_NEWIPC, .get = ipcns_get, .put = ipcns_put, .install = ipcns_install, .owner = ipcns_owner, }; |
| 1 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | /* * linux/drivers/video/fb_defio.c * * Copyright (C) 2006 Jaya Kumar * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive * for more details. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/fb.h> #include <linux/list.h> /* to support deferred IO */ #include <linux/rmap.h> #include <linux/pagemap.h> static struct page *fb_deferred_io_get_page(struct fb_info *info, unsigned long offs) { struct fb_deferred_io *fbdefio = info->fbdefio; const void *screen_buffer = info->screen_buffer; struct page *page = NULL; if (fbdefio->get_page) return fbdefio->get_page(info, offs); if (is_vmalloc_addr(screen_buffer + offs)) page = vmalloc_to_page(screen_buffer + offs); else if (info->fix.smem_start) page = pfn_to_page((info->fix.smem_start + offs) >> PAGE_SHIFT); if (page) get_page(page); return page; } static struct fb_deferred_io_pageref *fb_deferred_io_pageref_lookup(struct fb_info *info, unsigned long offset, struct page *page) { unsigned long pgoff = offset >> PAGE_SHIFT; struct fb_deferred_io_pageref *pageref; if (fb_WARN_ON_ONCE(info, pgoff >= info->npagerefs)) return NULL; /* incorrect allocation size */ /* 1:1 mapping between pageref and page offset */ pageref = &info->pagerefs[pgoff]; if (pageref->page) goto out; pageref->page = page; pageref->offset = pgoff << PAGE_SHIFT; INIT_LIST_HEAD(&pageref->list); out: if (fb_WARN_ON_ONCE(info, pageref->page != page)) return NULL; /* inconsistent state */ return pageref; } static void fb_deferred_io_pageref_clear(struct fb_deferred_io_pageref *pageref) { struct page *page = pageref->page; if (page) page->mapping = NULL; } static struct fb_deferred_io_pageref *fb_deferred_io_pageref_get(struct fb_info *info, unsigned long offset, struct page *page) { struct fb_deferred_io *fbdefio = info->fbdefio; struct list_head *pos = &fbdefio->pagereflist; struct fb_deferred_io_pageref *pageref, *cur; pageref = fb_deferred_io_pageref_lookup(info, offset, page); if (!pageref) return NULL; /* * This check is to catch the case where a new process could start * writing to the same page through a new PTE. This new access * can cause a call to .page_mkwrite even if the original process' * PTE is marked writable. */ if (!list_empty(&pageref->list)) goto pageref_already_added; if (unlikely(fbdefio->sort_pagereflist)) { /* * We loop through the list of pagerefs before adding in * order to keep the pagerefs sorted. This has significant * overhead of O(n^2) with n being the number of written * pages. If possible, drivers should try to work with * unsorted page lists instead. */ list_for_each_entry(cur, &fbdefio->pagereflist, list) { if (cur->offset > pageref->offset) break; } pos = &cur->list; } list_add_tail(&pageref->list, pos); pageref_already_added: return pageref; } static void fb_deferred_io_pageref_put(struct fb_deferred_io_pageref *pageref, struct fb_info *info) { list_del_init(&pageref->list); } /* this is to find and return the vmalloc-ed fb pages */ static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf) { unsigned long offset; struct page *page; struct fb_info *info = vmf->vma->vm_private_data; offset = vmf->pgoff << PAGE_SHIFT; if (offset >= info->fix.smem_len) return VM_FAULT_SIGBUS; page = fb_deferred_io_get_page(info, offset); if (!page) return VM_FAULT_SIGBUS; if (vmf->vma->vm_file) page->mapping = vmf->vma->vm_file->f_mapping; else printk(KERN_ERR "no mapping available\n"); BUG_ON(!page->mapping); page->index = vmf->pgoff; /* for folio_mkclean() */ vmf->page = page; return 0; } int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct fb_info *info = file->private_data; struct inode *inode = file_inode(file); int err = file_write_and_wait_range(file, start, end); if (err) return err; /* Skip if deferred io is compiled-in but disabled on this fbdev */ if (!info->fbdefio) return 0; inode_lock(inode); flush_delayed_work(&info->deferred_work); inode_unlock(inode); return 0; } EXPORT_SYMBOL_GPL(fb_deferred_io_fsync); /* * Adds a page to the dirty list. Call this from struct * vm_operations_struct.page_mkwrite. */ static vm_fault_t fb_deferred_io_track_page(struct fb_info *info, unsigned long offset, struct page *page) { struct fb_deferred_io *fbdefio = info->fbdefio; struct fb_deferred_io_pageref *pageref; vm_fault_t ret; /* protect against the workqueue changing the page list */ mutex_lock(&fbdefio->lock); pageref = fb_deferred_io_pageref_get(info, offset, page); if (WARN_ON_ONCE(!pageref)) { ret = VM_FAULT_OOM; goto err_mutex_unlock; } /* * We want the page to remain locked from ->page_mkwrite until * the PTE is marked dirty to avoid folio_mkclean() being called * before the PTE is updated, which would leave the page ignored * by defio. * Do this by locking the page here and informing the caller * about it with VM_FAULT_LOCKED. */ lock_page(pageref->page); mutex_unlock(&fbdefio->lock); /* come back after delay to process the deferred IO */ schedule_delayed_work(&info->deferred_work, fbdefio->delay); return VM_FAULT_LOCKED; err_mutex_unlock: mutex_unlock(&fbdefio->lock); return ret; } /* * fb_deferred_io_page_mkwrite - Mark a page as written for deferred I/O * @fb_info: The fbdev info structure * @vmf: The VM fault * * This is a callback we get when userspace first tries to * write to the page. We schedule a workqueue. That workqueue * will eventually mkclean the touched pages and execute the * deferred framebuffer IO. Then if userspace touches a page * again, we repeat the same scheme. * * Returns: * VM_FAULT_LOCKED on success, or a VM_FAULT error otherwise. */ static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_info *info, struct vm_fault *vmf) { unsigned long offset = vmf->pgoff << PAGE_SHIFT; struct page *page = vmf->page; file_update_time(vmf->vma->vm_file); return fb_deferred_io_track_page(info, offset, page); } /* vm_ops->page_mkwrite handler */ static vm_fault_t fb_deferred_io_mkwrite(struct vm_fault *vmf) { struct fb_info *info = vmf->vma->vm_private_data; return fb_deferred_io_page_mkwrite(info, vmf); } static const struct vm_operations_struct fb_deferred_io_vm_ops = { .fault = fb_deferred_io_fault, .page_mkwrite = fb_deferred_io_mkwrite, }; static const struct address_space_operations fb_deferred_io_aops = { .dirty_folio = noop_dirty_folio, }; int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma) { vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); vma->vm_ops = &fb_deferred_io_vm_ops; vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); if (!(info->flags & FBINFO_VIRTFB)) vm_flags_set(vma, VM_IO); vma->vm_private_data = info; return 0; } EXPORT_SYMBOL_GPL(fb_deferred_io_mmap); /* workqueue callback */ static void fb_deferred_io_work(struct work_struct *work) { struct fb_info *info = container_of(work, struct fb_info, deferred_work.work); struct fb_deferred_io_pageref *pageref, *next; struct fb_deferred_io *fbdefio = info->fbdefio; /* here we mkclean the pages, then do all deferred IO */ mutex_lock(&fbdefio->lock); list_for_each_entry(pageref, &fbdefio->pagereflist, list) { struct folio *folio = page_folio(pageref->page); folio_lock(folio); folio_mkclean(folio); folio_unlock(folio); } /* driver's callback with pagereflist */ fbdefio->deferred_io(info, &fbdefio->pagereflist); /* clear the list */ list_for_each_entry_safe(pageref, next, &fbdefio->pagereflist, list) fb_deferred_io_pageref_put(pageref, info); mutex_unlock(&fbdefio->lock); } int fb_deferred_io_init(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; struct fb_deferred_io_pageref *pagerefs; unsigned long npagerefs; int ret; BUG_ON(!fbdefio); if (WARN_ON(!info->fix.smem_len)) return -EINVAL; mutex_init(&fbdefio->lock); INIT_DELAYED_WORK(&info->deferred_work, fb_deferred_io_work); INIT_LIST_HEAD(&fbdefio->pagereflist); if (fbdefio->delay == 0) /* set a default of 1 s */ fbdefio->delay = HZ; npagerefs = DIV_ROUND_UP(info->fix.smem_len, PAGE_SIZE); /* alloc a page ref for each page of the display memory */ pagerefs = kvcalloc(npagerefs, sizeof(*pagerefs), GFP_KERNEL); if (!pagerefs) { ret = -ENOMEM; goto err; } info->npagerefs = npagerefs; info->pagerefs = pagerefs; return 0; err: mutex_destroy(&fbdefio->lock); return ret; } EXPORT_SYMBOL_GPL(fb_deferred_io_init); void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file) { struct fb_deferred_io *fbdefio = info->fbdefio; file->f_mapping->a_ops = &fb_deferred_io_aops; fbdefio->open_count++; } EXPORT_SYMBOL_GPL(fb_deferred_io_open); static void fb_deferred_io_lastclose(struct fb_info *info) { unsigned long i; flush_delayed_work(&info->deferred_work); /* clear out the mapping that we setup */ for (i = 0; i < info->npagerefs; ++i) fb_deferred_io_pageref_clear(&info->pagerefs[i]); } void fb_deferred_io_release(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; if (!--fbdefio->open_count) fb_deferred_io_lastclose(info); } EXPORT_SYMBOL_GPL(fb_deferred_io_release); void fb_deferred_io_cleanup(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; fb_deferred_io_lastclose(info); kvfree(info->pagerefs); mutex_destroy(&fbdefio->lock); } EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup); |
| 26 26 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NetLabel System * * The NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * * Author: Paul Moore <paul@paul-moore.com> */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2006, 2008 */ #ifndef _NETLABEL_H #define _NETLABEL_H #include <linux/types.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/in.h> #include <linux/in6.h> #include <net/netlink.h> #include <net/request_sock.h> #include <linux/refcount.h> struct cipso_v4_doi; struct calipso_doi; /* * NetLabel - A management interface for maintaining network packet label * mapping tables for explicit packet labling protocols. * * Network protocols such as CIPSO and RIPSO require a label translation layer * to convert the label on the packet into something meaningful on the host * machine. In the current Linux implementation these mapping tables live * inside the kernel; NetLabel provides a mechanism for user space applications * to manage these mapping tables. * * NetLabel makes use of the Generic NETLINK mechanism as a transport layer to * send messages between kernel and user space. The general format of a * NetLabel message is shown below: * * +-----------------+-------------------+--------- --- -- - * | struct nlmsghdr | struct genlmsghdr | payload * +-----------------+-------------------+--------- --- -- - * * The 'nlmsghdr' and 'genlmsghdr' structs should be dealt with like normal. * The payload is dependent on the subsystem specified in the * 'nlmsghdr->nlmsg_type' and should be defined below, supporting functions * should be defined in the corresponding net/netlabel/netlabel_<subsys>.h|c * file. All of the fields in the NetLabel payload are NETLINK attributes, see * the include/net/netlink.h file for more information on NETLINK attributes. * */ /* * NetLabel NETLINK protocol */ /* NetLabel NETLINK protocol version * 1: initial version * 2: added static labels for unlabeled connections * 3: network selectors added to the NetLabel/LSM domain mapping and the * CIPSO_V4_MAP_LOCAL CIPSO mapping was added */ #define NETLBL_PROTO_VERSION 3 /* NetLabel NETLINK types/families */ #define NETLBL_NLTYPE_NONE 0 #define NETLBL_NLTYPE_MGMT 1 #define NETLBL_NLTYPE_MGMT_NAME "NLBL_MGMT" #define NETLBL_NLTYPE_RIPSO 2 #define NETLBL_NLTYPE_RIPSO_NAME "NLBL_RIPSO" #define NETLBL_NLTYPE_CIPSOV4 3 #define NETLBL_NLTYPE_CIPSOV4_NAME "NLBL_CIPSOv4" #define NETLBL_NLTYPE_CIPSOV6 4 #define NETLBL_NLTYPE_CIPSOV6_NAME "NLBL_CIPSOv6" #define NETLBL_NLTYPE_UNLABELED 5 #define NETLBL_NLTYPE_UNLABELED_NAME "NLBL_UNLBL" #define NETLBL_NLTYPE_ADDRSELECT 6 #define NETLBL_NLTYPE_ADDRSELECT_NAME "NLBL_ADRSEL" #define NETLBL_NLTYPE_CALIPSO 7 #define NETLBL_NLTYPE_CALIPSO_NAME "NLBL_CALIPSO" /* * NetLabel - Kernel API for accessing the network packet label mappings. * * The following functions are provided for use by other kernel modules, * specifically kernel LSM modules, to provide a consistent, transparent API * for dealing with explicit packet labeling protocols such as CIPSO and * RIPSO. The functions defined here are implemented in the * net/netlabel/netlabel_kapi.c file. * */ /* NetLabel audit information */ struct netlbl_audit { u32 secid; kuid_t loginuid; unsigned int sessionid; }; /* * LSM security attributes */ /** * struct netlbl_lsm_cache - NetLabel LSM security attribute cache * @refcount: atomic reference counter * @free: LSM supplied function to free the cache data * @data: LSM supplied cache data * * Description: * This structure is provided for LSMs which wish to make use of the NetLabel * caching mechanism to store LSM specific data/attributes in the NetLabel * cache. If the LSM has to perform a lot of translation from the NetLabel * security attributes into it's own internal representation then the cache * mechanism can provide a way to eliminate some or all of that translation * overhead on a cache hit. * */ struct netlbl_lsm_cache { refcount_t refcount; void (*free) (const void *data); void *data; }; /** * struct netlbl_lsm_catmap - NetLabel LSM secattr category bitmap * @startbit: the value of the lowest order bit in the bitmap * @bitmap: the category bitmap * @next: pointer to the next bitmap "node" or NULL * * Description: * This structure is used to represent category bitmaps. Due to the large * number of categories supported by most labeling protocols it is not * practical to transfer a full bitmap internally so NetLabel adopts a sparse * bitmap structure modeled after SELinux's ebitmap structure. * The catmap bitmap field MUST be a power of two in length and large * enough to hold at least 240 bits. Special care (i.e. check the code!) * should be used when changing these values as the LSM implementation * probably has functions which rely on the sizes of these types to speed * processing. * */ #define NETLBL_CATMAP_MAPCNT 4 #define NETLBL_CATMAP_MAPSIZE (sizeof(u64) * 8) #define NETLBL_CATMAP_SIZE (NETLBL_CATMAP_MAPSIZE * \ NETLBL_CATMAP_MAPCNT) #define NETLBL_CATMAP_BIT ((u64)0x01) struct netlbl_lsm_catmap { u32 startbit; u64 bitmap[NETLBL_CATMAP_MAPCNT]; struct netlbl_lsm_catmap *next; }; /** * struct netlbl_lsm_secattr - NetLabel LSM security attributes * @flags: indicate structure attributes, see NETLBL_SECATTR_* * @type: indicate the NLTYPE of the attributes * @domain: the NetLabel LSM domain * @cache: NetLabel LSM specific cache * @attr.mls: MLS sensitivity label * @attr.mls.cat: MLS category bitmap * @attr.mls.lvl: MLS sensitivity level * @attr.secid: LSM specific secid token * * Description: * This structure is used to pass security attributes between NetLabel and the * LSM modules. The flags field is used to specify which fields within the * struct are valid and valid values can be created by bitwise OR'ing the * NETLBL_SECATTR_* defines. The domain field is typically set by the LSM to * specify domain specific configuration settings and is not usually used by * NetLabel itself when returning security attributes to the LSM. * */ struct netlbl_lsm_secattr { u32 flags; /* bitmap values for 'flags' */ #define NETLBL_SECATTR_NONE 0x00000000 #define NETLBL_SECATTR_DOMAIN 0x00000001 #define NETLBL_SECATTR_DOMAIN_CPY (NETLBL_SECATTR_DOMAIN | \ NETLBL_SECATTR_FREE_DOMAIN) #define NETLBL_SECATTR_CACHE 0x00000002 #define NETLBL_SECATTR_MLS_LVL 0x00000004 #define NETLBL_SECATTR_MLS_CAT 0x00000008 #define NETLBL_SECATTR_SECID 0x00000010 /* bitmap meta-values for 'flags' */ #define NETLBL_SECATTR_FREE_DOMAIN 0x01000000 #define NETLBL_SECATTR_CACHEABLE (NETLBL_SECATTR_MLS_LVL | \ NETLBL_SECATTR_MLS_CAT | \ NETLBL_SECATTR_SECID) u32 type; char *domain; struct netlbl_lsm_cache *cache; struct { struct { struct netlbl_lsm_catmap *cat; u32 lvl; } mls; u32 secid; } attr; }; /** * struct netlbl_calipso_ops - NetLabel CALIPSO operations * @doi_add: add a CALIPSO DOI * @doi_free: free a CALIPSO DOI * @doi_getdef: returns a reference to a DOI * @doi_putdef: releases a reference of a DOI * @doi_walk: enumerate the DOI list * @sock_getattr: retrieve the socket's attr * @sock_setattr: set the socket's attr * @sock_delattr: remove the socket's attr * @req_setattr: set the req socket's attr * @req_delattr: remove the req socket's attr * @opt_getattr: retrieve attr from memory block * @skbuff_optptr: find option in packet * @skbuff_setattr: set the skbuff's attr * @skbuff_delattr: remove the skbuff's attr * @cache_invalidate: invalidate cache * @cache_add: add cache entry * * Description: * This structure is filled out by the CALIPSO engine and passed * to the NetLabel core via a call to netlbl_calipso_ops_register(). * It enables the CALIPSO engine (and hence IPv6) to be compiled * as a module. */ struct netlbl_calipso_ops { int (*doi_add)(struct calipso_doi *doi_def, struct netlbl_audit *audit_info); void (*doi_free)(struct calipso_doi *doi_def); int (*doi_remove)(u32 doi, struct netlbl_audit *audit_info); struct calipso_doi *(*doi_getdef)(u32 doi); void (*doi_putdef)(struct calipso_doi *doi_def); int (*doi_walk)(u32 *skip_cnt, int (*callback)(struct calipso_doi *doi_def, void *arg), void *cb_arg); int (*sock_getattr)(struct sock *sk, struct netlbl_lsm_secattr *secattr); int (*sock_setattr)(struct sock *sk, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr); void (*sock_delattr)(struct sock *sk); int (*req_setattr)(struct request_sock *req, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr); void (*req_delattr)(struct request_sock *req); int (*opt_getattr)(const unsigned char *calipso, struct netlbl_lsm_secattr *secattr); unsigned char *(*skbuff_optptr)(const struct sk_buff *skb); int (*skbuff_setattr)(struct sk_buff *skb, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr); int (*skbuff_delattr)(struct sk_buff *skb); void (*cache_invalidate)(void); int (*cache_add)(const unsigned char *calipso_ptr, const struct netlbl_lsm_secattr *secattr); }; /* * LSM security attribute operations (inline) */ /** * netlbl_secattr_cache_alloc - Allocate and initialize a secattr cache * @flags: the memory allocation flags * * Description: * Allocate and initialize a netlbl_lsm_cache structure. Returns a pointer * on success, NULL on failure. * */ static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc_noprof(gfp_t flags) { struct netlbl_lsm_cache *cache; cache = kzalloc_noprof(sizeof(*cache), flags); if (cache) refcount_set(&cache->refcount, 1); return cache; } #define netlbl_secattr_cache_alloc(...) \ alloc_hooks(netlbl_secattr_cache_alloc_noprof(__VA_ARGS__)) /** * netlbl_secattr_cache_free - Frees a netlbl_lsm_cache struct * @cache: the struct to free * * Description: * Frees @secattr including all of the internal buffers. * */ static inline void netlbl_secattr_cache_free(struct netlbl_lsm_cache *cache) { if (!refcount_dec_and_test(&cache->refcount)) return; if (cache->free) cache->free(cache->data); kfree(cache); } /** * netlbl_catmap_alloc - Allocate a LSM secattr catmap * @flags: memory allocation flags * * Description: * Allocate memory for a LSM secattr catmap, returns a pointer on success, NULL * on failure. * */ static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc_noprof(gfp_t flags) { return kzalloc_noprof(sizeof(struct netlbl_lsm_catmap), flags); } #define netlbl_catmap_alloc(...) alloc_hooks(netlbl_catmap_alloc_noprof(__VA_ARGS__)) /** * netlbl_catmap_free - Free a LSM secattr catmap * @catmap: the category bitmap * * Description: * Free a LSM secattr catmap. * */ static inline void netlbl_catmap_free(struct netlbl_lsm_catmap *catmap) { struct netlbl_lsm_catmap *iter; while (catmap) { iter = catmap; catmap = catmap->next; kfree(iter); } } /** * netlbl_secattr_init - Initialize a netlbl_lsm_secattr struct * @secattr: the struct to initialize * * Description: * Initialize an already allocated netlbl_lsm_secattr struct. * */ static inline void netlbl_secattr_init(struct netlbl_lsm_secattr *secattr) { memset(secattr, 0, sizeof(*secattr)); } /** * netlbl_secattr_destroy - Clears a netlbl_lsm_secattr struct * @secattr: the struct to clear * * Description: * Destroys the @secattr struct, including freeing all of the internal buffers. * The struct must be reset with a call to netlbl_secattr_init() before reuse. * */ static inline void netlbl_secattr_destroy(struct netlbl_lsm_secattr *secattr) { if (secattr->flags & NETLBL_SECATTR_FREE_DOMAIN) kfree(secattr->domain); if (secattr->flags & NETLBL_SECATTR_CACHE) netlbl_secattr_cache_free(secattr->cache); if (secattr->flags & NETLBL_SECATTR_MLS_CAT) netlbl_catmap_free(secattr->attr.mls.cat); } /** * netlbl_secattr_alloc - Allocate and initialize a netlbl_lsm_secattr struct * @flags: the memory allocation flags * * Description: * Allocate and initialize a netlbl_lsm_secattr struct. Returns a valid * pointer on success, or NULL on failure. * */ static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc_noprof(gfp_t flags) { return kzalloc_noprof(sizeof(struct netlbl_lsm_secattr), flags); } #define netlbl_secattr_alloc(...) alloc_hooks(netlbl_secattr_alloc_noprof(__VA_ARGS__)) /** * netlbl_secattr_free - Frees a netlbl_lsm_secattr struct * @secattr: the struct to free * * Description: * Frees @secattr including all of the internal buffers. * */ static inline void netlbl_secattr_free(struct netlbl_lsm_secattr *secattr) { netlbl_secattr_destroy(secattr); kfree(secattr); } #ifdef CONFIG_NETLABEL /* * LSM configuration operations */ int netlbl_cfg_map_del(const char *domain, u16 family, const void *addr, const void *mask, struct netlbl_audit *audit_info); int netlbl_cfg_unlbl_map_add(const char *domain, u16 family, const void *addr, const void *mask, struct netlbl_audit *audit_info); int netlbl_cfg_unlbl_static_add(struct net *net, const char *dev_name, const void *addr, const void *mask, u16 family, u32 secid, struct netlbl_audit *audit_info); int netlbl_cfg_unlbl_static_del(struct net *net, const char *dev_name, const void *addr, const void *mask, u16 family, struct netlbl_audit *audit_info); int netlbl_cfg_cipsov4_add(struct cipso_v4_doi *doi_def, struct netlbl_audit *audit_info); void netlbl_cfg_cipsov4_del(u32 doi, struct netlbl_audit *audit_info); int netlbl_cfg_cipsov4_map_add(u32 doi, const char *domain, const struct in_addr *addr, const struct in_addr *mask, struct netlbl_audit *audit_info); int netlbl_cfg_calipso_add(struct calipso_doi *doi_def, struct netlbl_audit *audit_info); void netlbl_cfg_calipso_del(u32 doi, struct netlbl_audit *audit_info); int netlbl_cfg_calipso_map_add(u32 doi, const char *domain, const struct in6_addr *addr, const struct in6_addr *mask, struct netlbl_audit *audit_info); /* * LSM security attribute operations */ int netlbl_catmap_walk(struct netlbl_lsm_catmap *catmap, u32 offset); int netlbl_catmap_walkrng(struct netlbl_lsm_catmap *catmap, u32 offset); int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, u32 *offset, unsigned long *bitmap); int netlbl_catmap_setbit(struct netlbl_lsm_catmap **catmap, u32 bit, gfp_t flags); int netlbl_catmap_setrng(struct netlbl_lsm_catmap **catmap, u32 start, u32 end, gfp_t flags); int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, u32 offset, unsigned long bitmap, gfp_t flags); /* Bitmap functions */ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len, u32 offset, u8 state); void netlbl_bitmap_setbit(unsigned char *bitmap, u32 bit, u8 state); /* * LSM protocol operations (NetLabel LSM/kernel API) */ int netlbl_enabled(void); int netlbl_sock_setattr(struct sock *sk, u16 family, const struct netlbl_lsm_secattr *secattr, bool sk_locked); void netlbl_sock_delattr(struct sock *sk); int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); int netlbl_conn_setattr(struct sock *sk, struct sockaddr *addr, const struct netlbl_lsm_secattr *secattr); int netlbl_req_setattr(struct request_sock *req, const struct netlbl_lsm_secattr *secattr); void netlbl_req_delattr(struct request_sock *req); int netlbl_skbuff_setattr(struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr); int netlbl_skbuff_getattr(const struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr); void netlbl_skbuff_err(struct sk_buff *skb, u16 family, int error, int gateway); bool netlbl_sk_lock_check(struct sock *sk); /* * LSM label mapping cache operations */ void netlbl_cache_invalidate(void); int netlbl_cache_add(const struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr); /* * Protocol engine operations */ struct audit_buffer *netlbl_audit_start(int type, struct netlbl_audit *audit_info); #else static inline int netlbl_cfg_map_del(const char *domain, u16 family, const void *addr, const void *mask, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline int netlbl_cfg_unlbl_map_add(const char *domain, u16 family, void *addr, void *mask, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline int netlbl_cfg_unlbl_static_add(struct net *net, const char *dev_name, const void *addr, const void *mask, u16 family, u32 secid, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline int netlbl_cfg_unlbl_static_del(struct net *net, const char *dev_name, const void *addr, const void *mask, u16 family, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline int netlbl_cfg_cipsov4_add(struct cipso_v4_doi *doi_def, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline void netlbl_cfg_cipsov4_del(u32 doi, struct netlbl_audit *audit_info) { return; } static inline int netlbl_cfg_cipsov4_map_add(u32 doi, const char *domain, const struct in_addr *addr, const struct in_addr *mask, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline int netlbl_cfg_calipso_add(struct calipso_doi *doi_def, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline void netlbl_cfg_calipso_del(u32 doi, struct netlbl_audit *audit_info) { return; } static inline int netlbl_cfg_calipso_map_add(u32 doi, const char *domain, const struct in6_addr *addr, const struct in6_addr *mask, struct netlbl_audit *audit_info) { return -ENOSYS; } static inline int netlbl_catmap_walk(struct netlbl_lsm_catmap *catmap, u32 offset) { return -ENOENT; } static inline int netlbl_catmap_walkrng(struct netlbl_lsm_catmap *catmap, u32 offset) { return -ENOENT; } static inline int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, u32 *offset, unsigned long *bitmap) { return 0; } static inline int netlbl_catmap_setbit(struct netlbl_lsm_catmap **catmap, u32 bit, gfp_t flags) { return 0; } static inline int netlbl_catmap_setrng(struct netlbl_lsm_catmap **catmap, u32 start, u32 end, gfp_t flags) { return 0; } static inline int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, u32 offset, unsigned long bitmap, gfp_t flags) { return 0; } static inline int netlbl_enabled(void) { return 0; } static inline int netlbl_sock_setattr(struct sock *sk, u16 family, const struct netlbl_lsm_secattr *secattr, bool sk_locked) { return -ENOSYS; } static inline void netlbl_sock_delattr(struct sock *sk) { } static inline int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline int netlbl_conn_setattr(struct sock *sk, struct sockaddr *addr, const struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline int netlbl_req_setattr(struct request_sock *req, const struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline void netlbl_req_delattr(struct request_sock *req) { return; } static inline int netlbl_skbuff_setattr(struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline int netlbl_skbuff_getattr(const struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } static inline void netlbl_skbuff_err(struct sk_buff *skb, int error, int gateway) { return; } static inline void netlbl_cache_invalidate(void) { return; } static inline int netlbl_cache_add(const struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr) { return 0; } static inline struct audit_buffer *netlbl_audit_start(int type, struct netlbl_audit *audit_info) { return NULL; } static inline bool netlbl_sk_lock_check(struct sock *sk) { return true; } #endif /* CONFIG_NETLABEL */ const struct netlbl_calipso_ops * netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops); #endif /* _NETLABEL_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 | /* * Copyright 2016 Intel Corporation * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software") * to deal in the software without restriction, including without limitation * on the rights to use, copy, modify, merge, publish, distribute, sub * license, and/or sell copies of the Software, and to permit persons to whom * them Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTIBILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL * THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER * IN AN ACTION OF CONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */ #include <linux/dma-buf.h> #include <linux/dma-resv.h> #include <drm/drm_file.h> #include "vgem_drv.h" #define VGEM_FENCE_TIMEOUT (10*HZ) struct vgem_fence { struct dma_fence base; struct spinlock lock; struct timer_list timer; }; static const char *vgem_fence_get_driver_name(struct dma_fence *fence) { return "vgem"; } static const char *vgem_fence_get_timeline_name(struct dma_fence *fence) { return "unbound"; } static void vgem_fence_release(struct dma_fence *base) { struct vgem_fence *fence = container_of(base, typeof(*fence), base); del_timer_sync(&fence->timer); dma_fence_free(&fence->base); } static void vgem_fence_value_str(struct dma_fence *fence, char *str, int size) { snprintf(str, size, "%llu", fence->seqno); } static void vgem_fence_timeline_value_str(struct dma_fence *fence, char *str, int size) { snprintf(str, size, "%llu", dma_fence_is_signaled(fence) ? fence->seqno : 0); } static const struct dma_fence_ops vgem_fence_ops = { .get_driver_name = vgem_fence_get_driver_name, .get_timeline_name = vgem_fence_get_timeline_name, .release = vgem_fence_release, .fence_value_str = vgem_fence_value_str, .timeline_value_str = vgem_fence_timeline_value_str, }; static void vgem_fence_timeout(struct timer_list *t) { struct vgem_fence *fence = from_timer(fence, t, timer); dma_fence_signal(&fence->base); } static struct dma_fence *vgem_fence_create(struct vgem_file *vfile, unsigned int flags) { struct vgem_fence *fence; fence = kzalloc(sizeof(*fence), GFP_KERNEL); if (!fence) return NULL; spin_lock_init(&fence->lock); dma_fence_init(&fence->base, &vgem_fence_ops, &fence->lock, dma_fence_context_alloc(1), 1); timer_setup(&fence->timer, vgem_fence_timeout, 0); /* We force the fence to expire within 10s to prevent driver hangs */ mod_timer(&fence->timer, jiffies + VGEM_FENCE_TIMEOUT); return &fence->base; } /* * vgem_fence_attach_ioctl (DRM_IOCTL_VGEM_FENCE_ATTACH): * * Create and attach a fence to the vGEM handle. This fence is then exposed * via the dma-buf reservation object and visible to consumers of the exported * dma-buf. If the flags contain VGEM_FENCE_WRITE, the fence indicates the * vGEM buffer is being written to by the client and is exposed as an exclusive * fence, otherwise the fence indicates the client is current reading from the * buffer and all future writes should wait for the client to signal its * completion. Note that if a conflicting fence is already on the dma-buf (i.e. * an exclusive fence when adding a read, or any fence when adding a write), * -EBUSY is reported. Serialisation between operations should be handled * by waiting upon the dma-buf. * * This returns the handle for the new fence that must be signaled within 10 * seconds (or otherwise it will automatically expire). See * vgem_fence_signal_ioctl (DRM_IOCTL_VGEM_FENCE_SIGNAL). * * If the vGEM handle does not exist, vgem_fence_attach_ioctl returns -ENOENT. */ int vgem_fence_attach_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct drm_vgem_fence_attach *arg = data; struct vgem_file *vfile = file->driver_priv; struct dma_resv *resv; struct drm_gem_object *obj; enum dma_resv_usage usage; struct dma_fence *fence; int ret; if (arg->flags & ~VGEM_FENCE_WRITE) return -EINVAL; if (arg->pad) return -EINVAL; obj = drm_gem_object_lookup(file, arg->handle); if (!obj) return -ENOENT; fence = vgem_fence_create(vfile, arg->flags); if (!fence) { ret = -ENOMEM; goto err; } /* Check for a conflicting fence */ resv = obj->resv; usage = dma_resv_usage_rw(arg->flags & VGEM_FENCE_WRITE); if (!dma_resv_test_signaled(resv, usage)) { ret = -EBUSY; goto err_fence; } /* Expose the fence via the dma-buf */ dma_resv_lock(resv, NULL); ret = dma_resv_reserve_fences(resv, 1); if (!ret) dma_resv_add_fence(resv, fence, arg->flags & VGEM_FENCE_WRITE ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ); dma_resv_unlock(resv); /* Record the fence in our idr for later signaling */ if (ret == 0) { mutex_lock(&vfile->fence_mutex); ret = idr_alloc(&vfile->fence_idr, fence, 1, 0, GFP_KERNEL); mutex_unlock(&vfile->fence_mutex); if (ret > 0) { arg->out_fence = ret; ret = 0; } } err_fence: if (ret) { dma_fence_signal(fence); dma_fence_put(fence); } err: drm_gem_object_put(obj); return ret; } /* * vgem_fence_signal_ioctl (DRM_IOCTL_VGEM_FENCE_SIGNAL): * * Signal and consume a fence ealier attached to a vGEM handle using * vgem_fence_attach_ioctl (DRM_IOCTL_VGEM_FENCE_ATTACH). * * All fences must be signaled within 10s of attachment or otherwise they * will automatically expire (and a vgem_fence_signal_ioctl returns -ETIMEDOUT). * * Signaling a fence indicates to all consumers of the dma-buf that the * client has completed the operation associated with the fence, and that the * buffer is then ready for consumption. * * If the fence does not exist (or has already been signaled by the client), * vgem_fence_signal_ioctl returns -ENOENT. */ int vgem_fence_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct vgem_file *vfile = file->driver_priv; struct drm_vgem_fence_signal *arg = data; struct dma_fence *fence; int ret = 0; if (arg->flags) return -EINVAL; mutex_lock(&vfile->fence_mutex); fence = idr_replace(&vfile->fence_idr, NULL, arg->fence); mutex_unlock(&vfile->fence_mutex); if (!fence) return -ENOENT; if (IS_ERR(fence)) return PTR_ERR(fence); if (dma_fence_is_signaled(fence)) ret = -ETIMEDOUT; dma_fence_signal(fence); dma_fence_put(fence); return ret; } int vgem_fence_open(struct vgem_file *vfile) { mutex_init(&vfile->fence_mutex); idr_init_base(&vfile->fence_idr, 1); return 0; } static int __vgem_fence_idr_fini(int id, void *p, void *data) { dma_fence_signal(p); dma_fence_put(p); return 0; } void vgem_fence_close(struct vgem_file *vfile) { idr_for_each(&vfile->fence_idr, __vgem_fence_idr_fini, vfile); idr_destroy(&vfile->fence_idr); mutex_destroy(&vfile->fence_mutex); } |
| 453 453 878 74 813 870 803 33 48 1617 2580 2569 2377 122 206 1054 1548 1668 1669 1670 1079 1292 1672 2301 2305 1512 2300 21 66 118 103 103 26 26 2 2 76 63 1373 1369 1376 1377 151 2063 1005 42 123 1122 1560 830 1002 2602 2591 13 2556 97 2602 1499 1361 2552 58 1113 2582 2 2580 2578 2607 18 2604 43 2057 1 724 8 2576 28 101 621 13 13 7458 7463 7483 7482 5240 7467 7401 4 2506 41 4 26 5 21 26 1109 1108 1108 674 676 677 678 669 87 87 33 6 144 410 228 181 2133 2115 15 546 1 1 1 1 95 95 95 13 95 1500 1501 103 18 18 17 2 95 2 2 2 2 2 75 75 319 321 321 249 251 250 250 1 17 1 33 3 246 249 3 2 2 247 251 1 1 3 1 2 3 1125 1128 1127 1125 249 248 25 13 14 25 1 1 1 1 247 25 1 1 247 82 81 82 82 82 82 81 34 34 3 69 36 31 3 3 5538 1156 5077 774 5550 1716 4122 15 10 10 2080 49 2034 55 55 5539 5547 5537 4158 4097 1266 4097 1275 3692 2175 4774 301 3941 1903 4817 15 4767 301 18 6 2129 2169 260 2302 2170 4726 1 3679 3689 3675 3666 3679 3673 3258 3393 553 553 1098 1100 97 6 35 41 40 41 41 41 41 97 453 787 791 39 5 4 2908 790 2365 205 8 3699 1099 3365 6498 6489 6501 557 4427 6496 54 54 53 355 190 179 3914 3908 3914 75 2722 2715 2717 15 2906 2911 2909 12 5 2888 4 16 16 16 15 4 12 2894 2891 2890 2878 2887 2882 2884 231 3854 1573 2711 3047 1541 1538 1536 1574 2709 3045 1535 1590 1566 62 4 4 444 51 123 381 488 544 545 546 154 94 410 63 530 17 546 545 12 531 22 525 492 10 482 66 65 66 65 9 533 545 545 527 17 411 154 10 535 469 66 66 66 66 66 579 635 12 1 1 2 3 3377 106 2154 1014 628 23 2 12 11 2 10 164 42 150 151 151 150 14 14 5 14 169 169 169 168 641 641 641 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" #include <asm/runtime-const.h> /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_chilren * - childrens' d_sib and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __ro_after_init; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. * * Marking the variables "used" ensures that the compiler doesn't * optimize them away completely on architectures with runtime * constant infrastructure, this allows debuggers to see their * values. But updating these values has no effect on those arches. */ static unsigned int d_hash_shift __ro_after_init __used; static struct hlist_bl_head *dentry_hashtable __ro_after_init __used; static inline struct hlist_bl_head *d_hash(unsigned long hashlen) { return runtime_const_ptr(dentry_hashtable) + runtime_const_shift_right_32(hashlen, d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ static struct dentry_stat_t dentry_stat = { .age_limit = 45, }; /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, }; static int __init init_fs_dcache_sysctls(void) { register_sysctl_init("fs", fs_dcache_sysctls); return 0; } fs_initcall(init_fs_dcache_sysctls); #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } struct external_name { union { atomic_t count; struct rcu_head head; } u; unsigned char name[]; }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { spin_lock(&dentry->d_lock); name->name = dentry->d_name; if (unlikely(dname_external(dentry))) { atomic_inc(&external_name(dentry)->u.count); } else { memcpy(name->inline_name, dentry->d_iname, dentry->d_name.len + 1); name->name.name = name->inline_name; } spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) kfree_rcu(p, u.head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->u.count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(hlist_unhashed(&dentry->d_sib))) return; __hlist_del(&dentry->d_sib); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_sib.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_sib.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_sib.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_sib.next) { next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_sib.next = next->d_sib.next; } } static struct dentry *__dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); cond_resched(); /* now that it's negative, ->d_parent is stable */ if (!IS_ROOT(dentry)) { parent = dentry->d_parent; spin_lock(&parent->d_lock); } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry_unlist(dentry); if (dentry->d_flags & DCACHE_SHRINK_LIST) can_free = false; spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); if (parent && --parent->d_lockref.count) { spin_unlock(&parent->d_lock); return NULL; } return parent; } /* * Lock a dentry for feeding it to __dentry_kill(). * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry is busy. Otherwise, return true and have * that dentry's inode locked. */ static bool lock_for_kill(struct dentry *dentry) { struct inode *inode = dentry->d_inode; if (unlikely(dentry->d_lockref.count)) return false; if (!inode || likely(spin_trylock(&inode->i_lock))) return true; do { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (likely(inode == dentry->d_inode)) break; spin_unlock(&inode->i_lock); inode = dentry->d_inode; } while (inode); if (likely(!dentry->d_lockref.count)) return true; if (inode) spin_unlock(&inode->i_lock); return false; } /* * Decide if dentry is worth retaining. Usually this is called with dentry * locked; if not locked, we are more limited and might not be able to tell * without a lock. False in this case means "punt to locked path and recheck". * * In case we aren't locked, these predicates are not "stable". However, it is * sufficient that at some point after we dropped the reference the dentry was * hashed and the flags had the proper value. Other dentry users may have * re-gotten a reference to the dentry and change that, but our work is done - * we can leave the dentry around with a zero refcount. */ static inline bool retain_dentry(struct dentry *dentry, bool locked) { unsigned int d_flags; smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); // Unreachable? Nobody would be able to look it up, no point retaining if (unlikely(d_unhashed(dentry))) return false; // Same if it's disconnected if (unlikely(d_flags & DCACHE_DISCONNECTED)) return false; // ->d_delete() might tell us not to bother, but that requires // ->d_lock; can't decide without it if (unlikely(d_flags & DCACHE_OP_DELETE)) { if (!locked || dentry->d_op->d_delete(dentry)) return false; } // Explicitly told not to bother if (unlikely(d_flags & DCACHE_DONTCACHE)) return false; // At this point it looks like we ought to keep it. We also might // need to do something - put it on LRU if it wasn't there already // and mark it referenced if it was on LRU, but not marked yet. // Unfortunately, both actions require ->d_lock, so in lockless // case we'd have to punt rather than doing those. if (unlikely(!(d_flags & DCACHE_LRU_LIST))) { if (!locked) return false; d_lru_add(dentry); } else if (unlikely(!(d_flags & DCACHE_REFERENCED))) { if (!locked) return false; dentry->d_flags |= DCACHE_REFERENCED; } return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * In that case refcount is guaranteed to be zero and we have already * decided that it's not worth keeping around. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; /* * try to decrement the lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Can we decide that decrement of refcount is all we needed without * taking the lock? There's a very common case when it's all we need - * dentry looks like it ought to be retained and there's nothing else * to do. */ if (retain_dentry(dentry, false)) return true; /* * Either not worth retaining or we can't tell without the lock. * Get the lock, then. We've already decremented the refcount to 0, * but we'll need to re-check the situation after getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count || retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return true; } return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { if (!dentry) return; might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } while (lock_for_kill(dentry)) { rcu_read_unlock(); dentry = __dentry_kill(dentry); if (!dentry) return; if (retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return; } rcu_read_lock(); } rcu_read_unlock(); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(dput); static void to_shrink_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); to_shrink_list(dentry, list); spin_unlock(&dentry->d_lock); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); lockref_get(&alias->d_lockref); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { LIST_HEAD(dispose); struct dentry *dentry; spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) to_shrink_list(dentry, &dispose); spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); shrink_dentry_list(&dispose); } EXPORT_SYMBOL(d_prune_aliases); static inline void shrink_kill(struct dentry *victim) { do { rcu_read_unlock(); victim = __dentry_kill(victim); rcu_read_lock(); } while (victim && lock_for_kill(victim)); rcu_read_unlock(); if (victim) spin_unlock(&victim->d_lock); } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!lock_for_kill(dentry)) { bool can_free; rcu_read_unlock(); d_shrink_del(dentry); can_free = dentry->d_flags & DCACHE_DENTRY_KILLED; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } d_shrink_del(dentry); shrink_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add_obj and list_lru_del_obj. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent, *dentry; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: dentry = d_first_child(this_parent); resume: hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { dentry = this_parent; this_parent = dentry->d_parent; spin_unlock(&dentry->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ hlist_for_each_entry_continue(dentry, d_sib) { if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { rcu_read_unlock(); goto resume; } } goto ascend; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; write_seqlock(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: write_sequnlock(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_children list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else if (!dentry->d_lockref.count) { to_shrink_list(dentry, &data->dispose); data->found++; } else if (dentry->d_lockref.count < 0) { data->found++; } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (!dentry->d_lockref.count) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } to_shrink_list(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { spin_lock(&data.victim->d_lock); if (!lock_for_kill(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { shrink_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!hlist_empty(&dentry->d_children)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; WARN(1, "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; rwsem_assert_held_write(&sb->s_umount); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { *victim = dget_dlock(dentry); return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->u.count, 1); dname = p->name; } else { dname = dentry->d_iname; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = NULL; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_HLIST_HEAD(&dentry->d_children); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_HLIST_NODE(&dentry->d_sib); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ dentry->d_parent = dget_dlock(parent); hlist_add_head(&dentry->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) { dentry->d_flags |= DCACHE_NORCU; if (!sb->s_d_op) d_set_d_op(dentry, &anon_ops); } return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL(d_set_d_op); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct super_block *sb; struct dentry *new, *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); sb = inode->i_sb; res = d_find_any_alias(inode); /* existing alias? */ if (res) goto out; new = d_alloc_anon(sb); if (!new) { res = ERR_PTR(-ENOMEM); goto out; } security_d_instantiate(new, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); /* recheck under lock */ if (likely(!res)) { /* still no alias, attach a disconnected dentry */ unsigned add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&new->d_lock); __d_set_inode_and_type(new, inode, add_flags); hlist_add_head(&new->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&sb->s_roots); hlist_bl_add_head(&new->d_hash, &sb->s_roots); hlist_bl_unlock(&sb->s_roots); } spin_unlock(&new->d_lock); spin_unlock(&inode->i_lock); inode = NULL; /* consumed by new->d_inode */ res = new; } else { spin_unlock(&inode->i_lock); dput(new); } out: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @inode: the inode case-insensitive lookup has found * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name * @parent: parent dentry * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false */ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } EXPORT_SYMBOL_GPL(d_same_name); /* * This is __d_lookup_rcu() when the parent dentry has * DCACHE_OP_COMPARE, which makes things much nastier. */ static noinline struct dentry *__d_lookup_rcu_op_compare( const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { int tlen; const char *tname; unsigned seq; seqretry: seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * A refcount may be taken on the found dentry with the d_rcu_to_refcount * function. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) return __d_lookup_rcu_op_compare(parent, name, seqp); /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned int n, wait_queue_head_t *d_wait) { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); /* * - Unhash the dentry * - Retrieve and clear the waitqueue head in dentry * - Return the waitqueue head */ static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry) { wait_queue_head_t *d_wait; struct hlist_bl_head *b; lockdep_assert_held(&dentry->d_lock); b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); d_wait = dentry->d_wait; dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); return d_wait; } void __d_lookup_unhash_wake(struct dentry *dentry) { spin_lock(&dentry->d_lock); wake_up_all(__d_lookup_unhash(dentry)); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(__d_lookup_unhash_wake); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(dentry); } if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n, d_wait); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); /** * d_exact_alias - find and hash an exact unhashed alias * @entry: dentry to add * @inode: The inode to go with this dentry * * If an unhashed dentry with the same name/parent and desired * inode already exists, hash and return it. Otherwise, return * NULL. * * Parent directory should be locked. */ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) { struct dentry *alias; unsigned int hash = entry->d_name.hash; spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; if (!d_same_name(alias, entry->d_parent, &entry->d_name)) continue; spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { spin_unlock(&alias->d_lock); alias = NULL; } else { dget_dlock(alias); __d_rehash(alias); spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); return alias; } spin_unlock(&inode->i_lock); return NULL; } EXPORT_SYMBOL(d_exact_alias); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ memcpy(target->d_iname, dentry->d_name.name, dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; target->d_name.name = target->d_iname; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); target->d_name.name = dentry->d_name.name; dentry->d_name.name = dentry->d_iname; } else { /* * Both are internal. */ unsigned int i; BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { swap(((long *) &dentry->d_iname)[i], ((long *) &target->d_iname)[i]); } } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->u.count); dentry->d_name = target->d_name; } else { memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); dentry->d_name.name = dentry->d_iname; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) kfree_rcu(old_name, u.head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); if (!hlist_unhashed(&target->d_sib)) __hlist_del(&target->d_sib); hlist_add_head(&target->d_sib, &target->d_parent->d_children); __d_rehash(target); fsnotify_update_flags(target); } if (!hlist_unhashed(&dentry->d_sib)) __hlist_del(&dentry->d_sib); hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n, d_wait); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_mutex, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: __d_move(alias, dentry, false); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; BUG_ON(dentry->d_name.name != dentry->d_iname || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); } EXPORT_SYMBOL(d_mark_tmpfile); void d_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; inode_dec_link_count(inode); d_mark_tmpfile(file, inode); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); /* * Obtain inode number of the parent dentry. */ ino_t d_parent_ino(struct dentry *dentry) { struct dentry *parent; struct inode *iparent; unsigned seq; ino_t ret; scoped_guard(rcu) { seq = raw_seqcount_begin(&dentry->d_seq); parent = READ_ONCE(dentry->d_parent); iparent = d_inode_rcu(parent); if (likely(iparent)) { ret = iparent->i_ino; if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; } } spin_lock(&dentry->d_lock); ret = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(d_parent_ino); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_iname); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __ro_after_init; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 237 470 382 380 71 71 93 93 433 434 149 128 200 122 122 122 175 175 175 122 122 122 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include "messages.h" #include "ctree.h" #include "subpage.h" #include "btrfs_inode.h" /* * Subpage (sectorsize < PAGE_SIZE) support overview: * * Limitations: * * - Only support 64K page size for now * This is to make metadata handling easier, as 64K page would ensure * all nodesize would fit inside one page, thus we don't need to handle * cases where a tree block crosses several pages. * * - Only metadata read-write for now * The data read-write part is in development. * * - Metadata can't cross 64K page boundary * btrfs-progs and kernel have done that for a while, thus only ancient * filesystems could have such problem. For such case, do a graceful * rejection. * * Special behavior: * * - Metadata * Metadata read is fully supported. * Meaning when reading one tree block will only trigger the read for the * needed range, other unrelated range in the same page will not be touched. * * Metadata write support is partial. * The writeback is still for the full page, but we will only submit * the dirty extent buffers in the page. * * This means, if we have a metadata page like this: * * Page offset * 0 16K 32K 48K 64K * |/////////| |///////////| * \- Tree block A \- Tree block B * * Even if we just want to writeback tree block A, we will also writeback * tree block B if it's also dirty. * * This may cause extra metadata writeback which results more COW. * * Implementation: * * - Common * Both metadata and data will use a new structure, btrfs_subpage, to * record the status of each sector inside a page. This provides the extra * granularity needed. * * - Metadata * Since we have multiple tree blocks inside one page, we can't rely on page * locking anymore, or we will have greatly reduced concurrency or even * deadlocks (hold one tree lock while trying to lock another tree lock in * the same page). * * Thus for metadata locking, subpage support relies on io_tree locking only. * This means a slightly higher tree locking latency. */ bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info, struct address_space *mapping) { if (fs_info->sectorsize >= PAGE_SIZE) return false; /* * Only data pages (either through DIO or compression) can have no * mapping. And if page->mapping->host is data inode, it's subpage. * As we have ruled our sectorsize >= PAGE_SIZE case already. */ if (!mapping || !mapping->host || is_data_inode(BTRFS_I(mapping->host))) return true; /* * Now the only remaining case is metadata, which we only go subpage * routine if nodesize < PAGE_SIZE. */ if (fs_info->nodesize < PAGE_SIZE) return true; return false; } void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sectorsize) { unsigned int cur = 0; unsigned int nr_bits; ASSERT(IS_ALIGNED(PAGE_SIZE, sectorsize)); nr_bits = PAGE_SIZE / sectorsize; subpage_info->bitmap_nr_bits = nr_bits; subpage_info->uptodate_offset = cur; cur += nr_bits; subpage_info->dirty_offset = cur; cur += nr_bits; subpage_info->writeback_offset = cur; cur += nr_bits; subpage_info->ordered_offset = cur; cur += nr_bits; subpage_info->checked_offset = cur; cur += nr_bits; subpage_info->locked_offset = cur; cur += nr_bits; subpage_info->total_nr_bits = cur; } int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio, enum btrfs_subpage_type type) { struct btrfs_subpage *subpage; /* * We have cases like a dummy extent buffer page, which is not mapped * and doesn't need to be locked. */ if (folio->mapping) ASSERT(folio_test_locked(folio)); /* Either not subpage, or the folio already has private attached. */ if (!btrfs_is_subpage(fs_info, folio->mapping) || folio_test_private(folio)) return 0; subpage = btrfs_alloc_subpage(fs_info, type); if (IS_ERR(subpage)) return PTR_ERR(subpage); folio_attach_private(folio, subpage); return 0; } void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info, struct folio *folio) { struct btrfs_subpage *subpage; /* Either not subpage, or the folio already has private attached. */ if (!btrfs_is_subpage(fs_info, folio->mapping) || !folio_test_private(folio)) return; subpage = folio_detach_private(folio); ASSERT(subpage); btrfs_free_subpage(subpage); } struct btrfs_subpage *btrfs_alloc_subpage(const struct btrfs_fs_info *fs_info, enum btrfs_subpage_type type) { struct btrfs_subpage *ret; unsigned int real_size; ASSERT(fs_info->sectorsize < PAGE_SIZE); real_size = struct_size(ret, bitmaps, BITS_TO_LONGS(fs_info->subpage_info->total_nr_bits)); ret = kzalloc(real_size, GFP_NOFS); if (!ret) return ERR_PTR(-ENOMEM); spin_lock_init(&ret->lock); if (type == BTRFS_SUBPAGE_METADATA) { atomic_set(&ret->eb_refs, 0); } else { atomic_set(&ret->readers, 0); atomic_set(&ret->writers, 0); } return ret; } void btrfs_free_subpage(struct btrfs_subpage *subpage) { kfree(subpage); } /* * Increase the eb_refs of current subpage. * * This is important for eb allocation, to prevent race with last eb freeing * of the same page. * With the eb_refs increased before the eb inserted into radix tree, * detach_extent_buffer_page() won't detach the folio private while we're still * allocating the extent buffer. */ void btrfs_folio_inc_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio) { struct btrfs_subpage *subpage; if (!btrfs_is_subpage(fs_info, folio->mapping)) return; ASSERT(folio_test_private(folio) && folio->mapping); lockdep_assert_held(&folio->mapping->i_private_lock); subpage = folio_get_private(folio); atomic_inc(&subpage->eb_refs); } void btrfs_folio_dec_eb_refs(const struct btrfs_fs_info *fs_info, struct folio *folio) { struct btrfs_subpage *subpage; if (!btrfs_is_subpage(fs_info, folio->mapping)) return; ASSERT(folio_test_private(folio) && folio->mapping); lockdep_assert_held(&folio->mapping->i_private_lock); subpage = folio_get_private(folio); ASSERT(atomic_read(&subpage->eb_refs)); atomic_dec(&subpage->eb_refs); } static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { /* For subpage support, the folio must be single page. */ ASSERT(folio_order(folio) == 0); /* Basic checks */ ASSERT(folio_test_private(folio) && folio_get_private(folio)); ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && IS_ALIGNED(len, fs_info->sectorsize)); /* * The range check only works for mapped page, we can still have * unmapped page like dummy extent buffer pages. */ if (folio->mapping) ASSERT(folio_pos(folio) <= start && start + len <= folio_pos(folio) + PAGE_SIZE); } #define subpage_calc_start_bit(fs_info, folio, name, start, len) \ ({ \ unsigned int __start_bit; \ \ btrfs_subpage_assert(fs_info, folio, start, len); \ __start_bit = offset_in_page(start) >> fs_info->sectorsize_bits; \ __start_bit += fs_info->subpage_info->name##_offset; \ __start_bit; \ }) void btrfs_subpage_start_reader(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len); const int nbits = len >> fs_info->sectorsize_bits; unsigned long flags; btrfs_subpage_assert(fs_info, folio, start, len); spin_lock_irqsave(&subpage->lock, flags); /* * Even though it's just for reading the page, no one should have * locked the subpage range. */ ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); bitmap_set(subpage->bitmaps, start_bit, nbits); atomic_add(nbits, &subpage->readers); spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_end_reader(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len); const int nbits = len >> fs_info->sectorsize_bits; unsigned long flags; bool is_data; bool last; btrfs_subpage_assert(fs_info, folio, start, len); is_data = is_data_inode(BTRFS_I(folio->mapping->host)); spin_lock_irqsave(&subpage->lock, flags); /* The range should have already been locked. */ ASSERT(bitmap_test_range_all_set(subpage->bitmaps, start_bit, nbits)); ASSERT(atomic_read(&subpage->readers) >= nbits); bitmap_clear(subpage->bitmaps, start_bit, nbits); last = atomic_sub_and_test(nbits, &subpage->readers); /* * For data we need to unlock the page if the last read has finished. * * And please don't replace @last with atomic_sub_and_test() call * inside if () condition. * As we want the atomic_sub_and_test() to be always executed. */ if (is_data && last) folio_unlock(folio); spin_unlock_irqrestore(&subpage->lock, flags); } static void btrfs_subpage_clamp_range(struct folio *folio, u64 *start, u32 *len) { u64 orig_start = *start; u32 orig_len = *len; *start = max_t(u64, folio_pos(folio), orig_start); /* * For certain call sites like btrfs_drop_pages(), we may have pages * beyond the target range. In that case, just set @len to 0, subpage * helpers can handle @len == 0 without any problem. */ if (folio_pos(folio) >= orig_start + orig_len) *len = 0; else *len = min_t(u64, folio_pos(folio) + PAGE_SIZE, orig_start + orig_len) - *start; } static void btrfs_subpage_start_writer(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len); const int nbits = (len >> fs_info->sectorsize_bits); unsigned long flags; int ret; btrfs_subpage_assert(fs_info, folio, start, len); spin_lock_irqsave(&subpage->lock, flags); ASSERT(atomic_read(&subpage->readers) == 0); ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); bitmap_set(subpage->bitmaps, start_bit, nbits); ret = atomic_add_return(nbits, &subpage->writers); ASSERT(ret == nbits); spin_unlock_irqrestore(&subpage->lock, flags); } static bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); const int start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len); const int nbits = (len >> fs_info->sectorsize_bits); unsigned long flags; bool last; btrfs_subpage_assert(fs_info, folio, start, len); spin_lock_irqsave(&subpage->lock, flags); /* * We have call sites passing @lock_page into * extent_clear_unlock_delalloc() for compression path. * * This @locked_page is locked by plain lock_page(), thus its * subpage::writers is 0. Handle them in a special way. */ if (atomic_read(&subpage->writers) == 0) { spin_unlock_irqrestore(&subpage->lock, flags); return true; } ASSERT(atomic_read(&subpage->writers) >= nbits); /* The target range should have been locked. */ ASSERT(bitmap_test_range_all_set(subpage->bitmaps, start_bit, nbits)); bitmap_clear(subpage->bitmaps, start_bit, nbits); last = atomic_sub_and_test(nbits, &subpage->writers); spin_unlock_irqrestore(&subpage->lock, flags); return last; } /* * Lock a folio for delalloc page writeback. * * Return -EAGAIN if the page is not properly initialized. * Return 0 with the page locked, and writer counter updated. * * Even with 0 returned, the page still need extra check to make sure * it's really the correct page, as the caller is using * filemap_get_folios_contig(), which can race with page invalidating. */ int btrfs_folio_start_writer_lock(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, folio->mapping)) { folio_lock(folio); return 0; } folio_lock(folio); if (!folio_test_private(folio) || !folio_get_private(folio)) { folio_unlock(folio); return -EAGAIN; } btrfs_subpage_clamp_range(folio, &start, &len); btrfs_subpage_start_writer(fs_info, folio, start, len); return 0; } void btrfs_folio_end_writer_lock(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, folio->mapping)) { folio_unlock(folio); return; } btrfs_subpage_clamp_range(folio, &start, &len); if (btrfs_subpage_end_and_test_writer(fs_info, folio, start, len)) folio_unlock(folio); } #define subpage_test_bitmap_all_set(fs_info, subpage, name) \ bitmap_test_range_all_set(subpage->bitmaps, \ fs_info->subpage_info->name##_offset, \ fs_info->subpage_info->bitmap_nr_bits) #define subpage_test_bitmap_all_zero(fs_info, subpage, name) \ bitmap_test_range_all_zero(subpage->bitmaps, \ fs_info->subpage_info->name##_offset, \ fs_info->subpage_info->bitmap_nr_bits) void btrfs_subpage_set_uptodate(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, uptodate, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); if (subpage_test_bitmap_all_set(fs_info, subpage, uptodate)) folio_mark_uptodate(folio); spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_clear_uptodate(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, uptodate, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); folio_clear_uptodate(folio); spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_set_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, dirty, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); spin_unlock_irqrestore(&subpage->lock, flags); folio_mark_dirty(folio); } /* * Extra clear_and_test function for subpage dirty bitmap. * * Return true if we're the last bits in the dirty_bitmap and clear the * dirty_bitmap. * Return false otherwise. * * NOTE: Callers should manually clear page dirty for true case, as we have * extra handling for tree blocks. */ bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, dirty, start, len); unsigned long flags; bool last = false; spin_lock_irqsave(&subpage->lock, flags); bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); if (subpage_test_bitmap_all_zero(fs_info, subpage, dirty)) last = true; spin_unlock_irqrestore(&subpage->lock, flags); return last; } void btrfs_subpage_clear_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { bool last; last = btrfs_subpage_clear_and_test_dirty(fs_info, folio, start, len); if (last) folio_clear_dirty_for_io(folio); } void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, writeback, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); if (!folio_test_writeback(folio)) folio_start_writeback(folio); spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_clear_writeback(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, writeback, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); if (subpage_test_bitmap_all_zero(fs_info, subpage, writeback)) { ASSERT(folio_test_writeback(folio)); folio_end_writeback(folio); } spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_set_ordered(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, ordered, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); folio_set_ordered(folio); spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_clear_ordered(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, ordered, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); if (subpage_test_bitmap_all_zero(fs_info, subpage, ordered)) folio_clear_ordered(folio); spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_set_checked(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, checked, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_set(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); if (subpage_test_bitmap_all_set(fs_info, subpage, checked)) folio_set_checked(folio); spin_unlock_irqrestore(&subpage->lock, flags); } void btrfs_subpage_clear_checked(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage = folio_get_private(folio); unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, checked, start, len); unsigned long flags; spin_lock_irqsave(&subpage->lock, flags); bitmap_clear(subpage->bitmaps, start_bit, len >> fs_info->sectorsize_bits); folio_clear_checked(folio); spin_unlock_irqrestore(&subpage->lock, flags); } /* * Unlike set/clear which is dependent on each page status, for test all bits * are tested in the same way. */ #define IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(name) \ bool btrfs_subpage_test_##name(const struct btrfs_fs_info *fs_info, \ struct folio *folio, u64 start, u32 len) \ { \ struct btrfs_subpage *subpage = folio_get_private(folio); \ unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, \ name, start, len); \ unsigned long flags; \ bool ret; \ \ spin_lock_irqsave(&subpage->lock, flags); \ ret = bitmap_test_range_all_set(subpage->bitmaps, start_bit, \ len >> fs_info->sectorsize_bits); \ spin_unlock_irqrestore(&subpage->lock, flags); \ return ret; \ } IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(uptodate); IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(dirty); IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(writeback); IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(ordered); IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(checked); /* * Note that, in selftests (extent-io-tests), we can have empty fs_info passed * in. We only test sectorsize == PAGE_SIZE cases so far, thus we can fall * back to regular sectorsize branch. */ #define IMPLEMENT_BTRFS_PAGE_OPS(name, folio_set_func, \ folio_clear_func, folio_test_func) \ void btrfs_folio_set_##name(const struct btrfs_fs_info *fs_info, \ struct folio *folio, u64 start, u32 len) \ { \ if (unlikely(!fs_info) || \ !btrfs_is_subpage(fs_info, folio->mapping)) { \ folio_set_func(folio); \ return; \ } \ btrfs_subpage_set_##name(fs_info, folio, start, len); \ } \ void btrfs_folio_clear_##name(const struct btrfs_fs_info *fs_info, \ struct folio *folio, u64 start, u32 len) \ { \ if (unlikely(!fs_info) || \ !btrfs_is_subpage(fs_info, folio->mapping)) { \ folio_clear_func(folio); \ return; \ } \ btrfs_subpage_clear_##name(fs_info, folio, start, len); \ } \ bool btrfs_folio_test_##name(const struct btrfs_fs_info *fs_info, \ struct folio *folio, u64 start, u32 len) \ { \ if (unlikely(!fs_info) || \ !btrfs_is_subpage(fs_info, folio->mapping)) \ return folio_test_func(folio); \ return btrfs_subpage_test_##name(fs_info, folio, start, len); \ } \ void btrfs_folio_clamp_set_##name(const struct btrfs_fs_info *fs_info, \ struct folio *folio, u64 start, u32 len) \ { \ if (unlikely(!fs_info) || \ !btrfs_is_subpage(fs_info, folio->mapping)) { \ folio_set_func(folio); \ return; \ } \ btrfs_subpage_clamp_range(folio, &start, &len); \ btrfs_subpage_set_##name(fs_info, folio, start, len); \ } \ void btrfs_folio_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \ struct folio *folio, u64 start, u32 len) \ { \ if (unlikely(!fs_info) || \ !btrfs_is_subpage(fs_info, folio->mapping)) { \ folio_clear_func(folio); \ return; \ } \ btrfs_subpage_clamp_range(folio, &start, &len); \ btrfs_subpage_clear_##name(fs_info, folio, start, len); \ } \ bool btrfs_folio_clamp_test_##name(const struct btrfs_fs_info *fs_info, \ struct folio *folio, u64 start, u32 len) \ { \ if (unlikely(!fs_info) || \ !btrfs_is_subpage(fs_info, folio->mapping)) \ return folio_test_func(folio); \ btrfs_subpage_clamp_range(folio, &start, &len); \ return btrfs_subpage_test_##name(fs_info, folio, start, len); \ } IMPLEMENT_BTRFS_PAGE_OPS(uptodate, folio_mark_uptodate, folio_clear_uptodate, folio_test_uptodate); IMPLEMENT_BTRFS_PAGE_OPS(dirty, folio_mark_dirty, folio_clear_dirty_for_io, folio_test_dirty); IMPLEMENT_BTRFS_PAGE_OPS(writeback, folio_start_writeback, folio_end_writeback, folio_test_writeback); IMPLEMENT_BTRFS_PAGE_OPS(ordered, folio_set_ordered, folio_clear_ordered, folio_test_ordered); IMPLEMENT_BTRFS_PAGE_OPS(checked, folio_set_checked, folio_clear_checked, folio_test_checked); /* * Make sure not only the page dirty bit is cleared, but also subpage dirty bit * is cleared. */ void btrfs_folio_assert_not_dirty(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage; unsigned int start_bit; unsigned int nbits; unsigned long flags; if (!IS_ENABLED(CONFIG_BTRFS_ASSERT)) return; if (!btrfs_is_subpage(fs_info, folio->mapping)) { ASSERT(!folio_test_dirty(folio)); return; } start_bit = subpage_calc_start_bit(fs_info, folio, dirty, start, len); nbits = len >> fs_info->sectorsize_bits; subpage = folio_get_private(folio); ASSERT(subpage); spin_lock_irqsave(&subpage->lock, flags); ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); spin_unlock_irqrestore(&subpage->lock, flags); } /* * Handle different locked pages with different page sizes: * * - Page locked by plain lock_page() * It should not have any subpage::writers count. * Can be unlocked by unlock_page(). * This is the most common locked page for __extent_writepage() called * inside extent_write_cache_pages(). * Rarer cases include the @locked_page from extent_write_locked_range(). * * - Page locked by lock_delalloc_pages() * There is only one caller, all pages except @locked_page for * extent_write_locked_range(). * In this case, we have to call subpage helper to handle the case. */ void btrfs_folio_unlock_writer(struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage; ASSERT(folio_test_locked(folio)); /* For non-subpage case, we just unlock the page */ if (!btrfs_is_subpage(fs_info, folio->mapping)) { folio_unlock(folio); return; } ASSERT(folio_test_private(folio) && folio_get_private(folio)); subpage = folio_get_private(folio); /* * For subpage case, there are two types of locked page. With or * without writers number. * * Since we own the page lock, no one else could touch subpage::writers * and we are safe to do several atomic operations without spinlock. */ if (atomic_read(&subpage->writers) == 0) { /* No writers, locked by plain lock_page() */ folio_unlock(folio); return; } /* Have writers, use proper subpage helper to end it */ btrfs_folio_end_writer_lock(fs_info, folio, start, len); } /* * This is for folio already locked by plain lock_page()/folio_lock(), which * doesn't have any subpage awareness. * * This populates the involved subpage ranges so that subpage helpers can * properly unlock them. */ void btrfs_folio_set_writer_lock(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage *subpage; unsigned long flags; unsigned int start_bit; unsigned int nbits; int ret; ASSERT(folio_test_locked(folio)); if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, folio->mapping)) return; subpage = folio_get_private(folio); start_bit = subpage_calc_start_bit(fs_info, folio, locked, start, len); nbits = len >> fs_info->sectorsize_bits; spin_lock_irqsave(&subpage->lock, flags); /* Target range should not yet be locked. */ ASSERT(bitmap_test_range_all_zero(subpage->bitmaps, start_bit, nbits)); bitmap_set(subpage->bitmaps, start_bit, nbits); ret = atomic_add_return(nbits, &subpage->writers); ASSERT(ret <= fs_info->subpage_info->bitmap_nr_bits); spin_unlock_irqrestore(&subpage->lock, flags); } /* * Find any subpage writer locked range inside @folio, starting at file offset * @search_start. The caller should ensure the folio is locked. * * Return true and update @found_start_ret and @found_len_ret to the first * writer locked range. * Return false if there is no writer locked range. */ bool btrfs_subpage_find_writer_locked(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 search_start, u64 *found_start_ret, u32 *found_len_ret) { struct btrfs_subpage_info *subpage_info = fs_info->subpage_info; struct btrfs_subpage *subpage = folio_get_private(folio); const unsigned int len = PAGE_SIZE - offset_in_page(search_start); const unsigned int start_bit = subpage_calc_start_bit(fs_info, folio, locked, search_start, len); const unsigned int locked_bitmap_start = subpage_info->locked_offset; const unsigned int locked_bitmap_end = locked_bitmap_start + subpage_info->bitmap_nr_bits; unsigned long flags; int first_zero; int first_set; bool found = false; ASSERT(folio_test_locked(folio)); spin_lock_irqsave(&subpage->lock, flags); first_set = find_next_bit(subpage->bitmaps, locked_bitmap_end, start_bit); if (first_set >= locked_bitmap_end) goto out; found = true; *found_start_ret = folio_pos(folio) + ((first_set - locked_bitmap_start) << fs_info->sectorsize_bits); /* * Since @first_set is ensured to be smaller than locked_bitmap_end * here, @found_start_ret should be inside the folio. */ ASSERT(*found_start_ret < folio_pos(folio) + PAGE_SIZE); first_zero = find_next_zero_bit(subpage->bitmaps, locked_bitmap_end, first_set); *found_len_ret = (first_zero - first_set) << fs_info->sectorsize_bits; out: spin_unlock_irqrestore(&subpage->lock, flags); return found; } /* * Unlike btrfs_folio_end_writer_lock() which unlocks a specified subpage range, * this ends all writer locked ranges of a page. * * This is for the locked page of __extent_writepage(), as the locked page * can contain several locked subpage ranges. */ void btrfs_folio_end_all_writers(const struct btrfs_fs_info *fs_info, struct folio *folio) { struct btrfs_subpage *subpage = folio_get_private(folio); u64 folio_start = folio_pos(folio); u64 cur = folio_start; ASSERT(folio_test_locked(folio)); if (!btrfs_is_subpage(fs_info, folio->mapping)) { folio_unlock(folio); return; } /* The page has no new delalloc range locked on it. Just plain unlock. */ if (atomic_read(&subpage->writers) == 0) { folio_unlock(folio); return; } while (cur < folio_start + PAGE_SIZE) { u64 found_start; u32 found_len; bool found; bool last; found = btrfs_subpage_find_writer_locked(fs_info, folio, cur, &found_start, &found_len); if (!found) break; last = btrfs_subpage_end_and_test_writer(fs_info, folio, found_start, found_len); if (last) { folio_unlock(folio); break; } cur = found_start + found_len; } } #define GET_SUBPAGE_BITMAP(subpage, subpage_info, name, dst) \ bitmap_cut(dst, subpage->bitmaps, 0, \ subpage_info->name##_offset, subpage_info->bitmap_nr_bits) void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info, struct folio *folio, u64 start, u32 len) { struct btrfs_subpage_info *subpage_info = fs_info->subpage_info; struct btrfs_subpage *subpage; unsigned long uptodate_bitmap; unsigned long dirty_bitmap; unsigned long writeback_bitmap; unsigned long ordered_bitmap; unsigned long checked_bitmap; unsigned long flags; ASSERT(folio_test_private(folio) && folio_get_private(folio)); ASSERT(subpage_info); subpage = folio_get_private(folio); spin_lock_irqsave(&subpage->lock, flags); GET_SUBPAGE_BITMAP(subpage, subpage_info, uptodate, &uptodate_bitmap); GET_SUBPAGE_BITMAP(subpage, subpage_info, dirty, &dirty_bitmap); GET_SUBPAGE_BITMAP(subpage, subpage_info, writeback, &writeback_bitmap); GET_SUBPAGE_BITMAP(subpage, subpage_info, ordered, &ordered_bitmap); GET_SUBPAGE_BITMAP(subpage, subpage_info, checked, &checked_bitmap); GET_SUBPAGE_BITMAP(subpage, subpage_info, locked, &checked_bitmap); spin_unlock_irqrestore(&subpage->lock, flags); dump_page(folio_page(folio, 0), "btrfs subpage dump"); btrfs_warn(fs_info, "start=%llu len=%u page=%llu, bitmaps uptodate=%*pbl dirty=%*pbl writeback=%*pbl ordered=%*pbl checked=%*pbl", start, len, folio_pos(folio), subpage_info->bitmap_nr_bits, &uptodate_bitmap, subpage_info->bitmap_nr_bits, &dirty_bitmap, subpage_info->bitmap_nr_bits, &writeback_bitmap, subpage_info->bitmap_nr_bits, &ordered_bitmap, subpage_info->bitmap_nr_bits, &checked_bitmap); } |
| 89 128 19 162 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_POLL_H #define _LINUX_POLL_H #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #define MAX_STACK_ALLOC 832 #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC #define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) #define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) #define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM) struct poll_table_struct; /* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* * Do not touch the structure directly, use the access functions * poll_does_not_wait() and poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; __poll_t _key; } poll_table; static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { if (p && p->_qproc && wait_address) p->_qproc(filp, wait_address, p); } /* * Return true if it is guaranteed that poll will not wait. This is the case * if the poll() of another file descriptor in the set got an event, so there * is no need for waiting. */ static inline bool poll_does_not_wait(const poll_table *p) { return p == NULL || p->_qproc == NULL; } /* * Return the set of events that the application wants to poll for. * This is useful for drivers that need to know whether a DMA transfer has * to be started implicitly on poll(). You typically only want to do that * if the application is actually polling for POLLIN and/or POLLOUT. */ static inline __poll_t poll_requested_events(const poll_table *p) { return p ? p->_key : ~(__poll_t)0; } static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) { pt->_qproc = qproc; pt->_key = ~(__poll_t)0; /* all events enabled */ } static inline bool file_can_poll(struct file *file) { return file->f_op->poll; } static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) { if (unlikely(!file->f_op->poll)) return DEFAULT_POLLMASK; return file->f_op->poll(file, pt); } struct poll_table_entry { struct file *filp; __poll_t key; wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; /* * Structures and helpers for select/poll syscall */ struct poll_wqueues { poll_table pt; struct poll_table_page *table; struct task_struct *polling_task; int triggered; int error; int inline_index; struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; }; extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern u64 select_estimate_accuracy(struct timespec64 *tv); #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time); extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec); #define __MAP(v, from, to) \ (from < to ? (v & from) * (to/from) : (v & from) / (from/to)) static inline __u16 mangle_poll(__poll_t val) { __u16 v = (__force __u16)val; #define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } static inline __poll_t demangle_poll(u16 val) { #define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } #undef __MAP #endif /* _LINUX_POLL_H */ |
| 1 1 1 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 | /* $Id: capi.c,v 1.1.2.7 2004/04/28 09:48:59 armin Exp $ * * CAPI 2.0 Interface for Linux * * Copyright 1996 by Carsten Paeth <calle@calle.de> * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. * */ #include <linux/compiler.h> #include <linux/module.h> #include <linux/ethtool.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/fcntl.h> #include <linux/fs.h> #include <linux/signal.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/tty.h> #include <linux/netdevice.h> #include <linux/ppp_defs.h> #include <linux/ppp-ioctl.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/capi.h> #include <linux/kernelcapi.h> #include <linux/init.h> #include <linux/device.h> #include <linux/moduleparam.h> #include <linux/isdn/capiutil.h> #include <linux/isdn/capicmd.h> #include "kcapi.h" MODULE_DESCRIPTION("CAPI4Linux: kernel CAPI layer and /dev/capi20 interface"); MODULE_AUTHOR("Carsten Paeth"); MODULE_LICENSE("GPL"); /* -------- driver information -------------------------------------- */ static DEFINE_MUTEX(capi_mutex); static const struct class capi_class = { .name = "capi", }; static int capi_major = 68; /* allocated */ module_param_named(major, capi_major, uint, 0); #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE #define CAPINC_NR_PORTS 32 #define CAPINC_MAX_PORTS 256 static int capi_ttyminors = CAPINC_NR_PORTS; module_param_named(ttyminors, capi_ttyminors, uint, 0); #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */ /* -------- defines ------------------------------------------------- */ #define CAPINC_MAX_RECVQUEUE 10 #define CAPINC_MAX_SENDQUEUE 10 #define CAPI_MAX_BLKSIZE 2048 /* -------- data structures ----------------------------------------- */ struct capidev; struct capincci; struct capiminor; struct ackqueue_entry { struct list_head list; u16 datahandle; }; struct capiminor { unsigned int minor; struct capi20_appl *ap; u32 ncci; atomic_t datahandle; atomic_t msgid; struct tty_port port; int ttyinstop; int ttyoutstop; struct sk_buff_head inqueue; struct sk_buff_head outqueue; int outbytes; struct sk_buff *outskb; spinlock_t outlock; /* transmit path */ struct list_head ackqueue; int nack; spinlock_t ackqlock; }; struct capincci { struct list_head list; u32 ncci; struct capidev *cdev; #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE struct capiminor *minorp; #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */ }; struct capidev { struct list_head list; struct capi20_appl ap; u16 errcode; unsigned userflags; struct sk_buff_head recvqueue; wait_queue_head_t recvwait; struct list_head nccis; struct mutex lock; }; /* -------- global variables ---------------------------------------- */ static DEFINE_MUTEX(capidev_list_lock); static LIST_HEAD(capidev_list); #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE static DEFINE_SPINLOCK(capiminors_lock); static struct capiminor **capiminors; static struct tty_driver *capinc_tty_driver; /* -------- datahandles --------------------------------------------- */ static int capiminor_add_ack(struct capiminor *mp, u16 datahandle) { struct ackqueue_entry *n; n = kmalloc(sizeof(*n), GFP_ATOMIC); if (unlikely(!n)) { printk(KERN_ERR "capi: alloc datahandle failed\n"); return -1; } n->datahandle = datahandle; INIT_LIST_HEAD(&n->list); spin_lock_bh(&mp->ackqlock); list_add_tail(&n->list, &mp->ackqueue); mp->nack++; spin_unlock_bh(&mp->ackqlock); return 0; } static int capiminor_del_ack(struct capiminor *mp, u16 datahandle) { struct ackqueue_entry *p, *tmp; spin_lock_bh(&mp->ackqlock); list_for_each_entry_safe(p, tmp, &mp->ackqueue, list) { if (p->datahandle == datahandle) { list_del(&p->list); mp->nack--; spin_unlock_bh(&mp->ackqlock); kfree(p); return 0; } } spin_unlock_bh(&mp->ackqlock); return -1; } static void capiminor_del_all_ack(struct capiminor *mp) { struct ackqueue_entry *p, *tmp; list_for_each_entry_safe(p, tmp, &mp->ackqueue, list) { list_del(&p->list); kfree(p); mp->nack--; } } /* -------- struct capiminor ---------------------------------------- */ static void capiminor_destroy(struct tty_port *port) { struct capiminor *mp = container_of(port, struct capiminor, port); kfree_skb(mp->outskb); skb_queue_purge(&mp->inqueue); skb_queue_purge(&mp->outqueue); capiminor_del_all_ack(mp); kfree(mp); } static const struct tty_port_operations capiminor_port_ops = { .destruct = capiminor_destroy, }; static struct capiminor *capiminor_alloc(struct capi20_appl *ap, u32 ncci) { struct capiminor *mp; struct device *dev; unsigned int minor; mp = kzalloc(sizeof(*mp), GFP_KERNEL); if (!mp) { printk(KERN_ERR "capi: can't alloc capiminor\n"); return NULL; } mp->ap = ap; mp->ncci = ncci; INIT_LIST_HEAD(&mp->ackqueue); spin_lock_init(&mp->ackqlock); skb_queue_head_init(&mp->inqueue); skb_queue_head_init(&mp->outqueue); spin_lock_init(&mp->outlock); tty_port_init(&mp->port); mp->port.ops = &capiminor_port_ops; /* Allocate the least unused minor number. */ spin_lock(&capiminors_lock); for (minor = 0; minor < capi_ttyminors; minor++) if (!capiminors[minor]) { capiminors[minor] = mp; break; } spin_unlock(&capiminors_lock); if (minor == capi_ttyminors) { printk(KERN_NOTICE "capi: out of minors\n"); goto err_out1; } mp->minor = minor; dev = tty_port_register_device(&mp->port, capinc_tty_driver, minor, NULL); if (IS_ERR(dev)) goto err_out2; return mp; err_out2: spin_lock(&capiminors_lock); capiminors[minor] = NULL; spin_unlock(&capiminors_lock); err_out1: tty_port_put(&mp->port); return NULL; } static struct capiminor *capiminor_get(unsigned int minor) { struct capiminor *mp; spin_lock(&capiminors_lock); mp = capiminors[minor]; if (mp) tty_port_get(&mp->port); spin_unlock(&capiminors_lock); return mp; } static inline void capiminor_put(struct capiminor *mp) { tty_port_put(&mp->port); } static void capiminor_free(struct capiminor *mp) { tty_unregister_device(capinc_tty_driver, mp->minor); spin_lock(&capiminors_lock); capiminors[mp->minor] = NULL; spin_unlock(&capiminors_lock); capiminor_put(mp); } /* -------- struct capincci ----------------------------------------- */ static void capincci_alloc_minor(struct capidev *cdev, struct capincci *np) { if (cdev->userflags & CAPIFLAG_HIGHJACKING) np->minorp = capiminor_alloc(&cdev->ap, np->ncci); } static void capincci_free_minor(struct capincci *np) { struct capiminor *mp = np->minorp; struct tty_struct *tty; if (mp) { tty = tty_port_tty_get(&mp->port); if (tty) { tty_vhangup(tty); tty_kref_put(tty); } capiminor_free(mp); } } static inline unsigned int capincci_minor_opencount(struct capincci *np) { struct capiminor *mp = np->minorp; unsigned int count = 0; struct tty_struct *tty; if (mp) { tty = tty_port_tty_get(&mp->port); if (tty) { count = tty->count; tty_kref_put(tty); } } return count; } #else /* !CONFIG_ISDN_CAPI_MIDDLEWARE */ static inline void capincci_alloc_minor(struct capidev *cdev, struct capincci *np) { } static inline void capincci_free_minor(struct capincci *np) { } #endif /* !CONFIG_ISDN_CAPI_MIDDLEWARE */ static struct capincci *capincci_alloc(struct capidev *cdev, u32 ncci) { struct capincci *np; np = kzalloc(sizeof(*np), GFP_KERNEL); if (!np) return NULL; np->ncci = ncci; np->cdev = cdev; capincci_alloc_minor(cdev, np); list_add_tail(&np->list, &cdev->nccis); return np; } static void capincci_free(struct capidev *cdev, u32 ncci) { struct capincci *np, *tmp; list_for_each_entry_safe(np, tmp, &cdev->nccis, list) if (ncci == 0xffffffff || np->ncci == ncci) { capincci_free_minor(np); list_del(&np->list); kfree(np); } } #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE static struct capincci *capincci_find(struct capidev *cdev, u32 ncci) { struct capincci *np; list_for_each_entry(np, &cdev->nccis, list) if (np->ncci == ncci) return np; return NULL; } /* -------- handle data queue --------------------------------------- */ static struct sk_buff * gen_data_b3_resp_for(struct capiminor *mp, struct sk_buff *skb) { struct sk_buff *nskb; nskb = alloc_skb(CAPI_DATA_B3_RESP_LEN, GFP_KERNEL); if (nskb) { u16 datahandle = CAPIMSG_U16(skb->data, CAPIMSG_BASELEN + 4 + 4 + 2); unsigned char *s = skb_put(nskb, CAPI_DATA_B3_RESP_LEN); capimsg_setu16(s, 0, CAPI_DATA_B3_RESP_LEN); capimsg_setu16(s, 2, mp->ap->applid); capimsg_setu8 (s, 4, CAPI_DATA_B3); capimsg_setu8 (s, 5, CAPI_RESP); capimsg_setu16(s, 6, atomic_inc_return(&mp->msgid)); capimsg_setu32(s, 8, mp->ncci); capimsg_setu16(s, 12, datahandle); } return nskb; } static int handle_recv_skb(struct capiminor *mp, struct sk_buff *skb) { unsigned int datalen = skb->len - CAPIMSG_LEN(skb->data); struct tty_struct *tty; struct sk_buff *nskb; u16 errcode, datahandle; struct tty_ldisc *ld; int ret = -1; tty = tty_port_tty_get(&mp->port); if (!tty) { pr_debug("capi: currently no receiver\n"); return -1; } ld = tty_ldisc_ref(tty); if (!ld) { /* fatal error, do not requeue */ ret = 0; kfree_skb(skb); goto deref_tty; } if (ld->ops->receive_buf == NULL) { pr_debug("capi: ldisc has no receive_buf function\n"); /* fatal error, do not requeue */ goto free_skb; } if (mp->ttyinstop) { pr_debug("capi: recv tty throttled\n"); goto deref_ldisc; } if (tty->receive_room < datalen) { pr_debug("capi: no room in tty\n"); goto deref_ldisc; } nskb = gen_data_b3_resp_for(mp, skb); if (!nskb) { printk(KERN_ERR "capi: gen_data_b3_resp failed\n"); goto deref_ldisc; } datahandle = CAPIMSG_U16(skb->data, CAPIMSG_BASELEN + 4); errcode = capi20_put_message(mp->ap, nskb); if (errcode == CAPI_NOERROR) { skb_pull(skb, CAPIMSG_LEN(skb->data)); pr_debug("capi: DATA_B3_RESP %u len=%d => ldisc\n", datahandle, skb->len); ld->ops->receive_buf(tty, skb->data, NULL, skb->len); } else { printk(KERN_ERR "capi: send DATA_B3_RESP failed=%x\n", errcode); kfree_skb(nskb); if (errcode == CAPI_SENDQUEUEFULL) goto deref_ldisc; } free_skb: ret = 0; kfree_skb(skb); deref_ldisc: tty_ldisc_deref(ld); deref_tty: tty_kref_put(tty); return ret; } static void handle_minor_recv(struct capiminor *mp) { struct sk_buff *skb; while ((skb = skb_dequeue(&mp->inqueue)) != NULL) if (handle_recv_skb(mp, skb) < 0) { skb_queue_head(&mp->inqueue, skb); return; } } static void handle_minor_send(struct capiminor *mp) { struct tty_struct *tty; struct sk_buff *skb; u16 len; u16 errcode; u16 datahandle; tty = tty_port_tty_get(&mp->port); if (!tty) return; if (mp->ttyoutstop) { pr_debug("capi: send: tty stopped\n"); tty_kref_put(tty); return; } while (1) { spin_lock_bh(&mp->outlock); skb = __skb_dequeue(&mp->outqueue); if (!skb) { spin_unlock_bh(&mp->outlock); break; } len = (u16)skb->len; mp->outbytes -= len; spin_unlock_bh(&mp->outlock); datahandle = atomic_inc_return(&mp->datahandle); skb_push(skb, CAPI_DATA_B3_REQ_LEN); memset(skb->data, 0, CAPI_DATA_B3_REQ_LEN); capimsg_setu16(skb->data, 0, CAPI_DATA_B3_REQ_LEN); capimsg_setu16(skb->data, 2, mp->ap->applid); capimsg_setu8 (skb->data, 4, CAPI_DATA_B3); capimsg_setu8 (skb->data, 5, CAPI_REQ); capimsg_setu16(skb->data, 6, atomic_inc_return(&mp->msgid)); capimsg_setu32(skb->data, 8, mp->ncci); /* NCCI */ capimsg_setu32(skb->data, 12, (u32)(long)skb->data);/* Data32 */ capimsg_setu16(skb->data, 16, len); /* Data length */ capimsg_setu16(skb->data, 18, datahandle); capimsg_setu16(skb->data, 20, 0); /* Flags */ if (capiminor_add_ack(mp, datahandle) < 0) { skb_pull(skb, CAPI_DATA_B3_REQ_LEN); spin_lock_bh(&mp->outlock); __skb_queue_head(&mp->outqueue, skb); mp->outbytes += len; spin_unlock_bh(&mp->outlock); break; } errcode = capi20_put_message(mp->ap, skb); if (errcode == CAPI_NOERROR) { pr_debug("capi: DATA_B3_REQ %u len=%u\n", datahandle, len); continue; } capiminor_del_ack(mp, datahandle); if (errcode == CAPI_SENDQUEUEFULL) { skb_pull(skb, CAPI_DATA_B3_REQ_LEN); spin_lock_bh(&mp->outlock); __skb_queue_head(&mp->outqueue, skb); mp->outbytes += len; spin_unlock_bh(&mp->outlock); break; } /* ups, drop packet */ printk(KERN_ERR "capi: put_message = %x\n", errcode); kfree_skb(skb); } tty_kref_put(tty); } #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */ /* -------- function called by lower level -------------------------- */ static void capi_recv_message(struct capi20_appl *ap, struct sk_buff *skb) { struct capidev *cdev = ap->private; #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE struct capiminor *mp; u16 datahandle; struct capincci *np; #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */ mutex_lock(&cdev->lock); if (CAPIMSG_CMD(skb->data) == CAPI_CONNECT_B3_CONF) { u16 info = CAPIMSG_U16(skb->data, 12); // Info field if ((info & 0xff00) == 0) capincci_alloc(cdev, CAPIMSG_NCCI(skb->data)); } if (CAPIMSG_CMD(skb->data) == CAPI_CONNECT_B3_IND) capincci_alloc(cdev, CAPIMSG_NCCI(skb->data)); if (CAPIMSG_COMMAND(skb->data) != CAPI_DATA_B3) { skb_queue_tail(&cdev->recvqueue, skb); wake_up_interruptible(&cdev->recvwait); goto unlock_out; } #ifndef CONFIG_ISDN_CAPI_MIDDLEWARE skb_queue_tail(&cdev->recvqueue, skb); wake_up_interruptible(&cdev->recvwait); #else /* CONFIG_ISDN_CAPI_MIDDLEWARE */ np = capincci_find(cdev, CAPIMSG_CONTROL(skb->data)); if (!np) { printk(KERN_ERR "BUG: capi_signal: ncci not found\n"); skb_queue_tail(&cdev->recvqueue, skb); wake_up_interruptible(&cdev->recvwait); goto unlock_out; } mp = np->minorp; if (!mp) { skb_queue_tail(&cdev->recvqueue, skb); wake_up_interruptible(&cdev->recvwait); goto unlock_out; } if (CAPIMSG_SUBCOMMAND(skb->data) == CAPI_IND) { datahandle = CAPIMSG_U16(skb->data, CAPIMSG_BASELEN + 4 + 4 + 2); pr_debug("capi_signal: DATA_B3_IND %u len=%d\n", datahandle, skb->len-CAPIMSG_LEN(skb->data)); skb_queue_tail(&mp->inqueue, skb); handle_minor_recv(mp); } else if (CAPIMSG_SUBCOMMAND(skb->data) == CAPI_CONF) { datahandle = CAPIMSG_U16(skb->data, CAPIMSG_BASELEN + 4); pr_debug("capi_signal: DATA_B3_CONF %u 0x%x\n", datahandle, CAPIMSG_U16(skb->data, CAPIMSG_BASELEN + 4 + 2)); kfree_skb(skb); capiminor_del_ack(mp, datahandle); tty_port_tty_wakeup(&mp->port); handle_minor_send(mp); } else { /* ups, let capi application handle it :-) */ skb_queue_tail(&cdev->recvqueue, skb); wake_up_interruptible(&cdev->recvwait); } #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */ unlock_out: mutex_unlock(&cdev->lock); } /* -------- file_operations for capidev ----------------------------- */ static ssize_t capi_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct capidev *cdev = file->private_data; struct sk_buff *skb; size_t copied; int err; if (!cdev->ap.applid) return -ENODEV; skb = skb_dequeue(&cdev->recvqueue); if (!skb) { if (file->f_flags & O_NONBLOCK) return -EAGAIN; err = wait_event_interruptible(cdev->recvwait, (skb = skb_dequeue(&cdev->recvqueue))); if (err) return err; } if (skb->len > count) { skb_queue_head(&cdev->recvqueue, skb); return -EMSGSIZE; } if (copy_to_user(buf, skb->data, skb->len)) { skb_queue_head(&cdev->recvqueue, skb); return -EFAULT; } copied = skb->len; kfree_skb(skb); return copied; } static ssize_t capi_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct capidev *cdev = file->private_data; struct sk_buff *skb; u16 mlen; if (!cdev->ap.applid) return -ENODEV; if (count < CAPIMSG_BASELEN) return -EINVAL; skb = alloc_skb(count, GFP_USER); if (!skb) return -ENOMEM; if (copy_from_user(skb_put(skb, count), buf, count)) { kfree_skb(skb); return -EFAULT; } mlen = CAPIMSG_LEN(skb->data); if (CAPIMSG_CMD(skb->data) == CAPI_DATA_B3_REQ) { if (count < CAPI_DATA_B3_REQ_LEN || (size_t)(mlen + CAPIMSG_DATALEN(skb->data)) != count) { kfree_skb(skb); return -EINVAL; } } else { if (mlen != count) { kfree_skb(skb); return -EINVAL; } } CAPIMSG_SETAPPID(skb->data, cdev->ap.applid); if (CAPIMSG_CMD(skb->data) == CAPI_DISCONNECT_B3_RESP) { if (count < CAPI_DISCONNECT_B3_RESP_LEN) { kfree_skb(skb); return -EINVAL; } mutex_lock(&cdev->lock); capincci_free(cdev, CAPIMSG_NCCI(skb->data)); mutex_unlock(&cdev->lock); } cdev->errcode = capi20_put_message(&cdev->ap, skb); if (cdev->errcode) { kfree_skb(skb); return -EIO; } return count; } static __poll_t capi_poll(struct file *file, poll_table *wait) { struct capidev *cdev = file->private_data; __poll_t mask = 0; if (!cdev->ap.applid) return EPOLLERR; poll_wait(file, &(cdev->recvwait), wait); mask = EPOLLOUT | EPOLLWRNORM; if (!skb_queue_empty_lockless(&cdev->recvqueue)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } static int capi_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct capidev *cdev = file->private_data; capi_ioctl_struct data; int retval = -EINVAL; void __user *argp = (void __user *)arg; switch (cmd) { case CAPI_REGISTER: mutex_lock(&cdev->lock); if (cdev->ap.applid) { retval = -EEXIST; goto register_out; } if (copy_from_user(&cdev->ap.rparam, argp, sizeof(struct capi_register_params))) { retval = -EFAULT; goto register_out; } cdev->ap.private = cdev; cdev->ap.recv_message = capi_recv_message; cdev->errcode = capi20_register(&cdev->ap); retval = (int)cdev->ap.applid; if (cdev->errcode) { cdev->ap.applid = 0; retval = -EIO; } register_out: mutex_unlock(&cdev->lock); return retval; case CAPI_GET_VERSION: if (copy_from_user(&data.contr, argp, sizeof(data.contr))) return -EFAULT; cdev->errcode = capi20_get_version(data.contr, &data.version); if (cdev->errcode) return -EIO; if (copy_to_user(argp, &data.version, sizeof(data.version))) return -EFAULT; return 0; case CAPI_GET_SERIAL: if (copy_from_user(&data.contr, argp, sizeof(data.contr))) return -EFAULT; cdev->errcode = capi20_get_serial(data.contr, data.serial); if (cdev->errcode) return -EIO; if (copy_to_user(argp, data.serial, sizeof(data.serial))) return -EFAULT; return 0; case CAPI_GET_PROFILE: if (copy_from_user(&data.contr, argp, sizeof(data.contr))) return -EFAULT; if (data.contr == 0) { cdev->errcode = capi20_get_profile(data.contr, &data.profile); if (cdev->errcode) return -EIO; retval = copy_to_user(argp, &data.profile.ncontroller, sizeof(data.profile.ncontroller)); } else { cdev->errcode = capi20_get_profile(data.contr, &data.profile); if (cdev->errcode) return -EIO; retval = copy_to_user(argp, &data.profile, sizeof(data.profile)); } if (retval) return -EFAULT; return 0; case CAPI_GET_MANUFACTURER: if (copy_from_user(&data.contr, argp, sizeof(data.contr))) return -EFAULT; cdev->errcode = capi20_get_manufacturer(data.contr, data.manufacturer); if (cdev->errcode) return -EIO; if (copy_to_user(argp, data.manufacturer, sizeof(data.manufacturer))) return -EFAULT; return 0; case CAPI_GET_ERRCODE: data.errcode = cdev->errcode; cdev->errcode = CAPI_NOERROR; if (arg) { if (copy_to_user(argp, &data.errcode, sizeof(data.errcode))) return -EFAULT; } return data.errcode; case CAPI_INSTALLED: if (capi20_isinstalled() == CAPI_NOERROR) return 0; return -ENXIO; case CAPI_MANUFACTURER_CMD: { struct capi_manufacturer_cmd mcmd; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&mcmd, argp, sizeof(mcmd))) return -EFAULT; return capi20_manufacturer(mcmd.cmd, mcmd.data); } case CAPI_SET_FLAGS: case CAPI_CLR_FLAGS: { unsigned userflags; if (copy_from_user(&userflags, argp, sizeof(userflags))) return -EFAULT; mutex_lock(&cdev->lock); if (cmd == CAPI_SET_FLAGS) cdev->userflags |= userflags; else cdev->userflags &= ~userflags; mutex_unlock(&cdev->lock); return 0; } case CAPI_GET_FLAGS: if (copy_to_user(argp, &cdev->userflags, sizeof(cdev->userflags))) return -EFAULT; return 0; #ifndef CONFIG_ISDN_CAPI_MIDDLEWARE case CAPI_NCCI_OPENCOUNT: return 0; #else /* CONFIG_ISDN_CAPI_MIDDLEWARE */ case CAPI_NCCI_OPENCOUNT: { struct capincci *nccip; unsigned ncci; int count = 0; if (copy_from_user(&ncci, argp, sizeof(ncci))) return -EFAULT; mutex_lock(&cdev->lock); nccip = capincci_find(cdev, (u32)ncci); if (nccip) count = capincci_minor_opencount(nccip); mutex_unlock(&cdev->lock); return count; } case CAPI_NCCI_GETUNIT: { struct capincci *nccip; struct capiminor *mp; unsigned ncci; int unit = -ESRCH; if (copy_from_user(&ncci, argp, sizeof(ncci))) return -EFAULT; mutex_lock(&cdev->lock); nccip = capincci_find(cdev, (u32)ncci); if (nccip) { mp = nccip->minorp; if (mp) unit = mp->minor; } mutex_unlock(&cdev->lock); return unit; } #endif /* CONFIG_ISDN_CAPI_MIDDLEWARE */ default: return -EINVAL; } } static long capi_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; mutex_lock(&capi_mutex); ret = capi_ioctl(file, cmd, arg); mutex_unlock(&capi_mutex); return ret; } #ifdef CONFIG_COMPAT static long capi_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; if (cmd == CAPI_MANUFACTURER_CMD) { struct { compat_ulong_t cmd; compat_uptr_t data; } mcmd32; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&mcmd32, compat_ptr(arg), sizeof(mcmd32))) return -EFAULT; mutex_lock(&capi_mutex); ret = capi20_manufacturer(mcmd32.cmd, compat_ptr(mcmd32.data)); mutex_unlock(&capi_mutex); return ret; } return capi_unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } #endif static int capi_open(struct inode *inode, struct file *file) { struct capidev *cdev; cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) return -ENOMEM; mutex_init(&cdev->lock); skb_queue_head_init(&cdev->recvqueue); init_waitqueue_head(&cdev->recvwait); INIT_LIST_HEAD(&cdev->nccis); file->private_data = cdev; mutex_lock(&capidev_list_lock); list_add_tail(&cdev->list, &capidev_list); mutex_unlock(&capidev_list_lock); return stream_open(inode, file); } static int capi_release(struct inode *inode, struct file *file) { struct capidev *cdev = file->private_data; mutex_lock(&capidev_list_lock); list_del(&cdev->list); mutex_unlock(&capidev_list_lock); if (cdev->ap.applid) capi20_release(&cdev->ap); skb_queue_purge(&cdev->recvqueue); capincci_free(cdev, 0xffffffff); kfree(cdev); return 0; } static const struct file_operations capi_fops = { .owner = THIS_MODULE, .llseek = no_llseek, .read = capi_read, .write = capi_write, .poll = capi_poll, .unlocked_ioctl = capi_unlocked_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = capi_compat_ioctl, #endif .open = capi_open, .release = capi_release, }; #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE /* -------- tty_operations for capincci ----------------------------- */ static int capinc_tty_install(struct tty_driver *driver, struct tty_struct *tty) { struct capiminor *mp = capiminor_get(tty->index); int ret = tty_standard_install(driver, tty); if (ret == 0) tty->driver_data = mp; else capiminor_put(mp); return ret; } static void capinc_tty_cleanup(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; tty->driver_data = NULL; capiminor_put(mp); } static int capinc_tty_open(struct tty_struct *tty, struct file *filp) { struct capiminor *mp = tty->driver_data; int err; err = tty_port_open(&mp->port, tty, filp); if (err) return err; handle_minor_recv(mp); return 0; } static void capinc_tty_close(struct tty_struct *tty, struct file *filp) { struct capiminor *mp = tty->driver_data; tty_port_close(&mp->port, tty, filp); } static ssize_t capinc_tty_write(struct tty_struct *tty, const u8 *buf, size_t count) { struct capiminor *mp = tty->driver_data; struct sk_buff *skb; pr_debug("capinc_tty_write(count=%zu)\n", count); spin_lock_bh(&mp->outlock); skb = mp->outskb; if (skb) { mp->outskb = NULL; __skb_queue_tail(&mp->outqueue, skb); mp->outbytes += skb->len; } skb = alloc_skb(CAPI_DATA_B3_REQ_LEN + count, GFP_ATOMIC); if (!skb) { printk(KERN_ERR "capinc_tty_write: alloc_skb failed\n"); spin_unlock_bh(&mp->outlock); return -ENOMEM; } skb_reserve(skb, CAPI_DATA_B3_REQ_LEN); skb_put_data(skb, buf, count); __skb_queue_tail(&mp->outqueue, skb); mp->outbytes += skb->len; spin_unlock_bh(&mp->outlock); handle_minor_send(mp); return count; } static int capinc_tty_put_char(struct tty_struct *tty, u8 ch) { struct capiminor *mp = tty->driver_data; bool invoke_send = false; struct sk_buff *skb; int ret = 1; pr_debug("capinc_put_char(%u)\n", ch); spin_lock_bh(&mp->outlock); skb = mp->outskb; if (skb) { if (skb_tailroom(skb) > 0) { skb_put_u8(skb, ch); goto unlock_out; } mp->outskb = NULL; __skb_queue_tail(&mp->outqueue, skb); mp->outbytes += skb->len; invoke_send = true; } skb = alloc_skb(CAPI_DATA_B3_REQ_LEN + CAPI_MAX_BLKSIZE, GFP_ATOMIC); if (skb) { skb_reserve(skb, CAPI_DATA_B3_REQ_LEN); skb_put_u8(skb, ch); mp->outskb = skb; } else { printk(KERN_ERR "capinc_put_char: char %u lost\n", ch); ret = 0; } unlock_out: spin_unlock_bh(&mp->outlock); if (invoke_send) handle_minor_send(mp); return ret; } static void capinc_tty_flush_chars(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; struct sk_buff *skb; spin_lock_bh(&mp->outlock); skb = mp->outskb; if (skb) { mp->outskb = NULL; __skb_queue_tail(&mp->outqueue, skb); mp->outbytes += skb->len; spin_unlock_bh(&mp->outlock); handle_minor_send(mp); } else spin_unlock_bh(&mp->outlock); handle_minor_recv(mp); } static unsigned int capinc_tty_write_room(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; unsigned int room; room = CAPINC_MAX_SENDQUEUE-skb_queue_len(&mp->outqueue); room *= CAPI_MAX_BLKSIZE; pr_debug("capinc_tty_write_room = %u\n", room); return room; } static unsigned int capinc_tty_chars_in_buffer(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; pr_debug("capinc_tty_chars_in_buffer = %d nack=%d sq=%d rq=%d\n", mp->outbytes, mp->nack, skb_queue_len(&mp->outqueue), skb_queue_len(&mp->inqueue)); return mp->outbytes; } static void capinc_tty_throttle(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; mp->ttyinstop = 1; } static void capinc_tty_unthrottle(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; mp->ttyinstop = 0; handle_minor_recv(mp); } static void capinc_tty_stop(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; mp->ttyoutstop = 1; } static void capinc_tty_start(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; mp->ttyoutstop = 0; handle_minor_send(mp); } static void capinc_tty_hangup(struct tty_struct *tty) { struct capiminor *mp = tty->driver_data; tty_port_hangup(&mp->port); } static void capinc_tty_send_xchar(struct tty_struct *tty, u8 ch) { pr_debug("capinc_tty_send_xchar(%u)\n", ch); } static const struct tty_operations capinc_ops = { .open = capinc_tty_open, .close = capinc_tty_close, .write = capinc_tty_write, .put_char = capinc_tty_put_char, .flush_chars = capinc_tty_flush_chars, .write_room = capinc_tty_write_room, .chars_in_buffer = capinc_tty_chars_in_buffer, .throttle = capinc_tty_throttle, .unthrottle = capinc_tty_unthrottle, .stop = capinc_tty_stop, .start = capinc_tty_start, .hangup = capinc_tty_hangup, .send_xchar = capinc_tty_send_xchar, .install = capinc_tty_install, .cleanup = capinc_tty_cleanup, }; static int __init capinc_tty_init(void) { struct tty_driver *drv; int err; if (capi_ttyminors > CAPINC_MAX_PORTS) capi_ttyminors = CAPINC_MAX_PORTS; if (capi_ttyminors <= 0) capi_ttyminors = CAPINC_NR_PORTS; capiminors = kcalloc(capi_ttyminors, sizeof(struct capiminor *), GFP_KERNEL); if (!capiminors) return -ENOMEM; drv = tty_alloc_driver(capi_ttyminors, TTY_DRIVER_REAL_RAW | TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_DYNAMIC_DEV); if (IS_ERR(drv)) { kfree(capiminors); return PTR_ERR(drv); } drv->driver_name = "capi_nc"; drv->name = "capi!"; drv->major = 0; drv->minor_start = 0; drv->type = TTY_DRIVER_TYPE_SERIAL; drv->subtype = SERIAL_TYPE_NORMAL; drv->init_termios = tty_std_termios; drv->init_termios.c_iflag = ICRNL; drv->init_termios.c_oflag = OPOST | ONLCR; drv->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; drv->init_termios.c_lflag = 0; tty_set_operations(drv, &capinc_ops); err = tty_register_driver(drv); if (err) { tty_driver_kref_put(drv); kfree(capiminors); printk(KERN_ERR "Couldn't register capi_nc driver\n"); return err; } capinc_tty_driver = drv; return 0; } static void __exit capinc_tty_exit(void) { tty_unregister_driver(capinc_tty_driver); tty_driver_kref_put(capinc_tty_driver); kfree(capiminors); } #else /* !CONFIG_ISDN_CAPI_MIDDLEWARE */ static inline int capinc_tty_init(void) { return 0; } static inline void capinc_tty_exit(void) { } #endif /* !CONFIG_ISDN_CAPI_MIDDLEWARE */ /* -------- /proc functions ----------------------------------------- */ /* * /proc/capi/capi20: * minor applid nrecvctlpkt nrecvdatapkt nsendctlpkt nsenddatapkt */ static int __maybe_unused capi20_proc_show(struct seq_file *m, void *v) { struct capidev *cdev; struct list_head *l; mutex_lock(&capidev_list_lock); list_for_each(l, &capidev_list) { cdev = list_entry(l, struct capidev, list); seq_printf(m, "0 %d %lu %lu %lu %lu\n", cdev->ap.applid, cdev->ap.nrecvctlpkt, cdev->ap.nrecvdatapkt, cdev->ap.nsentctlpkt, cdev->ap.nsentdatapkt); } mutex_unlock(&capidev_list_lock); return 0; } /* * /proc/capi/capi20ncci: * applid ncci */ static int __maybe_unused capi20ncci_proc_show(struct seq_file *m, void *v) { struct capidev *cdev; struct capincci *np; mutex_lock(&capidev_list_lock); list_for_each_entry(cdev, &capidev_list, list) { mutex_lock(&cdev->lock); list_for_each_entry(np, &cdev->nccis, list) seq_printf(m, "%d 0x%x\n", cdev->ap.applid, np->ncci); mutex_unlock(&cdev->lock); } mutex_unlock(&capidev_list_lock); return 0; } static void __init proc_init(void) { proc_create_single("capi/capi20", 0, NULL, capi20_proc_show); proc_create_single("capi/capi20ncci", 0, NULL, capi20ncci_proc_show); } static void __exit proc_exit(void) { remove_proc_entry("capi/capi20", NULL); remove_proc_entry("capi/capi20ncci", NULL); } /* -------- init function and module interface ---------------------- */ static int __init capi_init(void) { const char *compileinfo; int major_ret; int ret; ret = kcapi_init(); if (ret) return ret; major_ret = register_chrdev(capi_major, "capi20", &capi_fops); if (major_ret < 0) { printk(KERN_ERR "capi20: unable to get major %d\n", capi_major); kcapi_exit(); return major_ret; } ret = class_register(&capi_class); if (ret) { unregister_chrdev(capi_major, "capi20"); kcapi_exit(); return ret; } device_create(&capi_class, NULL, MKDEV(capi_major, 0), NULL, "capi20"); if (capinc_tty_init() < 0) { device_destroy(&capi_class, MKDEV(capi_major, 0)); class_unregister(&capi_class); unregister_chrdev(capi_major, "capi20"); kcapi_exit(); return -ENOMEM; } proc_init(); #ifdef CONFIG_ISDN_CAPI_MIDDLEWARE compileinfo = " (middleware)"; #else compileinfo = " (no middleware)"; #endif printk(KERN_NOTICE "CAPI 2.0 started up with major %d%s\n", capi_major, compileinfo); return 0; } static void __exit capi_exit(void) { proc_exit(); device_destroy(&capi_class, MKDEV(capi_major, 0)); class_unregister(&capi_class); unregister_chrdev(capi_major, "capi20"); capinc_tty_exit(); kcapi_exit(); } module_init(capi_init); module_exit(capi_exit); |
| 6 3 6 3 6 6 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 | // 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>"); |
| 267 267 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 | // SPDX-License-Identifier: GPL-2.0-only /* * crc-itu-t.c */ #include <linux/types.h> #include <linux/module.h> #include <linux/crc-itu-t.h> /* CRC table for the CRC ITU-T V.41 0x1021 (x^16 + x^12 + x^5 + 1) */ const u16 crc_itu_t_table[256] = { 0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50a5, 0x60c6, 0x70e7, 0x8108, 0x9129, 0xa14a, 0xb16b, 0xc18c, 0xd1ad, 0xe1ce, 0xf1ef, 0x1231, 0x0210, 0x3273, 0x2252, 0x52b5, 0x4294, 0x72f7, 0x62d6, 0x9339, 0x8318, 0xb37b, 0xa35a, 0xd3bd, 0xc39c, 0xf3ff, 0xe3de, 0x2462, 0x3443, 0x0420, 0x1401, 0x64e6, 0x74c7, 0x44a4, 0x5485, 0xa56a, 0xb54b, 0x8528, 0x9509, 0xe5ee, 0xf5cf, 0xc5ac, 0xd58d, 0x3653, 0x2672, 0x1611, 0x0630, 0x76d7, 0x66f6, 0x5695, 0x46b4, 0xb75b, 0xa77a, 0x9719, 0x8738, 0xf7df, 0xe7fe, 0xd79d, 0xc7bc, 0x48c4, 0x58e5, 0x6886, 0x78a7, 0x0840, 0x1861, 0x2802, 0x3823, 0xc9cc, 0xd9ed, 0xe98e, 0xf9af, 0x8948, 0x9969, 0xa90a, 0xb92b, 0x5af5, 0x4ad4, 0x7ab7, 0x6a96, 0x1a71, 0x0a50, 0x3a33, 0x2a12, 0xdbfd, 0xcbdc, 0xfbbf, 0xeb9e, 0x9b79, 0x8b58, 0xbb3b, 0xab1a, 0x6ca6, 0x7c87, 0x4ce4, 0x5cc5, 0x2c22, 0x3c03, 0x0c60, 0x1c41, 0xedae, 0xfd8f, 0xcdec, 0xddcd, 0xad2a, 0xbd0b, 0x8d68, 0x9d49, 0x7e97, 0x6eb6, 0x5ed5, 0x4ef4, 0x3e13, 0x2e32, 0x1e51, 0x0e70, 0xff9f, 0xefbe, 0xdfdd, 0xcffc, 0xbf1b, 0xaf3a, 0x9f59, 0x8f78, 0x9188, 0x81a9, 0xb1ca, 0xa1eb, 0xd10c, 0xc12d, 0xf14e, 0xe16f, 0x1080, 0x00a1, 0x30c2, 0x20e3, 0x5004, 0x4025, 0x7046, 0x6067, 0x83b9, 0x9398, 0xa3fb, 0xb3da, 0xc33d, 0xd31c, 0xe37f, 0xf35e, 0x02b1, 0x1290, 0x22f3, 0x32d2, 0x4235, 0x5214, 0x6277, 0x7256, 0xb5ea, 0xa5cb, 0x95a8, 0x8589, 0xf56e, 0xe54f, 0xd52c, 0xc50d, 0x34e2, 0x24c3, 0x14a0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405, 0xa7db, 0xb7fa, 0x8799, 0x97b8, 0xe75f, 0xf77e, 0xc71d, 0xd73c, 0x26d3, 0x36f2, 0x0691, 0x16b0, 0x6657, 0x7676, 0x4615, 0x5634, 0xd94c, 0xc96d, 0xf90e, 0xe92f, 0x99c8, 0x89e9, 0xb98a, 0xa9ab, 0x5844, 0x4865, 0x7806, 0x6827, 0x18c0, 0x08e1, 0x3882, 0x28a3, 0xcb7d, 0xdb5c, 0xeb3f, 0xfb1e, 0x8bf9, 0x9bd8, 0xabbb, 0xbb9a, 0x4a75, 0x5a54, 0x6a37, 0x7a16, 0x0af1, 0x1ad0, 0x2ab3, 0x3a92, 0xfd2e, 0xed0f, 0xdd6c, 0xcd4d, 0xbdaa, 0xad8b, 0x9de8, 0x8dc9, 0x7c26, 0x6c07, 0x5c64, 0x4c45, 0x3ca2, 0x2c83, 0x1ce0, 0x0cc1, 0xef1f, 0xff3e, 0xcf5d, 0xdf7c, 0xaf9b, 0xbfba, 0x8fd9, 0x9ff8, 0x6e17, 0x7e36, 0x4e55, 0x5e74, 0x2e93, 0x3eb2, 0x0ed1, 0x1ef0 }; EXPORT_SYMBOL(crc_itu_t_table); /** * crc_itu_t - Compute the CRC-ITU-T for the data buffer * * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer * * Returns the updated CRC value */ u16 crc_itu_t(u16 crc, const u8 *buffer, size_t len) { while (len--) crc = crc_itu_t_byte(crc, *buffer++); return crc; } EXPORT_SYMBOL(crc_itu_t); MODULE_DESCRIPTION("CRC ITU-T V.41 calculations"); MODULE_LICENSE("GPL"); |
| 252 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_KSM_H #define __LINUX_KSM_H /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork(). */ #include <linux/bitops.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> #include <linux/sched/coredump.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); /* * To identify zeropages that were mapped by KSM, we reuse the dirty bit * in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when * deduplicating memory. */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) extern atomic_long_t ksm_zero_pages; static inline void ksm_map_zero_page(struct mm_struct *mm) { atomic_long_inc(&ksm_zero_pages); atomic_long_inc(&mm->ksm_zero_pages); } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { atomic_long_dec(&ksm_zero_pages); atomic_long_dec(&mm->ksm_zero_pages); } } static inline long mm_ksm_zero_pages(struct mm_struct *mm) { return atomic_long_read(&mm->ksm_zero_pages); } static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) return __ksm_enter(mm); return 0; } static inline int ksm_execve(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return __ksm_enter(mm); return 0; } static inline void ksm_exit(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) __ksm_exit(mm); } /* * When do_swap_page() first faults in from swap what used to be a KSM page, * no problem, it will be assigned to this vma's anon_vma; but thereafter, * it might be faulted into a different anon_vma (or perhaps to a different * offset in the same anon_vma). do_swap_page() cannot do all the locking * needed to reconstitute a cross-anon_vma KSM page: for now it has to make * a copy, and leave remerging the pages to a later pass of ksmd. * * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr); void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); void collect_procs_ksm(struct folio *folio, struct page *page, struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); #else /* !CONFIG_KSM */ static inline void ksm_add_vma(struct vm_area_struct *vma) { } static inline int ksm_disable(struct mm_struct *mm) { return 0; } static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; } static inline int ksm_execve(struct mm_struct *mm) { return 0; } static inline void ksm_exit(struct mm_struct *mm) { } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } static inline void collect_procs_ksm(struct folio *folio, struct page *page, struct list_head *to_kill, int force_early) { } #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { return 0; } static inline struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { return folio; } static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old) { } #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ #endif /* __LINUX_KSM_H */ |
| 2 2 183 252 1 251 380 4 380 380 254 255 253 255 2 164 174 1 377 110 110 2 107 105 2 86 20 104 72 32 25 8 104 2 107 109 82 29 53 82 82 53 28 40 47 49 1 12 5 49 20 1 1 13 38 4 38 24 5 20 44 53 46 171 6 48 4 123 5 2 50 201 218 2 216 10 1 2 238 6 234 18 49 174 231 3 7 233 1 227 18 216 18 79 171 82 10 2 221 220 220 1 213 16 202 213 212 212 86 86 14 81 86 170 53 23 23 127 86 169 76 142 71 71 213 157 56 186 95 1 116 1 197 17 6 1 209 67 137 204 40 157 4 2 38 111 3 103 10 5 3 8 285 285 286 286 286 286 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/ialloc.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * BSD ufs-inspired inode and directory allocation by * Stephen Tweedie (sct@redhat.com), 1993 * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/time.h> #include <linux/fs.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include <linux/random.h> #include <linux/bitops.h> #include <linux/blkdev.h> #include <linux/cred.h> #include <asm/byteorder.h> #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include <trace/events/ext4.h> /* * ialloc.c contains the inodes allocation and deallocation routines */ /* * The free inodes are managed by bitmaps. A file system contains several * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap * block for inodes, N blocks for the inode table and data blocks. * * The file system contains group descriptors which are located after the * super block. Each descriptor contains the number of the bitmap block and * the free blocks count in the block. */ /* * To avoid calling the atomic setbit hundreds or thousands of times, we only * need to use it within a single byte (to ensure we get endianness right). * We can use memset for the rest of the bitmap as there are no other users. */ void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap) { int i; if (start_bit >= end_bit) return; ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit); for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++) ext4_set_bit(i, bitmap); if (i < end_bit) memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3); } void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); set_bitmap_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } static int ext4_validate_inode_bitmap(struct super_block *sb, struct ext4_group_desc *desc, ext4_group_t block_group, struct buffer_head *bh) { ext4_fsblk_t blk; struct ext4_group_info *grp; if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return 0; grp = ext4_get_group_info(sb, block_group); if (buffer_verified(bh)) return 0; if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); if (buffer_verified(bh)) goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, desc, bh, EXT4_INODES_PER_GROUP(sb) / 8) || ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) { ext4_unlock_group(sb, block_group); ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " "inode_bitmap = %llu", block_group, blk); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); return -EFSBADCRC; } set_buffer_verified(bh); verified: ext4_unlock_group(sb, block_group); return 0; } /* * Read the inode allocation bitmap for a given block_group, reading * into the specified slot in the superblock's bitmap cache. * * Return buffer_head of bitmap on success, or an ERR_PTR on error. */ static struct buffer_head * ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) { struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh = NULL; ext4_fsblk_t bitmap_blk; int err; desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return ERR_PTR(-EFSCORRUPTED); bitmap_blk = ext4_inode_bitmap(sb, desc); if ((bitmap_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || (bitmap_blk >= ext4_blocks_count(sbi->s_es))) { ext4_error(sb, "Invalid inode bitmap blk %llu in " "block_group %u", bitmap_blk, block_group); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); return ERR_PTR(-EFSCORRUPTED); } bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { ext4_warning(sb, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); return ERR_PTR(-ENOMEM); } if (bitmap_uptodate(bh)) goto verify; lock_buffer(bh); if (bitmap_uptodate(bh)) { unlock_buffer(bh); goto verify; } ext4_lock_group(sb, block_group); if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) { if (block_group == 0) { ext4_unlock_group(sb, block_group); unlock_buffer(bh); ext4_error(sb, "Inode bitmap for bg 0 marked " "uninitialized"); err = -EFSCORRUPTED; goto out; } memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; } ext4_unlock_group(sb, block_group); if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, * bitmap is also uptodate */ set_bitmap_uptodate(bh); unlock_buffer(bh); goto verify; } /* * submit the buffer_head for reading */ trace_ext4_load_inode_bitmap(sb, block_group); ext4_read_bh(bh, REQ_META | REQ_PRIO, ext4_end_bitmap_read); ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO); if (!buffer_uptodate(bh)) { put_bh(bh); ext4_error_err(sb, EIO, "Cannot read inode bitmap - " "block_group = %u, inode_bitmap = %llu", block_group, bitmap_blk); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); return ERR_PTR(-EIO); } verify: err = ext4_validate_inode_bitmap(sb, desc, block_group, bh); if (err) goto out; return bh; out: put_bh(bh); return ERR_PTR(err); } /* * NOTE! When we get the inode, we're the only people * that have access to it, and as such there are no * race conditions we have to worry about. The inode * is not on the hash-lists, and it cannot be reached * through the filesystem because the directory entry * has been deleted earlier. * * HOWEVER: we must make sure that we get no aliases, * which means that we have to call "clear_inode()" * _before_ we mark the inode not in use in the inode * bitmaps. Otherwise a newly created file might use * the same inode number (not actually the same pointer * though), and then we'd have two inodes sharing the * same inode number and space on the harddisk. */ void ext4_free_inode(handle_t *handle, struct inode *inode) { struct super_block *sb = inode->i_sb; int is_directory; unsigned long ino; struct buffer_head *bitmap_bh = NULL; struct buffer_head *bh2; ext4_group_t block_group; unsigned long bit; struct ext4_group_desc *gdp; struct ext4_super_block *es; struct ext4_sb_info *sbi; int fatal = 0, err, count, cleared; struct ext4_group_info *grp; if (!sb) { printk(KERN_ERR "EXT4-fs: %s:%d: inode on " "nonexistent device\n", __func__, __LINE__); return; } if (atomic_read(&inode->i_count) > 1) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: count=%d", __func__, __LINE__, inode->i_ino, atomic_read(&inode->i_count)); return; } if (inode->i_nlink) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: nlink=%d\n", __func__, __LINE__, inode->i_ino, inode->i_nlink); return; } sbi = EXT4_SB(sb); ino = inode->i_ino; ext4_debug("freeing inode %lu\n", ino); trace_ext4_free_inode(inode); dquot_initialize(inode); dquot_free_inode(inode); is_directory = S_ISDIR(inode->i_mode); /* Do this BEFORE marking the inode not in use or returning an error */ ext4_clear_inode(inode); es = sbi->s_es; if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { ext4_error(sb, "reserved or nonexistent inode %lu", ino); goto error_return; } block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); /* Don't bother if the inode bitmap is corrupt. */ if (IS_ERR(bitmap_bh)) { fatal = PTR_ERR(bitmap_bh); bitmap_bh = NULL; goto error_return; } if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, block_group); if (!grp || unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { fatal = -EFSCORRUPTED; goto error_return; } } BUFFER_TRACE(bitmap_bh, "get_write_access"); fatal = ext4_journal_get_write_access(handle, sb, bitmap_bh, EXT4_JTR_NONE); if (fatal) goto error_return; fatal = -ESRCH; gdp = ext4_get_group_desc(sb, block_group, &bh2); if (gdp) { BUFFER_TRACE(bh2, "get_write_access"); fatal = ext4_journal_get_write_access(handle, sb, bh2, EXT4_JTR_NONE); } ext4_lock_group(sb, block_group); cleared = ext4_test_and_clear_bit(bit, bitmap_bh->b_data); if (fatal || !cleared) { ext4_unlock_group(sb, block_group); goto out; } count = ext4_free_inodes_count(sb, gdp) + 1; ext4_free_inodes_set(sb, gdp, count); if (is_directory) { count = ext4_used_dirs_count(sb, gdp) - 1; ext4_used_dirs_set(sb, gdp, count); if (percpu_counter_initialized(&sbi->s_dirs_counter)) percpu_counter_dec(&sbi->s_dirs_counter); } ext4_inode_bitmap_csum_set(sb, gdp, bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) percpu_counter_inc(&sbi->s_freeinodes_counter); if (sbi->s_log_groups_per_flex) { struct flex_groups *fg; fg = sbi_array_rcu_deref(sbi, s_flex_groups, ext4_flex_group(sbi, block_group)); atomic_inc(&fg->free_inodes); if (is_directory) atomic_dec(&fg->used_dirs); } BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata"); fatal = ext4_handle_dirty_metadata(handle, NULL, bh2); out: if (cleared) { BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (!fatal) fatal = err; } else { ext4_error(sb, "bit already cleared for inode %lu", ino); ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); } error_return: brelse(bitmap_bh); ext4_std_error(sb, fatal); } struct orlov_stats { __u64 free_clusters; __u32 free_inodes; __u32 used_dirs; }; /* * Helper function for Orlov's allocator; returns critical information * for a particular block group or flex_bg. If flex_size is 1, then g * is a block group number; otherwise it is flex_bg number. */ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, int flex_size, struct orlov_stats *stats) { struct ext4_group_desc *desc; if (flex_size > 1) { struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb), s_flex_groups, g); stats->free_inodes = atomic_read(&fg->free_inodes); stats->free_clusters = atomic64_read(&fg->free_clusters); stats->used_dirs = atomic_read(&fg->used_dirs); return; } desc = ext4_get_group_desc(sb, g, NULL); if (desc) { stats->free_inodes = ext4_free_inodes_count(sb, desc); stats->free_clusters = ext4_free_group_clusters(sb, desc); stats->used_dirs = ext4_used_dirs_count(sb, desc); } else { stats->free_inodes = 0; stats->free_clusters = 0; stats->used_dirs = 0; } } /* * Orlov's allocator for directories. * * We always try to spread first-level directories. * * If there are blockgroups with both free inodes and free clusters counts * not worse than average we return one with smallest directory count. * Otherwise we simply return a random group. * * For the rest rules look so: * * It's OK to put directory into a group unless * it has too many directories already (max_dirs) or * it has too few free inodes left (min_inodes) or * it has too few free clusters left (min_clusters) or * Parent's group is preferred, if it doesn't satisfy these * conditions we search cyclically through the rest. If none * of the groups look good we just look for a group with more * free inodes than average (starting at parent's group). */ static int find_group_orlov(struct super_block *sb, struct inode *parent, ext4_group_t *group, umode_t mode, const struct qstr *qstr) { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei, grp_free; ext4_fsblk_t freec, avefreec; unsigned int ndirs; int max_dirs, min_inodes; ext4_grpblk_t min_clusters; ext4_group_t i, grp, g, ngroups; struct ext4_group_desc *desc; struct orlov_stats stats; int flex_size = ext4_flex_bg_size(sbi); struct dx_hash_info hinfo; ngroups = real_ngroups; if (flex_size > 1) { ngroups = (real_ngroups + flex_size - 1) >> sbi->s_log_groups_per_flex; parent_group >>= sbi->s_log_groups_per_flex; } freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter); avefreec = freec; do_div(avefreec, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); if (S_ISDIR(mode) && ((parent == d_inode(sb->s_root)) || (ext4_test_inode_flag(parent, EXT4_INODE_TOPDIR)))) { int best_ndir = inodes_per_group; int ret = -1; if (qstr) { hinfo.hash_version = DX_HASH_HALF_MD4; hinfo.seed = sbi->s_hash_seed; ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo); parent_group = hinfo.hash % ngroups; } else parent_group = get_random_u32_below(ngroups); for (i = 0; i < ngroups; i++) { g = (parent_group + i) % ngroups; get_orlov_stats(sb, g, flex_size, &stats); if (!stats.free_inodes) continue; if (stats.used_dirs >= best_ndir) continue; if (stats.free_inodes < avefreei) continue; if (stats.free_clusters < avefreec) continue; grp = g; ret = 0; best_ndir = stats.used_dirs; } if (ret) goto fallback; found_flex_bg: if (flex_size == 1) { *group = grp; return 0; } /* * We pack inodes at the beginning of the flexgroup's * inode tables. Block allocation decisions will do * something similar, although regular files will * start at 2nd block group of the flexgroup. See * ext4_ext_find_goal() and ext4_find_near(). */ grp *= flex_size; for (i = 0; i < flex_size; i++) { if (grp+i >= real_ngroups) break; desc = ext4_get_group_desc(sb, grp+i, NULL); if (desc && ext4_free_inodes_count(sb, desc)) { *group = grp+i; return 0; } } goto fallback; } max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16; min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4; /* * Start looking in the flex group where we last allocated an * inode for this parent directory */ if (EXT4_I(parent)->i_last_alloc_group != ~0) { parent_group = EXT4_I(parent)->i_last_alloc_group; if (flex_size > 1) parent_group >>= sbi->s_log_groups_per_flex; } for (i = 0; i < ngroups; i++) { grp = (parent_group + i) % ngroups; get_orlov_stats(sb, grp, flex_size, &stats); if (stats.used_dirs >= max_dirs) continue; if (stats.free_inodes < min_inodes) continue; if (stats.free_clusters < min_clusters) continue; goto found_flex_bg; } fallback: ngroups = real_ngroups; avefreei = freei / ngroups; fallback_retry: parent_group = EXT4_I(parent)->i_block_group; for (i = 0; i < ngroups; i++) { grp = (parent_group + i) % ngroups; desc = ext4_get_group_desc(sb, grp, NULL); if (desc) { grp_free = ext4_free_inodes_count(sb, desc); if (grp_free && grp_free >= avefreei) { *group = grp; return 0; } } } if (avefreei) { /* * The free-inodes counter is approximate, and for really small * filesystems the above test can fail to find any blockgroups */ avefreei = 0; goto fallback_retry; } return -1; } static int find_group_other(struct super_block *sb, struct inode *parent, ext4_group_t *group, umode_t mode) { ext4_group_t parent_group = EXT4_I(parent)->i_block_group; ext4_group_t i, last, ngroups = ext4_get_groups_count(sb); struct ext4_group_desc *desc; int flex_size = ext4_flex_bg_size(EXT4_SB(sb)); /* * Try to place the inode is the same flex group as its * parent. If we can't find space, use the Orlov algorithm to * find another flex group, and store that information in the * parent directory's inode information so that use that flex * group for future allocations. */ if (flex_size > 1) { int retry = 0; try_again: parent_group &= ~(flex_size-1); last = parent_group + flex_size; if (last > ngroups) last = ngroups; for (i = parent_group; i < last; i++) { desc = ext4_get_group_desc(sb, i, NULL); if (desc && ext4_free_inodes_count(sb, desc)) { *group = i; return 0; } } if (!retry && EXT4_I(parent)->i_last_alloc_group != ~0) { retry = 1; parent_group = EXT4_I(parent)->i_last_alloc_group; goto try_again; } /* * If this didn't work, use the Orlov search algorithm * to find a new flex group; we pass in the mode to * avoid the topdir algorithms. */ *group = parent_group + flex_size; if (*group > ngroups) *group = 0; return find_group_orlov(sb, parent, group, mode, NULL); } /* * Try to place the inode in its parent directory */ *group = parent_group; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc) && ext4_free_group_clusters(sb, desc)) return 0; /* * We're going to place this inode in a different blockgroup from its * parent. We want to cause files in a common directory to all land in * the same blockgroup. But we want files which are in a different * directory which shares a blockgroup with our parent to land in a * different blockgroup. * * So add our directory's i_ino into the starting point for the hash. */ *group = (*group + parent->i_ino) % ngroups; /* * Use a quadratic hash to find a group with a free inode and some free * blocks. */ for (i = 1; i < ngroups; i <<= 1) { *group += i; if (*group >= ngroups) *group -= ngroups; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc) && ext4_free_group_clusters(sb, desc)) return 0; } /* * That failed: try linear search for a free inode, even if that group * has no free blocks. */ *group = parent_group; for (i = 0; i < ngroups; i++) { if (++*group >= ngroups) *group = 0; desc = ext4_get_group_desc(sb, *group, NULL); if (desc && ext4_free_inodes_count(sb, desc)) return 0; } return -1; } /* * In no journal mode, if an inode has recently been deleted, we want * to avoid reusing it until we're reasonably sure the inode table * block has been written back to disk. (Yes, these values are * somewhat arbitrary...) */ #define RECENTCY_MIN 60 #define RECENTCY_DIRTY 300 static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino) { struct ext4_group_desc *gdp; struct ext4_inode *raw_inode; struct buffer_head *bh; int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; int offset, ret = 0; int recentcy = RECENTCY_MIN; u32 dtime, now; gdp = ext4_get_group_desc(sb, group, NULL); if (unlikely(!gdp)) return 0; bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) + (ino / inodes_per_block)); if (!bh || !buffer_uptodate(bh)) /* * If the block is not in the buffer cache, then it * must have been written out. */ goto out; offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb); raw_inode = (struct ext4_inode *) (bh->b_data + offset); /* i_dtime is only 32 bits on disk, but we only care about relative * times in the range of a few minutes (i.e. long enough to sync a * recently-deleted inode to disk), so using the low 32 bits of the * clock (a 68 year range) is enough, see time_before32() */ dtime = le32_to_cpu(raw_inode->i_dtime); now = ktime_get_real_seconds(); if (buffer_dirty(bh)) recentcy += RECENTCY_DIRTY; if (dtime && time_before32(dtime, now) && time_before32(now, dtime + recentcy)) ret = 1; out: brelse(bh); return ret; } static int find_inode_bit(struct super_block *sb, ext4_group_t group, struct buffer_head *bitmap, unsigned long *ino) { bool check_recently_deleted = EXT4_SB(sb)->s_journal == NULL; unsigned long recently_deleted_ino = EXT4_INODES_PER_GROUP(sb); next: *ino = ext4_find_next_zero_bit((unsigned long *) bitmap->b_data, EXT4_INODES_PER_GROUP(sb), *ino); if (*ino >= EXT4_INODES_PER_GROUP(sb)) goto not_found; if (check_recently_deleted && recently_deleted(sb, group, *ino)) { recently_deleted_ino = *ino; *ino = *ino + 1; if (*ino < EXT4_INODES_PER_GROUP(sb)) goto next; goto not_found; } return 1; not_found: if (recently_deleted_ino >= EXT4_INODES_PER_GROUP(sb)) return 0; /* * Not reusing recently deleted inodes is mostly a preference. We don't * want to report ENOSPC or skew allocation patterns because of that. * So return even recently deleted inode if we could find better in the * given range. */ *ino = recently_deleted_ino; return 1; } int ext4_mark_inode_used(struct super_block *sb, int ino) { unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count); struct buffer_head *inode_bitmap_bh = NULL, *group_desc_bh = NULL; struct ext4_group_desc *gdp; ext4_group_t group; int bit; int err = -EFSCORRUPTED; if (ino < EXT4_FIRST_INO(sb) || ino > max_ino) goto out; group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); if (IS_ERR(inode_bitmap_bh)) return PTR_ERR(inode_bitmap_bh); if (ext4_test_bit(bit, inode_bitmap_bh->b_data)) { err = 0; goto out; } gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp || !group_desc_bh) { err = -EINVAL; goto out; } ext4_set_bit(bit, inode_bitmap_bh->b_data); BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(NULL, NULL, inode_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; } err = sync_dirty_buffer(inode_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; } /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { struct buffer_head *block_bitmap_bh; block_bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(block_bitmap_bh)) { err = PTR_ERR(block_bitmap_bh); goto out; } BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); err = ext4_handle_dirty_metadata(NULL, NULL, block_bitmap_bh); sync_dirty_buffer(block_bitmap_bh); /* recheck and clear flag under lock if we still need to */ ext4_lock_group(sb, group); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); brelse(block_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; } } /* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { int free; ext4_lock_group(sb, group); /* while we modify the bg desc */ free = EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT); free = 0; } /* * Check the relative inode number against the last used * relative inode number in this group. if it is greater * we need to update the bg_itable_unused count */ if (bit >= free) ext4_itable_unused_set(sb, gdp, (EXT4_INODES_PER_GROUP(sb) - bit - 1)); } else { ext4_lock_group(sb, group); } ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1); if (ext4_has_group_desc_csum(sb)) { ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh); sync_dirty_buffer(group_desc_bh); out: return err; } static int ext4_xattr_credits_for_new_inode(struct inode *dir, mode_t mode, bool encrypt) { struct super_block *sb = dir->i_sb; int nblocks = 0; #ifdef CONFIG_EXT4_FS_POSIX_ACL struct posix_acl *p = get_inode_acl(dir, ACL_TYPE_DEFAULT); if (IS_ERR(p)) return PTR_ERR(p); if (p) { int acl_size = p->a_count * sizeof(ext4_acl_entry); nblocks += (S_ISDIR(mode) ? 2 : 1) * __ext4_xattr_set_credits(sb, NULL /* inode */, NULL /* block_bh */, acl_size, true /* is_create */); posix_acl_release(p); } #endif #ifdef CONFIG_SECURITY { int num_security_xattrs = 1; #ifdef CONFIG_INTEGRITY num_security_xattrs++; #endif /* * We assume that security xattrs are never more than 1k. * In practice they are under 128 bytes. */ nblocks += num_security_xattrs * __ext4_xattr_set_credits(sb, NULL /* inode */, NULL /* block_bh */, 1024, true /* is_create */); } #endif if (encrypt) nblocks += __ext4_xattr_set_credits(sb, NULL /* inode */, NULL /* block_bh */, FSCRYPT_SET_CONTEXT_MAX_SIZE, true /* is_create */); return nblocks; } /* * There are two policies for allocating an inode. If the new inode is * a directory, then a forward search is made for a block group with both * free space and a low directory-to-inode ratio; if that fails, then of * the groups with above-average free space, that group with the fewest * directories already is chosen. * * For other inodes, search forward from the parent directory's block * group to find a free inode. */ struct inode *__ext4_new_inode(struct mnt_idmap *idmap, handle_t *handle, struct inode *dir, umode_t mode, const struct qstr *qstr, __u32 goal, uid_t *owner, __u32 i_flags, int handle_type, unsigned int line_no, int nblocks) { struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; struct buffer_head *group_desc_bh; ext4_group_t ngroups, group = 0; unsigned long ino = 0; struct inode *inode; struct ext4_group_desc *gdp = NULL; struct ext4_inode_info *ei; struct ext4_sb_info *sbi; int ret2, err; struct inode *ret; ext4_group_t i; ext4_group_t flex_group; struct ext4_group_info *grp = NULL; bool encrypt = false; /* Cannot create files in a deleted directory */ if (!dir || !dir->i_nlink) return ERR_PTR(-EPERM); sb = dir->i_sb; sbi = EXT4_SB(sb); if (unlikely(ext4_forced_shutdown(sb))) return ERR_PTR(-EIO); ngroups = ext4_get_groups_count(sb); trace_ext4_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); /* * Initialize owners and quota early so that we don't have to account * for quota initialization worst case in standard inode creating * transaction */ if (owner) { inode->i_mode = mode; i_uid_write(inode, owner[0]); i_gid_write(inode, owner[1]); } else if (test_opt(sb, GRPID)) { inode->i_mode = mode; inode_fsuid_set(inode, idmap); inode->i_gid = dir->i_gid; } else inode_init_owner(idmap, inode, dir, mode); if (ext4_has_feature_project(sb) && ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) ei->i_projid = EXT4_I(dir)->i_projid; else ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID); if (!(i_flags & EXT4_EA_INODE_FL)) { err = fscrypt_prepare_new_inode(dir, inode, &encrypt); if (err) goto out; } err = dquot_initialize(inode); if (err) goto out; if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) { ret2 = ext4_xattr_credits_for_new_inode(dir, mode, encrypt); if (ret2 < 0) { err = ret2; goto out; } nblocks += ret2; } if (!goal) goal = sbi->s_inode_goal; if (goal && goal <= le32_to_cpu(sbi->s_es->s_inodes_count)) { group = (goal - 1) / EXT4_INODES_PER_GROUP(sb); ino = (goal - 1) % EXT4_INODES_PER_GROUP(sb); ret2 = 0; goto got_group; } if (S_ISDIR(mode)) ret2 = find_group_orlov(sb, dir, &group, mode, qstr); else ret2 = find_group_other(sb, dir, &group, mode); got_group: EXT4_I(dir)->i_last_alloc_group = group; err = -ENOSPC; if (ret2 == -1) goto out; /* * Normally we will only go through one pass of this loop, * unless we get unlucky and it turns out the group we selected * had its last inode grabbed by someone else. */ for (i = 0; i < ngroups; i++, ino = 0) { err = -EIO; gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp) goto out; /* * Check free inodes count before loading bitmap. */ if (ext4_free_inodes_count(sb, gdp) == 0) goto next_group; if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, group); /* * Skip groups with already-known suspicious inode * tables */ if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) goto next_group; } brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); /* Skip groups with suspicious inode tables */ if (((!(sbi->s_mount_state & EXT4_FC_REPLAY)) && EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) || IS_ERR(inode_bitmap_bh)) { inode_bitmap_bh = NULL; goto next_group; } repeat_in_this_group: ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino); if (!ret2) goto next_group; if (group == 0 && (ino + 1) < EXT4_FIRST_INO(sb)) { ext4_error(sb, "reserved inode found cleared - " "inode=%lu", ino + 1); ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto next_group; } if ((!(sbi->s_mount_state & EXT4_FC_REPLAY)) && !handle) { BUG_ON(nblocks <= 0); handle = __ext4_journal_start_sb(NULL, dir->i_sb, line_no, handle_type, nblocks, 0, ext4_trans_default_revoke_credits(sb)); if (IS_ERR(handle)) { err = PTR_ERR(handle); ext4_std_error(sb, err); goto out; } } BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, inode_bitmap_bh, EXT4_JTR_NONE); if (err) { ext4_std_error(sb, err); goto out; } ext4_lock_group(sb, group); ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data); if (ret2) { /* Someone already took the bit. Repeat the search * with lock held. */ ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino); if (ret2) { ext4_set_bit(ino, inode_bitmap_bh->b_data); ret2 = 0; } else { ret2 = 1; /* we didn't grab the inode */ } } ext4_unlock_group(sb, group); ino++; /* the inode bitmap is zero-based */ if (!ret2) goto got; /* we grabbed the inode! */ if (ino < EXT4_INODES_PER_GROUP(sb)) goto repeat_in_this_group; next_group: if (++group == ngroups) group = 0; } err = -ENOSPC; goto out; got: BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; } BUFFER_TRACE(group_desc_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, group_desc_bh, EXT4_JTR_NONE); if (err) { ext4_std_error(sb, err); goto out; } /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { struct buffer_head *block_bitmap_bh; block_bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(block_bitmap_bh)) { err = PTR_ERR(block_bitmap_bh); goto out; } BUFFER_TRACE(block_bitmap_bh, "get block bitmap access"); err = ext4_journal_get_write_access(handle, sb, block_bitmap_bh, EXT4_JTR_NONE); if (err) { brelse(block_bitmap_bh); ext4_std_error(sb, err); goto out; } BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap"); err = ext4_handle_dirty_metadata(handle, NULL, block_bitmap_bh); /* recheck and clear flag under lock if we still need to */ ext4_lock_group(sb, group); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); ext4_block_bitmap_csum_set(sb, gdp, block_bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); brelse(block_bitmap_bh); if (err) { ext4_std_error(sb, err); goto out; } } /* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { int free; struct ext4_group_info *grp = NULL; if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, group); if (!grp) { err = -EFSCORRUPTED; goto out; } down_read(&grp->alloc_sem); /* * protect vs itable * lazyinit */ } ext4_lock_group(sb, group); /* while we modify the bg desc */ free = EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp); if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT); free = 0; } /* * Check the relative inode number against the last used * relative inode number in this group. if it is greater * we need to update the bg_itable_unused count */ if (ino > free) ext4_itable_unused_set(sb, gdp, (EXT4_INODES_PER_GROUP(sb) - ino)); if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) up_read(&grp->alloc_sem); } else { ext4_lock_group(sb, group); } ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1); if (S_ISDIR(mode)) { ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1); if (sbi->s_log_groups_per_flex) { ext4_group_t f = ext4_flex_group(sbi, group); atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups, f)->used_dirs); } } if (ext4_has_group_desc_csum(sb)) { ext4_inode_bitmap_csum_set(sb, gdp, inode_bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8); ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); if (err) { ext4_std_error(sb, err); goto out; } percpu_counter_dec(&sbi->s_freeinodes_counter); if (S_ISDIR(mode)) percpu_counter_inc(&sbi->s_dirs_counter); if (sbi->s_log_groups_per_flex) { flex_group = ext4_flex_group(sbi, group); atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups, flex_group)->free_inodes); } inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; simple_inode_init_ts(inode); ei->i_crtime = inode_get_mtime(inode); memset(ei->i_data, 0, sizeof(ei->i_data)); ei->i_dir_start_lookup = 0; ei->i_disksize = 0; /* Don't inherit extent flag from directory, amongst others. */ ei->i_flags = ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED); ei->i_flags |= i_flags; ei->i_file_acl = 0; ei->i_dtime = 0; ei->i_block_group = group; ei->i_last_alloc_group = ~0; ext4_set_inode_flags(inode, true); if (IS_DIRSYNC(inode)) ext4_handle_sync(handle); if (insert_inode_locked(inode) < 0) { /* * Likely a bitmap corruption causing inode to be allocated * twice. */ err = -EIO; ext4_error(sb, "failed to insert inode %lu: doubly allocated?", inode->i_ino); ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto out; } inode->i_generation = get_random_u32(); /* Precompute checksum seed for inode metadata */ if (ext4_has_metadata_csum(sb)) { __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen)); } ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ext4_set_inode_state(inode, EXT4_STATE_NEW); ei->i_extra_isize = sbi->s_want_extra_isize; ei->i_inline_off = 0; if (ext4_has_feature_inline_data(sb) && (!(ei->i_flags & EXT4_DAX_FL) || S_ISDIR(mode))) ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); ret = inode; err = dquot_alloc_inode(inode); if (err) goto fail_drop; /* * Since the encryption xattr will always be unique, create it first so * that it's less likely to end up in an external xattr block and * prevent its deduplication. */ if (encrypt) { err = fscrypt_set_context(inode, handle); if (err) goto fail_free_drop; } if (!(ei->i_flags & EXT4_EA_INODE_FL)) { err = ext4_init_acl(handle, inode, dir); if (err) goto fail_free_drop; err = ext4_init_security(handle, inode, dir, qstr); if (err) goto fail_free_drop; } if (ext4_has_feature_extents(sb)) { /* set extent flag only for directory, file and normal symlink*/ if (S_ISDIR(mode) || S_ISREG(mode) || S_ISLNK(mode)) { ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode); } } ext4_update_inode_fsync_trans(handle, inode, 1); err = ext4_mark_inode_dirty(handle, inode); if (err) { ext4_std_error(sb, err); goto fail_free_drop; } ext4_debug("allocating inode %lu\n", inode->i_ino); trace_ext4_allocate_inode(inode, dir, mode); brelse(inode_bitmap_bh); return ret; fail_free_drop: dquot_free_inode(inode); fail_drop: clear_nlink(inode); unlock_new_inode(inode); out: dquot_drop(inode); inode->i_flags |= S_NOQUOTA; iput(inode); brelse(inode_bitmap_bh); return ERR_PTR(err); } /* Verify that we are loading a valid orphan from disk */ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) { unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count); ext4_group_t block_group; int bit; struct buffer_head *bitmap_bh = NULL; struct inode *inode = NULL; int err = -EFSCORRUPTED; if (ino < EXT4_FIRST_INO(sb) || ino > max_ino) goto bad_orphan; block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); if (IS_ERR(bitmap_bh)) return ERR_CAST(bitmap_bh); /* Having the inode bit set should be a 100% indicator that this * is a valid orphan (no e2fsck run on fs). Orphans also include * inodes that were being truncated, so we can't check i_nlink==0. */ if (!ext4_test_bit(bit, bitmap_bh->b_data)) goto bad_orphan; inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error_err(sb, -err, "couldn't read orphan inode %lu (err %d)", ino, err); brelse(bitmap_bh); return inode; } /* * If the orphans has i_nlinks > 0 then it should be able to * be truncated, otherwise it won't be removed from the orphan * list during processing and an infinite loop will result. * Similarly, it must not be a bad inode. */ if ((inode->i_nlink && !ext4_can_truncate(inode)) || is_bad_inode(inode)) goto bad_orphan; if (NEXT_ORPHAN(inode) > max_ino) goto bad_orphan; brelse(bitmap_bh); return inode; bad_orphan: ext4_error(sb, "bad orphan inode %lu", ino); if (bitmap_bh) printk(KERN_ERR "ext4_test_bit(bit=%d, block=%llu) = %d\n", bit, (unsigned long long)bitmap_bh->b_blocknr, ext4_test_bit(bit, bitmap_bh->b_data)); if (inode) { printk(KERN_ERR "is_bad_inode(inode)=%d\n", is_bad_inode(inode)); printk(KERN_ERR "NEXT_ORPHAN(inode)=%u\n", NEXT_ORPHAN(inode)); printk(KERN_ERR "max_ino=%lu\n", max_ino); printk(KERN_ERR "i_nlink=%u\n", inode->i_nlink); /* Avoid freeing blocks if we got a bad deleted inode */ if (inode->i_nlink == 0) inode->i_blocks = 0; iput(inode); } brelse(bitmap_bh); return ERR_PTR(err); } unsigned long ext4_count_free_inodes(struct super_block *sb) { unsigned long desc_count; struct ext4_group_desc *gdp; ext4_group_t i, ngroups = ext4_get_groups_count(sb); #ifdef EXT4FS_DEBUG struct ext4_super_block *es; unsigned long bitmap_count, x; struct buffer_head *bitmap_bh = NULL; es = EXT4_SB(sb)->s_es; desc_count = 0; bitmap_count = 0; gdp = NULL; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; desc_count += ext4_free_inodes_count(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_inode_bitmap(sb, i); if (IS_ERR(bitmap_bh)) { bitmap_bh = NULL; continue; } x = ext4_count_free(bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb) / 8); printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n", (unsigned long) i, ext4_free_inodes_count(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); printk(KERN_DEBUG "ext4_count_free_inodes: " "stored = %u, computed = %lu, %lu\n", le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count); return desc_count; #else desc_count = 0; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; desc_count += ext4_free_inodes_count(sb, gdp); cond_resched(); } return desc_count; #endif } /* Called at mount-time, super-block is locked */ unsigned long ext4_count_dirs(struct super_block * sb) { unsigned long count = 0; ext4_group_t i, ngroups = ext4_get_groups_count(sb); for (i = 0; i < ngroups; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; count += ext4_used_dirs_count(sb, gdp); } return count; } /* * Zeroes not yet zeroed inode table - just write zeroes through the whole * inode table. Must be called without any spinlock held. The only place * where it is called from on active part of filesystem is ext4lazyinit * thread, so we do not need any special locks, however we have to prevent * inode allocation from the current group, so we take alloc_sem lock, to * block ext4_new_inode() until we are finished. */ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, int barrier) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; struct buffer_head *group_desc_bh; handle_t *handle; ext4_fsblk_t blk; int num, ret = 0, used_blks = 0; unsigned long used_inos = 0; gdp = ext4_get_group_desc(sb, group, &group_desc_bh); if (!gdp || !grp) goto out; /* * We do not need to lock this, because we are the only one * handling this flag. */ if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) goto out; handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; } down_write(&grp->alloc_sem); /* * If inode bitmap was already initialized there may be some * used inodes so we need to skip blocks with used inodes in * inode table. */ if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) { used_inos = EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp); used_blks = DIV_ROUND_UP(used_inos, sbi->s_inodes_per_block); /* Bogus inode unused count? */ if (used_blks < 0 || used_blks > sbi->s_itb_per_group) { ext4_error(sb, "Something is wrong with group %u: " "used itable blocks: %d; " "itable unused count: %u", group, used_blks, ext4_itable_unused_count(sb, gdp)); ret = 1; goto err_out; } used_inos += group * EXT4_INODES_PER_GROUP(sb); /* * Are there some uninitialized inodes in the inode table * before the first normal inode? */ if ((used_blks != sbi->s_itb_per_group) && (used_inos < EXT4_FIRST_INO(sb))) { ext4_error(sb, "Something is wrong with group %u: " "itable unused count: %u; " "itables initialized count: %ld", group, ext4_itable_unused_count(sb, gdp), used_inos); ret = 1; goto err_out; } } blk = ext4_inode_table(sb, gdp) + used_blks; num = sbi->s_itb_per_group - used_blks; BUFFER_TRACE(group_desc_bh, "get_write_access"); ret = ext4_journal_get_write_access(handle, sb, group_desc_bh, EXT4_JTR_NONE); if (ret) goto err_out; /* * Skip zeroout if the inode table is full. But we set the ZEROED * flag anyway, because obviously, when it is full it does not need * further zeroing. */ if (unlikely(num == 0)) goto skip_zeroout; ext4_debug("going to zero out inode table in group %d\n", group); ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS); if (ret < 0) goto err_out; if (barrier) blkdev_issue_flush(sb->s_bdev); skip_zeroout: ext4_lock_group(sb, group); gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED); ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group); BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); ret = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); err_out: up_write(&grp->alloc_sem); ext4_journal_stop(handle); out: return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * configfs_internal.h - Internal stuff for configfs * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. */ #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> #include <linux/list.h> #include <linux/spinlock.h> struct configfs_fragment { atomic_t frag_count; struct rw_semaphore frag_sem; bool frag_dead; }; void put_fragment(struct configfs_fragment *); struct configfs_fragment *get_fragment(struct configfs_fragment *); struct configfs_dirent { atomic_t s_count; int s_dependent_count; struct list_head s_sibling; struct list_head s_children; int s_links; void * s_element; int s_type; umode_t s_mode; struct dentry * s_dentry; struct iattr * s_iattr; #ifdef CONFIG_LOCKDEP int s_depth; #endif struct configfs_fragment *s_frag; }; #define CONFIGFS_ROOT 0x0001 #define CONFIGFS_DIR 0x0002 #define CONFIGFS_ITEM_ATTR 0x0004 #define CONFIGFS_ITEM_BIN_ATTR 0x0008 #define CONFIGFS_ITEM_LINK 0x0020 #define CONFIGFS_USET_DIR 0x0040 #define CONFIGFS_USET_DEFAULT 0x0080 #define CONFIGFS_USET_DROPPING 0x0100 #define CONFIGFS_USET_IN_MKDIR 0x0200 #define CONFIGFS_USET_CREATING 0x0400 #define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR | CONFIGFS_ITEM_BIN_ATTR) extern struct mutex configfs_symlink_mutex; extern spinlock_t configfs_dirent_lock; extern struct kmem_cache *configfs_dir_cachep; extern int configfs_is_root(struct config_item *item); extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *); extern struct inode *configfs_create(struct dentry *, umode_t mode); extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); extern int configfs_create_bin_file(struct config_item *, const struct configfs_bin_attribute *); extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *, void *, umode_t, int, struct configfs_fragment *); extern int configfs_dirent_is_ready(struct configfs_dirent *); extern void configfs_hash_and_remove(struct dentry * dir, const char * name); extern const unsigned char * configfs_get_name(struct configfs_dirent *sd); extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent); extern int configfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr); extern struct dentry *configfs_pin_fs(void); extern void configfs_release_fs(void); extern const struct file_operations configfs_dir_operations; extern const struct file_operations configfs_file_operations; extern const struct file_operations configfs_bin_file_operations; extern const struct inode_operations configfs_dir_inode_operations; extern const struct inode_operations configfs_root_inode_operations; extern const struct inode_operations configfs_symlink_inode_operations; extern const struct dentry_operations configfs_dentry_ops; extern int configfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname); extern int configfs_unlink(struct inode *dir, struct dentry *dentry); int configfs_create_link(struct configfs_dirent *target, struct dentry *parent, struct dentry *dentry, char *body); static inline struct config_item * to_item(struct dentry * dentry) { struct configfs_dirent * sd = dentry->d_fsdata; return ((struct config_item *) sd->s_element); } static inline struct configfs_attribute * to_attr(struct dentry * dentry) { struct configfs_dirent * sd = dentry->d_fsdata; return ((struct configfs_attribute *) sd->s_element); } static inline struct configfs_bin_attribute *to_bin_attr(struct dentry *dentry) { struct configfs_attribute *attr = to_attr(dentry); return container_of(attr, struct configfs_bin_attribute, cb_attr); } static inline struct config_item *configfs_get_config_item(struct dentry *dentry) { struct config_item * item = NULL; spin_lock(&dentry->d_lock); if (!d_unhashed(dentry)) { struct configfs_dirent * sd = dentry->d_fsdata; item = config_item_get(sd->s_element); } spin_unlock(&dentry->d_lock); return item; } static inline void release_configfs_dirent(struct configfs_dirent * sd) { if (!(sd->s_type & CONFIGFS_ROOT)) { kfree(sd->s_iattr); put_fragment(sd->s_frag); kmem_cache_free(configfs_dir_cachep, sd); } } static inline struct configfs_dirent * configfs_get(struct configfs_dirent * sd) { if (sd) { WARN_ON(!atomic_read(&sd->s_count)); atomic_inc(&sd->s_count); } return sd; } static inline void configfs_put(struct configfs_dirent * sd) { WARN_ON(!atomic_read(&sd->s_count)); if (atomic_dec_and_test(&sd->s_count)) release_configfs_dirent(sd); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H #ifndef __ASSEMBLY__ /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ static __always_inline void rep_nop(void) { asm volatile("rep; nop" ::: "memory"); } static __always_inline void cpu_relax(void) { rep_nop(); } struct getcpu_cache; notrace long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused); #endif /* __ASSEMBLY__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ |
| 1035 1036 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * blk-integrity.c - Block layer data integrity extensions * * Copyright (C) 2007, 2008 Oracle Corporation * Written by: Martin K. Petersen <martin.petersen@oracle.com> */ #include <linux/blk-integrity.h> #include <linux/backing-dev.h> #include <linux/mempool.h> #include <linux/bio.h> #include <linux/scatterlist.h> #include <linux/export.h> #include <linux/slab.h> #include "blk.h" /** * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements * @q: request queue * @bio: bio with integrity metadata attached * * Description: Returns the number of elements required in a * scatterlist corresponding to the integrity metadata in a bio. */ int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio) { struct bio_vec iv, ivprv = { NULL }; unsigned int segments = 0; unsigned int seg_size = 0; struct bvec_iter iter; int prev = 0; bio_for_each_integrity_vec(iv, bio, iter) { if (prev) { if (!biovec_phys_mergeable(q, &ivprv, &iv)) goto new_segment; if (seg_size + iv.bv_len > queue_max_segment_size(q)) goto new_segment; seg_size += iv.bv_len; } else { new_segment: segments++; seg_size = iv.bv_len; } prev = 1; ivprv = iv; } return segments; } EXPORT_SYMBOL(blk_rq_count_integrity_sg); /** * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist * @q: request queue * @bio: bio with integrity metadata attached * @sglist: target scatterlist * * Description: Map the integrity vectors in request into a * scatterlist. The scatterlist must be big enough to hold all * elements. I.e. sized using blk_rq_count_integrity_sg(). */ int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist) { struct bio_vec iv, ivprv = { NULL }; struct scatterlist *sg = NULL; unsigned int segments = 0; struct bvec_iter iter; int prev = 0; bio_for_each_integrity_vec(iv, bio, iter) { if (prev) { if (!biovec_phys_mergeable(q, &ivprv, &iv)) goto new_segment; if (sg->length + iv.bv_len > queue_max_segment_size(q)) goto new_segment; sg->length += iv.bv_len; } else { new_segment: if (!sg) sg = sglist; else { sg_unmark_end(sg); sg = sg_next(sg); } sg_set_page(sg, iv.bv_page, iv.bv_len, iv.bv_offset); segments++; } prev = 1; ivprv = iv; } if (sg) sg_mark_end(sg); return segments; } EXPORT_SYMBOL(blk_rq_map_integrity_sg); bool blk_integrity_merge_rq(struct request_queue *q, struct request *req, struct request *next) { if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0) return true; if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0) return false; if (bio_integrity(req->bio)->bip_flags != bio_integrity(next->bio)->bip_flags) return false; if (req->nr_integrity_segments + next->nr_integrity_segments > q->limits.max_integrity_segments) return false; if (integrity_req_gap_back_merge(req, next->bio)) return false; return true; } bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, struct bio *bio) { int nr_integrity_segs; struct bio *next = bio->bi_next; if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL) return true; if (blk_integrity_rq(req) == 0 || bio_integrity(bio) == NULL) return false; if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags) return false; bio->bi_next = NULL; nr_integrity_segs = blk_rq_count_integrity_sg(q, bio); bio->bi_next = next; if (req->nr_integrity_segments + nr_integrity_segs > q->limits.max_integrity_segments) return false; req->nr_integrity_segments += nr_integrity_segs; return true; } static inline struct blk_integrity *dev_to_bi(struct device *dev) { return &dev_to_disk(dev)->queue->limits.integrity; } const char *blk_integrity_profile_name(struct blk_integrity *bi) { switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_IP: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "T10-DIF-TYPE1-IP"; return "T10-DIF-TYPE3-IP"; case BLK_INTEGRITY_CSUM_CRC: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "T10-DIF-TYPE1-CRC"; return "T10-DIF-TYPE3-CRC"; case BLK_INTEGRITY_CSUM_CRC64: if (bi->flags & BLK_INTEGRITY_REF_TAG) return "EXT-DIF-TYPE1-CRC64"; return "EXT-DIF-TYPE3-CRC64"; case BLK_INTEGRITY_CSUM_NONE: break; } return "nop"; } EXPORT_SYMBOL_GPL(blk_integrity_profile_name); static ssize_t flag_store(struct device *dev, const char *page, size_t count, unsigned char flag) { struct request_queue *q = dev_to_disk(dev)->queue; struct queue_limits lim; unsigned long val; int err; err = kstrtoul(page, 10, &val); if (err) return err; /* note that the flags are inverted vs the values in the sysfs files */ lim = queue_limits_start_update(q); if (val) lim.integrity.flags &= ~flag; else lim.integrity.flags |= flag; blk_mq_freeze_queue(q); err = queue_limits_commit_update(q, &lim); blk_mq_unfreeze_queue(q); if (err) return err; return count; } static ssize_t flag_show(struct device *dev, char *page, unsigned char flag) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%d\n", !(bi->flags & flag)); } static ssize_t format_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); if (!bi->tuple_size) return sysfs_emit(page, "none\n"); return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi)); } static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", bi->tag_size); } static ssize_t protection_interval_bytes_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", bi->interval_exp ? 1 << bi->interval_exp : 0); } static ssize_t read_verify_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { return flag_store(dev, page, count, BLK_INTEGRITY_NOVERIFY); } static ssize_t read_verify_show(struct device *dev, struct device_attribute *attr, char *page) { return flag_show(dev, page, BLK_INTEGRITY_NOVERIFY); } static ssize_t write_generate_store(struct device *dev, struct device_attribute *attr, const char *page, size_t count) { return flag_store(dev, page, count, BLK_INTEGRITY_NOGENERATE); } static ssize_t write_generate_show(struct device *dev, struct device_attribute *attr, char *page) { return flag_show(dev, page, BLK_INTEGRITY_NOGENERATE); } static ssize_t device_is_integrity_capable_show(struct device *dev, struct device_attribute *attr, char *page) { struct blk_integrity *bi = dev_to_bi(dev); return sysfs_emit(page, "%u\n", !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)); } static DEVICE_ATTR_RO(format); static DEVICE_ATTR_RO(tag_size); static DEVICE_ATTR_RO(protection_interval_bytes); static DEVICE_ATTR_RW(read_verify); static DEVICE_ATTR_RW(write_generate); static DEVICE_ATTR_RO(device_is_integrity_capable); static struct attribute *integrity_attrs[] = { &dev_attr_format.attr, &dev_attr_tag_size.attr, &dev_attr_protection_interval_bytes.attr, &dev_attr_read_verify.attr, &dev_attr_write_generate.attr, &dev_attr_device_is_integrity_capable.attr, NULL }; const struct attribute_group blk_integrity_attr_group = { .name = "integrity", .attrs = integrity_attrs, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * pm_runtime.h - Device run-time power management helper functions. * * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl> */ #ifndef _LINUX_PM_RUNTIME_H #define _LINUX_PM_RUNTIME_H #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm.h> #include <linux/jiffies.h> /* Runtime PM flag argument bits */ #define RPM_ASYNC 0x01 /* Request is asynchronous */ #define RPM_NOWAIT 0x02 /* Don't wait for concurrent state change */ #define RPM_GET_PUT 0x04 /* Increment/decrement the usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ /* * Use this for defining a set of PM operations to be used in all situations * (system suspend, hibernation or runtime PM). * * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() * macro, which uses the provided callbacks for both runtime PM and system * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() * and pm_runtime_force_resume() for its system sleep callbacks. * * If the underlying dev_pm_ops struct symbol has to be exported, use * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. */ #define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ pm_runtime_force_resume, suspend_fn, \ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_GPL_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; static inline bool queue_pm_work(struct work_struct *work) { return queue_work(pm_wq, work); } extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); extern int pm_runtime_force_suspend(struct device *dev); extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); extern int pm_runtime_get_if_active(struct device *dev); extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); extern void pm_runtime_enable(struct device *dev); extern void __pm_runtime_disable(struct device *dev, bool check_resume); extern void pm_runtime_allow(struct device *dev); extern void pm_runtime_forbid(struct device *dev); extern void pm_runtime_no_callbacks(struct device *dev); extern void pm_runtime_irq_safe(struct device *dev); extern void __pm_runtime_use_autosuspend(struct device *dev, bool use); extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); extern void pm_runtime_release_supplier(struct device_link *link); extern int devm_pm_runtime_enable(struct device *dev); /** * pm_suspend_ignore_children - Set runtime PM behavior regarding children. * @dev: Target device. * @enable: Whether or not to ignore possible dependencies on children. * * The dependencies of @dev on its children will not be taken into account by * the runtime PM framework going forward if @enable is %true, or they will * be taken into account otherwise. */ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { dev->power.ignore_children = enable; } /** * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device. * @dev: Target device. */ static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); } /** * pm_runtime_put_noidle - Drop runtime PM usage counter of a device. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev unless it is 0 already. */ static inline void pm_runtime_put_noidle(struct device *dev) { atomic_add_unless(&dev->power.usage_count, -1, 0); } /** * pm_runtime_suspended - Check whether or not a device is runtime-suspended. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev and its runtime PM status is * %RPM_SUSPENDED, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED && !dev->power.disable_depth; } /** * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_active(struct device *dev) { return dev->power.runtime_status == RPM_ACTIVE || dev->power.disable_depth; } /** * pm_runtime_status_suspended - Check if runtime PM status is "suspended". * @dev: Target device. * * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false * otherwise, regardless of whether or not runtime PM has been enabled for @dev. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which the * runtime PM status of @dev cannot change. */ static inline bool pm_runtime_status_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED; } /** * pm_runtime_enabled - Check if runtime PM is enabled. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev. */ static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; } /** * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. * @dev: Target device. * * Return %true if @dev is a special device without runtime PM callbacks or * %false otherwise. */ static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return dev->power.no_callbacks; } /** * pm_runtime_mark_last_busy - Update the last access time of a device. * @dev: Target device. * * Update the last access time of @dev used by the runtime PM autosuspend * mechanism to the current time as returned by ktime_get_mono_fast_ns(). */ static inline void pm_runtime_mark_last_busy(struct device *dev) { WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } /** * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context. * @dev: Target device. * * Return %true if @dev has been marked as an "IRQ-safe" device (with respect * to runtime PM), in which case its runtime PM callabcks can be expected to * work correctly when invoked from interrupt handlers. */ static inline bool pm_runtime_is_irq_safe(struct device *dev) { return dev->power.irq_safe; } extern u64 pm_runtime_suspended_time(struct device *dev); #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } static inline int pm_runtime_force_suspend(struct device *dev) { return 0; } static inline int pm_runtime_force_resume(struct device *dev) { return 0; } static inline int __pm_runtime_idle(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_suspend(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_resume(struct device *dev, int rpmflags) { return 1; } static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) { return -ENOSYS; } static inline int pm_runtime_get_if_in_use(struct device *dev) { return -EINVAL; } static inline int pm_runtime_get_if_active(struct device *dev) { return -EINVAL; } static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } static inline void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} static inline void pm_runtime_irq_safe(struct device *dev) {} static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; } static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return false; } static inline void pm_runtime_mark_last_busy(struct device *dev) {} static inline void __pm_runtime_use_autosuspend(struct device *dev, bool use) {} static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ /** * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it. * @dev: Target device. * * Invoke the "idle check" callback of @dev and, depending on its return value, * set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend has been enabled for it). */ static inline int pm_runtime_idle(struct device *dev) { return __pm_runtime_idle(dev, 0); } /** * pm_runtime_suspend - Suspend a device synchronously. * @dev: Target device. */ static inline int pm_runtime_suspend(struct device *dev) { return __pm_runtime_suspend(dev, 0); } /** * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it. * @dev: Target device. * * Set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend is enabled for it) without engaging its "idle check" callback. */ static inline int pm_runtime_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_AUTO); } /** * pm_runtime_resume - Resume a device synchronously. * @dev: Target device. */ static inline int pm_runtime_resume(struct device *dev) { return __pm_runtime_resume(dev, 0); } /** * pm_request_idle - Queue up "idle check" execution for a device. * @dev: Target device. * * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev * asynchronously. */ static inline int pm_request_idle(struct device *dev) { return __pm_runtime_idle(dev, RPM_ASYNC); } /** * pm_request_resume - Queue up runtime-resume of a device. * @dev: Target device. */ static inline int pm_request_resume(struct device *dev) { return __pm_runtime_resume(dev, RPM_ASYNC); } /** * pm_request_autosuspend - Queue up autosuspend of a device. * @dev: Target device. * * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev * asynchronously. */ static inline int pm_request_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_get - Bump up usage counter and queue up resume of a device. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and queue up a work item to * carry out runtime-resume of it. */ static inline int pm_runtime_get(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC); } /** * pm_runtime_get_sync - Bump up usage counter of a device and resume it. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of * it synchronously. * * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. * Consider using pm_runtime_resume_and_get() instead of it, especially * if its return value is checked by the caller, as this is likely to result * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT); } /** * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. * @dev: Target device. * * Resume @dev synchronously and if that is successful, increment its runtime * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been * incremented or a negative error code otherwise. */ static inline int pm_runtime_resume_and_get(struct device *dev) { int ret; ret = __pm_runtime_resume(dev, RPM_GET_PUT); if (ret < 0) { pm_runtime_put_noidle(dev); return ret; } return 0; } /** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). */ static inline int pm_runtime_put(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } /** * __pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int __pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, invoke the "idle check" callback of @dev and, depending on its * return value, set up autosuspend of @dev or suspend it (depending on whether * or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_idle() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, carry out runtime-suspend of @dev synchronously. * * The possible return values of this function are the same as for * pm_runtime_suspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_suspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending * on whether or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); } /** * pm_runtime_set_active - Set runtime PM status to "active". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies * of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_active(struct device *dev) { return __pm_runtime_set_status(dev, RPM_ACTIVE); } /** * pm_runtime_set_suspended - Set runtime PM status to "suspended". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that * dependencies of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_suspended(struct device *dev) { return __pm_runtime_set_status(dev, RPM_SUSPENDED); } /** * pm_runtime_disable - Disable runtime PM for a device. * @dev: Target device. * * Prevent the runtime PM framework from working with @dev (by incrementing its * "blocking" counter). * * For each invocation of this function for @dev there must be a matching * pm_runtime_enable() call in order for runtime PM to be enabled for it. */ static inline void pm_runtime_disable(struct device *dev) { __pm_runtime_disable(dev, true); } /** * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device. * @dev: Target device. * * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). * * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() * at driver exit time unless your driver initially enabled pm_runtime * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, true); } /** * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used. * @dev: Target device. * * Prevent the runtime PM autosuspend mechanism from being used for @dev which * means that "autosuspend" will be handled as direct runtime-suspend for it * going forward. */ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, false); } #endif |
| 183 8322 7168 7459 7318 4438 6254 39 3273 3273 14 1592 1590 590 147 3 99 9 118 1707 522 461 23 3907 2080 1117 104 1892 6118 4433 1 2 599 1187 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/container_of.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <asm/barrier.h> /* * Circular doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } #ifdef CONFIG_LIST_HARDENED #ifdef CONFIG_DEBUG_LIST # define __list_valid_slowpath #else # define __list_valid_slowpath __cold __preserve_most #endif /* * Performs the full set of list corruption checks before __list_add(). * On list corruption reports a warning, and returns false. */ extern bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new, struct list_head *prev, struct list_head *next); /* * Performs list corruption checks before __list_add(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_add_valid_or_report(). */ static __always_inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { /* * With the hardening version, elide checking if next and prev * are NULL, since the immediate dereference of them below would * result in a fault if NULL. * * With the reduced set of checks, we can afford to inline the * checks, which also gives the compiler a chance to elide some * of them completely if they can be proven at compile-time. If * one of the pre-conditions does not hold, the slow-path will * show a report which pre-condition failed. */ if (likely(next->prev == prev && prev->next == next && new != prev && new != next)) return true; ret = false; } ret &= __list_add_valid_or_report(new, prev, next); return ret; } /* * Performs the full set of list corruption checks before __list_del_entry(). * On list corruption reports a warning, and returns false. */ extern bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry); /* * Performs list corruption checks before __list_del_entry(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_del_entry_valid_or_report(). */ static __always_inline bool __list_del_entry_valid(struct list_head *entry) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { struct list_head *prev = entry->prev; struct list_head *next = entry->next; /* * With the hardening version, elide checking if next and prev * are NULL, LIST_POISON1 or LIST_POISON2, since the immediate * dereference of them below would result in a fault. */ if (likely(prev->next == entry && next->prev == entry)) return true; ret = false; } ret &= __list_del_entry_valid_or_report(entry); return ret; } #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_is_head - tests whether @list is the list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_head(const struct list_head *list, const struct list_head *head) { return list == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_next_entry_circular - get the next element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the last element (return the first element). * Note, that list is expected to be not empty. */ #define list_next_entry_circular(pos, head, member) \ (list_is_last(&(pos)->member, head) ? \ list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_prev_entry_circular - get the prev element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the first element (return the last element). * Note, that list is expected to be not empty. */ #define list_prev_entry_circular(pos, head, member) \ (list_is_first(&(pos)->member, head) ? \ list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_reverse - iterate backwards over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_reverse(pos, head) \ for (pos = (head)->prev; pos != (head); pos = pos->prev) /** * list_for_each_rcu - Iterate over a list in an RCU-safe fashion * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_rcu(pos, head) \ for (pos = rcu_dereference((head)->next); \ !list_is_head(pos, (head)); \ pos = rcu_dereference(pos->next)) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; \ !list_is_head(pos, (head)); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** * list_count_nodes - count nodes in the list * @head: the head for your list. */ static inline size_t list_count_nodes(struct list_head *head) { struct list_head *pos; size_t count = 0; list_for_each(pos, head) count++; return count; } /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ list_is_head(&pos->member, (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behind - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } /** * hlist_splice_init() - move all entries from one list to another * @from: hlist_head from which entries will be moved * @last: last entry on the @from list * @to: hlist_head to which entries will be moved * * @to can be empty, @from must contain at least @last. */ static inline void hlist_splice_init(struct hlist_head *from, struct hlist_node *last, struct hlist_head *to) { if (to->first) to->first->pprev = &last->next; last->next = to->first; to->first = from->first; from->first->pprev = &to->first; from->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) /** * hlist_count_nodes - count nodes in the hlist * @head: the head for your hlist. */ static inline size_t hlist_count_nodes(struct hlist_head *head) { struct hlist_node *pos; size_t count = 0; hlist_for_each(pos, head) count++; return count; } #endif |
| 10 10 2 31 32 30 50 50 50 49 50 50 50 43 44 2 42 41 41 1 49 50 47 1 1 1 1 43 1 42 2 41 3 1 43 44 42 2 43 2 2 39 2 4 33 33 33 49 50 1 50 3 47 48 50 50 50 50 47 1 1 2 2 2 48 48 50 48 1 1 1 1 37 37 37 1 33 37 36 37 37 37 37 37 | 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "checksum.h" #include "disk_groups.h" #include "ec.h" #include "error.h" #include "journal.h" #include "journal_sb.h" #include "journal_seq_blacklist.h" #include "recovery_passes.h" #include "replicas.h" #include "quota.h" #include "sb-clean.h" #include "sb-counters.h" #include "sb-downgrade.h" #include "sb-errors.h" #include "sb-members.h" #include "super-io.h" #include "super.h" #include "trace.h" #include "vstructs.h" #include <linux/backing-dev.h> #include <linux/sort.h> static const struct blk_holder_ops bch2_sb_handle_bdev_ops = { }; struct bch2_metadata_version { u16 version; const char *name; }; static const struct bch2_metadata_version bch2_metadata_versions[] = { #define x(n, v) { \ .version = v, \ .name = #n, \ }, BCH_METADATA_VERSIONS() #undef x }; void bch2_version_to_text(struct printbuf *out, unsigned v) { const char *str = "(unknown version)"; for (unsigned i = 0; i < ARRAY_SIZE(bch2_metadata_versions); i++) if (bch2_metadata_versions[i].version == v) { str = bch2_metadata_versions[i].name; break; } prt_printf(out, "%u.%u: %s", BCH_VERSION_MAJOR(v), BCH_VERSION_MINOR(v), str); } unsigned bch2_latest_compatible_version(unsigned v) { if (!BCH_VERSION_MAJOR(v)) return v; for (unsigned i = 0; i < ARRAY_SIZE(bch2_metadata_versions); i++) if (bch2_metadata_versions[i].version > v && BCH_VERSION_MAJOR(bch2_metadata_versions[i].version) == BCH_VERSION_MAJOR(v)) v = bch2_metadata_versions[i].version; return v; } const char * const bch2_sb_fields[] = { #define x(name, nr) #name, BCH_SB_FIELDS() #undef x NULL }; static int bch2_sb_field_validate(struct bch_sb *, struct bch_sb_field *, enum bch_validate_flags, struct printbuf *); struct bch_sb_field *bch2_sb_field_get_id(struct bch_sb *sb, enum bch_sb_field_type type) { /* XXX: need locking around superblock to access optional fields */ vstruct_for_each(sb, f) if (le32_to_cpu(f->type) == type) return f; return NULL; } static struct bch_sb_field *__bch2_sb_field_resize(struct bch_sb_handle *sb, struct bch_sb_field *f, unsigned u64s) { unsigned old_u64s = f ? le32_to_cpu(f->u64s) : 0; unsigned sb_u64s = le32_to_cpu(sb->sb->u64s) + u64s - old_u64s; BUG_ON(__vstruct_bytes(struct bch_sb, sb_u64s) > sb->buffer_size); if (!f && !u64s) { /* nothing to do: */ } else if (!f) { f = vstruct_last(sb->sb); memset(f, 0, sizeof(u64) * u64s); f->u64s = cpu_to_le32(u64s); f->type = 0; } else { void *src, *dst; src = vstruct_end(f); if (u64s) { f->u64s = cpu_to_le32(u64s); dst = vstruct_end(f); } else { dst = f; } memmove(dst, src, vstruct_end(sb->sb) - src); if (dst > src) memset(src, 0, dst - src); } sb->sb->u64s = cpu_to_le32(sb_u64s); return u64s ? f : NULL; } void bch2_sb_field_delete(struct bch_sb_handle *sb, enum bch_sb_field_type type) { struct bch_sb_field *f = bch2_sb_field_get_id(sb->sb, type); if (f) __bch2_sb_field_resize(sb, f, 0); } /* Superblock realloc/free: */ void bch2_free_super(struct bch_sb_handle *sb) { kfree(sb->bio); if (!IS_ERR_OR_NULL(sb->s_bdev_file)) bdev_fput(sb->s_bdev_file); kfree(sb->holder); kfree(sb->sb_name); kfree(sb->sb); memset(sb, 0, sizeof(*sb)); } int bch2_sb_realloc(struct bch_sb_handle *sb, unsigned u64s) { size_t new_bytes = __vstruct_bytes(struct bch_sb, u64s); size_t new_buffer_size; struct bch_sb *new_sb; struct bio *bio; if (sb->bdev) new_bytes = max_t(size_t, new_bytes, bdev_logical_block_size(sb->bdev)); new_buffer_size = roundup_pow_of_two(new_bytes); if (sb->sb && sb->buffer_size >= new_buffer_size) return 0; if (sb->sb && sb->have_layout) { u64 max_bytes = 512 << sb->sb->layout.sb_max_size_bits; if (new_bytes > max_bytes) { struct printbuf buf = PRINTBUF; prt_bdevname(&buf, sb->bdev); prt_printf(&buf, ": superblock too big: want %zu but have %llu", new_bytes, max_bytes); pr_err("%s", buf.buf); printbuf_exit(&buf); return -BCH_ERR_ENOSPC_sb; } } if (sb->buffer_size >= new_buffer_size && sb->sb) return 0; if (dynamic_fault("bcachefs:add:super_realloc")) return -BCH_ERR_ENOMEM_sb_realloc_injected; new_sb = krealloc(sb->sb, new_buffer_size, GFP_NOFS|__GFP_ZERO); if (!new_sb) return -BCH_ERR_ENOMEM_sb_buf_realloc; sb->sb = new_sb; if (sb->have_bio) { unsigned nr_bvecs = buf_pages(sb->sb, new_buffer_size); bio = bio_kmalloc(nr_bvecs, GFP_KERNEL); if (!bio) return -BCH_ERR_ENOMEM_sb_bio_realloc; bio_init(bio, NULL, bio->bi_inline_vecs, nr_bvecs, 0); kfree(sb->bio); sb->bio = bio; } sb->buffer_size = new_buffer_size; return 0; } struct bch_sb_field *bch2_sb_field_resize_id(struct bch_sb_handle *sb, enum bch_sb_field_type type, unsigned u64s) { struct bch_sb_field *f = bch2_sb_field_get_id(sb->sb, type); ssize_t old_u64s = f ? le32_to_cpu(f->u64s) : 0; ssize_t d = -old_u64s + u64s; if (bch2_sb_realloc(sb, le32_to_cpu(sb->sb->u64s) + d)) return NULL; if (sb->fs_sb) { struct bch_fs *c = container_of(sb, struct bch_fs, disk_sb); lockdep_assert_held(&c->sb_lock); /* XXX: we're not checking that offline device have enough space */ for_each_online_member(c, ca) { struct bch_sb_handle *dev_sb = &ca->disk_sb; if (bch2_sb_realloc(dev_sb, le32_to_cpu(dev_sb->sb->u64s) + d)) { percpu_ref_put(&ca->io_ref); return NULL; } } } f = bch2_sb_field_get_id(sb->sb, type); f = __bch2_sb_field_resize(sb, f, u64s); if (f) f->type = cpu_to_le32(type); return f; } struct bch_sb_field *bch2_sb_field_get_minsize_id(struct bch_sb_handle *sb, enum bch_sb_field_type type, unsigned u64s) { struct bch_sb_field *f = bch2_sb_field_get_id(sb->sb, type); if (!f || le32_to_cpu(f->u64s) < u64s) f = bch2_sb_field_resize_id(sb, type, u64s); return f; } /* Superblock validate: */ static int validate_sb_layout(struct bch_sb_layout *layout, struct printbuf *out) { u64 offset, prev_offset, max_sectors; unsigned i; BUILD_BUG_ON(sizeof(struct bch_sb_layout) != 512); if (!uuid_equal(&layout->magic, &BCACHE_MAGIC) && !uuid_equal(&layout->magic, &BCHFS_MAGIC)) { prt_printf(out, "Not a bcachefs superblock layout"); return -BCH_ERR_invalid_sb_layout; } if (layout->layout_type != 0) { prt_printf(out, "Invalid superblock layout type %u", layout->layout_type); return -BCH_ERR_invalid_sb_layout_type; } if (!layout->nr_superblocks) { prt_printf(out, "Invalid superblock layout: no superblocks"); return -BCH_ERR_invalid_sb_layout_nr_superblocks; } if (layout->nr_superblocks > ARRAY_SIZE(layout->sb_offset)) { prt_printf(out, "Invalid superblock layout: too many superblocks"); return -BCH_ERR_invalid_sb_layout_nr_superblocks; } max_sectors = 1 << layout->sb_max_size_bits; prev_offset = le64_to_cpu(layout->sb_offset[0]); for (i = 1; i < layout->nr_superblocks; i++) { offset = le64_to_cpu(layout->sb_offset[i]); if (offset < prev_offset + max_sectors) { prt_printf(out, "Invalid superblock layout: superblocks overlap\n" " (sb %u ends at %llu next starts at %llu", i - 1, prev_offset + max_sectors, offset); return -BCH_ERR_invalid_sb_layout_superblocks_overlap; } prev_offset = offset; } return 0; } static int bch2_sb_compatible(struct bch_sb *sb, struct printbuf *out) { u16 version = le16_to_cpu(sb->version); u16 version_min = le16_to_cpu(sb->version_min); if (!bch2_version_compatible(version)) { prt_str(out, "Unsupported superblock version "); bch2_version_to_text(out, version); prt_str(out, " (min "); bch2_version_to_text(out, bcachefs_metadata_version_min); prt_str(out, ", max "); bch2_version_to_text(out, bcachefs_metadata_version_current); prt_str(out, ")"); return -BCH_ERR_invalid_sb_version; } if (!bch2_version_compatible(version_min)) { prt_str(out, "Unsupported superblock version_min "); bch2_version_to_text(out, version_min); prt_str(out, " (min "); bch2_version_to_text(out, bcachefs_metadata_version_min); prt_str(out, ", max "); bch2_version_to_text(out, bcachefs_metadata_version_current); prt_str(out, ")"); return -BCH_ERR_invalid_sb_version; } if (version_min > version) { prt_str(out, "Bad minimum version "); bch2_version_to_text(out, version_min); prt_str(out, ", greater than version field "); bch2_version_to_text(out, version); return -BCH_ERR_invalid_sb_version; } return 0; } static int bch2_sb_validate(struct bch_sb_handle *disk_sb, enum bch_validate_flags flags, struct printbuf *out) { struct bch_sb *sb = disk_sb->sb; struct bch_sb_field_members_v1 *mi; enum bch_opt_id opt_id; u16 block_size; int ret; ret = bch2_sb_compatible(sb, out); if (ret) return ret; if (sb->features[1] || (le64_to_cpu(sb->features[0]) & (~0ULL << BCH_FEATURE_NR))) { prt_printf(out, "Filesystem has incompatible features"); return -BCH_ERR_invalid_sb_features; } block_size = le16_to_cpu(sb->block_size); if (block_size > PAGE_SECTORS) { prt_printf(out, "Block size too big (got %u, max %u)", block_size, PAGE_SECTORS); return -BCH_ERR_invalid_sb_block_size; } if (bch2_is_zero(sb->user_uuid.b, sizeof(sb->user_uuid))) { prt_printf(out, "Bad user UUID (got zeroes)"); return -BCH_ERR_invalid_sb_uuid; } if (bch2_is_zero(sb->uuid.b, sizeof(sb->uuid))) { prt_printf(out, "Bad internal UUID (got zeroes)"); return -BCH_ERR_invalid_sb_uuid; } if (!sb->nr_devices || sb->nr_devices > BCH_SB_MEMBERS_MAX) { prt_printf(out, "Bad number of member devices %u (max %u)", sb->nr_devices, BCH_SB_MEMBERS_MAX); return -BCH_ERR_invalid_sb_too_many_members; } if (sb->dev_idx >= sb->nr_devices) { prt_printf(out, "Bad dev_idx (got %u, nr_devices %u)", sb->dev_idx, sb->nr_devices); return -BCH_ERR_invalid_sb_dev_idx; } if (!sb->time_precision || le32_to_cpu(sb->time_precision) > NSEC_PER_SEC) { prt_printf(out, "Invalid time precision: %u (min 1, max %lu)", le32_to_cpu(sb->time_precision), NSEC_PER_SEC); return -BCH_ERR_invalid_sb_time_precision; } if (!flags) { /* * Been seeing a bug where these are getting inexplicably * zeroed, so we're now validating them, but we have to be * careful not to preven people's filesystems from mounting: */ if (!BCH_SB_JOURNAL_FLUSH_DELAY(sb)) SET_BCH_SB_JOURNAL_FLUSH_DELAY(sb, 1000); if (!BCH_SB_JOURNAL_RECLAIM_DELAY(sb)) SET_BCH_SB_JOURNAL_RECLAIM_DELAY(sb, 1000); if (!BCH_SB_VERSION_UPGRADE_COMPLETE(sb)) SET_BCH_SB_VERSION_UPGRADE_COMPLETE(sb, le16_to_cpu(sb->version)); if (le16_to_cpu(sb->version) <= bcachefs_metadata_version_disk_accounting_v2 && !BCH_SB_ALLOCATOR_STUCK_TIMEOUT(sb)) SET_BCH_SB_ALLOCATOR_STUCK_TIMEOUT(sb, 30); } for (opt_id = 0; opt_id < bch2_opts_nr; opt_id++) { const struct bch_option *opt = bch2_opt_table + opt_id; if (opt->get_sb != BCH2_NO_SB_OPT) { u64 v = bch2_opt_from_sb(sb, opt_id); prt_printf(out, "Invalid option "); ret = bch2_opt_validate(opt, v, out); if (ret) return ret; printbuf_reset(out); } } /* validate layout */ ret = validate_sb_layout(&sb->layout, out); if (ret) return ret; vstruct_for_each(sb, f) { if (!f->u64s) { prt_printf(out, "Invalid superblock: optional field with size 0 (type %u)", le32_to_cpu(f->type)); return -BCH_ERR_invalid_sb_field_size; } if (vstruct_next(f) > vstruct_last(sb)) { prt_printf(out, "Invalid superblock: optional field extends past end of superblock (type %u)", le32_to_cpu(f->type)); return -BCH_ERR_invalid_sb_field_size; } } /* members must be validated first: */ mi = bch2_sb_field_get(sb, members_v1); if (!mi) { prt_printf(out, "Invalid superblock: member info area missing"); return -BCH_ERR_invalid_sb_members_missing; } ret = bch2_sb_field_validate(sb, &mi->field, flags, out); if (ret) return ret; vstruct_for_each(sb, f) { if (le32_to_cpu(f->type) == BCH_SB_FIELD_members_v1) continue; ret = bch2_sb_field_validate(sb, f, flags, out); if (ret) return ret; } if ((flags & BCH_VALIDATE_write) && bch2_sb_member_get(sb, sb->dev_idx).seq != sb->seq) { prt_printf(out, "Invalid superblock: member seq %llu != sb seq %llu", le64_to_cpu(bch2_sb_member_get(sb, sb->dev_idx).seq), le64_to_cpu(sb->seq)); return -BCH_ERR_invalid_sb_members_missing; } return 0; } /* device open: */ static unsigned long le_ulong_to_cpu(unsigned long v) { return sizeof(unsigned long) == 8 ? le64_to_cpu(v) : le32_to_cpu(v); } static void le_bitvector_to_cpu(unsigned long *dst, unsigned long *src, unsigned nr) { BUG_ON(nr & (BITS_PER_TYPE(long) - 1)); for (unsigned i = 0; i < BITS_TO_LONGS(nr); i++) dst[i] = le_ulong_to_cpu(src[i]); } static void bch2_sb_update(struct bch_fs *c) { struct bch_sb *src = c->disk_sb.sb; lockdep_assert_held(&c->sb_lock); c->sb.uuid = src->uuid; c->sb.user_uuid = src->user_uuid; c->sb.version = le16_to_cpu(src->version); c->sb.version_min = le16_to_cpu(src->version_min); c->sb.version_upgrade_complete = BCH_SB_VERSION_UPGRADE_COMPLETE(src); c->sb.nr_devices = src->nr_devices; c->sb.clean = BCH_SB_CLEAN(src); c->sb.encryption_type = BCH_SB_ENCRYPTION_TYPE(src); c->sb.nsec_per_time_unit = le32_to_cpu(src->time_precision); c->sb.time_units_per_sec = NSEC_PER_SEC / c->sb.nsec_per_time_unit; /* XXX this is wrong, we need a 96 or 128 bit integer type */ c->sb.time_base_lo = div_u64(le64_to_cpu(src->time_base_lo), c->sb.nsec_per_time_unit); c->sb.time_base_hi = le32_to_cpu(src->time_base_hi); c->sb.features = le64_to_cpu(src->features[0]); c->sb.compat = le64_to_cpu(src->compat[0]); memset(c->sb.errors_silent, 0, sizeof(c->sb.errors_silent)); struct bch_sb_field_ext *ext = bch2_sb_field_get(src, ext); if (ext) { le_bitvector_to_cpu(c->sb.errors_silent, (void *) ext->errors_silent, sizeof(c->sb.errors_silent) * 8); c->sb.btrees_lost_data = le64_to_cpu(ext->btrees_lost_data); } for_each_member_device(c, ca) { struct bch_member m = bch2_sb_member_get(src, ca->dev_idx); ca->mi = bch2_mi_to_cpu(&m); } } static int __copy_super(struct bch_sb_handle *dst_handle, struct bch_sb *src) { struct bch_sb_field *src_f, *dst_f; struct bch_sb *dst = dst_handle->sb; unsigned i; dst->version = src->version; dst->version_min = src->version_min; dst->seq = src->seq; dst->uuid = src->uuid; dst->user_uuid = src->user_uuid; memcpy(dst->label, src->label, sizeof(dst->label)); dst->block_size = src->block_size; dst->nr_devices = src->nr_devices; dst->time_base_lo = src->time_base_lo; dst->time_base_hi = src->time_base_hi; dst->time_precision = src->time_precision; dst->write_time = src->write_time; memcpy(dst->flags, src->flags, sizeof(dst->flags)); memcpy(dst->features, src->features, sizeof(dst->features)); memcpy(dst->compat, src->compat, sizeof(dst->compat)); for (i = 0; i < BCH_SB_FIELD_NR; i++) { int d; if ((1U << i) & BCH_SINGLE_DEVICE_SB_FIELDS) continue; src_f = bch2_sb_field_get_id(src, i); dst_f = bch2_sb_field_get_id(dst, i); d = (src_f ? le32_to_cpu(src_f->u64s) : 0) - (dst_f ? le32_to_cpu(dst_f->u64s) : 0); if (d > 0) { int ret = bch2_sb_realloc(dst_handle, le32_to_cpu(dst_handle->sb->u64s) + d); if (ret) return ret; dst = dst_handle->sb; dst_f = bch2_sb_field_get_id(dst, i); } dst_f = __bch2_sb_field_resize(dst_handle, dst_f, src_f ? le32_to_cpu(src_f->u64s) : 0); if (src_f) memcpy(dst_f, src_f, vstruct_bytes(src_f)); } return 0; } int bch2_sb_to_fs(struct bch_fs *c, struct bch_sb *src) { int ret; lockdep_assert_held(&c->sb_lock); ret = bch2_sb_realloc(&c->disk_sb, 0) ?: __copy_super(&c->disk_sb, src) ?: bch2_sb_replicas_to_cpu_replicas(c) ?: bch2_sb_disk_groups_to_cpu(c); if (ret) return ret; bch2_sb_update(c); return 0; } int bch2_sb_from_fs(struct bch_fs *c, struct bch_dev *ca) { return __copy_super(&ca->disk_sb, c->disk_sb.sb); } /* read superblock: */ static int read_one_super(struct bch_sb_handle *sb, u64 offset, struct printbuf *err) { size_t bytes; int ret; reread: bio_reset(sb->bio, sb->bdev, REQ_OP_READ|REQ_SYNC|REQ_META); sb->bio->bi_iter.bi_sector = offset; bch2_bio_map(sb->bio, sb->sb, sb->buffer_size); ret = submit_bio_wait(sb->bio); if (ret) { prt_printf(err, "IO error: %i", ret); return ret; } if (!uuid_equal(&sb->sb->magic, &BCACHE_MAGIC) && !uuid_equal(&sb->sb->magic, &BCHFS_MAGIC)) { prt_str(err, "Not a bcachefs superblock (got magic "); pr_uuid(err, sb->sb->magic.b); prt_str(err, ")"); return -BCH_ERR_invalid_sb_magic; } ret = bch2_sb_compatible(sb->sb, err); if (ret) return ret; bytes = vstruct_bytes(sb->sb); u64 sb_size = 512ULL << min(BCH_SB_LAYOUT_SIZE_BITS_MAX, sb->sb->layout.sb_max_size_bits); if (bytes > sb_size) { prt_printf(err, "Invalid superblock: too big (got %zu bytes, layout max %llu)", bytes, sb_size); return -BCH_ERR_invalid_sb_too_big; } if (bytes > sb->buffer_size) { ret = bch2_sb_realloc(sb, le32_to_cpu(sb->sb->u64s)); if (ret) return ret; goto reread; } enum bch_csum_type csum_type = BCH_SB_CSUM_TYPE(sb->sb); if (csum_type >= BCH_CSUM_NR) { prt_printf(err, "unknown checksum type %llu", BCH_SB_CSUM_TYPE(sb->sb)); return -BCH_ERR_invalid_sb_csum_type; } /* XXX: verify MACs */ struct bch_csum csum = csum_vstruct(NULL, csum_type, null_nonce(), sb->sb); if (bch2_crc_cmp(csum, sb->sb->csum)) { bch2_csum_err_msg(err, csum_type, sb->sb->csum, csum); return -BCH_ERR_invalid_sb_csum; } sb->seq = le64_to_cpu(sb->sb->seq); return 0; } static int __bch2_read_super(const char *path, struct bch_opts *opts, struct bch_sb_handle *sb, bool ignore_notbchfs_msg) { u64 offset = opt_get(*opts, sb); struct bch_sb_layout layout; struct printbuf err = PRINTBUF; struct printbuf err2 = PRINTBUF; __le64 *i; int ret; #ifndef __KERNEL__ retry: #endif memset(sb, 0, sizeof(*sb)); sb->mode = BLK_OPEN_READ; sb->have_bio = true; sb->holder = kmalloc(1, GFP_KERNEL); if (!sb->holder) return -ENOMEM; sb->sb_name = kstrdup(path, GFP_KERNEL); if (!sb->sb_name) { ret = -ENOMEM; prt_printf(&err, "error allocating memory for sb_name"); goto err; } #ifndef __KERNEL__ if (opt_get(*opts, direct_io) == false) sb->mode |= BLK_OPEN_BUFFERED; #endif if (!opt_get(*opts, noexcl)) sb->mode |= BLK_OPEN_EXCL; if (!opt_get(*opts, nochanges)) sb->mode |= BLK_OPEN_WRITE; sb->s_bdev_file = bdev_file_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops); if (IS_ERR(sb->s_bdev_file) && PTR_ERR(sb->s_bdev_file) == -EACCES && opt_get(*opts, read_only)) { sb->mode &= ~BLK_OPEN_WRITE; sb->s_bdev_file = bdev_file_open_by_path(path, sb->mode, sb->holder, &bch2_sb_handle_bdev_ops); if (!IS_ERR(sb->s_bdev_file)) opt_set(*opts, nochanges, true); } if (IS_ERR(sb->s_bdev_file)) { ret = PTR_ERR(sb->s_bdev_file); prt_printf(&err, "error opening %s: %s", path, bch2_err_str(ret)); goto err; } sb->bdev = file_bdev(sb->s_bdev_file); ret = bch2_sb_realloc(sb, 0); if (ret) { prt_printf(&err, "error allocating memory for superblock"); goto err; } if (bch2_fs_init_fault("read_super")) { prt_printf(&err, "dynamic fault"); ret = -EFAULT; goto err; } ret = read_one_super(sb, offset, &err); if (!ret) goto got_super; if (opt_defined(*opts, sb)) goto err; prt_printf(&err2, "bcachefs (%s): error reading default superblock: %s\n", path, err.buf); if (ret == -BCH_ERR_invalid_sb_magic && ignore_notbchfs_msg) bch2_print_opts(opts, KERN_INFO "%s", err2.buf); else bch2_print_opts(opts, KERN_ERR "%s", err2.buf); printbuf_exit(&err2); printbuf_reset(&err); /* * Error reading primary superblock - read location of backup * superblocks: */ bio_reset(sb->bio, sb->bdev, REQ_OP_READ|REQ_SYNC|REQ_META); sb->bio->bi_iter.bi_sector = BCH_SB_LAYOUT_SECTOR; /* * use sb buffer to read layout, since sb buffer is page aligned but * layout won't be: */ bch2_bio_map(sb->bio, sb->sb, sizeof(struct bch_sb_layout)); ret = submit_bio_wait(sb->bio); if (ret) { prt_printf(&err, "IO error: %i", ret); goto err; } memcpy(&layout, sb->sb, sizeof(layout)); ret = validate_sb_layout(&layout, &err); if (ret) goto err; for (i = layout.sb_offset; i < layout.sb_offset + layout.nr_superblocks; i++) { offset = le64_to_cpu(*i); if (offset == opt_get(*opts, sb)) continue; ret = read_one_super(sb, offset, &err); if (!ret) goto got_super; } goto err; got_super: if (le16_to_cpu(sb->sb->block_size) << 9 < bdev_logical_block_size(sb->bdev) && opt_get(*opts, direct_io)) { #ifndef __KERNEL__ opt_set(*opts, direct_io, false); bch2_free_super(sb); goto retry; #endif prt_printf(&err, "block size (%u) smaller than device block size (%u)", le16_to_cpu(sb->sb->block_size) << 9, bdev_logical_block_size(sb->bdev)); ret = -BCH_ERR_block_size_too_small; goto err; } sb->have_layout = true; ret = bch2_sb_validate(sb, 0, &err); if (ret) { bch2_print_opts(opts, KERN_ERR "bcachefs (%s): error validating superblock: %s\n", path, err.buf); goto err_no_print; } out: printbuf_exit(&err); return ret; err: bch2_print_opts(opts, KERN_ERR "bcachefs (%s): error reading superblock: %s\n", path, err.buf); err_no_print: bch2_free_super(sb); goto out; } int bch2_read_super(const char *path, struct bch_opts *opts, struct bch_sb_handle *sb) { return __bch2_read_super(path, opts, sb, false); } /* provide a silenced version for mount.bcachefs */ int bch2_read_super_silent(const char *path, struct bch_opts *opts, struct bch_sb_handle *sb) { return __bch2_read_super(path, opts, sb, true); } /* write superblock: */ static void write_super_endio(struct bio *bio) { struct bch_dev *ca = bio->bi_private; /* XXX: return errors directly */ if (bch2_dev_io_err_on(bio->bi_status, ca, bio_data_dir(bio) ? BCH_MEMBER_ERROR_write : BCH_MEMBER_ERROR_read, "superblock %s error: %s", bio_data_dir(bio) ? "write" : "read", bch2_blk_status_to_str(bio->bi_status))) ca->sb_write_error = 1; closure_put(&ca->fs->sb_write); percpu_ref_put(&ca->io_ref); } static void read_back_super(struct bch_fs *c, struct bch_dev *ca) { struct bch_sb *sb = ca->disk_sb.sb; struct bio *bio = ca->disk_sb.bio; bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ|REQ_SYNC|REQ_META); bio->bi_iter.bi_sector = le64_to_cpu(sb->layout.sb_offset[0]); bio->bi_end_io = write_super_endio; bio->bi_private = ca; bch2_bio_map(bio, ca->sb_read_scratch, PAGE_SIZE); this_cpu_add(ca->io_done->sectors[READ][BCH_DATA_sb], bio_sectors(bio)); percpu_ref_get(&ca->io_ref); closure_bio_submit(bio, &c->sb_write); } static void write_one_super(struct bch_fs *c, struct bch_dev *ca, unsigned idx) { struct bch_sb *sb = ca->disk_sb.sb; struct bio *bio = ca->disk_sb.bio; sb->offset = sb->layout.sb_offset[idx]; SET_BCH_SB_CSUM_TYPE(sb, bch2_csum_opt_to_type(c->opts.metadata_checksum, false)); sb->csum = csum_vstruct(c, BCH_SB_CSUM_TYPE(sb), null_nonce(), sb); bio_reset(bio, ca->disk_sb.bdev, REQ_OP_WRITE|REQ_SYNC|REQ_META); bio->bi_iter.bi_sector = le64_to_cpu(sb->offset); bio->bi_end_io = write_super_endio; bio->bi_private = ca; bch2_bio_map(bio, sb, roundup((size_t) vstruct_bytes(sb), bdev_logical_block_size(ca->disk_sb.bdev))); this_cpu_add(ca->io_done->sectors[WRITE][BCH_DATA_sb], bio_sectors(bio)); percpu_ref_get(&ca->io_ref); closure_bio_submit(bio, &c->sb_write); } int bch2_write_super(struct bch_fs *c) { struct closure *cl = &c->sb_write; struct printbuf err = PRINTBUF; unsigned sb = 0, nr_wrote; struct bch_devs_mask sb_written; bool wrote, can_mount_without_written, can_mount_with_written; unsigned degraded_flags = BCH_FORCE_IF_DEGRADED; DARRAY(struct bch_dev *) online_devices = {}; int ret = 0; trace_and_count(c, write_super, c, _RET_IP_); if (c->opts.very_degraded) degraded_flags |= BCH_FORCE_IF_LOST; lockdep_assert_held(&c->sb_lock); closure_init_stack(cl); memset(&sb_written, 0, sizeof(sb_written)); for_each_online_member(c, ca) { ret = darray_push(&online_devices, ca); if (bch2_fs_fatal_err_on(ret, c, "%s: error allocating online devices", __func__)) { percpu_ref_put(&ca->io_ref); goto out; } percpu_ref_get(&ca->io_ref); } /* Make sure we're using the new magic numbers: */ c->disk_sb.sb->magic = BCHFS_MAGIC; c->disk_sb.sb->layout.magic = BCHFS_MAGIC; le64_add_cpu(&c->disk_sb.sb->seq, 1); struct bch_sb_field_members_v2 *mi = bch2_sb_field_get(c->disk_sb.sb, members_v2); darray_for_each(online_devices, ca) __bch2_members_v2_get_mut(mi, (*ca)->dev_idx)->seq = c->disk_sb.sb->seq; c->disk_sb.sb->write_time = cpu_to_le64(ktime_get_real_seconds()); if (test_bit(BCH_FS_error, &c->flags)) SET_BCH_SB_HAS_ERRORS(c->disk_sb.sb, 1); if (test_bit(BCH_FS_topology_error, &c->flags)) SET_BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb, 1); SET_BCH_SB_BIG_ENDIAN(c->disk_sb.sb, CPU_BIG_ENDIAN); bch2_sb_counters_from_cpu(c); bch2_sb_members_from_cpu(c); bch2_sb_members_cpy_v2_v1(&c->disk_sb); bch2_sb_errors_from_cpu(c); bch2_sb_downgrade_update(c); darray_for_each(online_devices, ca) bch2_sb_from_fs(c, (*ca)); darray_for_each(online_devices, ca) { printbuf_reset(&err); ret = bch2_sb_validate(&(*ca)->disk_sb, BCH_VALIDATE_write, &err); if (ret) { bch2_fs_inconsistent(c, "sb invalid before write: %s", err.buf); goto out; } } if (c->opts.nochanges) goto out; /* * Defer writing the superblock until filesystem initialization is * complete - don't write out a partly initialized superblock: */ if (!BCH_SB_INITIALIZED(c->disk_sb.sb)) goto out; if (le16_to_cpu(c->disk_sb.sb->version) > bcachefs_metadata_version_current) { struct printbuf buf = PRINTBUF; prt_printf(&buf, "attempting to write superblock that wasn't version downgraded ("); bch2_version_to_text(&buf, le16_to_cpu(c->disk_sb.sb->version)); prt_str(&buf, " > "); bch2_version_to_text(&buf, bcachefs_metadata_version_current); prt_str(&buf, ")"); bch2_fs_fatal_error(c, ": %s", buf.buf); printbuf_exit(&buf); return -BCH_ERR_sb_not_downgraded; } darray_for_each(online_devices, ca) { __set_bit((*ca)->dev_idx, sb_written.d); (*ca)->sb_write_error = 0; } darray_for_each(online_devices, ca) read_back_super(c, *ca); closure_sync(cl); darray_for_each(online_devices, cap) { struct bch_dev *ca = *cap; if (ca->sb_write_error) continue; if (le64_to_cpu(ca->sb_read_scratch->seq) < ca->disk_sb.seq) { struct printbuf buf = PRINTBUF; prt_char(&buf, ' '); prt_bdevname(&buf, ca->disk_sb.bdev); prt_printf(&buf, ": Superblock write was silently dropped! (seq %llu expected %llu)", le64_to_cpu(ca->sb_read_scratch->seq), ca->disk_sb.seq); bch2_fs_fatal_error(c, "%s", buf.buf); printbuf_exit(&buf); ret = -BCH_ERR_erofs_sb_err; } if (le64_to_cpu(ca->sb_read_scratch->seq) > ca->disk_sb.seq) { struct printbuf buf = PRINTBUF; prt_char(&buf, ' '); prt_bdevname(&buf, ca->disk_sb.bdev); prt_printf(&buf, ": Superblock modified by another process (seq %llu expected %llu)", le64_to_cpu(ca->sb_read_scratch->seq), ca->disk_sb.seq); bch2_fs_fatal_error(c, "%s", buf.buf); printbuf_exit(&buf); ret = -BCH_ERR_erofs_sb_err; } } if (ret) goto out; do { wrote = false; darray_for_each(online_devices, cap) { struct bch_dev *ca = *cap; if (!ca->sb_write_error && sb < ca->disk_sb.sb->layout.nr_superblocks) { write_one_super(c, ca, sb); wrote = true; } } closure_sync(cl); sb++; } while (wrote); darray_for_each(online_devices, cap) { struct bch_dev *ca = *cap; if (ca->sb_write_error) __clear_bit(ca->dev_idx, sb_written.d); else ca->disk_sb.seq = le64_to_cpu(ca->disk_sb.sb->seq); } nr_wrote = dev_mask_nr(&sb_written); can_mount_with_written = bch2_have_enough_devs(c, sb_written, degraded_flags, false); for (unsigned i = 0; i < ARRAY_SIZE(sb_written.d); i++) sb_written.d[i] = ~sb_written.d[i]; can_mount_without_written = bch2_have_enough_devs(c, sb_written, degraded_flags, false); /* * If we would be able to mount _without_ the devices we successfully * wrote superblocks to, we weren't able to write to enough devices: * * Exception: if we can mount without the successes because we haven't * written anything (new filesystem), we continue if we'd be able to * mount with the devices we did successfully write to: */ if (bch2_fs_fatal_err_on(!nr_wrote || !can_mount_with_written || (can_mount_without_written && !can_mount_with_written), c, ": Unable to write superblock to sufficient devices (from %ps)", (void *) _RET_IP_)) ret = -1; out: /* Make new options visible after they're persistent: */ bch2_sb_update(c); darray_for_each(online_devices, ca) percpu_ref_put(&(*ca)->io_ref); darray_exit(&online_devices); printbuf_exit(&err); return ret; } void __bch2_check_set_feature(struct bch_fs *c, unsigned feat) { mutex_lock(&c->sb_lock); if (!(c->sb.features & (1ULL << feat))) { c->disk_sb.sb->features[0] |= cpu_to_le64(1ULL << feat); bch2_write_super(c); } mutex_unlock(&c->sb_lock); } /* Downgrade if superblock is at a higher version than currently supported: */ bool bch2_check_version_downgrade(struct bch_fs *c) { bool ret = bcachefs_metadata_version_current < c->sb.version; lockdep_assert_held(&c->sb_lock); /* * Downgrade, if superblock is at a higher version than currently * supported: * * c->sb will be checked before we write the superblock, so update it as * well: */ if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); if (c->sb.version > bcachefs_metadata_version_current) c->disk_sb.sb->version = cpu_to_le16(bcachefs_metadata_version_current); if (c->sb.version_min > bcachefs_metadata_version_current) c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current); c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1); return ret; } void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version) { lockdep_assert_held(&c->sb_lock); if (BCH_VERSION_MAJOR(new_version) > BCH_VERSION_MAJOR(le16_to_cpu(c->disk_sb.sb->version))) bch2_sb_field_resize(&c->disk_sb, downgrade, 0); c->disk_sb.sb->version = cpu_to_le16(new_version); c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL); } static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { if (vstruct_bytes(f) < 88) { prt_printf(err, "field too small (%zu < %u)", vstruct_bytes(f), 88); return -BCH_ERR_invalid_sb_ext; } return 0; } static void bch2_sb_ext_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { struct bch_sb_field_ext *e = field_to_type(f, ext); prt_printf(out, "Recovery passes required:\t"); prt_bitflags(out, bch2_recovery_passes, bch2_recovery_passes_from_stable(le64_to_cpu(e->recovery_passes_required[0]))); prt_newline(out); unsigned long *errors_silent = kmalloc(sizeof(e->errors_silent), GFP_KERNEL); if (errors_silent) { le_bitvector_to_cpu(errors_silent, (void *) e->errors_silent, sizeof(e->errors_silent) * 8); prt_printf(out, "Errors to silently fix:\t"); prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, sizeof(e->errors_silent) * 8); prt_newline(out); kfree(errors_silent); } prt_printf(out, "Btrees with missing data:\t"); prt_bitflags(out, __bch2_btree_ids, le64_to_cpu(e->btrees_lost_data)); prt_newline(out); } static const struct bch_sb_field_ops bch_sb_field_ops_ext = { .validate = bch2_sb_ext_validate, .to_text = bch2_sb_ext_to_text, }; static const struct bch_sb_field_ops *bch2_sb_field_ops[] = { #define x(f, nr) \ [BCH_SB_FIELD_##f] = &bch_sb_field_ops_##f, BCH_SB_FIELDS() #undef x }; static const struct bch_sb_field_ops bch2_sb_field_null_ops; static const struct bch_sb_field_ops *bch2_sb_field_type_ops(unsigned type) { return likely(type < ARRAY_SIZE(bch2_sb_field_ops)) ? bch2_sb_field_ops[type] : &bch2_sb_field_null_ops; } static int bch2_sb_field_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { unsigned type = le32_to_cpu(f->type); struct printbuf field_err = PRINTBUF; const struct bch_sb_field_ops *ops = bch2_sb_field_type_ops(type); int ret; ret = ops->validate ? ops->validate(sb, f, flags, &field_err) : 0; if (ret) { prt_printf(err, "Invalid superblock section %s: %s", bch2_sb_fields[type], field_err.buf); prt_newline(err); bch2_sb_field_to_text(err, sb, f); } printbuf_exit(&field_err); return ret; } void __bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { unsigned type = le32_to_cpu(f->type); const struct bch_sb_field_ops *ops = bch2_sb_field_type_ops(type); if (!out->nr_tabstops) printbuf_tabstop_push(out, 32); if (ops->to_text) ops->to_text(out, sb, f); } void bch2_sb_field_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { unsigned type = le32_to_cpu(f->type); if (type < BCH_SB_FIELD_NR) prt_printf(out, "%s", bch2_sb_fields[type]); else prt_printf(out, "(unknown field %u)", type); prt_printf(out, " (size %zu):", vstruct_bytes(f)); prt_newline(out); __bch2_sb_field_to_text(out, sb, f); } void bch2_sb_layout_to_text(struct printbuf *out, struct bch_sb_layout *l) { unsigned i; prt_printf(out, "Type: %u", l->layout_type); prt_newline(out); prt_str(out, "Superblock max size: "); prt_units_u64(out, 512 << l->sb_max_size_bits); prt_newline(out); prt_printf(out, "Nr superblocks: %u", l->nr_superblocks); prt_newline(out); prt_str(out, "Offsets: "); for (i = 0; i < l->nr_superblocks; i++) { if (i) prt_str(out, ", "); prt_printf(out, "%llu", le64_to_cpu(l->sb_offset[i])); } prt_newline(out); } void bch2_sb_to_text(struct printbuf *out, struct bch_sb *sb, bool print_layout, unsigned fields) { u64 fields_have = 0; unsigned nr_devices = 0; if (!out->nr_tabstops) printbuf_tabstop_push(out, 44); for (int i = 0; i < sb->nr_devices; i++) nr_devices += bch2_member_exists(sb, i); prt_printf(out, "External UUID:\t"); pr_uuid(out, sb->user_uuid.b); prt_newline(out); prt_printf(out, "Internal UUID:\t"); pr_uuid(out, sb->uuid.b); prt_newline(out); prt_printf(out, "Magic number:\t"); pr_uuid(out, sb->magic.b); prt_newline(out); prt_printf(out, "Device index:\t%u\n", sb->dev_idx); prt_printf(out, "Label:\t"); if (!strlen(sb->label)) prt_printf(out, "(none)"); else prt_printf(out, "%.*s", (int) sizeof(sb->label), sb->label); prt_newline(out); prt_printf(out, "Version:\t"); bch2_version_to_text(out, le16_to_cpu(sb->version)); prt_newline(out); prt_printf(out, "Version upgrade complete:\t"); bch2_version_to_text(out, BCH_SB_VERSION_UPGRADE_COMPLETE(sb)); prt_newline(out); prt_printf(out, "Oldest version on disk:\t"); bch2_version_to_text(out, le16_to_cpu(sb->version_min)); prt_newline(out); prt_printf(out, "Created:\t"); if (sb->time_base_lo) bch2_prt_datetime(out, div_u64(le64_to_cpu(sb->time_base_lo), NSEC_PER_SEC)); else prt_printf(out, "(not set)"); prt_newline(out); prt_printf(out, "Sequence number:\t"); prt_printf(out, "%llu", le64_to_cpu(sb->seq)); prt_newline(out); prt_printf(out, "Time of last write:\t"); bch2_prt_datetime(out, le64_to_cpu(sb->write_time)); prt_newline(out); prt_printf(out, "Superblock size:\t"); prt_units_u64(out, vstruct_bytes(sb)); prt_str(out, "/"); prt_units_u64(out, 512ULL << sb->layout.sb_max_size_bits); prt_newline(out); prt_printf(out, "Clean:\t%llu\n", BCH_SB_CLEAN(sb)); prt_printf(out, "Devices:\t%u\n", nr_devices); prt_printf(out, "Sections:\t"); vstruct_for_each(sb, f) fields_have |= 1 << le32_to_cpu(f->type); prt_bitflags(out, bch2_sb_fields, fields_have); prt_newline(out); prt_printf(out, "Features:\t"); prt_bitflags(out, bch2_sb_features, le64_to_cpu(sb->features[0])); prt_newline(out); prt_printf(out, "Compat features:\t"); prt_bitflags(out, bch2_sb_compat, le64_to_cpu(sb->compat[0])); prt_newline(out); prt_newline(out); prt_printf(out, "Options:"); prt_newline(out); printbuf_indent_add(out, 2); { enum bch_opt_id id; for (id = 0; id < bch2_opts_nr; id++) { const struct bch_option *opt = bch2_opt_table + id; if (opt->get_sb != BCH2_NO_SB_OPT) { u64 v = bch2_opt_from_sb(sb, id); prt_printf(out, "%s:\t", opt->attr.name); bch2_opt_to_text(out, NULL, sb, opt, v, OPT_HUMAN_READABLE|OPT_SHOW_FULL_LIST); prt_newline(out); } } } printbuf_indent_sub(out, 2); if (print_layout) { prt_newline(out); prt_printf(out, "layout:"); prt_newline(out); printbuf_indent_add(out, 2); bch2_sb_layout_to_text(out, &sb->layout); printbuf_indent_sub(out, 2); } vstruct_for_each(sb, f) if (fields & (1 << le32_to_cpu(f->type))) { prt_newline(out); bch2_sb_field_to_text(out, sb, f); } } |
| 121 120 120 60 59 3 11 50 49 4 11 11 49 49 49 49 49 48 47 13 45 57 27 35 29 48 2 1753 121 59 2 1 48 12 59 60 1895 1898 1899 11 1897 1869 49 121 13 120 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991-1998 Linus Torvalds * Re-organised Feb 1998 Russell King * Copyright (C) 2020 Christoph Hellwig */ #include <linux/fs.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/vmalloc.h> #include <linux/raid/detect.h> #include "check.h" static int (*const check_part[])(struct parsed_partitions *) = { /* * Probe partition formats with tables at disk address 0 * that also have an ADFS boot block at 0xdc0. */ #ifdef CONFIG_ACORN_PARTITION_ICS adfspart_check_ICS, #endif #ifdef CONFIG_ACORN_PARTITION_POWERTEC adfspart_check_POWERTEC, #endif #ifdef CONFIG_ACORN_PARTITION_EESOX adfspart_check_EESOX, #endif /* * Now move on to formats that only have partition info at * disk address 0xdc0. Since these may also have stale * PC/BIOS partition tables, they need to come before * the msdos entry. */ #ifdef CONFIG_ACORN_PARTITION_CUMANA adfspart_check_CUMANA, #endif #ifdef CONFIG_ACORN_PARTITION_ADFS adfspart_check_ADFS, #endif #ifdef CONFIG_CMDLINE_PARTITION cmdline_partition, #endif #ifdef CONFIG_EFI_PARTITION efi_partition, /* this must come before msdos */ #endif #ifdef CONFIG_SGI_PARTITION sgi_partition, #endif #ifdef CONFIG_LDM_PARTITION ldm_partition, /* this must come before msdos */ #endif #ifdef CONFIG_MSDOS_PARTITION msdos_partition, #endif #ifdef CONFIG_OSF_PARTITION osf_partition, #endif #ifdef CONFIG_SUN_PARTITION sun_partition, #endif #ifdef CONFIG_AMIGA_PARTITION amiga_partition, #endif #ifdef CONFIG_ATARI_PARTITION atari_partition, #endif #ifdef CONFIG_MAC_PARTITION mac_partition, #endif #ifdef CONFIG_ULTRIX_PARTITION ultrix_partition, #endif #ifdef CONFIG_IBM_PARTITION ibm_partition, #endif #ifdef CONFIG_KARMA_PARTITION karma_partition, #endif #ifdef CONFIG_SYSV68_PARTITION sysv68_partition, #endif NULL }; static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; int nr = DISK_MAX_PARTS; state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) return NULL; state->parts = vzalloc(array_size(nr, sizeof(state->parts[0]))); if (!state->parts) { kfree(state); return NULL; } state->limit = nr; return state; } static void free_partitions(struct parsed_partitions *state) { vfree(state->parts); kfree(state); } static struct parsed_partitions *check_partition(struct gendisk *hd) { struct parsed_partitions *state; int i, res, err; state = allocate_partitions(hd); if (!state) return NULL; state->pp_buf = (char *)__get_free_page(GFP_KERNEL); if (!state->pp_buf) { free_partitions(state); return NULL; } state->pp_buf[0] = '\0'; state->disk = hd; snprintf(state->name, BDEVNAME_SIZE, "%s", hd->disk_name); snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name); if (isdigit(state->name[strlen(state->name)-1])) sprintf(state->name, "p"); i = res = err = 0; while (!res && check_part[i]) { memset(state->parts, 0, state->limit * sizeof(state->parts[0])); res = check_part[i++](state); if (res < 0) { /* * We have hit an I/O error which we don't report now. * But record it, and let the others do their job. */ err = res; res = 0; } } if (res > 0) { printk(KERN_INFO "%s", state->pp_buf); free_page((unsigned long)state->pp_buf); return state; } if (state->access_beyond_eod) err = -ENOSPC; /* * The partition is unrecognized. So report I/O errors if there were any */ if (err) res = err; if (res) { strlcat(state->pp_buf, " unable to read partition table\n", PAGE_SIZE); printk(KERN_INFO "%s", state->pp_buf); } free_page((unsigned long)state->pp_buf); free_partitions(state); return ERR_PTR(res); } static ssize_t part_partition_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_partno(dev_to_bdev(dev))); } static ssize_t part_start_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%llu\n", dev_to_bdev(dev)->bd_start_sect); } static ssize_t part_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", bdev_read_only(dev_to_bdev(dev))); } static ssize_t part_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_alignment_offset(dev_to_bdev(dev))); } static ssize_t part_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", bdev_discard_alignment(dev_to_bdev(dev))); } static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); static DEVICE_ATTR(start, 0444, part_start_show, NULL); static DEVICE_ATTR(size, 0444, part_size_show, NULL); static DEVICE_ATTR(ro, 0444, part_ro_show, NULL); static DEVICE_ATTR(alignment_offset, 0444, part_alignment_offset_show, NULL); static DEVICE_ATTR(discard_alignment, 0444, part_discard_alignment_show, NULL); static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif static struct attribute *part_attrs[] = { &dev_attr_partition.attr, &dev_attr_start.attr, &dev_attr_size.attr, &dev_attr_ro.attr, &dev_attr_alignment_offset.attr, &dev_attr_discard_alignment.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif NULL }; static const struct attribute_group part_attr_group = { .attrs = part_attrs, }; static const struct attribute_group *part_attr_groups[] = { &part_attr_group, #ifdef CONFIG_BLK_DEV_IO_TRACE &blk_trace_attr_group, #endif NULL }; static void part_release(struct device *dev) { put_disk(dev_to_bdev(dev)->bd_disk); bdev_drop(dev_to_bdev(dev)); } static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct block_device *part = dev_to_bdev(dev); add_uevent_var(env, "PARTN=%u", bdev_partno(part)); if (part->bd_meta_info && part->bd_meta_info->volname[0]) add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname); return 0; } const struct device_type part_type = { .name = "partition", .groups = part_attr_groups, .release = part_release, .uevent = part_uevent, }; void drop_partition(struct block_device *part) { lockdep_assert_held(&part->bd_disk->open_mutex); xa_erase(&part->bd_disk->part_tbl, bdev_partno(part)); kobject_put(part->bd_holder_dir); device_del(&part->bd_device); put_device(&part->bd_device); } static ssize_t whole_disk_show(struct device *dev, struct device_attribute *attr, char *buf) { return 0; } static const DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static struct block_device *add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, struct partition_meta_info *info) { dev_t devt = MKDEV(0, 0); struct device *ddev = disk_to_dev(disk); struct device *pdev; struct block_device *bdev; const char *dname; int err; lockdep_assert_held(&disk->open_mutex); if (partno >= DISK_MAX_PARTS) return ERR_PTR(-EINVAL); /* * Partitions are not supported on zoned block devices that are used as * such. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: partitions not supported on host managed zoned block device\n", disk->disk_name); return ERR_PTR(-ENXIO); } if (xa_load(&disk->part_tbl, partno)) return ERR_PTR(-EBUSY); /* ensure we always have a reference to the whole disk */ get_device(disk_to_dev(disk)); err = -ENOMEM; bdev = bdev_alloc(disk, partno); if (!bdev) goto out_put_disk; bdev->bd_start_sect = start; bdev_set_nr_sectors(bdev, len); pdev = &bdev->bd_device; dname = dev_name(ddev); if (isdigit(dname[strlen(dname) - 1])) dev_set_name(pdev, "%sp%d", dname, partno); else dev_set_name(pdev, "%s%d", dname, partno); device_initialize(pdev); pdev->class = &block_class; pdev->type = &part_type; pdev->parent = ddev; /* in consecutive minor range? */ if (bdev_partno(bdev) < disk->minors) { devt = MKDEV(disk->major, disk->first_minor + bdev_partno(bdev)); } else { err = blk_alloc_ext_minor(); if (err < 0) goto out_put; devt = MKDEV(BLOCK_EXT_MAJOR, err); } pdev->devt = devt; if (info) { err = -ENOMEM; bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL); if (!bdev->bd_meta_info) goto out_put; } /* delay uevent until 'holders' subdir is created */ dev_set_uevent_suppress(pdev, 1); err = device_add(pdev); if (err) goto out_put; err = -ENOMEM; bdev->bd_holder_dir = kobject_create_and_add("holders", &pdev->kobj); if (!bdev->bd_holder_dir) goto out_del; dev_set_uevent_suppress(pdev, 0); if (flags & ADDPART_FLAG_WHOLEDISK) { err = device_create_file(pdev, &dev_attr_whole_disk); if (err) goto out_del; } /* everything is up and running, commence */ err = xa_insert(&disk->part_tbl, partno, bdev, GFP_KERNEL); if (err) goto out_del; bdev_add(bdev, devt); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); return bdev; out_del: kobject_put(bdev->bd_holder_dir); device_del(pdev); out_put: put_device(pdev); return ERR_PTR(err); out_put_disk: put_disk(disk); return ERR_PTR(err); } static bool partition_overlaps(struct gendisk *disk, sector_t start, sector_t length, int skip_partno) { struct block_device *part; bool overlap = false; unsigned long idx; rcu_read_lock(); xa_for_each_start(&disk->part_tbl, idx, part, 1) { if (bdev_partno(part) != skip_partno && start < part->bd_start_sect + bdev_nr_sectors(part) && start + length > part->bd_start_sect) { overlap = true; break; } } rcu_read_unlock(); return overlap; } int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part; int ret; mutex_lock(&disk->open_mutex); if (!disk_live(disk)) { ret = -ENXIO; goto out; } if (disk->flags & GENHD_FL_NO_PART) { ret = -EINVAL; goto out; } if (partition_overlaps(disk, start, length, -1)) { ret = -EBUSY; goto out; } part = add_partition(disk, partno, start, length, ADDPART_FLAG_NONE, NULL); ret = PTR_ERR_OR_ZERO(part); out: mutex_unlock(&disk->open_mutex); return ret; } int bdev_del_partition(struct gendisk *disk, int partno) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EBUSY; if (atomic_read(&part->bd_openers)) goto out_unlock; /* * We verified that @part->bd_openers is zero above and so * @part->bd_holder{_ops} can't be set. And since we hold * @disk->open_mutex the device can't be claimed by anyone. * * So no need to call @part->bd_holder_ops->mark_dead() here. * Just delete the partition and invalidate it. */ bdev_unhash(part); invalidate_bdev(part); drop_partition(part); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { struct block_device *part = NULL; int ret = -ENXIO; mutex_lock(&disk->open_mutex); part = xa_load(&disk->part_tbl, partno); if (!part) goto out_unlock; ret = -EINVAL; if (start != part->bd_start_sect) goto out_unlock; ret = -EBUSY; if (partition_overlaps(disk, start, length, partno)) goto out_unlock; bdev_set_nr_sectors(part, length); ret = 0; out_unlock: mutex_unlock(&disk->open_mutex); return ret; } static bool disk_unlock_native_capacity(struct gendisk *disk) { if (!disk->fops->unlock_native_capacity || test_and_set_bit(GD_NATIVE_CAPACITY, &disk->state)) { printk(KERN_CONT "truncated\n"); return false; } printk(KERN_CONT "enabling native capacity\n"); disk->fops->unlock_native_capacity(disk); return true; } static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { sector_t size = state->parts[p].size; sector_t from = state->parts[p].from; struct block_device *part; if (!size) return true; if (from >= get_capacity(disk)) { printk(KERN_WARNING "%s: p%d start %llu is beyond EOD, ", disk->disk_name, p, (unsigned long long) from); if (disk_unlock_native_capacity(disk)) return false; return true; } if (from + size > get_capacity(disk)) { printk(KERN_WARNING "%s: p%d size %llu extends beyond EOD, ", disk->disk_name, p, (unsigned long long) size); if (disk_unlock_native_capacity(disk)) return false; /* * We can not ignore partitions of broken tables created by for * example camera firmware, but we limit them to the end of the * disk to avoid creating invalid block devices. */ size = get_capacity(disk) - from; } part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) { printk(KERN_ERR " %s: p%d could not be added: %pe\n", disk->disk_name, p, part); return true; } if (IS_BUILTIN(CONFIG_BLK_DEV_MD) && (state->parts[p].flags & ADDPART_FLAG_RAID)) md_autodetect_dev(part->bd_dev); return true; } static int blk_add_partitions(struct gendisk *disk) { struct parsed_partitions *state; int ret = -EAGAIN, p; if (!disk_has_partscan(disk)) return 0; state = check_partition(disk); if (!state) return 0; if (IS_ERR(state)) { /* * I/O error reading the partition table. If we tried to read * beyond EOD, retry after unlocking the native capacity. */ if (PTR_ERR(state) == -ENOSPC) { printk(KERN_WARNING "%s: partition table beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) return -EAGAIN; } return -EIO; } /* * Partitions are not supported on host managed zoned block devices. */ if (bdev_is_zoned(disk->part0)) { pr_warn("%s: ignoring partition table on host managed zoned block device\n", disk->disk_name); ret = 0; goto out_free_state; } /* * If we read beyond EOD, try unlocking native capacity even if the * partition table was successfully read as we could be missing some * partitions. */ if (state->access_beyond_eod) { printk(KERN_WARNING "%s: partition table partially beyond EOD, ", disk->disk_name); if (disk_unlock_native_capacity(disk)) goto out_free_state; } /* tell userspace that the media / partition table may have changed */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); for (p = 1; p < state->limit; p++) if (!blk_add_partition(disk, state, p)) goto out_free_state; ret = 0; out_free_state: free_partitions(state); return ret; } int bdev_disk_changed(struct gendisk *disk, bool invalidate) { struct block_device *part; unsigned long idx; int ret = 0; lockdep_assert_held(&disk->open_mutex); if (!disk_live(disk)) return -ENXIO; rescan: if (disk->open_partitions) return -EBUSY; sync_blockdev(disk->part0); invalidate_bdev(disk->part0); xa_for_each_start(&disk->part_tbl, idx, part, 1) { /* * Remove the block device from the inode hash, so that * it cannot be looked up any more even when openers * still hold references. */ bdev_unhash(part); /* * If @disk->open_partitions isn't elevated but there's * still an active holder of that block device things * are broken. */ WARN_ON_ONCE(atomic_read(&part->bd_openers)); invalidate_bdev(part); drop_partition(part); } clear_bit(GD_NEED_PART_SCAN, &disk->state); /* * Historically we only set the capacity to zero for devices that * support partitions (independ of actually having partitions created). * Doing that is rather inconsistent, but changing it broke legacy * udisks polling for legacy ide-cdrom devices. Use the crude check * below to get the sane behavior for most device while not breaking * userspace for this particular setup. */ if (invalidate) { if (!(disk->flags & GENHD_FL_NO_PART) || !(disk->flags & GENHD_FL_REMOVABLE)) set_capacity(disk, 0); } if (get_capacity(disk)) { ret = blk_add_partitions(disk); if (ret == -EAGAIN) goto rescan; } else if (invalidate) { /* * Tell userspace that the media / partition table may have * changed. */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); } return ret; } /* * Only exported for loop and dasd for historic reasons. Don't use in new * code! */ EXPORT_SYMBOL_GPL(bdev_disk_changed); void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { struct address_space *mapping = state->disk->part0->bd_mapping; struct folio *folio; if (n >= get_capacity(state->disk)) { state->access_beyond_eod = true; goto out; } folio = read_mapping_folio(mapping, n >> PAGE_SECTORS_SHIFT, NULL); if (IS_ERR(folio)) goto out; p->v = folio; return folio_address(folio) + offset_in_folio(folio, n * SECTOR_SIZE); out: p->v = NULL; return NULL; } |
| 1 1 1 1 1 1 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * LED Triggers Core * * Copyright 2005-2007 Openedhand Ltd. * * Author: Richard Purdie <rpurdie@openedhand.com> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/device.h> #include <linux/timer.h> #include <linux/rwsem.h> #include <linux/leds.h> #include <linux/slab.h> #include <linux/mm.h> #include "leds.h" /* * Nests outside led_cdev->trigger_lock */ static DECLARE_RWSEM(triggers_list_lock); static LIST_HEAD(trigger_list); /* Used by LED Class */ static inline bool trigger_relevant(struct led_classdev *led_cdev, struct led_trigger *trig) { return !trig->trigger_type || trig->trigger_type == led_cdev->trigger_type; } ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); struct led_trigger *trig; int ret = count; mutex_lock(&led_cdev->led_access); if (led_sysfs_is_disabled(led_cdev)) { ret = -EBUSY; goto unlock; } if (sysfs_streq(buf, "none")) { led_trigger_remove(led_cdev); goto unlock; } down_read(&triggers_list_lock); list_for_each_entry(trig, &trigger_list, next_trig) { if (sysfs_streq(buf, trig->name) && trigger_relevant(led_cdev, trig)) { down_write(&led_cdev->trigger_lock); led_trigger_set(led_cdev, trig); up_write(&led_cdev->trigger_lock); up_read(&triggers_list_lock); goto unlock; } } /* we come here only if buf matches no trigger */ ret = -EINVAL; up_read(&triggers_list_lock); unlock: mutex_unlock(&led_cdev->led_access); return ret; } EXPORT_SYMBOL_GPL(led_trigger_write); __printf(3, 4) static int led_trigger_snprintf(char *buf, ssize_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); if (size <= 0) i = vsnprintf(NULL, 0, fmt, args); else i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } static int led_trigger_format(char *buf, size_t size, struct led_classdev *led_cdev) { struct led_trigger *trig; int len = led_trigger_snprintf(buf, size, "%s", led_cdev->trigger ? "none" : "[none]"); list_for_each_entry(trig, &trigger_list, next_trig) { bool hit; if (!trigger_relevant(led_cdev, trig)) continue; hit = led_cdev->trigger && !strcmp(led_cdev->trigger->name, trig->name); len += led_trigger_snprintf(buf + len, size - len, " %s%s%s", hit ? "[" : "", trig->name, hit ? "]" : ""); } len += led_trigger_snprintf(buf + len, size - len, "\n"); return len; } /* * It was stupid to create 10000 cpu triggers, but we are stuck with it now. * Don't make that mistake again. We work around it here by creating binary * attribute, which is not limited by length. This is _not_ good design, do not * copy it. */ ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t pos, size_t count) { struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); void *data; int len; down_read(&triggers_list_lock); down_read(&led_cdev->trigger_lock); len = led_trigger_format(NULL, 0, led_cdev); data = kvmalloc(len + 1, GFP_KERNEL); if (!data) { up_read(&led_cdev->trigger_lock); up_read(&triggers_list_lock); return -ENOMEM; } len = led_trigger_format(data, len + 1, led_cdev); up_read(&led_cdev->trigger_lock); up_read(&triggers_list_lock); len = memory_read_from_buffer(buf, count, &pos, data, len); kvfree(data); return len; } EXPORT_SYMBOL_GPL(led_trigger_read); /* Caller must ensure led_cdev->trigger_lock held */ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) { char *event = NULL; char *envp[2]; const char *name; int ret; if (!led_cdev->trigger && !trig) return 0; name = trig ? trig->name : "none"; event = kasprintf(GFP_KERNEL, "TRIGGER=%s", name); /* Remove any existing trigger */ if (led_cdev->trigger) { spin_lock(&led_cdev->trigger->leddev_list_lock); list_del_rcu(&led_cdev->trig_list); spin_unlock(&led_cdev->trigger->leddev_list_lock); /* ensure it's no longer visible on the led_cdevs list */ synchronize_rcu(); cancel_work_sync(&led_cdev->set_brightness_work); led_stop_software_blink(led_cdev); device_remove_groups(led_cdev->dev, led_cdev->trigger->groups); if (led_cdev->trigger->deactivate) led_cdev->trigger->deactivate(led_cdev); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_cdev->activated = false; led_cdev->flags &= ~LED_INIT_DEFAULT_TRIGGER; led_set_brightness(led_cdev, LED_OFF); } if (trig) { spin_lock(&trig->leddev_list_lock); list_add_tail_rcu(&led_cdev->trig_list, &trig->led_cdevs); spin_unlock(&trig->leddev_list_lock); led_cdev->trigger = trig; /* * Some activate() calls use led_trigger_event() to initialize * the brightness of the LED for which the trigger is being set. * Ensure the led_cdev is visible on trig->led_cdevs for this. */ synchronize_rcu(); /* * If "set brightness to 0" is pending in workqueue, * we don't want that to be reordered after ->activate() */ flush_work(&led_cdev->set_brightness_work); ret = 0; if (trig->activate) ret = trig->activate(led_cdev); else led_set_brightness(led_cdev, trig->brightness); if (ret) goto err_activate; ret = device_add_groups(led_cdev->dev, trig->groups); if (ret) { dev_err(led_cdev->dev, "Failed to add trigger attributes\n"); goto err_add_groups; } } if (event) { envp[0] = event; envp[1] = NULL; if (kobject_uevent_env(&led_cdev->dev->kobj, KOBJ_CHANGE, envp)) dev_err(led_cdev->dev, "%s: Error sending uevent\n", __func__); kfree(event); } return 0; err_add_groups: if (trig->deactivate) trig->deactivate(led_cdev); err_activate: spin_lock(&led_cdev->trigger->leddev_list_lock); list_del_rcu(&led_cdev->trig_list); spin_unlock(&led_cdev->trigger->leddev_list_lock); synchronize_rcu(); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_set_brightness(led_cdev, LED_OFF); kfree(event); return ret; } EXPORT_SYMBOL_GPL(led_trigger_set); void led_trigger_remove(struct led_classdev *led_cdev) { down_write(&led_cdev->trigger_lock); led_trigger_set(led_cdev, NULL); up_write(&led_cdev->trigger_lock); } EXPORT_SYMBOL_GPL(led_trigger_remove); static bool led_match_default_trigger(struct led_classdev *led_cdev, struct led_trigger *trig) { if (!strcmp(led_cdev->default_trigger, trig->name) && trigger_relevant(led_cdev, trig)) { led_cdev->flags |= LED_INIT_DEFAULT_TRIGGER; led_trigger_set(led_cdev, trig); return true; } return false; } void led_trigger_set_default(struct led_classdev *led_cdev) { struct led_trigger *trig; bool found = false; if (!led_cdev->default_trigger) return; down_read(&triggers_list_lock); down_write(&led_cdev->trigger_lock); list_for_each_entry(trig, &trigger_list, next_trig) { found = led_match_default_trigger(led_cdev, trig); if (found) break; } up_write(&led_cdev->trigger_lock); up_read(&triggers_list_lock); /* * If default trigger wasn't found, maybe trigger module isn't loaded yet. * Once loaded it will re-probe with all led_cdev's. */ if (!found) request_module_nowait("ledtrig:%s", led_cdev->default_trigger); } EXPORT_SYMBOL_GPL(led_trigger_set_default); /* LED Trigger Interface */ int led_trigger_register(struct led_trigger *trig) { struct led_classdev *led_cdev; struct led_trigger *_trig; spin_lock_init(&trig->leddev_list_lock); INIT_LIST_HEAD(&trig->led_cdevs); down_write(&triggers_list_lock); /* Make sure the trigger's name isn't already in use */ list_for_each_entry(_trig, &trigger_list, next_trig) { if (!strcmp(_trig->name, trig->name) && (trig->trigger_type == _trig->trigger_type || !trig->trigger_type || !_trig->trigger_type)) { up_write(&triggers_list_lock); return -EEXIST; } } /* Add to the list of led triggers */ list_add_tail(&trig->next_trig, &trigger_list); up_write(&triggers_list_lock); /* Register with any LEDs that have this as a default trigger */ down_read(&leds_list_lock); list_for_each_entry(led_cdev, &leds_list, node) { down_write(&led_cdev->trigger_lock); if (!led_cdev->trigger && led_cdev->default_trigger) led_match_default_trigger(led_cdev, trig); up_write(&led_cdev->trigger_lock); } up_read(&leds_list_lock); return 0; } EXPORT_SYMBOL_GPL(led_trigger_register); void led_trigger_unregister(struct led_trigger *trig) { struct led_classdev *led_cdev; if (list_empty_careful(&trig->next_trig)) return; /* Remove from the list of led triggers */ down_write(&triggers_list_lock); list_del_init(&trig->next_trig); up_write(&triggers_list_lock); /* Remove anyone actively using this trigger */ down_read(&leds_list_lock); list_for_each_entry(led_cdev, &leds_list, node) { down_write(&led_cdev->trigger_lock); if (led_cdev->trigger == trig) led_trigger_set(led_cdev, NULL); up_write(&led_cdev->trigger_lock); } up_read(&leds_list_lock); } EXPORT_SYMBOL_GPL(led_trigger_unregister); static void devm_led_trigger_release(struct device *dev, void *res) { led_trigger_unregister(*(struct led_trigger **)res); } int devm_led_trigger_register(struct device *dev, struct led_trigger *trig) { struct led_trigger **dr; int rc; dr = devres_alloc(devm_led_trigger_release, sizeof(*dr), GFP_KERNEL); if (!dr) return -ENOMEM; *dr = trig; rc = led_trigger_register(trig); if (rc) devres_free(dr); else devres_add(dev, dr); return rc; } EXPORT_SYMBOL_GPL(devm_led_trigger_register); /* Simple LED Trigger Interface */ void led_trigger_event(struct led_trigger *trig, enum led_brightness brightness) { struct led_classdev *led_cdev; if (!trig) return; trig->brightness = brightness; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) led_set_brightness(led_cdev, brightness); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(led_trigger_event); void led_mc_trigger_event(struct led_trigger *trig, unsigned int *intensity_value, unsigned int num_colors, enum led_brightness brightness) { struct led_classdev *led_cdev; if (!trig) return; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) { if (!(led_cdev->flags & LED_MULTI_COLOR)) continue; led_mc_set_brightness(led_cdev, intensity_value, num_colors, brightness); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(led_mc_trigger_event); static void led_trigger_blink_setup(struct led_trigger *trig, unsigned long delay_on, unsigned long delay_off, int oneshot, int invert) { struct led_classdev *led_cdev; if (!trig) return; rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) { if (oneshot) led_blink_set_oneshot(led_cdev, &delay_on, &delay_off, invert); else led_blink_set_nosleep(led_cdev, delay_on, delay_off); } rcu_read_unlock(); } void led_trigger_blink(struct led_trigger *trig, unsigned long delay_on, unsigned long delay_off) { led_trigger_blink_setup(trig, delay_on, delay_off, 0, 0); } EXPORT_SYMBOL_GPL(led_trigger_blink); void led_trigger_blink_oneshot(struct led_trigger *trig, unsigned long delay_on, unsigned long delay_off, int invert) { led_trigger_blink_setup(trig, delay_on, delay_off, 1, invert); } EXPORT_SYMBOL_GPL(led_trigger_blink_oneshot); void led_trigger_register_simple(const char *name, struct led_trigger **tp) { struct led_trigger *trig; int err; trig = kzalloc(sizeof(struct led_trigger), GFP_KERNEL); if (trig) { trig->name = name; err = led_trigger_register(trig); if (err < 0) { kfree(trig); trig = NULL; pr_warn("LED trigger %s failed to register (%d)\n", name, err); } } else { pr_warn("LED trigger %s failed to register (no memory)\n", name); } *tp = trig; } EXPORT_SYMBOL_GPL(led_trigger_register_simple); void led_trigger_unregister_simple(struct led_trigger *trig) { if (trig) led_trigger_unregister(trig); kfree(trig); } EXPORT_SYMBOL_GPL(led_trigger_unregister_simple); |
| 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2004, 2005 Oracle. All rights reserved. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/uaccess.h> #include "masklog.h" struct mlog_bits mlog_and_bits = MLOG_BITS_RHS(MLOG_INITIAL_AND_MASK); EXPORT_SYMBOL_GPL(mlog_and_bits); struct mlog_bits mlog_not_bits = MLOG_BITS_RHS(0); EXPORT_SYMBOL_GPL(mlog_not_bits); static ssize_t mlog_mask_show(u64 mask, char *buf) { char *state; if (__mlog_test_u64(mask, mlog_and_bits)) state = "allow"; else if (__mlog_test_u64(mask, mlog_not_bits)) state = "deny"; else state = "off"; return snprintf(buf, PAGE_SIZE, "%s\n", state); } static ssize_t mlog_mask_store(u64 mask, const char *buf, size_t count) { if (!strncasecmp(buf, "allow", 5)) { __mlog_set_u64(mask, mlog_and_bits); __mlog_clear_u64(mask, mlog_not_bits); } else if (!strncasecmp(buf, "deny", 4)) { __mlog_set_u64(mask, mlog_not_bits); __mlog_clear_u64(mask, mlog_and_bits); } else if (!strncasecmp(buf, "off", 3)) { __mlog_clear_u64(mask, mlog_not_bits); __mlog_clear_u64(mask, mlog_and_bits); } else return -EINVAL; return count; } void __mlog_printk(const u64 *mask, const char *func, int line, const char *fmt, ...) { struct va_format vaf; va_list args; const char *level; const char *prefix = ""; if (!__mlog_test_u64(*mask, mlog_and_bits) || __mlog_test_u64(*mask, mlog_not_bits)) return; if (*mask & ML_ERROR) { level = KERN_ERR; prefix = "ERROR: "; } else if (*mask & ML_NOTICE) { level = KERN_NOTICE; } else { level = KERN_INFO; } va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk("%s(%s,%u,%u):%s:%d %s%pV", level, current->comm, task_pid_nr(current), raw_smp_processor_id(), func, line, prefix, &vaf); va_end(args); } EXPORT_SYMBOL_GPL(__mlog_printk); struct mlog_attribute { struct attribute attr; u64 mask; }; #define to_mlog_attr(_attr) container_of(_attr, struct mlog_attribute, attr) #define define_mask(_name) { \ .attr = { \ .name = #_name, \ .mode = S_IRUGO | S_IWUSR, \ }, \ .mask = ML_##_name, \ } static struct mlog_attribute mlog_attrs[MLOG_MAX_BITS] = { define_mask(TCP), define_mask(MSG), define_mask(SOCKET), define_mask(HEARTBEAT), define_mask(HB_BIO), define_mask(DLMFS), define_mask(DLM), define_mask(DLM_DOMAIN), define_mask(DLM_THREAD), define_mask(DLM_MASTER), define_mask(DLM_RECOVERY), define_mask(DLM_GLUE), define_mask(VOTE), define_mask(CONN), define_mask(QUORUM), define_mask(BASTS), define_mask(CLUSTER), define_mask(ERROR), define_mask(NOTICE), define_mask(KTHREAD), }; static struct attribute *mlog_default_attrs[MLOG_MAX_BITS] = {NULL, }; ATTRIBUTE_GROUPS(mlog_default); static ssize_t mlog_show(struct kobject *obj, struct attribute *attr, char *buf) { struct mlog_attribute *mlog_attr = to_mlog_attr(attr); return mlog_mask_show(mlog_attr->mask, buf); } static ssize_t mlog_store(struct kobject *obj, struct attribute *attr, const char *buf, size_t count) { struct mlog_attribute *mlog_attr = to_mlog_attr(attr); return mlog_mask_store(mlog_attr->mask, buf, count); } static const struct sysfs_ops mlog_attr_ops = { .show = mlog_show, .store = mlog_store, }; static struct kobj_type mlog_ktype = { .default_groups = mlog_default_groups, .sysfs_ops = &mlog_attr_ops, }; static struct kset mlog_kset = { .kobj = {.ktype = &mlog_ktype}, }; int mlog_sys_init(struct kset *o2cb_kset) { int i = 0; while (mlog_attrs[i].attr.mode) { mlog_default_attrs[i] = &mlog_attrs[i].attr; i++; } mlog_default_attrs[i] = NULL; kobject_set_name(&mlog_kset.kobj, "logmask"); mlog_kset.kobj.kset = o2cb_kset; return kset_register(&mlog_kset); } void mlog_sys_shutdown(void) { kset_unregister(&mlog_kset); } |
| 212 211 10 6 6 11 11 11 11 38 38 37 38 61 61 45 16 24 11 38 49 124 123 4 120 48 83 85 55 80 80 80 256 157 143 1 38 2 1 1 87 80 1 14 14 74 15 87 87 3 3 3 211 3 7 111 148 1 108 2 201 102 183 200 4 199 269 268 267 267 266 267 87 212 212 212 166 7 3 4 4 4 4 4 4 4 4 4 4 4 3 3 3 3 2 2 1 1 5 4 5 5 5 5 3 2 48 9 45 45 28 28 51 8 48 48 45 45 1 1 5 5 4 1 1 1 25 25 16 16 13 13 13 90 2 89 89 2 4 19 19 19 5 14 14 14 14 16 11 5 12 4 15 1 15 11 4 5 4 9 5 4 9 9 9 9 9 9 9 6 9 9 5 9 9 5 9 19 5 16 16 16 16 65 65 65 39 39 38 14 14 14 14 90 1 89 89 36 1 36 2 2 37 37 37 37 37 37 37 37 52 52 52 37 16 127 127 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 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_trans_priv.h" #include "xfs_inode_item.h" #include "xfs_quota.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_bmap_util.h" #include "xfs_dquot_item.h" #include "xfs_dquot.h" #include "xfs_reflink.h" #include "xfs_ialloc.h" #include "xfs_ag.h" #include "xfs_log_priv.h" #include "xfs_health.h" #include <linux/iversion.h> /* Radix tree tags for incore inode tree. */ /* inode is to be reclaimed */ #define XFS_ICI_RECLAIM_TAG 0 /* Inode has speculative preallocations (posteof or cow) to clean. */ #define XFS_ICI_BLOCKGC_TAG 1 /* * The goal for walking incore inodes. These can correspond with incore inode * radix tree tags when convenient. Avoid existing XFS_IWALK namespace. */ enum xfs_icwalk_goal { /* Goals directly associated with tagged inodes. */ XFS_ICWALK_BLOCKGC = XFS_ICI_BLOCKGC_TAG, XFS_ICWALK_RECLAIM = XFS_ICI_RECLAIM_TAG, }; static int xfs_icwalk(struct xfs_mount *mp, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw); static int xfs_icwalk_ag(struct xfs_perag *pag, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw); /* * Private inode cache walk flags for struct xfs_icwalk. Must not * coincide with XFS_ICWALK_FLAGS_VALID. */ /* Stop scanning after icw_scan_limit inodes. */ #define XFS_ICWALK_FLAG_SCAN_LIMIT (1U << 28) #define XFS_ICWALK_FLAG_RECLAIM_SICK (1U << 27) #define XFS_ICWALK_FLAG_UNION (1U << 26) /* union filter algorithm */ #define XFS_ICWALK_PRIVATE_FLAGS (XFS_ICWALK_FLAG_SCAN_LIMIT | \ XFS_ICWALK_FLAG_RECLAIM_SICK | \ XFS_ICWALK_FLAG_UNION) /* * Allocate and initialise an xfs_inode. */ struct xfs_inode * xfs_inode_alloc( struct xfs_mount *mp, xfs_ino_t ino) { struct xfs_inode *ip; /* * XXX: If this didn't occur in transactions, we could drop GFP_NOFAIL * and return NULL here on ENOMEM. */ ip = alloc_inode_sb(mp->m_super, xfs_inode_cache, GFP_KERNEL | __GFP_NOFAIL); if (inode_init_always(mp->m_super, VFS_I(ip))) { kmem_cache_free(xfs_inode_cache, ip); return NULL; } /* VFS doesn't initialise i_mode! */ VFS_I(ip)->i_mode = 0; mapping_set_large_folios(VFS_I(ip)->i_mapping); XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(ip->i_ino == 0); /* initialise the xfs inode */ ip->i_ino = ino; ip->i_mount = mp; memset(&ip->i_imap, 0, sizeof(struct xfs_imap)); ip->i_cowfp = NULL; memset(&ip->i_af, 0, sizeof(ip->i_af)); ip->i_af.if_format = XFS_DINODE_FMT_EXTENTS; memset(&ip->i_df, 0, sizeof(ip->i_df)); ip->i_flags = 0; ip->i_delayed_blks = 0; ip->i_diflags2 = mp->m_ino_geo.new_diflags2; ip->i_nblocks = 0; ip->i_forkoff = 0; ip->i_sick = 0; ip->i_checked = 0; INIT_WORK(&ip->i_ioend_work, xfs_end_io); INIT_LIST_HEAD(&ip->i_ioend_list); spin_lock_init(&ip->i_ioend_lock); ip->i_next_unlinked = NULLAGINO; ip->i_prev_unlinked = 0; return ip; } STATIC void xfs_inode_free_callback( struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); struct xfs_inode *ip = XFS_I(inode); switch (VFS_I(ip)->i_mode & S_IFMT) { case S_IFREG: case S_IFDIR: case S_IFLNK: xfs_idestroy_fork(&ip->i_df); break; } xfs_ifork_zap_attr(ip); if (ip->i_cowfp) { xfs_idestroy_fork(ip->i_cowfp); kmem_cache_free(xfs_ifork_cache, ip->i_cowfp); } if (ip->i_itemp) { ASSERT(!test_bit(XFS_LI_IN_AIL, &ip->i_itemp->ili_item.li_flags)); xfs_inode_item_destroy(ip); ip->i_itemp = NULL; } kmem_cache_free(xfs_inode_cache, ip); } static void __xfs_inode_free( struct xfs_inode *ip) { /* asserts to verify all state is correct here */ ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list)); XFS_STATS_DEC(ip->i_mount, vn_active); call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); } void xfs_inode_free( struct xfs_inode *ip) { ASSERT(!xfs_iflags_test(ip, XFS_IFLUSHING)); /* * Because we use RCU freeing we need to ensure the inode always * appears to be reclaimed with an invalid inode number when in the * free state. The ip->i_flags_lock provides the barrier against lookup * races. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; ip->i_ino = 0; spin_unlock(&ip->i_flags_lock); __xfs_inode_free(ip); } /* * Queue background inode reclaim work if there are reclaimable inodes and there * isn't reclaim work already scheduled or in progress. */ static void xfs_reclaim_work_queue( struct xfs_mount *mp) { rcu_read_lock(); if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) { queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work, msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10)); } rcu_read_unlock(); } /* * Background scanning to trim preallocated space. This is queued based on the * 'speculative_prealloc_lifetime' tunable (5m by default). */ static inline void xfs_blockgc_queue( struct xfs_perag *pag) { struct xfs_mount *mp = pag->pag_mount; if (!xfs_is_blockgc_enabled(mp)) return; rcu_read_lock(); if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG)) queue_delayed_work(pag->pag_mount->m_blockgc_wq, &pag->pag_blockgc_work, msecs_to_jiffies(xfs_blockgc_secs * 1000)); rcu_read_unlock(); } /* Set a tag on both the AG incore inode tree and the AG radix tree. */ static void xfs_perag_set_inode_tag( struct xfs_perag *pag, xfs_agino_t agino, unsigned int tag) { struct xfs_mount *mp = pag->pag_mount; bool was_tagged; lockdep_assert_held(&pag->pag_ici_lock); was_tagged = radix_tree_tagged(&pag->pag_ici_root, tag); radix_tree_tag_set(&pag->pag_ici_root, agino, tag); if (tag == XFS_ICI_RECLAIM_TAG) pag->pag_ici_reclaimable++; if (was_tagged) return; /* propagate the tag up into the perag radix tree */ spin_lock(&mp->m_perag_lock); radix_tree_tag_set(&mp->m_perag_tree, pag->pag_agno, tag); spin_unlock(&mp->m_perag_lock); /* start background work */ switch (tag) { case XFS_ICI_RECLAIM_TAG: xfs_reclaim_work_queue(mp); break; case XFS_ICI_BLOCKGC_TAG: xfs_blockgc_queue(pag); break; } trace_xfs_perag_set_inode_tag(pag, _RET_IP_); } /* Clear a tag on both the AG incore inode tree and the AG radix tree. */ static void xfs_perag_clear_inode_tag( struct xfs_perag *pag, xfs_agino_t agino, unsigned int tag) { struct xfs_mount *mp = pag->pag_mount; lockdep_assert_held(&pag->pag_ici_lock); /* * Reclaim can signal (with a null agino) that it cleared its own tag * by removing the inode from the radix tree. */ if (agino != NULLAGINO) radix_tree_tag_clear(&pag->pag_ici_root, agino, tag); else ASSERT(tag == XFS_ICI_RECLAIM_TAG); if (tag == XFS_ICI_RECLAIM_TAG) pag->pag_ici_reclaimable--; if (radix_tree_tagged(&pag->pag_ici_root, tag)) return; /* clear the tag from the perag radix tree */ spin_lock(&mp->m_perag_lock); radix_tree_tag_clear(&mp->m_perag_tree, pag->pag_agno, tag); spin_unlock(&mp->m_perag_lock); trace_xfs_perag_clear_inode_tag(pag, _RET_IP_); } /* * When we recycle a reclaimable inode, we need to re-initialise the VFS inode * part of the structure. This is made more complex by the fact we store * information about the on-disk values in the VFS inode and so we can't just * overwrite the values unconditionally. Hence we save the parameters we * need to retain across reinitialisation, and rewrite them into the VFS inode * after reinitialisation even if it fails. */ static int xfs_reinit_inode( struct xfs_mount *mp, struct inode *inode) { int error; uint32_t nlink = inode->i_nlink; uint32_t generation = inode->i_generation; uint64_t version = inode_peek_iversion(inode); umode_t mode = inode->i_mode; dev_t dev = inode->i_rdev; kuid_t uid = inode->i_uid; kgid_t gid = inode->i_gid; unsigned long state = inode->i_state; error = inode_init_always(mp->m_super, inode); set_nlink(inode, nlink); inode->i_generation = generation; inode_set_iversion_queried(inode, version); inode->i_mode = mode; inode->i_rdev = dev; inode->i_uid = uid; inode->i_gid = gid; inode->i_state = state; mapping_set_large_folios(inode->i_mapping); return error; } /* * Carefully nudge an inode whose VFS state has been torn down back into a * usable state. Drops the i_flags_lock and the rcu read lock. */ static int xfs_iget_recycle( struct xfs_perag *pag, struct xfs_inode *ip) __releases(&ip->i_flags_lock) { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); int error; trace_xfs_iget_recycle(ip); if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) return -EAGAIN; /* * We need to make it look like the inode is being reclaimed to prevent * the actual reclaim workers from stomping over us while we recycle * the inode. We can't clear the radix tree tag yet as it requires * pag_ici_lock to be held exclusive. */ ip->i_flags |= XFS_IRECLAIM; spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); ASSERT(!rwsem_is_locked(&inode->i_rwsem)); error = xfs_reinit_inode(mp, inode); xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) { /* * Re-initializing the inode failed, and we are in deep * trouble. Try to re-add it to the reclaim list. */ rcu_read_lock(); spin_lock(&ip->i_flags_lock); ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); ASSERT(ip->i_flags & XFS_IRECLAIMABLE); spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); trace_xfs_iget_recycle_fail(ip); return error; } spin_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); /* * Clear the per-lifetime state in the inode as we are now effectively * a new inode and need to return to the initial state before reuse * occurs. */ ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS; ip->i_flags |= XFS_INEW; xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); inode->i_state = I_NEW; spin_unlock(&ip->i_flags_lock); spin_unlock(&pag->pag_ici_lock); return 0; } /* * If we are allocating a new inode, then check what was returned is * actually a free, empty inode. If we are not allocating an inode, * then check we didn't find a free inode. * * Returns: * 0 if the inode free state matches the lookup context * -ENOENT if the inode is free and we are not allocating * -EFSCORRUPTED if there is any state mismatch at all */ static int xfs_iget_check_free_state( struct xfs_inode *ip, int flags) { if (flags & XFS_IGET_CREATE) { /* should be a free inode */ if (VFS_I(ip)->i_mode != 0) { xfs_warn(ip->i_mount, "Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)", ip->i_ino, VFS_I(ip)->i_mode); xfs_agno_mark_sick(ip->i_mount, XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), XFS_SICK_AG_INOBT); return -EFSCORRUPTED; } if (ip->i_nblocks != 0) { xfs_warn(ip->i_mount, "Corruption detected! Free inode 0x%llx has blocks allocated!", ip->i_ino); xfs_agno_mark_sick(ip->i_mount, XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino), XFS_SICK_AG_INOBT); return -EFSCORRUPTED; } return 0; } /* should be an allocated inode */ if (VFS_I(ip)->i_mode == 0) return -ENOENT; return 0; } /* Make all pending inactivation work start immediately. */ static bool xfs_inodegc_queue_all( struct xfs_mount *mp) { struct xfs_inodegc *gc; int cpu; bool ret = false; for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); ret = true; } } return ret; } /* Wait for all queued work and collect errors */ static int xfs_inodegc_wait_all( struct xfs_mount *mp) { int cpu; int error = 0; flush_workqueue(mp->m_inodegc_wq); for_each_cpu(cpu, &mp->m_inodegc_cpumask) { struct xfs_inodegc *gc; gc = per_cpu_ptr(mp->m_inodegc, cpu); if (gc->error && !error) error = gc->error; gc->error = 0; } return error; } /* * Check the validity of the inode we just found it the cache */ static int xfs_iget_cache_hit( struct xfs_perag *pag, struct xfs_inode *ip, xfs_ino_t ino, int flags, int lock_flags) __releases(RCU) { struct inode *inode = VFS_I(ip); struct xfs_mount *mp = ip->i_mount; int error; /* * check for re-use of an inode within an RCU grace period due to the * radix tree nodes not being updated yet. We monitor for this by * setting the inode number to zero before freeing the inode structure. * If the inode has been reallocated and set up, then the inode number * will not match, so check for that, too. */ spin_lock(&ip->i_flags_lock); if (ip->i_ino != ino) goto out_skip; /* * If we are racing with another cache hit that is currently * instantiating this inode or currently recycling it out of * reclaimable state, wait for the initialisation to complete * before continuing. * * If we're racing with the inactivation worker we also want to wait. * If we're creating a new file, it's possible that the worker * previously marked the inode as free on disk but hasn't finished * updating the incore state yet. The AGI buffer will be dirty and * locked to the icreate transaction, so a synchronous push of the * inodegc workers would result in deadlock. For a regular iget, the * worker is running already, so we might as well wait. * * XXX(hch): eventually we should do something equivalent to * wait_on_inode to wait for these flags to be cleared * instead of polling for it. */ if (ip->i_flags & (XFS_INEW | XFS_IRECLAIM | XFS_INACTIVATING)) goto out_skip; if (ip->i_flags & XFS_NEED_INACTIVE) { /* Unlinked inodes cannot be re-grabbed. */ if (VFS_I(ip)->i_nlink == 0) { error = -ENOENT; goto out_error; } goto out_inodegc_flush; } /* * Check the inode free state is valid. This also detects lookup * racing with unlinks. */ error = xfs_iget_check_free_state(ip, flags); if (error) goto out_error; /* Skip inodes that have no vfs state. */ if ((flags & XFS_IGET_INCORE) && (ip->i_flags & XFS_IRECLAIMABLE)) goto out_skip; /* The inode fits the selection criteria; process it. */ if (ip->i_flags & XFS_IRECLAIMABLE) { /* Drops i_flags_lock and RCU read lock. */ error = xfs_iget_recycle(pag, ip); if (error == -EAGAIN) goto out_skip; if (error) return error; } else { /* If the VFS inode is being torn down, pause and try again. */ if (!igrab(inode)) goto out_skip; /* We've got a live one. */ spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); trace_xfs_iget_hit(ip); } if (lock_flags != 0) xfs_ilock(ip, lock_flags); if (!(flags & XFS_IGET_INCORE)) xfs_iflags_clear(ip, XFS_ISTALE); XFS_STATS_INC(mp, xs_ig_found); return 0; out_skip: trace_xfs_iget_skip(ip); XFS_STATS_INC(mp, xs_ig_frecycle); error = -EAGAIN; out_error: spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); return error; out_inodegc_flush: spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); /* * Do not wait for the workers, because the caller could hold an AGI * buffer lock. We're just going to sleep in a loop anyway. */ if (xfs_is_inodegc_enabled(mp)) xfs_inodegc_queue_all(mp); return -EAGAIN; } static int xfs_iget_cache_miss( struct xfs_mount *mp, struct xfs_perag *pag, xfs_trans_t *tp, xfs_ino_t ino, struct xfs_inode **ipp, int flags, int lock_flags) { struct xfs_inode *ip; int error; xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino); ip = xfs_inode_alloc(mp, ino); if (!ip) return -ENOMEM; error = xfs_imap(pag, tp, ip->i_ino, &ip->i_imap, flags); if (error) goto out_destroy; /* * For version 5 superblocks, if we are initialising a new inode and we * are not utilising the XFS_FEAT_IKEEP inode cluster mode, we can * simply build the new inode core with a random generation number. * * For version 4 (and older) superblocks, log recovery is dependent on * the i_flushiter field being initialised from the current on-disk * value and hence we must also read the inode off disk even when * initializing new inodes. */ if (xfs_has_v3inodes(mp) && (flags & XFS_IGET_CREATE) && !xfs_has_ikeep(mp)) { VFS_I(ip)->i_generation = get_random_u32(); } else { struct xfs_buf *bp; error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp); if (error) goto out_destroy; error = xfs_inode_from_disk(ip, xfs_buf_offset(bp, ip->i_imap.im_boffset)); if (!error) xfs_buf_set_ref(bp, XFS_INO_REF); else xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); xfs_trans_brelse(tp, bp); if (error) goto out_destroy; } trace_xfs_iget_miss(ip); /* * Check the inode free state is valid. This also detects lookup * racing with unlinks. */ error = xfs_iget_check_free_state(ip, flags); if (error) goto out_destroy; /* * Preload the radix tree so we can insert safely under the * write spinlock. Note that we cannot sleep inside the preload * region. */ if (radix_tree_preload(GFP_KERNEL | __GFP_NOLOCKDEP)) { error = -EAGAIN; goto out_destroy; } /* * Because the inode hasn't been added to the radix-tree yet it can't * be found by another thread, so we can do the non-sleeping lock here. */ if (lock_flags) { if (!xfs_ilock_nowait(ip, lock_flags)) BUG(); } /* * These values must be set before inserting the inode into the radix * tree as the moment it is inserted a concurrent lookup (allowed by the * RCU locking mechanism) can find it and that lookup must see that this * is an inode currently under construction (i.e. that XFS_INEW is set). * The ip->i_flags_lock that protects the XFS_INEW flag forms the * memory barrier that ensures this detection works correctly at lookup * time. */ if (flags & XFS_IGET_DONTCACHE) d_mark_dontcache(VFS_I(ip)); ip->i_udquot = NULL; ip->i_gdquot = NULL; ip->i_pdquot = NULL; xfs_iflags_set(ip, XFS_INEW); /* insert the new inode */ spin_lock(&pag->pag_ici_lock); error = radix_tree_insert(&pag->pag_ici_root, agino, ip); if (unlikely(error)) { WARN_ON(error != -EEXIST); XFS_STATS_INC(mp, xs_ig_dup); error = -EAGAIN; goto out_preload_end; } spin_unlock(&pag->pag_ici_lock); radix_tree_preload_end(); *ipp = ip; return 0; out_preload_end: spin_unlock(&pag->pag_ici_lock); radix_tree_preload_end(); if (lock_flags) xfs_iunlock(ip, lock_flags); out_destroy: __destroy_inode(VFS_I(ip)); xfs_inode_free(ip); return error; } /* * Look up an inode by number in the given file system. The inode is looked up * in the cache held in each AG. If the inode is found in the cache, initialise * the vfs inode if necessary. * * If it is not in core, read it in from the file system's device, add it to the * cache and initialise the vfs inode. * * The inode is locked according to the value of the lock_flags parameter. * Inode lookup is only done during metadata operations and not as part of the * data IO path. Hence we only allow locking of the XFS_ILOCK during lookup. */ int xfs_iget( struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, uint flags, uint lock_flags, struct xfs_inode **ipp) { struct xfs_inode *ip; struct xfs_perag *pag; xfs_agino_t agino; int error; ASSERT((lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) == 0); /* reject inode numbers outside existing AGs */ if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount) return -EINVAL; XFS_STATS_INC(mp, xs_ig_attempts); /* get the perag structure and ensure that it's inode capable */ pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ino)); agino = XFS_INO_TO_AGINO(mp, ino); again: error = 0; rcu_read_lock(); ip = radix_tree_lookup(&pag->pag_ici_root, agino); if (ip) { error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags); if (error) goto out_error_or_again; } else { rcu_read_unlock(); if (flags & XFS_IGET_INCORE) { error = -ENODATA; goto out_error_or_again; } XFS_STATS_INC(mp, xs_ig_missed); error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, flags, lock_flags); if (error) goto out_error_or_again; } xfs_perag_put(pag); *ipp = ip; /* * If we have a real type for an on-disk inode, we can setup the inode * now. If it's a new inode being created, xfs_init_new_inode will * handle it. */ if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0) xfs_setup_existing_inode(ip); return 0; out_error_or_again: if (!(flags & (XFS_IGET_INCORE | XFS_IGET_NORETRY)) && error == -EAGAIN) { delay(1); goto again; } xfs_perag_put(pag); return error; } /* * Grab the inode for reclaim exclusively. * * We have found this inode via a lookup under RCU, so the inode may have * already been freed, or it may be in the process of being recycled by * xfs_iget(). In both cases, the inode will have XFS_IRECLAIM set. If the inode * has been fully recycled by the time we get the i_flags_lock, XFS_IRECLAIMABLE * will not be set. Hence we need to check for both these flag conditions to * avoid inodes that are no longer reclaim candidates. * * Note: checking for other state flags here, under the i_flags_lock or not, is * racy and should be avoided. Those races should be resolved only after we have * ensured that we are able to reclaim this inode and the world can see that we * are going to reclaim it. * * Return true if we grabbed it, false otherwise. */ static bool xfs_reclaim_igrab( struct xfs_inode *ip, struct xfs_icwalk *icw) { ASSERT(rcu_read_lock_held()); spin_lock(&ip->i_flags_lock); if (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) || __xfs_iflags_test(ip, XFS_IRECLAIM)) { /* not a reclaim candidate. */ spin_unlock(&ip->i_flags_lock); return false; } /* Don't reclaim a sick inode unless the caller asked for it. */ if (ip->i_sick && (!icw || !(icw->icw_flags & XFS_ICWALK_FLAG_RECLAIM_SICK))) { spin_unlock(&ip->i_flags_lock); return false; } __xfs_iflags_set(ip, XFS_IRECLAIM); spin_unlock(&ip->i_flags_lock); return true; } /* * Inode reclaim is non-blocking, so the default action if progress cannot be * made is to "requeue" the inode for reclaim by unlocking it and clearing the * XFS_IRECLAIM flag. If we are in a shutdown state, we don't care about * blocking anymore and hence we can wait for the inode to be able to reclaim * it. * * We do no IO here - if callers require inodes to be cleaned they must push the * AIL first to trigger writeback of dirty inodes. This enables writeback to be * done in the background in a non-blocking manner, and enables memory reclaim * to make progress without blocking. */ static void xfs_reclaim_inode( struct xfs_inode *ip, struct xfs_perag *pag) { xfs_ino_t ino = ip->i_ino; /* for radix_tree_delete */ if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) goto out; if (xfs_iflags_test_and_set(ip, XFS_IFLUSHING)) goto out_iunlock; /* * Check for log shutdown because aborting the inode can move the log * tail and corrupt in memory state. This is fine if the log is shut * down, but if the log is still active and only the mount is shut down * then the in-memory log tail movement caused by the abort can be * incorrectly propagated to disk. */ if (xlog_is_shutdown(ip->i_mount->m_log)) { xfs_iunpin_wait(ip); xfs_iflush_shutdown_abort(ip); goto reclaim; } if (xfs_ipincount(ip)) goto out_clear_flush; if (!xfs_inode_clean(ip)) goto out_clear_flush; xfs_iflags_clear(ip, XFS_IFLUSHING); reclaim: trace_xfs_inode_reclaiming(ip); /* * Because we use RCU freeing we need to ensure the inode always appears * to be reclaimed with an invalid inode number when in the free state. * We do this as early as possible under the ILOCK so that * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to * detect races with us here. By doing this, we guarantee that once * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that * it will see either a valid inode that will serialise correctly, or it * will see an invalid inode that it can skip. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; ip->i_ino = 0; ip->i_sick = 0; ip->i_checked = 0; spin_unlock(&ip->i_flags_lock); ASSERT(!ip->i_itemp || ip->i_itemp->ili_item.li_buf == NULL); xfs_iunlock(ip, XFS_ILOCK_EXCL); XFS_STATS_INC(ip->i_mount, xs_ig_reclaims); /* * Remove the inode from the per-AG radix tree. * * Because radix_tree_delete won't complain even if the item was never * added to the tree assert that it's been there before to catch * problems with the inode life time early on. */ spin_lock(&pag->pag_ici_lock); if (!radix_tree_delete(&pag->pag_ici_root, XFS_INO_TO_AGINO(ip->i_mount, ino))) ASSERT(0); xfs_perag_clear_inode_tag(pag, NULLAGINO, XFS_ICI_RECLAIM_TAG); spin_unlock(&pag->pag_ici_lock); /* * Here we do an (almost) spurious inode lock in order to coordinate * with inode cache radix tree lookups. This is because the lookup * can reference the inodes in the cache without taking references. * * We make that OK here by ensuring that we wait until the inode is * unlocked after the lookup before we go ahead and free it. */ xfs_ilock(ip, XFS_ILOCK_EXCL); ASSERT(!ip->i_udquot && !ip->i_gdquot && !ip->i_pdquot); xfs_iunlock(ip, XFS_ILOCK_EXCL); ASSERT(xfs_inode_clean(ip)); __xfs_inode_free(ip); return; out_clear_flush: xfs_iflags_clear(ip, XFS_IFLUSHING); out_iunlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); out: xfs_iflags_clear(ip, XFS_IRECLAIM); } /* Reclaim sick inodes if we're unmounting or the fs went down. */ static inline bool xfs_want_reclaim_sick( struct xfs_mount *mp) { return xfs_is_unmounting(mp) || xfs_has_norecovery(mp) || xfs_is_shutdown(mp); } void xfs_reclaim_inodes( struct xfs_mount *mp) { struct xfs_icwalk icw = { .icw_flags = 0, }; if (xfs_want_reclaim_sick(mp)) icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK; while (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) { xfs_ail_push_all_sync(mp->m_ail); xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw); } } /* * The shrinker infrastructure determines how many inodes we should scan for * reclaim. We want as many clean inodes ready to reclaim as possible, so we * push the AIL here. We also want to proactively free up memory if we can to * minimise the amount of work memory reclaim has to do so we kick the * background reclaim if it isn't already scheduled. */ long xfs_reclaim_inodes_nr( struct xfs_mount *mp, unsigned long nr_to_scan) { struct xfs_icwalk icw = { .icw_flags = XFS_ICWALK_FLAG_SCAN_LIMIT, .icw_scan_limit = min_t(unsigned long, LONG_MAX, nr_to_scan), }; if (xfs_want_reclaim_sick(mp)) icw.icw_flags |= XFS_ICWALK_FLAG_RECLAIM_SICK; /* kick background reclaimer and push the AIL */ xfs_reclaim_work_queue(mp); xfs_ail_push_all(mp->m_ail); xfs_icwalk(mp, XFS_ICWALK_RECLAIM, &icw); return 0; } /* * Return the number of reclaimable inodes in the filesystem for * the shrinker to determine how much to reclaim. */ long xfs_reclaim_inodes_count( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t ag = 0; long reclaimable = 0; while ((pag = xfs_perag_get_tag(mp, ag, XFS_ICI_RECLAIM_TAG))) { ag = pag->pag_agno + 1; reclaimable += pag->pag_ici_reclaimable; xfs_perag_put(pag); } return reclaimable; } STATIC bool xfs_icwalk_match_id( struct xfs_inode *ip, struct xfs_icwalk *icw) { if ((icw->icw_flags & XFS_ICWALK_FLAG_UID) && !uid_eq(VFS_I(ip)->i_uid, icw->icw_uid)) return false; if ((icw->icw_flags & XFS_ICWALK_FLAG_GID) && !gid_eq(VFS_I(ip)->i_gid, icw->icw_gid)) return false; if ((icw->icw_flags & XFS_ICWALK_FLAG_PRID) && ip->i_projid != icw->icw_prid) return false; return true; } /* * A union-based inode filtering algorithm. Process the inode if any of the * criteria match. This is for global/internal scans only. */ STATIC bool xfs_icwalk_match_id_union( struct xfs_inode *ip, struct xfs_icwalk *icw) { if ((icw->icw_flags & XFS_ICWALK_FLAG_UID) && uid_eq(VFS_I(ip)->i_uid, icw->icw_uid)) return true; if ((icw->icw_flags & XFS_ICWALK_FLAG_GID) && gid_eq(VFS_I(ip)->i_gid, icw->icw_gid)) return true; if ((icw->icw_flags & XFS_ICWALK_FLAG_PRID) && ip->i_projid == icw->icw_prid) return true; return false; } /* * Is this inode @ip eligible for eof/cow block reclamation, given some * filtering parameters @icw? The inode is eligible if @icw is null or * if the predicate functions match. */ static bool xfs_icwalk_match( struct xfs_inode *ip, struct xfs_icwalk *icw) { bool match; if (!icw) return true; if (icw->icw_flags & XFS_ICWALK_FLAG_UNION) match = xfs_icwalk_match_id_union(ip, icw); else match = xfs_icwalk_match_id(ip, icw); if (!match) return false; /* skip the inode if the file size is too small */ if ((icw->icw_flags & XFS_ICWALK_FLAG_MINFILESIZE) && XFS_ISIZE(ip) < icw->icw_min_file_size) return false; return true; } /* * This is a fast pass over the inode cache to try to get reclaim moving on as * many inodes as possible in a short period of time. It kicks itself every few * seconds, as well as being kicked by the inode cache shrinker when memory * goes low. */ void xfs_reclaim_worker( struct work_struct *work) { struct xfs_mount *mp = container_of(to_delayed_work(work), struct xfs_mount, m_reclaim_work); xfs_icwalk(mp, XFS_ICWALK_RECLAIM, NULL); xfs_reclaim_work_queue(mp); } STATIC int xfs_inode_free_eofblocks( struct xfs_inode *ip, struct xfs_icwalk *icw, unsigned int *lockflags) { bool wait; wait = icw && (icw->icw_flags & XFS_ICWALK_FLAG_SYNC); if (!xfs_iflags_test(ip, XFS_IEOFBLOCKS)) return 0; /* * If the mapping is dirty the operation can block and wait for some * time. Unless we are waiting, skip it. */ if (!wait && mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY)) return 0; if (!xfs_icwalk_match(ip, icw)) return 0; /* * If the caller is waiting, return -EAGAIN to keep the background * scanner moving and revisit the inode in a subsequent pass. */ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { if (wait) return -EAGAIN; return 0; } *lockflags |= XFS_IOLOCK_EXCL; if (xfs_can_free_eofblocks(ip)) return xfs_free_eofblocks(ip); /* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); xfs_inode_clear_eofblocks_tag(ip); return 0; } static void xfs_blockgc_set_iflag( struct xfs_inode *ip, unsigned long iflag) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); /* * Don't bother locking the AG and looking up in the radix trees * if we already know that we have the tag set. */ if (ip->i_flags & iflag) return; spin_lock(&ip->i_flags_lock); ip->i_flags |= iflag; spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); xfs_perag_set_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_BLOCKGC_TAG); spin_unlock(&pag->pag_ici_lock); xfs_perag_put(pag); } void xfs_inode_set_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_eofblocks_tag(ip); return xfs_blockgc_set_iflag(ip, XFS_IEOFBLOCKS); } static void xfs_blockgc_clear_iflag( struct xfs_inode *ip, unsigned long iflag) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; bool clear_tag; ASSERT((iflag & ~(XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0); spin_lock(&ip->i_flags_lock); ip->i_flags &= ~iflag; clear_tag = (ip->i_flags & (XFS_IEOFBLOCKS | XFS_ICOWBLOCKS)) == 0; spin_unlock(&ip->i_flags_lock); if (!clear_tag) return; pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_BLOCKGC_TAG); spin_unlock(&pag->pag_ici_lock); xfs_perag_put(pag); } void xfs_inode_clear_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_eofblocks_tag(ip); return xfs_blockgc_clear_iflag(ip, XFS_IEOFBLOCKS); } /* * Set ourselves up to free CoW blocks from this file. If it's already clean * then we can bail out quickly, but otherwise we must back off if the file * is undergoing some kind of write. */ static bool xfs_prep_free_cowblocks( struct xfs_inode *ip) { /* * Just clear the tag if we have an empty cow fork or none at all. It's * possible the inode was fully unshared since it was originally tagged. */ if (!xfs_inode_has_cow_data(ip)) { trace_xfs_inode_free_cowblocks_invalid(ip); xfs_inode_clear_cowblocks_tag(ip); return false; } /* * If the mapping is dirty or under writeback we cannot touch the * CoW fork. Leave it alone if we're in the midst of a directio. */ if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) || mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) || atomic_read(&VFS_I(ip)->i_dio_count)) return false; return true; } /* * Automatic CoW Reservation Freeing * * These functions automatically garbage collect leftover CoW reservations * that were made on behalf of a cowextsize hint when we start to run out * of quota or when the reservations sit around for too long. If the file * has dirty pages or is undergoing writeback, its CoW reservations will * be retained. * * The actual garbage collection piggybacks off the same code that runs * the speculative EOF preallocation garbage collector. */ STATIC int xfs_inode_free_cowblocks( struct xfs_inode *ip, struct xfs_icwalk *icw, unsigned int *lockflags) { bool wait; int ret = 0; wait = icw && (icw->icw_flags & XFS_ICWALK_FLAG_SYNC); if (!xfs_iflags_test(ip, XFS_ICOWBLOCKS)) return 0; if (!xfs_prep_free_cowblocks(ip)) return 0; if (!xfs_icwalk_match(ip, icw)) return 0; /* * If the caller is waiting, return -EAGAIN to keep the background * scanner moving and revisit the inode in a subsequent pass. */ if (!(*lockflags & XFS_IOLOCK_EXCL) && !xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { if (wait) return -EAGAIN; return 0; } *lockflags |= XFS_IOLOCK_EXCL; if (!xfs_ilock_nowait(ip, XFS_MMAPLOCK_EXCL)) { if (wait) return -EAGAIN; return 0; } *lockflags |= XFS_MMAPLOCK_EXCL; /* * Check again, nobody else should be able to dirty blocks or change * the reflink iflag now that we have the first two locks held. */ if (xfs_prep_free_cowblocks(ip)) ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false); return ret; } void xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_cowblocks_tag(ip); return xfs_blockgc_set_iflag(ip, XFS_ICOWBLOCKS); } void xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_cowblocks_tag(ip); return xfs_blockgc_clear_iflag(ip, XFS_ICOWBLOCKS); } /* Disable post-EOF and CoW block auto-reclamation. */ void xfs_blockgc_stop( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t agno; if (!xfs_clear_blockgc_enabled(mp)) return; for_each_perag(mp, agno, pag) cancel_delayed_work_sync(&pag->pag_blockgc_work); trace_xfs_blockgc_stop(mp, __return_address); } /* Enable post-EOF and CoW block auto-reclamation. */ void xfs_blockgc_start( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t agno; if (xfs_set_blockgc_enabled(mp)) return; trace_xfs_blockgc_start(mp, __return_address); for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) xfs_blockgc_queue(pag); } /* Don't try to run block gc on an inode that's in any of these states. */ #define XFS_BLOCKGC_NOGRAB_IFLAGS (XFS_INEW | \ XFS_NEED_INACTIVE | \ XFS_INACTIVATING | \ XFS_IRECLAIMABLE | \ XFS_IRECLAIM) /* * Decide if the given @ip is eligible for garbage collection of speculative * preallocations, and grab it if so. Returns true if it's ready to go or * false if we should just ignore it. */ static bool xfs_blockgc_igrab( struct xfs_inode *ip) { struct inode *inode = VFS_I(ip); ASSERT(rcu_read_lock_held()); /* Check for stale RCU freed inode */ spin_lock(&ip->i_flags_lock); if (!ip->i_ino) goto out_unlock_noent; if (ip->i_flags & XFS_BLOCKGC_NOGRAB_IFLAGS) goto out_unlock_noent; spin_unlock(&ip->i_flags_lock); /* nothing to sync during shutdown */ if (xfs_is_shutdown(ip->i_mount)) return false; /* If we can't grab the inode, it must on it's way to reclaim. */ if (!igrab(inode)) return false; /* inode is valid */ return true; out_unlock_noent: spin_unlock(&ip->i_flags_lock); return false; } /* Scan one incore inode for block preallocations that we can remove. */ static int xfs_blockgc_scan_inode( struct xfs_inode *ip, struct xfs_icwalk *icw) { unsigned int lockflags = 0; int error; error = xfs_inode_free_eofblocks(ip, icw, &lockflags); if (error) goto unlock; error = xfs_inode_free_cowblocks(ip, icw, &lockflags); unlock: if (lockflags) xfs_iunlock(ip, lockflags); xfs_irele(ip); return error; } /* Background worker that trims preallocated space. */ void xfs_blockgc_worker( struct work_struct *work) { struct xfs_perag *pag = container_of(to_delayed_work(work), struct xfs_perag, pag_blockgc_work); struct xfs_mount *mp = pag->pag_mount; int error; trace_xfs_blockgc_worker(mp, __return_address); error = xfs_icwalk_ag(pag, XFS_ICWALK_BLOCKGC, NULL); if (error) xfs_info(mp, "AG %u preallocation gc worker failed, err=%d", pag->pag_agno, error); xfs_blockgc_queue(pag); } /* * Try to free space in the filesystem by purging inactive inodes, eofblocks * and cowblocks. */ int xfs_blockgc_free_space( struct xfs_mount *mp, struct xfs_icwalk *icw) { int error; trace_xfs_blockgc_free_space(mp, icw, _RET_IP_); error = xfs_icwalk(mp, XFS_ICWALK_BLOCKGC, icw); if (error) return error; return xfs_inodegc_flush(mp); } /* * Reclaim all the free space that we can by scheduling the background blockgc * and inodegc workers immediately and waiting for them all to clear. */ int xfs_blockgc_flush_all( struct xfs_mount *mp) { struct xfs_perag *pag; xfs_agnumber_t agno; trace_xfs_blockgc_flush_all(mp, __return_address); /* * For each blockgc worker, move its queue time up to now. If it * wasn't queued, it will not be requeued. Then flush whatever's * left. */ for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) mod_delayed_work(pag->pag_mount->m_blockgc_wq, &pag->pag_blockgc_work, 0); for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) flush_delayed_work(&pag->pag_blockgc_work); return xfs_inodegc_flush(mp); } /* * Run cow/eofblocks scans on the supplied dquots. We don't know exactly which * quota caused an allocation failure, so we make a best effort by including * each quota under low free space conditions (less than 1% free space) in the * scan. * * Callers must not hold any inode's ILOCK. If requesting a synchronous scan * (XFS_ICWALK_FLAG_SYNC), the caller also must not hold any inode's IOLOCK or * MMAPLOCK. */ int xfs_blockgc_free_dquots( struct xfs_mount *mp, struct xfs_dquot *udqp, struct xfs_dquot *gdqp, struct xfs_dquot *pdqp, unsigned int iwalk_flags) { struct xfs_icwalk icw = {0}; bool do_work = false; if (!udqp && !gdqp && !pdqp) return 0; /* * Run a scan to free blocks using the union filter to cover all * applicable quotas in a single scan. */ icw.icw_flags = XFS_ICWALK_FLAG_UNION | iwalk_flags; if (XFS_IS_UQUOTA_ENFORCED(mp) && udqp && xfs_dquot_lowsp(udqp)) { icw.icw_uid = make_kuid(mp->m_super->s_user_ns, udqp->q_id); icw.icw_flags |= XFS_ICWALK_FLAG_UID; do_work = true; } if (XFS_IS_UQUOTA_ENFORCED(mp) && gdqp && xfs_dquot_lowsp(gdqp)) { icw.icw_gid = make_kgid(mp->m_super->s_user_ns, gdqp->q_id); icw.icw_flags |= XFS_ICWALK_FLAG_GID; do_work = true; } if (XFS_IS_PQUOTA_ENFORCED(mp) && pdqp && xfs_dquot_lowsp(pdqp)) { icw.icw_prid = pdqp->q_id; icw.icw_flags |= XFS_ICWALK_FLAG_PRID; do_work = true; } if (!do_work) return 0; return xfs_blockgc_free_space(mp, &icw); } /* Run cow/eofblocks scans on the quotas attached to the inode. */ int xfs_blockgc_free_quota( struct xfs_inode *ip, unsigned int iwalk_flags) { return xfs_blockgc_free_dquots(ip->i_mount, xfs_inode_dquot(ip, XFS_DQTYPE_USER), xfs_inode_dquot(ip, XFS_DQTYPE_GROUP), xfs_inode_dquot(ip, XFS_DQTYPE_PROJ), iwalk_flags); } /* XFS Inode Cache Walking Code */ /* * The inode lookup is done in batches to keep the amount of lock traffic and * radix tree lookups to a minimum. The batch size is a trade off between * lookup reduction and stack usage. This is in the reclaim path, so we can't * be too greedy. */ #define XFS_LOOKUP_BATCH 32 /* * Decide if we want to grab this inode in anticipation of doing work towards * the goal. */ static inline bool xfs_icwalk_igrab( enum xfs_icwalk_goal goal, struct xfs_inode *ip, struct xfs_icwalk *icw) { switch (goal) { case XFS_ICWALK_BLOCKGC: return xfs_blockgc_igrab(ip); case XFS_ICWALK_RECLAIM: return xfs_reclaim_igrab(ip, icw); default: return false; } } /* * Process an inode. Each processing function must handle any state changes * made by the icwalk igrab function. Return -EAGAIN to skip an inode. */ static inline int xfs_icwalk_process_inode( enum xfs_icwalk_goal goal, struct xfs_inode *ip, struct xfs_perag *pag, struct xfs_icwalk *icw) { int error = 0; switch (goal) { case XFS_ICWALK_BLOCKGC: error = xfs_blockgc_scan_inode(ip, icw); break; case XFS_ICWALK_RECLAIM: xfs_reclaim_inode(ip, pag); break; } return error; } /* * For a given per-AG structure @pag and a goal, grab qualifying inodes and * process them in some manner. */ static int xfs_icwalk_ag( struct xfs_perag *pag, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw) { struct xfs_mount *mp = pag->pag_mount; uint32_t first_index; int last_error = 0; int skipped; bool done; int nr_found; restart: done = false; skipped = 0; if (goal == XFS_ICWALK_RECLAIM) first_index = READ_ONCE(pag->pag_ici_reclaim_cursor); else first_index = 0; nr_found = 0; do { struct xfs_inode *batch[XFS_LOOKUP_BATCH]; int error = 0; int i; rcu_read_lock(); nr_found = radix_tree_gang_lookup_tag(&pag->pag_ici_root, (void **) batch, first_index, XFS_LOOKUP_BATCH, goal); if (!nr_found) { done = true; rcu_read_unlock(); break; } /* * Grab the inodes before we drop the lock. if we found * nothing, nr == 0 and the loop will be skipped. */ for (i = 0; i < nr_found; i++) { struct xfs_inode *ip = batch[i]; if (done || !xfs_icwalk_igrab(goal, ip, icw)) batch[i] = NULL; /* * Update the index for the next lookup. Catch * overflows into the next AG range which can occur if * we have inodes in the last block of the AG and we * are currently pointing to the last inode. * * Because we may see inodes that are from the wrong AG * due to RCU freeing and reallocation, only update the * index if it lies in this AG. It was a race that lead * us to see this inode, so another lookup from the * same index will not find it again. */ if (XFS_INO_TO_AGNO(mp, ip->i_ino) != pag->pag_agno) continue; first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1); if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) done = true; } /* unlock now we've grabbed the inodes. */ rcu_read_unlock(); for (i = 0; i < nr_found; i++) { if (!batch[i]) continue; error = xfs_icwalk_process_inode(goal, batch[i], pag, icw); if (error == -EAGAIN) { skipped++; continue; } if (error && last_error != -EFSCORRUPTED) last_error = error; } /* bail out if the filesystem is corrupted. */ if (error == -EFSCORRUPTED) break; cond_resched(); if (icw && (icw->icw_flags & XFS_ICWALK_FLAG_SCAN_LIMIT)) { icw->icw_scan_limit -= XFS_LOOKUP_BATCH; if (icw->icw_scan_limit <= 0) break; } } while (nr_found && !done); if (goal == XFS_ICWALK_RECLAIM) { if (done) first_index = 0; WRITE_ONCE(pag->pag_ici_reclaim_cursor, first_index); } if (skipped) { delay(1); goto restart; } return last_error; } /* Walk all incore inodes to achieve a given goal. */ static int xfs_icwalk( struct xfs_mount *mp, enum xfs_icwalk_goal goal, struct xfs_icwalk *icw) { struct xfs_perag *pag; int error = 0; int last_error = 0; xfs_agnumber_t agno; for_each_perag_tag(mp, agno, pag, goal) { error = xfs_icwalk_ag(pag, goal, icw); if (error) { last_error = error; if (error == -EFSCORRUPTED) { xfs_perag_rele(pag); break; } } } return last_error; BUILD_BUG_ON(XFS_ICWALK_PRIVATE_FLAGS & XFS_ICWALK_FLAGS_VALID); } #ifdef DEBUG static void xfs_check_delalloc( struct xfs_inode *ip, int whichfork) { struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_bmbt_irec got; struct xfs_iext_cursor icur; if (!ifp || !xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got)) return; do { if (isnullstartblock(got.br_startblock)) { xfs_warn(ip->i_mount, "ino %llx %s fork has delalloc extent at [0x%llx:0x%llx]", ip->i_ino, whichfork == XFS_DATA_FORK ? "data" : "cow", got.br_startoff, got.br_blockcount); } } while (xfs_iext_next_extent(ifp, &icur, &got)); } #else #define xfs_check_delalloc(ip, whichfork) do { } while (0) #endif /* Schedule the inode for reclaim. */ static void xfs_inodegc_set_reclaimable( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; if (!xfs_is_shutdown(mp) && ip->i_delayed_blks) { xfs_check_delalloc(ip, XFS_DATA_FORK); xfs_check_delalloc(ip, XFS_COW_FORK); ASSERT(0); } pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); spin_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); trace_xfs_inode_set_reclaimable(ip); ip->i_flags &= ~(XFS_NEED_INACTIVE | XFS_INACTIVATING); ip->i_flags |= XFS_IRECLAIMABLE; xfs_perag_set_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG); spin_unlock(&ip->i_flags_lock); spin_unlock(&pag->pag_ici_lock); xfs_perag_put(pag); } /* * Free all speculative preallocations and possibly even the inode itself. * This is the last chance to make changes to an otherwise unreferenced file * before incore reclamation happens. */ static int xfs_inodegc_inactivate( struct xfs_inode *ip) { int error; trace_xfs_inode_inactivating(ip); error = xfs_inactive(ip); xfs_inodegc_set_reclaimable(ip); return error; } void xfs_inodegc_worker( struct work_struct *work) { struct xfs_inodegc *gc = container_of(to_delayed_work(work), struct xfs_inodegc, work); struct llist_node *node = llist_del_all(&gc->list); struct xfs_inode *ip, *n; struct xfs_mount *mp = gc->mp; unsigned int nofs_flag; /* * Clear the cpu mask bit and ensure that we have seen the latest * update of the gc structure associated with this CPU. This matches * with the release semantics used when setting the cpumask bit in * xfs_inodegc_queue. */ cpumask_clear_cpu(gc->cpu, &mp->m_inodegc_cpumask); smp_mb__after_atomic(); WRITE_ONCE(gc->items, 0); if (!node) return; /* * We can allocate memory here while doing writeback on behalf of * memory reclaim. To avoid memory allocation deadlocks set the * task-wide nofs context for the following operations. */ nofs_flag = memalloc_nofs_save(); ip = llist_entry(node, struct xfs_inode, i_gclist); trace_xfs_inodegc_worker(mp, READ_ONCE(gc->shrinker_hits)); WRITE_ONCE(gc->shrinker_hits, 0); llist_for_each_entry_safe(ip, n, node, i_gclist) { int error; xfs_iflags_set(ip, XFS_INACTIVATING); error = xfs_inodegc_inactivate(ip); if (error && !gc->error) gc->error = error; } memalloc_nofs_restore(nofs_flag); } /* * Expedite all pending inodegc work to run immediately. This does not wait for * completion of the work. */ void xfs_inodegc_push( struct xfs_mount *mp) { if (!xfs_is_inodegc_enabled(mp)) return; trace_xfs_inodegc_push(mp, __return_address); xfs_inodegc_queue_all(mp); } /* * Force all currently queued inode inactivation work to run immediately and * wait for the work to finish. */ int xfs_inodegc_flush( struct xfs_mount *mp) { xfs_inodegc_push(mp); trace_xfs_inodegc_flush(mp, __return_address); return xfs_inodegc_wait_all(mp); } /* * Flush all the pending work and then disable the inode inactivation background * workers and wait for them to stop. Caller must hold sb->s_umount to * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_stop( struct xfs_mount *mp) { bool rerun; if (!xfs_clear_inodegc_enabled(mp)) return; /* * Drain all pending inodegc work, including inodes that could be * queued by racing xfs_inodegc_queue or xfs_inodegc_shrinker_scan * threads that sample the inodegc state just prior to us clearing it. * The inodegc flag state prevents new threads from queuing more * inodes, so we queue pending work items and flush the workqueue until * all inodegc lists are empty. IOWs, we cannot use drain_workqueue * here because it does not allow other unserialized mechanisms to * reschedule inodegc work while this draining is in progress. */ xfs_inodegc_queue_all(mp); do { flush_workqueue(mp->m_inodegc_wq); rerun = xfs_inodegc_queue_all(mp); } while (rerun); trace_xfs_inodegc_stop(mp, __return_address); } /* * Enable the inode inactivation background workers and schedule deferred inode * inactivation work if there is any. Caller must hold sb->s_umount to * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_start( struct xfs_mount *mp) { if (xfs_set_inodegc_enabled(mp)) return; trace_xfs_inodegc_start(mp, __return_address); xfs_inodegc_queue_all(mp); } #ifdef CONFIG_XFS_RT static inline bool xfs_inodegc_want_queue_rt_file( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; if (!XFS_IS_REALTIME_INODE(ip)) return false; if (__percpu_counter_compare(&mp->m_frextents, mp->m_low_rtexts[XFS_LOWSP_5_PCNT], XFS_FDBLOCKS_BATCH) < 0) return true; return false; } #else # define xfs_inodegc_want_queue_rt_file(ip) (false) #endif /* CONFIG_XFS_RT */ /* * Schedule the inactivation worker when: * * - We've accumulated more than one inode cluster buffer's worth of inodes. * - There is less than 5% free space left. * - Any of the quotas for this inode are near an enforcement limit. */ static inline bool xfs_inodegc_want_queue_work( struct xfs_inode *ip, unsigned int items) { struct xfs_mount *mp = ip->i_mount; if (items > mp->m_ino_geo.inodes_per_cluster) return true; if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_low_space[XFS_LOWSP_5_PCNT], XFS_FDBLOCKS_BATCH) < 0) return true; if (xfs_inodegc_want_queue_rt_file(ip)) return true; if (xfs_inode_near_dquot_enforcement(ip, XFS_DQTYPE_USER)) return true; if (xfs_inode_near_dquot_enforcement(ip, XFS_DQTYPE_GROUP)) return true; if (xfs_inode_near_dquot_enforcement(ip, XFS_DQTYPE_PROJ)) return true; return false; } /* * Upper bound on the number of inodes in each AG that can be queued for * inactivation at any given time, to avoid monopolizing the workqueue. */ #define XFS_INODEGC_MAX_BACKLOG (4 * XFS_INODES_PER_CHUNK) /* * Make the frontend wait for inactivations when: * * - Memory shrinkers queued the inactivation worker and it hasn't finished. * - The queue depth exceeds the maximum allowable percpu backlog. * * Note: If we are in a NOFS context here (e.g. current thread is running a * transaction) the we don't want to block here as inodegc progress may require * filesystem resources we hold to make progress and that could result in a * deadlock. Hence we skip out of here if we are in a scoped NOFS context. */ static inline bool xfs_inodegc_want_flush_work( struct xfs_inode *ip, unsigned int items, unsigned int shrinker_hits) { if (current->flags & PF_MEMALLOC_NOFS) return false; if (shrinker_hits > 0) return true; if (items > XFS_INODEGC_MAX_BACKLOG) return true; return false; } /* * Queue a background inactivation worker if there are inodes that need to be * inactivated and higher level xfs code hasn't disabled the background * workers. */ static void xfs_inodegc_queue( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_inodegc *gc; int items; unsigned int shrinker_hits; unsigned int cpu_nr; unsigned long queue_delay = 1; trace_xfs_inode_set_need_inactive(ip); spin_lock(&ip->i_flags_lock); ip->i_flags |= XFS_NEED_INACTIVE; spin_unlock(&ip->i_flags_lock); cpu_nr = get_cpu(); gc = this_cpu_ptr(mp->m_inodegc); llist_add(&ip->i_gclist, &gc->list); items = READ_ONCE(gc->items); WRITE_ONCE(gc->items, items + 1); shrinker_hits = READ_ONCE(gc->shrinker_hits); /* * Ensure the list add is always seen by anyone who finds the cpumask * bit set. This effectively gives the cpumask bit set operation * release ordering semantics. */ smp_mb__before_atomic(); if (!cpumask_test_cpu(cpu_nr, &mp->m_inodegc_cpumask)) cpumask_test_and_set_cpu(cpu_nr, &mp->m_inodegc_cpumask); /* * We queue the work while holding the current CPU so that the work * is scheduled to run on this CPU. */ if (!xfs_is_inodegc_enabled(mp)) { put_cpu(); return; } if (xfs_inodegc_want_queue_work(ip, items)) queue_delay = 0; trace_xfs_inodegc_queue(mp, __return_address); mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, queue_delay); put_cpu(); if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) { trace_xfs_inodegc_throttle(mp, __return_address); flush_delayed_work(&gc->work); } } /* * We set the inode flag atomically with the radix tree tag. Once we get tag * lookups on the radix tree, this inode flag can go away. * * We always use background reclaim here because even if the inode is clean, it * still may be under IO and hence we have wait for IO completion to occur * before we can reclaim the inode. The background reclaim path handles this * more efficiently than we can here, so simply let background reclaim tear down * all inodes. */ void xfs_inode_mark_reclaimable( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; bool need_inactive; XFS_STATS_INC(mp, vn_reclaim); /* * We should never get here with any of the reclaim flags already set. */ ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_ALL_IRECLAIM_FLAGS)); need_inactive = xfs_inode_needs_inactive(ip); if (need_inactive) { xfs_inodegc_queue(ip); return; } /* Going straight to reclaim, so drop the dquots. */ xfs_qm_dqdetach(ip); xfs_inodegc_set_reclaimable(ip); } /* * Register a phony shrinker so that we can run background inodegc sooner when * there's memory pressure. Inactivation does not itself free any memory but * it does make inodes reclaimable, which eventually frees memory. * * The count function, seek value, and batch value are crafted to trigger the * scan function during the second round of scanning. Hopefully this means * that we reclaimed enough memory that initiating metadata transactions won't * make things worse. */ #define XFS_INODEGC_SHRINKER_COUNT (1UL << DEF_PRIORITY) #define XFS_INODEGC_SHRINKER_BATCH ((XFS_INODEGC_SHRINKER_COUNT / 2) + 1) static unsigned long xfs_inodegc_shrinker_count( struct shrinker *shrink, struct shrink_control *sc) { struct xfs_mount *mp = shrink->private_data; struct xfs_inodegc *gc; int cpu; if (!xfs_is_inodegc_enabled(mp)) return 0; for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) return XFS_INODEGC_SHRINKER_COUNT; } return 0; } static unsigned long xfs_inodegc_shrinker_scan( struct shrinker *shrink, struct shrink_control *sc) { struct xfs_mount *mp = shrink->private_data; struct xfs_inodegc *gc; int cpu; bool no_items = true; if (!xfs_is_inodegc_enabled(mp)) return SHRINK_STOP; trace_xfs_inodegc_shrinker_scan(mp, sc, __return_address); for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { unsigned int h = READ_ONCE(gc->shrinker_hits); WRITE_ONCE(gc->shrinker_hits, h + 1); mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); no_items = false; } } /* * If there are no inodes to inactivate, we don't want the shrinker * to think there's deferred work to call us back about. */ if (no_items) return LONG_MAX; return SHRINK_STOP; } /* Register a shrinker so we can accelerate inodegc and throttle queuing. */ int xfs_inodegc_register_shrinker( struct xfs_mount *mp) { mp->m_inodegc_shrinker = shrinker_alloc(SHRINKER_NONSLAB, "xfs-inodegc:%s", mp->m_super->s_id); if (!mp->m_inodegc_shrinker) return -ENOMEM; mp->m_inodegc_shrinker->count_objects = xfs_inodegc_shrinker_count; mp->m_inodegc_shrinker->scan_objects = xfs_inodegc_shrinker_scan; mp->m_inodegc_shrinker->seeks = 0; mp->m_inodegc_shrinker->batch = XFS_INODEGC_SHRINKER_BATCH; mp->m_inodegc_shrinker->private_data = mp; shrinker_register(mp->m_inodegc_shrinker); return 0; } |
| 343 344 344 1 1 1 1 2327 2324 285 2223 2320 2325 1963 1964 2212 2211 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * mm/pgtable-generic.c * * Generic pgtable methods declared in linux/pgtable.h * * Copyright (C) 2010 Linus Torvalds */ #include <linux/pagemap.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mm_inline.h> #include <asm/pgalloc.h> #include <asm/tlb.h> /* * If a p?d_bad entry is found while walking page tables, report * the error, before resetting entry to p?d_none. Usually (but * very seldom) called out from the p?d_none_or_clear_bad macros. */ void pgd_clear_bad(pgd_t *pgd) { pgd_ERROR(*pgd); pgd_clear(pgd); } #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *p4d) { p4d_ERROR(*p4d); p4d_clear(p4d); } #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); pud_clear(pud); } #endif /* * Note that the pmd variant below can't be stub'ed out just as for p4d/pud * above. pmd folding is special and typically pmd_* macros refer to upper * level even when folded */ void pmd_clear_bad(pmd_t *pmd) { pmd_ERROR(*pmd); pmd_clear(pmd); } #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* * Only sets the access flags (dirty, accessed), as well as write * permission. Furthermore, we know it always gets set to a "more * permissive" setting, which allows most architectures to optimize * this. We return whether the PTE actually changed, which in turn * instructs the caller to do things like update__mmu_cache. This * used to be done in the caller, but sparc needs minor faults to * force that call on sun4c so we changed this macro slightly */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { int changed = !pte_same(ptep_get(ptep), entry); if (changed) { set_pte_at(vma->vm_mm, address, ptep, entry); flush_tlb_fix_spurious_fault(vma, address, ptep); } return changed; } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { int young; young = ptep_test_and_clear_young(vma, address, ptep); if (young) flush_tlb_page(vma, address); return young; } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { struct mm_struct *mm = (vma)->vm_mm; pte_t pte; pte = ptep_get_and_clear(mm, address, ptep); if (pte_accessible(mm, pte)) flush_tlb_page(vma, address); return pte; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { int changed = !pmd_same(*pmdp, entry); VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed) { set_pmd_at(vma->vm_mm, address, pmdp, entry); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { int young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return young; } #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { pud_t pud; VM_BUG_ON(address & ~HPAGE_PUD_MASK); VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp)); pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); return pud; } #endif #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ if (!pmd_huge_pte(mm, pmdp)) INIT_LIST_HEAD(&pgtable->lru); else list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru); pmd_huge_pte(mm, pmdp) = pgtable; } #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW /* no "address" argument so destroys page coloring of some arch */ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { pgtable_t pgtable; assert_spin_locked(pmd_lockptr(mm, pmdp)); /* FIFO */ pgtable = pmd_huge_pte(mm, pmdp); pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru, struct page, lru); if (pmd_huge_pte(mm, pmdp)) list_del(&pgtable->lru); return pgtable; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return old; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); return pmdp_invalidate(vma, address, pmdp); } #endif #ifndef pmdp_collapse_flush pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { /* * pmd and hugepage pte format are same. So we could * use the same function. */ pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); /* collapse entails shooting down ptes not pmd */ flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif /* arch define pte_free_defer in asm/pgalloc.h for its own implementation */ #ifndef pte_free_defer static void pte_free_now(struct rcu_head *head) { struct page *page; page = container_of(head, struct page, rcu_head); pte_free(NULL /* mm not passed and not used */, (pgtable_t)page); } void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) { struct page *page; page = pgtable; call_rcu(&page->rcu_head, pte_free_now); } #endif /* pte_free_defer */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \ (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RCU)) /* * See the comment above ptep_get_lockless() in include/linux/pgtable.h: * the barriers in pmdp_get_lockless() cannot guarantee that the value in * pmd_high actually belongs with the value in pmd_low; but holding interrupts * off blocks the TLB flush between present updates, which guarantees that a * successful __pte_offset_map() points to a page from matched halves. */ static unsigned long pmdp_get_lockless_start(void) { unsigned long irqflags; local_irq_save(irqflags); return irqflags; } static void pmdp_get_lockless_end(unsigned long irqflags) { local_irq_restore(irqflags); } #else static unsigned long pmdp_get_lockless_start(void) { return 0; } static void pmdp_get_lockless_end(unsigned long irqflags) { } #endif pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp) { unsigned long irqflags; pmd_t pmdval; rcu_read_lock(); irqflags = pmdp_get_lockless_start(); pmdval = pmdp_get_lockless(pmd); pmdp_get_lockless_end(irqflags); if (pmdvalp) *pmdvalp = pmdval; if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval))) goto nomap; if (unlikely(pmd_trans_huge(pmdval) || pmd_devmap(pmdval))) goto nomap; if (unlikely(pmd_bad(pmdval))) { pmd_clear_bad(pmd); goto nomap; } return __pte_map(&pmdval, addr); nomap: rcu_read_unlock(); return NULL; } pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { pmd_t pmdval; pte_t *pte; pte = __pte_offset_map(pmd, addr, &pmdval); if (likely(pte)) *ptlp = pte_lockptr(mm, &pmdval); return pte; } /* * pte_offset_map_lock(mm, pmd, addr, ptlp), and its internal implementation * __pte_offset_map_lock() below, is usually called with the pmd pointer for * addr, reached by walking down the mm's pgd, p4d, pud for addr: either while * holding mmap_lock or vma lock for read or for write; or in truncate or rmap * context, while holding file's i_mmap_lock or anon_vma lock for read (or for * write). In a few cases, it may be used with pmd pointing to a pmd_t already * copied to or constructed on the stack. * * When successful, it returns the pte pointer for addr, with its page table * kmapped if necessary (when CONFIG_HIGHPTE), and locked against concurrent * modification by software, with a pointer to that spinlock in ptlp (in some * configs mm->page_table_lock, in SPLIT_PTLOCK configs a spinlock in table's * struct page). pte_unmap_unlock(pte, ptl) to unlock and unmap afterwards. * * But it is unsuccessful, returning NULL with *ptlp unchanged, if there is no * page table at *pmd: if, for example, the page table has just been removed, * or replaced by the huge pmd of a THP. (When successful, *pmd is rechecked * after acquiring the ptlock, and retried internally if it changed: so that a * page table can be safely removed or replaced by THP while holding its lock.) * * pte_offset_map(pmd, addr), and its internal helper __pte_offset_map() above, * just returns the pte pointer for addr, its page table kmapped if necessary; * or NULL if there is no page table at *pmd. It does not attempt to lock the * page table, so cannot normally be used when the page table is to be updated, * or when entries read must be stable. But it does take rcu_read_lock(): so * that even when page table is racily removed, it remains a valid though empty * and disconnected table. Until pte_unmap(pte) unmaps and rcu_read_unlock()s * afterwards. * * pte_offset_map_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map(); * but when successful, it also outputs a pointer to the spinlock in ptlp - as * pte_offset_map_lock() does, but in this case without locking it. This helps * the caller to avoid a later pte_lockptr(mm, *pmd), which might by that time * act on a changed *pmd: pte_offset_map_nolock() provides the correct spinlock * pointer for the page table that it returns. In principle, the caller should * recheck *pmd once the lock is taken; in practice, no callsite needs that - * either the mmap_lock for write, or pte_same() check on contents, is enough. * * Note that free_pgtables(), used after unmapping detached vmas, or when * exiting the whole mm, does not take page table lock before freeing a page * table, and may not use RCU at all: "outsiders" like khugepaged should avoid * pte_offset_map() and co once the vma is detached from mm or mm_users is zero. */ pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, spinlock_t **ptlp) { spinlock_t *ptl; pmd_t pmdval; pte_t *pte; again: pte = __pte_offset_map(pmd, addr, &pmdval); if (unlikely(!pte)) return pte; ptl = pte_lockptr(mm, &pmdval); spin_lock(ptl); if (likely(pmd_same(pmdval, pmdp_get_lockless(pmd)))) { *ptlp = ptl; return pte; } pte_unmap_unlock(pte, ptl); goto again; } |
| 222 7 2 218 1 217 1 223 222 157 65 185 2 11 179 2 9 186 7 186 186 183 17 3 17 3 3 185 186 15 15 7 2 2 186 186 176 2 186 136 2 186 2 11 2 4 222 82 186 5 186 222 9 211 211 61 174 10 8 2 176 224 224 223 27 145 26 2 136 26 145 145 43 131 131 145 145 145 144 48 108 26 145 48 108 26 109 6 6 106 29 30 30 30 2 6 25 162 84 15 159 215 72 56 215 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * directory.c * * PURPOSE * Directory related functions * */ #include "udfdecl.h" #include "udf_i.h" #include <linux/fs.h> #include <linux/string.h> #include <linux/bio.h> #include <linux/crc-itu-t.h> #include <linux/iversion.h> static int udf_verify_fi(struct udf_fileident_iter *iter) { unsigned int len; if (iter->fi.descTag.tagIdent != cpu_to_le16(TAG_IDENT_FID)) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry at pos %llu with incorrect tag %x\n", iter->dir->i_ino, (unsigned long long)iter->pos, le16_to_cpu(iter->fi.descTag.tagIdent)); return -EFSCORRUPTED; } len = udf_dir_entry_len(&iter->fi); if (le16_to_cpu(iter->fi.lengthOfImpUse) & 3) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry at pos %llu with unaligned length of impUse field\n", iter->dir->i_ino, (unsigned long long)iter->pos); return -EFSCORRUPTED; } /* * This is in fact allowed by the spec due to long impUse field but * we don't support it. If there is real media with this large impUse * field, support can be added. */ if (len > 1 << iter->dir->i_blkbits) { udf_err(iter->dir->i_sb, "directory (ino %lu) has too big (%u) entry at pos %llu\n", iter->dir->i_ino, len, (unsigned long long)iter->pos); return -EFSCORRUPTED; } if (iter->pos + len > iter->dir->i_size) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry past directory size at pos %llu\n", iter->dir->i_ino, (unsigned long long)iter->pos); return -EFSCORRUPTED; } if (udf_dir_entry_len(&iter->fi) != sizeof(struct tag) + le16_to_cpu(iter->fi.descTag.descCRCLength)) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry where CRC length (%u) does not match entry length (%u)\n", iter->dir->i_ino, (unsigned)le16_to_cpu(iter->fi.descTag.descCRCLength), (unsigned)(udf_dir_entry_len(&iter->fi) - sizeof(struct tag))); return -EFSCORRUPTED; } return 0; } static int udf_copy_fi(struct udf_fileident_iter *iter) { struct udf_inode_info *iinfo = UDF_I(iter->dir); u32 blksize = 1 << iter->dir->i_blkbits; u32 off, len, nameoff; int err; /* Skip copying when we are at EOF */ if (iter->pos >= iter->dir->i_size) { iter->name = NULL; return 0; } if (iter->dir->i_size < iter->pos + sizeof(struct fileIdentDesc)) { udf_err(iter->dir->i_sb, "directory (ino %lu) has entry straddling EOF\n", iter->dir->i_ino); return -EFSCORRUPTED; } if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { memcpy(&iter->fi, iinfo->i_data + iinfo->i_lenEAttr + iter->pos, sizeof(struct fileIdentDesc)); err = udf_verify_fi(iter); if (err < 0) return err; iter->name = iinfo->i_data + iinfo->i_lenEAttr + iter->pos + sizeof(struct fileIdentDesc) + le16_to_cpu(iter->fi.lengthOfImpUse); return 0; } off = iter->pos & (blksize - 1); len = min_t(u32, sizeof(struct fileIdentDesc), blksize - off); memcpy(&iter->fi, iter->bh[0]->b_data + off, len); if (len < sizeof(struct fileIdentDesc)) memcpy((char *)(&iter->fi) + len, iter->bh[1]->b_data, sizeof(struct fileIdentDesc) - len); err = udf_verify_fi(iter); if (err < 0) return err; /* Handle directory entry name */ nameoff = off + sizeof(struct fileIdentDesc) + le16_to_cpu(iter->fi.lengthOfImpUse); if (off + udf_dir_entry_len(&iter->fi) <= blksize) { iter->name = iter->bh[0]->b_data + nameoff; } else if (nameoff >= blksize) { iter->name = iter->bh[1]->b_data + (nameoff - blksize); } else { iter->name = iter->namebuf; len = blksize - nameoff; memcpy(iter->name, iter->bh[0]->b_data + nameoff, len); memcpy(iter->name + len, iter->bh[1]->b_data, iter->fi.lengthFileIdent - len); } return 0; } /* Readahead 8k once we are at 8k boundary */ static void udf_readahead_dir(struct udf_fileident_iter *iter) { unsigned int ralen = 16 >> (iter->dir->i_blkbits - 9); struct buffer_head *tmp, *bha[16]; int i, num; udf_pblk_t blk; if (iter->loffset & (ralen - 1)) return; if (iter->loffset + ralen > (iter->elen >> iter->dir->i_blkbits)) ralen = (iter->elen >> iter->dir->i_blkbits) - iter->loffset; num = 0; for (i = 0; i < ralen; i++) { blk = udf_get_lb_pblock(iter->dir->i_sb, &iter->eloc, iter->loffset + i); tmp = sb_getblk(iter->dir->i_sb, blk); if (tmp && !buffer_uptodate(tmp) && !buffer_locked(tmp)) bha[num++] = tmp; else brelse(tmp); } if (num) { bh_readahead_batch(num, bha, REQ_RAHEAD); for (i = 0; i < num; i++) brelse(bha[i]); } } static struct buffer_head *udf_fiiter_bread_blk(struct udf_fileident_iter *iter) { udf_pblk_t blk; udf_readahead_dir(iter); blk = udf_get_lb_pblock(iter->dir->i_sb, &iter->eloc, iter->loffset); return sb_bread(iter->dir->i_sb, blk); } /* * Updates loffset to point to next directory block; eloc, elen & epos are * updated if we need to traverse to the next extent as well. */ static int udf_fiiter_advance_blk(struct udf_fileident_iter *iter) { iter->loffset++; if (iter->loffset < DIV_ROUND_UP(iter->elen, 1<<iter->dir->i_blkbits)) return 0; iter->loffset = 0; if (udf_next_aext(iter->dir, &iter->epos, &iter->eloc, &iter->elen, 1) != (EXT_RECORDED_ALLOCATED >> 30)) { if (iter->pos == iter->dir->i_size) { iter->elen = 0; return 0; } udf_err(iter->dir->i_sb, "extent after position %llu not allocated in directory (ino %lu)\n", (unsigned long long)iter->pos, iter->dir->i_ino); return -EFSCORRUPTED; } return 0; } static int udf_fiiter_load_bhs(struct udf_fileident_iter *iter) { int blksize = 1 << iter->dir->i_blkbits; int off = iter->pos & (blksize - 1); int err; struct fileIdentDesc *fi; /* Is there any further extent we can map from? */ if (!iter->bh[0] && iter->elen) { iter->bh[0] = udf_fiiter_bread_blk(iter); if (!iter->bh[0]) { err = -ENOMEM; goto out_brelse; } if (!buffer_uptodate(iter->bh[0])) { err = -EIO; goto out_brelse; } } /* There's no next block so we are done */ if (iter->pos >= iter->dir->i_size) return 0; /* Need to fetch next block as well? */ if (off + sizeof(struct fileIdentDesc) > blksize) goto fetch_next; fi = (struct fileIdentDesc *)(iter->bh[0]->b_data + off); /* Need to fetch next block to get name? */ if (off + udf_dir_entry_len(fi) > blksize) { fetch_next: err = udf_fiiter_advance_blk(iter); if (err) goto out_brelse; iter->bh[1] = udf_fiiter_bread_blk(iter); if (!iter->bh[1]) { err = -ENOMEM; goto out_brelse; } if (!buffer_uptodate(iter->bh[1])) { err = -EIO; goto out_brelse; } } return 0; out_brelse: brelse(iter->bh[0]); brelse(iter->bh[1]); iter->bh[0] = iter->bh[1] = NULL; return err; } int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir, loff_t pos) { struct udf_inode_info *iinfo = UDF_I(dir); int err = 0; iter->dir = dir; iter->bh[0] = iter->bh[1] = NULL; iter->pos = pos; iter->elen = 0; iter->epos.bh = NULL; iter->name = NULL; /* * When directory is verified, we don't expect directory iteration to * fail and it can be difficult to undo without corrupting filesystem. * So just do not allow memory allocation failures here. */ iter->namebuf = kmalloc(UDF_NAME_LEN_CS0, GFP_KERNEL | __GFP_NOFAIL); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { err = udf_copy_fi(iter); goto out; } if (inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos, &iter->eloc, &iter->elen, &iter->loffset) != (EXT_RECORDED_ALLOCATED >> 30)) { if (pos == dir->i_size) return 0; udf_err(dir->i_sb, "position %llu not allocated in directory (ino %lu)\n", (unsigned long long)pos, dir->i_ino); err = -EFSCORRUPTED; goto out; } err = udf_fiiter_load_bhs(iter); if (err < 0) goto out; err = udf_copy_fi(iter); out: if (err < 0) udf_fiiter_release(iter); return err; } int udf_fiiter_advance(struct udf_fileident_iter *iter) { unsigned int oldoff, len; int blksize = 1 << iter->dir->i_blkbits; int err; oldoff = iter->pos & (blksize - 1); len = udf_dir_entry_len(&iter->fi); iter->pos += len; if (UDF_I(iter->dir)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { if (oldoff + len >= blksize) { brelse(iter->bh[0]); iter->bh[0] = NULL; /* Next block already loaded? */ if (iter->bh[1]) { iter->bh[0] = iter->bh[1]; iter->bh[1] = NULL; } else { err = udf_fiiter_advance_blk(iter); if (err < 0) return err; } } err = udf_fiiter_load_bhs(iter); if (err < 0) return err; } return udf_copy_fi(iter); } void udf_fiiter_release(struct udf_fileident_iter *iter) { iter->dir = NULL; brelse(iter->bh[0]); brelse(iter->bh[1]); iter->bh[0] = iter->bh[1] = NULL; kfree(iter->namebuf); iter->namebuf = NULL; } static void udf_copy_to_bufs(void *buf1, int len1, void *buf2, int len2, int off, void *src, int len) { int copy; if (off >= len1) { off -= len1; } else { copy = min(off + len, len1) - off; memcpy(buf1 + off, src, copy); src += copy; len -= copy; off = 0; } if (len > 0) { if (WARN_ON_ONCE(off + len > len2 || !buf2)) return; memcpy(buf2 + off, src, len); } } static uint16_t udf_crc_fi_bufs(void *buf1, int len1, void *buf2, int len2, int off, int len) { int copy; uint16_t crc = 0; if (off >= len1) { off -= len1; } else { copy = min(off + len, len1) - off; crc = crc_itu_t(crc, buf1 + off, copy); len -= copy; off = 0; } if (len > 0) { if (WARN_ON_ONCE(off + len > len2 || !buf2)) return 0; crc = crc_itu_t(crc, buf2 + off, len); } return crc; } static void udf_copy_fi_to_bufs(char *buf1, int len1, char *buf2, int len2, int off, struct fileIdentDesc *fi, uint8_t *impuse, uint8_t *name) { uint16_t crc; int fioff = off; int crcoff = off + sizeof(struct tag); unsigned int crclen = udf_dir_entry_len(fi) - sizeof(struct tag); char zeros[UDF_NAME_PAD] = {}; int endoff = off + udf_dir_entry_len(fi); udf_copy_to_bufs(buf1, len1, buf2, len2, off, fi, sizeof(struct fileIdentDesc)); off += sizeof(struct fileIdentDesc); if (impuse) udf_copy_to_bufs(buf1, len1, buf2, len2, off, impuse, le16_to_cpu(fi->lengthOfImpUse)); off += le16_to_cpu(fi->lengthOfImpUse); if (name) { udf_copy_to_bufs(buf1, len1, buf2, len2, off, name, fi->lengthFileIdent); off += fi->lengthFileIdent; udf_copy_to_bufs(buf1, len1, buf2, len2, off, zeros, endoff - off); } crc = udf_crc_fi_bufs(buf1, len1, buf2, len2, crcoff, crclen); fi->descTag.descCRC = cpu_to_le16(crc); fi->descTag.descCRCLength = cpu_to_le16(crclen); fi->descTag.tagChecksum = udf_tag_checksum(&fi->descTag); udf_copy_to_bufs(buf1, len1, buf2, len2, fioff, fi, sizeof(struct tag)); } void udf_fiiter_write_fi(struct udf_fileident_iter *iter, uint8_t *impuse) { struct udf_inode_info *iinfo = UDF_I(iter->dir); void *buf1, *buf2 = NULL; int len1, len2 = 0, off; int blksize = 1 << iter->dir->i_blkbits; off = iter->pos & (blksize - 1); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { buf1 = iinfo->i_data + iinfo->i_lenEAttr; len1 = iter->dir->i_size; } else { buf1 = iter->bh[0]->b_data; len1 = blksize; if (iter->bh[1]) { buf2 = iter->bh[1]->b_data; len2 = blksize; } } udf_copy_fi_to_bufs(buf1, len1, buf2, len2, off, &iter->fi, impuse, iter->name == iter->namebuf ? iter->name : NULL); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { mark_inode_dirty(iter->dir); } else { mark_buffer_dirty_inode(iter->bh[0], iter->dir); if (iter->bh[1]) mark_buffer_dirty_inode(iter->bh[1], iter->dir); } inode_inc_iversion(iter->dir); } void udf_fiiter_update_elen(struct udf_fileident_iter *iter, uint32_t new_elen) { struct udf_inode_info *iinfo = UDF_I(iter->dir); int diff = new_elen - iter->elen; /* Skip update when we already went past the last extent */ if (!iter->elen) return; iter->elen = new_elen; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) iter->epos.offset -= sizeof(struct short_ad); else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) iter->epos.offset -= sizeof(struct long_ad); udf_write_aext(iter->dir, &iter->epos, &iter->eloc, iter->elen, 1); iinfo->i_lenExtents += diff; mark_inode_dirty(iter->dir); } /* Append new block to directory. @iter is expected to point at EOF */ int udf_fiiter_append_blk(struct udf_fileident_iter *iter) { struct udf_inode_info *iinfo = UDF_I(iter->dir); int blksize = 1 << iter->dir->i_blkbits; struct buffer_head *bh; sector_t block; uint32_t old_elen = iter->elen; int err; if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)) return -EINVAL; /* Round up last extent in the file */ udf_fiiter_update_elen(iter, ALIGN(iter->elen, blksize)); /* Allocate new block and refresh mapping information */ block = iinfo->i_lenExtents >> iter->dir->i_blkbits; bh = udf_bread(iter->dir, block, 1, &err); if (!bh) { udf_fiiter_update_elen(iter, old_elen); return err; } if (inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen, &iter->loffset) != (EXT_RECORDED_ALLOCATED >> 30)) { udf_err(iter->dir->i_sb, "block %llu not allocated in directory (ino %lu)\n", (unsigned long long)block, iter->dir->i_ino); return -EFSCORRUPTED; } if (!(iter->pos & (blksize - 1))) { brelse(iter->bh[0]); iter->bh[0] = bh; } else { iter->bh[1] = bh; } return 0; } struct short_ad *udf_get_fileshortad(uint8_t *ptr, int maxoffset, uint32_t *offset, int inc) { struct short_ad *sa; if ((!ptr) || (!offset)) { pr_err("%s: invalidparms\n", __func__); return NULL; } if ((*offset + sizeof(struct short_ad)) > maxoffset) return NULL; else { sa = (struct short_ad *)ptr; if (sa->extLength == 0) return NULL; } if (inc) *offset += sizeof(struct short_ad); return sa; } struct long_ad *udf_get_filelongad(uint8_t *ptr, int maxoffset, uint32_t *offset, int inc) { struct long_ad *la; if ((!ptr) || (!offset)) { pr_err("%s: invalidparms\n", __func__); return NULL; } if ((*offset + sizeof(struct long_ad)) > maxoffset) return NULL; else { la = (struct long_ad *)ptr; if (la->extLength == 0) return NULL; } if (inc) *offset += sizeof(struct long_ad); return la; } |
| 906 907 907 910 908 5350 4829 910 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * SafeSetID Linux Security Module * * Author: Micah Morton <mortonm@chromium.org> * * Copyright (C) 2018 The Chromium OS Authors. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2, as * published by the Free Software Foundation. * */ #define pr_fmt(fmt) "SafeSetID: " fmt #include <linux/lsm_hooks.h> #include <linux/module.h> #include <linux/ptrace.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <uapi/linux/lsm.h> #include "lsm.h" /* Flag indicating whether initialization completed */ int safesetid_initialized __initdata; struct setid_ruleset __rcu *safesetid_setuid_rules; struct setid_ruleset __rcu *safesetid_setgid_rules; /* Compute a decision for a transition from @src to @dst under @policy. */ enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy, kid_t src, kid_t dst) { struct setid_rule *rule; enum sid_policy_type result = SIDPOL_DEFAULT; if (policy->type == UID) { hash_for_each_possible(policy->rules, rule, next, __kuid_val(src.uid)) { if (!uid_eq(rule->src_id.uid, src.uid)) continue; if (uid_eq(rule->dst_id.uid, dst.uid)) return SIDPOL_ALLOWED; result = SIDPOL_CONSTRAINED; } } else if (policy->type == GID) { hash_for_each_possible(policy->rules, rule, next, __kgid_val(src.gid)) { if (!gid_eq(rule->src_id.gid, src.gid)) continue; if (gid_eq(rule->dst_id.gid, dst.gid)){ return SIDPOL_ALLOWED; } result = SIDPOL_CONSTRAINED; } } else { /* Should not reach here, report the ID as contrainsted */ result = SIDPOL_CONSTRAINED; } return result; } /* * Compute a decision for a transition from @src to @dst under the active * policy. */ static enum sid_policy_type setid_policy_lookup(kid_t src, kid_t dst, enum setid_type new_type) { enum sid_policy_type result = SIDPOL_DEFAULT; struct setid_ruleset *pol; rcu_read_lock(); if (new_type == UID) pol = rcu_dereference(safesetid_setuid_rules); else if (new_type == GID) pol = rcu_dereference(safesetid_setgid_rules); else { /* Should not reach here */ result = SIDPOL_CONSTRAINED; rcu_read_unlock(); return result; } if (pol) { pol->type = new_type; result = _setid_policy_lookup(pol, src, dst); } rcu_read_unlock(); return result; } static int safesetid_security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { /* We're only interested in CAP_SETUID and CAP_SETGID. */ if (cap != CAP_SETUID && cap != CAP_SETGID) return 0; /* * If CAP_SET{U/G}ID is currently used for a setid or setgroups syscall, we * want to let it go through here; the real security check happens later, in * the task_fix_set{u/g}id or task_fix_setgroups hooks. */ if ((opts & CAP_OPT_INSETID) != 0) return 0; switch (cap) { case CAP_SETUID: /* * If no policy applies to this task, allow the use of CAP_SETUID for * other purposes. */ if (setid_policy_lookup((kid_t){.uid = cred->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*uid() (e.g. setting up userns uid mappings). */ pr_warn("Operation requires CAP_SETUID, which is not available to UID %u for operations besides approved set*uid transitions\n", __kuid_val(cred->uid)); return -EPERM; case CAP_SETGID: /* * If no policy applies to this task, allow the use of CAP_SETGID for * other purposes. */ if (setid_policy_lookup((kid_t){.gid = cred->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; /* * Reject use of CAP_SETUID for functionality other than calling * set*gid() (e.g. setting up userns gid mappings). */ pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n", __kgid_val(cred->gid)); return -EPERM; default: /* Error, the only capabilities were checking for is CAP_SETUID/GID */ return 0; } return 0; } /* * Check whether a caller with old credentials @old is allowed to switch to * credentials that contain @new_id. */ static bool id_permitted_for_cred(const struct cred *old, kid_t new_id, enum setid_type new_type) { bool permitted; /* If our old creds already had this ID in it, it's fine. */ if (new_type == UID) { if (uid_eq(new_id.uid, old->uid) || uid_eq(new_id.uid, old->euid) || uid_eq(new_id.uid, old->suid)) return true; } else if (new_type == GID){ if (gid_eq(new_id.gid, old->gid) || gid_eq(new_id.gid, old->egid) || gid_eq(new_id.gid, old->sgid)) return true; } else /* Error, new_type is an invalid type */ return false; /* * Transitions to new UIDs require a check against the policy of the old * RUID. */ permitted = setid_policy_lookup((kid_t){.uid = old->uid}, new_id, new_type) != SIDPOL_CONSTRAINED; if (!permitted) { if (new_type == UID) { pr_warn("UID transition ((%d,%d,%d) -> %d) blocked\n", __kuid_val(old->uid), __kuid_val(old->euid), __kuid_val(old->suid), __kuid_val(new_id.uid)); } else if (new_type == GID) { pr_warn("GID transition ((%d,%d,%d) -> %d) blocked\n", __kgid_val(old->gid), __kgid_val(old->egid), __kgid_val(old->sgid), __kgid_val(new_id.gid)); } else /* Error, new_type is an invalid type */ return false; } return permitted; } /* * Check whether there is either an exception for user under old cred struct to * set*uid to user under new cred struct, or the UID transition is allowed (by * Linux set*uid rules) even without CAP_SETUID. */ static int safesetid_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setuid restrictions for our old RUID. */ if (setid_policy_lookup((kid_t){.uid = old->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.uid = new->uid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->euid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->suid}, UID) && id_permitted_for_cred(old, (kid_t){.uid = new->fsuid}, UID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; if (id_permitted_for_cred(old, (kid_t){.gid = new->gid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->egid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->sgid}, GID) && id_permitted_for_cred(old, (kid_t){.gid = new->fsgid}, GID)) return 0; /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old) { int i; /* Do nothing if there are no setgid restrictions for our old RGID. */ if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT) return 0; get_group_info(new->group_info); for (i = 0; i < new->group_info->ngroups; i++) { if (!id_permitted_for_cred(old, (kid_t){.gid = new->group_info->gid[i]}, GID)) { put_group_info(new->group_info); /* * Kill this process to avoid potential security vulnerabilities * that could arise from a missing allowlist entry preventing a * privileged process from dropping to a lesser-privileged one. */ force_sig(SIGKILL); return -EACCES; } } put_group_info(new->group_info); return 0; } static const struct lsm_id safesetid_lsmid = { .name = "safesetid", .id = LSM_ID_SAFESETID, }; static struct security_hook_list safesetid_security_hooks[] = { LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid), LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid), LSM_HOOK_INIT(task_fix_setgroups, safesetid_task_fix_setgroups), LSM_HOOK_INIT(capable, safesetid_security_capable) }; static int __init safesetid_security_init(void) { security_add_hooks(safesetid_security_hooks, ARRAY_SIZE(safesetid_security_hooks), &safesetid_lsmid); /* Report that SafeSetID successfully initialized */ safesetid_initialized = 1; return 0; } DEFINE_LSM(safesetid_security_init) = { .init = safesetid_security_init, .name = "safesetid", }; |
| 3 1 2 4 4 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Neighbour Discovery for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Mike Shaver <shaver@ingenia.com> */ /* * Changes: * * Alexey I. Froloff : RFC6106 (DNSSL) support * Pierre Ynard : export userland ND options * through netlink (RDNSS support) * Lars Fenneberg : fixed MTU setting on receipt * of an RA. * Janos Farkas : kmalloc failure checks * Alexey Kuznetsov : state machine reworked * and moved to net/core. * Pekka Savola : RFC2461 validation * YOSHIFUJI Hideaki @USAGI : Verify ND options properly */ #define pr_fmt(fmt) "ICMPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/sched.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/route.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/jhash.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, .is_multicast = ndisc_is_multicast, .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { .tbl = &nd_tbl, .reachable_time = ND_REACHABLE_TIME, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL_GPL(nd_tbl); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad) { int space = __ndisc_opt_addr_space(data_len, pad); u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; memset(opt + 2, 0, pad); opt += pad; space -= pad; memcpy(opt+2, data, data_len); data_len += 2; opt += data_len; space -= data_len; if (space > 0) memset(opt, 0, space); } EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, u8 icmp6_type) { __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, ndisc_addr_option_pad(skb->dev->type)); ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type); } static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb, void *ha, const u8 *ops_data) { ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT); ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data); } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { int type; if (!cur || !end || cur >= end) return NULL; type = cur->nd_opt_type; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && cur->nd_opt_type != type); return cur <= end && cur->nd_opt_type == type ? cur : NULL; } static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { return opt->nd_opt_type == ND_OPT_PREFIX_INFO || opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || ndisc_ops_is_useropt(dev, opt->nd_opt_type); } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { if (!cur || !end || cur >= end) return NULL; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && !ndisc_is_useropt(dev, cur)); return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL; } struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; if (!nd_opt || opt_len < 0 || !ndopts) return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; l = nd_opt->nd_opt_len << 3; if (opt_len < l || l == 0) return NULL; if (ndisc_ops_parse_options(dev, nd_opt, ndopts)) goto next_opt; switch (nd_opt->nd_opt_type) { case ND_OPT_SOURCE_LL_ADDR: case ND_OPT_TARGET_LL_ADDR: case ND_OPT_MTU: case ND_OPT_NONCE: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { ND_PRINTK(2, warn, "%s: duplicated ND6 option found: type=%d\n", __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } break; case ND_OPT_PREFIX_INFO: ndopts->nd_opts_pi_end = nd_opt; if (!ndopts->nd_opt_array[nd_opt->nd_opt_type]) ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; break; #ifdef CONFIG_IPV6_ROUTE_INFO case ND_OPT_ROUTE_INFO: ndopts->nd_opts_ri_end = nd_opt; if (!ndopts->nd_opts_ri) ndopts->nd_opts_ri = nd_opt; break; #endif default: unknown = true; } if (ndisc_is_useropt(dev, nd_opt)) { ndopts->nd_useropts_end = nd_opt; if (!ndopts->nd_useropts) ndopts->nd_useropts = nd_opt; } else if (unknown) { /* * Unknown options must be silently ignored, * to accommodate future extension to the * protocol. */ ND_PRINTK(2, notice, "%s: ignored unsupported option; type=%d, len=%d\n", __func__, nd_opt->nd_opt_type, nd_opt->nd_opt_len); } next_opt: opt_len -= l; nd_opt = ((void *)nd_opt) + l; } return ndopts; } int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */ case ARPHRD_FDDI: ipv6_eth_mc_map(addr, buf); return 0; case ARPHRD_ARCNET: ipv6_arcnet_mc_map(addr, buf); return 0; case ARPHRD_INFINIBAND: ipv6_ib_mc_map(addr, dev->broadcast, buf); return 0; case ARPHRD_IPGRE: return ipv6_ipgre_mc_map(addr, dev->broadcast, buf); default: if (dir) { memcpy(buf, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return ndisc_hashfn(pkey, dev, hash_rnd); } static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) { return neigh_key_eq128(n, pkey); } static int ndisc_constructor(struct neighbour *neigh) { struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); if (!in6_dev) { return -EINVAL; } parms = in6_dev->nd_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST; if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &ndisc_direct_ops; neigh->output = neigh_direct_output; } else { if (is_multicast) { neigh->nud_state = NUD_NOARP; ndisc_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); if (dev->flags&IFF_LOOPBACK) neigh->type = RTN_LOCAL; } else if (dev->flags&IFF_POINTOPOINT) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &ndisc_hh_ops; else neigh->ops = &ndisc_generic_ops; if (neigh->nud_state&NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } in6_dev_put(in6_dev); return 0; } static int pndisc_constructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return -EINVAL; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_inc(dev, &maddr); return 0; } static void pndisc_destructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_dec(dev, &maddr); } /* called with rtnl held */ static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device"); return false; } return true; } static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int len) { int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); if (!skb) { ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", __func__); return NULL; } skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); /* Manually assign socket ownership as we avoid calling * sock_alloc_send_pskb() to bypass wmem buffer limits */ skb_set_owner_w(skb, sk); return skb; } static void ip6_nd_hdr(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int hop_limit, int len) { struct ipv6hdr *hdr; struct inet6_dev *idev; unsigned tclass; rcu_read_lock(); idev = __in6_dev_get(skb->dev); tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0; rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; hdr->hop_limit = hop_limit; hdr->saddr = *saddr; hdr->daddr = *daddr; } void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(skb->dev); struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; int err; struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; if (!dst) { struct flowi6 fl6; int oif = skb->dev->ifindex; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); return; } skb_dst_set(skb, dst); } icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, csum_partial(icmp6h, skb->len, 0)); ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len); rcu_read_lock(); idev = __in6_dev_get(dst->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } rcu_read_unlock(); } EXPORT_SYMBOL(ndisc_send_skb); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt) { struct sk_buff *skb; struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; struct nd_msg *msg; int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = false; inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao); in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; src_addr = &tmpaddr; } if (!dev->addr_len) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_ADVERTISEMENT); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, .icmp6_router = router, .icmp6_solicited = solicited, .icmp6_override = override, }, .target = *solicited_addr, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_ADVERTISEMENT); ndisc_send_skb(skb, daddr, src_addr); } static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; idev = in6_dev_get(dev); if (!idev) return; read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { /* skip tentative addresses until dad completes */ if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_OPTIMISTIC)) continue; ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); } read_unlock_bh(&idev->lock); in6_dev_put(idev); } struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *saddr, u64 nonce) { int inc_opt = dev->addr_len; struct sk_buff *skb; struct nd_msg *msg; int optlen = 0; if (!saddr) return NULL; if (ipv6_addr_any(saddr)) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) optlen += 8; skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return NULL; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, }, .target = *solicit, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) { u8 *opt = skb_put(skb, 8); opt[0] = ND_OPT_NONCE; opt[1] = 8 >> 3; memcpy(opt + 2, &nonce, 6); } return skb; } EXPORT_SYMBOL(ndisc_ns_create); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce) { struct in6_addr addr_buf; struct sk_buff *skb; if (!saddr) { if (ipv6_get_lladdr(dev, &addr_buf, (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC))) return; saddr = &addr_buf; } skb = ndisc_ns_create(dev, solicit, saddr, nonce); if (skb) ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr) { struct sk_buff *skb; struct rs_msg *msg; int send_sllao = dev->addr_len; int optlen = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * According to section 2.2 of RFC 4429, we must not * send router solicitations with a sllao from * optimistic addresses, but we may send the solicitation * if we don't include the sllao. So here we check * if our address is optimistic, and if so, we * suppress the inclusion of the sllao. */ if (send_sllao) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr, dev, 1); if (ifp) { if (ifp->flags & IFA_F_OPTIMISTIC) { send_sllao = 0; } in6_ifa_put(ifp); } else { send_sllao = 0; } } #endif if (send_sllao) optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, }, }; if (send_sllao) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_ROUTER_SOLICITATION); ndisc_send_skb(skb, daddr, saddr); } static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) { /* * "The sender MUST return an ICMP * destination unreachable" */ dst_link_failure(skb); kfree_skb(skb); } /* Called with locked neigh: either read or both */ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) { struct in6_addr *saddr = NULL; struct in6_addr mcaddr; struct net_device *dev = neigh->dev; struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, false, 1, IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) { ND_PRINTK(1, dbg, "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } ndisc_send_ns(dev, target, target, saddr, 0); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(dev, target, &mcaddr, saddr, 0); } } static int pndisc_is_router(const void *pkey, struct net_device *dev) { struct pneigh_entry *n; int ret = -1; read_lock_bh(&nd_tbl.lock); n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); if (n) ret = !!(n->flags & NTF_ROUTER); read_unlock_bh(&nd_tbl.lock); return ret; } void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts) { neigh_update(neigh, lladdr, new, flags, 0); /* report ndisc ops about neighbour update */ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts); } static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); int is_router = -1; SKB_DR(reason); u64 nonce = 0; bool inc; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NS: multicast target address\n"); return reason; } /* * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ if (dad && !ipv6_addr_is_solict_mult(daddr)) { ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return reason; } if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NS: invalid link-layer address length\n"); return reason; } /* RFC2461 7.1.1: * If the IP source address is the unspecified address, * there MUST NOT be source link-layer address option * in the message. */ if (dad) { ND_PRINTK(2, warn, "NS: bad DAD packet (link-layer address option)\n"); return reason; } } if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { if (nonce != 0 && ifp->dad_nonce == nonce) { u8 *np = (u8 *)&nonce; /* Matching nonce if looped back */ ND_PRINTK(2, notice, "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n", ifp->idev->dev->name, &ifp->addr, np); goto out; } /* * We are colliding with another node * who is doing DAD * so fail our DAD process */ addrconf_dad_failure(skb, ifp); return reason; } else { /* * This is not a dad solicitation. * If we are an optimistic node, * we should respond. * Otherwise, we should ignore it. */ if (!(ifp->flags & IFA_F_OPTIMISTIC)) goto out; } } idev = ifp->idev; } else { struct net *net = dev_net(dev); /* perhaps an address on the master device */ if (netif_is_l3_slave(dev)) { struct net_device *mdev; mdev = netdev_master_upper_dev_get_rcu(dev); if (mdev) { ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); if (ifp) goto have_ifp; } } idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ return reason; } if (ipv6_chk_acast_addr(net, dev, &msg->target) || (READ_ONCE(idev->cnf.forwarding) && (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) || READ_ONCE(idev->cnf.proxy_ndp)) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc && NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, * sender should delay its response * by a random time between 0 and * MAX_ANYCAST_DELAY_TIME seconds. * (RFC2461) -- yoshfuji */ struct sk_buff *n = skb_clone(skb, GFP_ATOMIC); if (n) pneigh_enqueue(&nd_tbl, idev->nd_parms, n); goto out; } } else { SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST); goto out; } } if (is_router < 0) is_router = READ_ONCE(idev->cnf.forwarding); if (dad) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } if (inc) NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast); else NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast); /* * update / create cache entry * for the source address */ neigh = __neigh_lookup(&nd_tbl, saddr, dev, !inc || lladdr || !dev->addr_len); if (neigh) ndisc_update(dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE, NDISC_NEIGHBOUR_SOLICITATION, &ndopts); if (neigh || !dev->header_ops) { ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); reason = SKB_CONSUMED; } out: if (ifp) in6_ifa_put(ifp); else in6_dev_put(idev); return reason; } static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) { struct inet6_dev *idev = __in6_dev_get(dev); switch (READ_ONCE(idev->cnf.accept_untracked_na)) { case 0: /* Don't accept untracked na (absent in neighbor cache) */ return 0; case 1: /* Create new entries from na if currently untracked */ return 1; case 2: /* Create new entries from untracked na only if saddr is in the * same subnet as an address configured on the interface that * received the na */ return !!ipv6_chk_prefix(saddr, dev); default: return 0; } } static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; SKB_DR(reason); u8 new_state; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NA: target address is multicast\n"); return reason; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n"); return reason; } /* For some 802.11 wireless deployments (and possibly other networks), * there will be a NA proxy and unsolicitd packets are attacks * and thus should not be accepted. * drop_unsolicited_na takes precedence over accept_untracked_na */ if (!msg->icmph.icmp6_solicited && idev && READ_ONCE(idev->cnf.drop_unsolicited_na)) return reason; if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NA: invalid link-layer address length\n"); return reason; } } ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { addrconf_dad_failure(skb, ifp); return reason; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing about it. It could be misconfiguration, or an smart proxy agent tries to help us :-) We should not print the error if NA has been received from loopback - it is just our own unsolicited advertisement. */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK(1, warn, "NA: %pM advertised our address %pI6c on %s!\n", eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return reason; } neigh = neigh_lookup(&nd_tbl, &msg->target, dev); /* RFC 9131 updates original Neighbour Discovery RFC 4861. * NAs with Target LL Address option without a corresponding * entry in the neighbour cache can now create a STALE neighbour * cache entry on routers. * * entry accept fwding solicited behaviour * ------- ------ ------ --------- ---------------------- * present X X 0 Set state to STALE * present X X 1 Set state to REACHABLE * absent 0 X X Do nothing * absent 1 0 X Do nothing * absent 1 1 X Add a new STALE entry * * Note that we don't do a (daddr == all-routers-mcast) check. */ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) { if (accept_untracked_na(dev, saddr)) { neigh = neigh_create(&nd_tbl, &msg->target, dev); new_state = NUD_STALE; } } if (neigh && !IS_ERR(neigh)) { u8 old_flags = neigh->flags; struct net *net = dev_net(dev); if (READ_ONCE(neigh->nud_state) & NUD_FAILED) goto out; /* * Don't update the neighbor cache entry on a proxy NA from * ourselves because either the proxied node is off link or it * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && READ_ONCE(net->ipv6.devconf_all->forwarding) && READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { /* XXX: idev->cnf.proxy_ndp */ goto out; } ndisc_update(dev, neigh, lladdr, new_state, NEIGH_UPDATE_F_WEAK_OVERRIDE| (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0), NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts); if ((old_flags & ~neigh->flags) & NTF_ROUTER) { /* * Change: router to host */ rt6_clean_tohost(dev_net(dev), saddr); } reason = SKB_CONSUMED; out: neigh_release(neigh); } return reason; } static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb) { struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb); unsigned long ndoptlen = skb->len - sizeof(*rs_msg); struct neighbour *neigh; struct inet6_dev *idev; const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; SKB_DR(reason); if (skb->len < sizeof(*rs_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; idev = __in6_dev_get(skb->dev); if (!idev) { ND_PRINTK(1, err, "RS: can't find in6 device\n"); return reason; } /* Don't accept RS if we're not in router mode */ if (!READ_ONCE(idev->cnf.forwarding)) goto out; /* * Don't update NCE if src = ::; * this implies that the source node has no ip address assigned yet. */ if (ipv6_addr_any(saddr)) goto out; /* Parse ND options */ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) goto out; } neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1); if (neigh) { ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER, NDISC_ROUTER_SOLICITATION, &ndopts); neigh_release(neigh); reason = SKB_CONSUMED; } out: return reason; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) { struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra); struct sk_buff *skb; struct nlmsghdr *nlh; struct nduseroptmsg *ndmsg; struct net *net = dev_net(ra->dev); int err; int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg) + (opt->nd_opt_len << 3)); size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); skb = nlmsg_new(msg_size, GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); if (!nlh) { goto nla_put_failure; } ndmsg = nlmsg_data(nlh); ndmsg->nduseropt_family = AF_INET6; ndmsg->nduseropt_ifindex = ra->dev->ifindex; ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); err = -EMSGSIZE; errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); bool send_ifinfo_notify = false; struct neighbour *neigh = NULL; struct ndisc_options ndopts; struct fib6_info *rt = NULL; struct inet6_dev *in6_dev; struct fib6_table *table; u32 defrtr_usr_metric; unsigned int pref = 0; __u32 old_if_flags; struct net *net; SKB_DR(reason); int lifetime; int optlen; __u8 *opt = (__u8 *)(ra_msg + 1); optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); ND_PRINTK(2, info, "RA: %s, dev: %s\n", __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return reason; } if (optlen < 0) return SKB_DROP_REASON_PKT_TOO_SMALL; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { ND_PRINTK(2, warn, "RA: from host or unauthorized router\n"); return reason; } #endif in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) { ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", skb->dev->name); return reason; } if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT, dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #endif if (in6_dev->if_flags & IF_RS_SENT) { /* * flag that an RA was received after an RS was sent * out on this interface. */ in6_dev->if_flags |= IF_RA_RCVD; } /* * Remember the managed/otherconf flags from most recently * received RA message (RFC 2462) -- yoshfuji */ old_if_flags = in6_dev->if_flags; in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED | IF_RA_OTHERCONF)) | (ra_msg->icmph.icmp6_addrconf_managed ? IF_RA_MANAGED : 0) | (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); if (old_if_flags != in6_dev->if_flags) send_ifinfo_notify = true; if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) { ND_PRINTK(2, info, "RA: %s, defrtr is false for dev: %s\n", __func__, skb->dev->name); goto skip_defrtr; } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); if (lifetime != 0 && lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) { ND_PRINTK(2, info, "RA: router lifetime (%ds) is too short: %s\n", lifetime, skb->dev->name); goto skip_defrtr; } /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ net = dev_net(in6_dev->dev); if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); goto skip_defrtr; } #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref)) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif /* routes added from RAs do not use nexthop objects */ rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); if (rt) { neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } } /* Set default route metric as specified by user */ defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; /* delete the route if lifetime is 0 or if metric needs change */ if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { ip6_del_rt(net, rt, false); rt = NULL; } ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", rt, lifetime, defrtr_usr_metric, skb->dev->name); if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); if (neigh) neigh_release(neigh); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev, pref, defrtr_usr_metric, lifetime); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", __func__); return reason; } neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } neigh->flags |= NTF_ROUTER; } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) { struct nl_info nlinfo = { .nl_net = net, }; rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); fib6_set_expires(rt, jiffies + (HZ * lifetime)); fib6_add_gc_list(rt); spin_unlock_bh(&table->tb6_lock); } if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 && ra_msg->icmph.icmp6_hop_limit) { if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <= ra_msg->icmph.icmp6_hop_limit) { WRITE_ONCE(in6_dev->cnf.hop_limit, ra_msg->icmph.icmp6_hop_limit); fib6_metric_set(rt, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); } else { ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } } skip_defrtr: /* * Update Reachable Time and Retrans Timer */ if (in6_dev->nd_parms) { unsigned long rtime = ntohl(ra_msg->retrans_timer); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) { rtime = (rtime*HZ)/1000; if (rtime < HZ/100) rtime = HZ/100; NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } rtime = ntohl(ra_msg->reachable_time); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) { rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { NEIGH_VAR_SET(in6_dev->nd_parms, BASE_REACHABLE_TIME, rtime); NEIGH_VAR_SET(in6_dev->nd_parms, GC_STALETIME, 3 * rtime); in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } } } skip_linkparms: /* * Process options. */ if (!neigh) neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr, skb->dev, 1); if (neigh) { u8 *lladdr = NULL; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { ND_PRINTK(2, warn, "RA: invalid link-layer address length\n"); goto out; } } ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER, NDISC_ROUTER_ADVERTISEMENT, &ndopts); reason = SKB_CONSUMED; } if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, accept_ra is false for dev: %s\n", __func__, skb->dev->name); goto out; } #ifdef CONFIG_IPV6_ROUTE_INFO if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: router info ignored.\n", skb->dev->name); goto skip_routeinfo; } if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) { struct route_info *ri = (struct route_info *)p; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT && ri->prefix_len == 0) continue; #endif if (ri->prefix_len == 0 && !READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) continue; if (ri->lifetime != 0 && ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) continue; if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen)) continue; if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen)) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); } } skip_routeinfo: #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", __func__, skb->dev->name); goto out; } #endif if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) { addrconf_prefix_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, ndopts.nd_opts_src_lladdr != NULL); } } if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) { __be32 n; u32 mtu; memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); if (in6_dev->ra_mtu != mtu) { in6_dev->ra_mtu = mtu; send_ifinfo_notify = true; } if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) { WRITE_ONCE(in6_dev->cnf.mtu6, mtu); fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } if (ndopts.nd_useropts) { struct nd_opt_hdr *p; for (p = ndopts.nd_useropts; p; p = ndisc_next_useropt(skb->dev, p, ndopts.nd_useropts_end)) { ndisc_ra_useropt(skb, p); } } if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: /* Send a notify if RA changed managed/otherconf flags or * timer settings or ra_mtu value */ if (send_ifinfo_notify) inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); fib6_info_release(rt); if (neigh) neigh_release(neigh); return reason; } static enum skb_drop_reason ndisc_redirect_rcv(struct sk_buff *skb) { struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); struct ndisc_options ndopts; SKB_DR(reason); u8 *hdr; #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: case NDISC_NODETYPE_NODEFAULT: ND_PRINTK(2, warn, "Redirect: from host or unauthorized router\n"); return reason; } #endif if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: source address is not link-local\n"); return reason; } if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ndopts.nd_opts_rh) { ip6_redirect_no_header(skb, dev_net(skb->dev), skb->dev->ifindex); return reason; } hdr = (u8 *)ndopts.nd_opts_rh; hdr += 8; if (!pskb_pull(skb, hdr - skb_transport_header(skb))) return SKB_DROP_REASON_PKT_TOO_SMALL; return icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, struct sk_buff *orig_skb, int rd_len) { u8 *opt = skb_put(skb, rd_len); memset(opt, 0, 8); *(opt++) = ND_OPT_REDIRECT_HDR; *(opt++) = (rd_len >> 3); opt += 6; skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int optlen = 0; struct inet_peer *peer; struct sk_buff *buff; struct rd_msg *msg; struct in6_addr saddr_buf; struct rt6_info *rt; struct dst_entry *dst; struct flowi6 fl6; int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL, ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) return; } if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", dev->name); return; } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: target address is not link-local unicast\n"); return; } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); return; } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) { ND_PRINTK(2, warn, "Redirect: destination is not a neighbour\n"); goto release; } peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1); ret = inet_peer_xrlim_allow(peer, 1*HZ); if (peer) inet_putpeer(peer); if (!ret) goto release; if (dev->addr_len) { struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); if (!neigh) { ND_PRINTK(2, warn, "Redirect: no neigh for target address\n"); goto release; } read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) { memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; optlen += ndisc_redirect_opt_addr_space(dev, neigh, ops_data_buf, &ops_data); } else read_unlock_bh(&neigh->lock); neigh_release(neigh); } rd_len = min_t(unsigned int, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, skb->len + 8); rd_len &= ~0x7; optlen += rd_len; buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!buff) goto release; msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, }, .target = *target, .dest = ipv6_hdr(skb)->daddr, }; /* * include target_address option */ if (ha) ndisc_fill_redirect_addr_option(buff, ha, ops_data); /* * build redirect option and copy skb over to the new packet. */ if (rd_len) ndisc_fill_redirect_hdr_option(buff, skb, rd_len); skb_dst_set(buff, dst); ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); return; release: dst_release(dst); } static void pndisc_redo(struct sk_buff *skb) { enum skb_drop_reason reason = ndisc_recv_ns(skb); kfree_skb_reason(skb, reason); } static int ndisc_is_multicast(const void *pkey) { return ipv6_addr_is_multicast((struct in6_addr *)pkey); } static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev) return true; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && READ_ONCE(idev->cnf.suppress_frag_ndisc)) { net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); return true; } return false; } enum skb_drop_reason ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; SKB_DR(reason); if (ndisc_suppress_frag_ndisc(skb)) return SKB_DROP_REASON_IPV6_NDISC_FRAG; if (skb_linearize(skb)) return SKB_DROP_REASON_NOMEM; msg = (struct nd_msg *)skb_transport_header(skb); __skb_push(skb, skb->data - skb_transport_header(skb)); if (ipv6_hdr(skb)->hop_limit != 255) { ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n", ipv6_hdr(skb)->hop_limit); return SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT; } if (msg->icmph.icmp6_code != 0) { ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n", msg->icmph.icmp6_code); return SKB_DROP_REASON_IPV6_NDISC_BAD_CODE; } switch (msg->icmph.icmp6_type) { case NDISC_NEIGHBOUR_SOLICITATION: memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); reason = ndisc_recv_ns(skb); break; case NDISC_NEIGHBOUR_ADVERTISEMENT: reason = ndisc_recv_na(skb); break; case NDISC_ROUTER_SOLICITATION: reason = ndisc_recv_rs(skb); break; case NDISC_ROUTER_ADVERTISEMENT: reason = ndisc_router_discovery(skb); break; case NDISC_REDIRECT: reason = ndisc_redirect_rcv(skb); break; } return reason; } static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(0, net, false); fallthrough; case NETDEV_UP: idev = in6_dev_get(dev); if (!idev) break; if (READ_ONCE(idev->cnf.ndisc_notify) || READ_ONCE(net->ipv6.devconf_all->ndisc_notify)) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; case NETDEV_CHANGE: idev = in6_dev_get(dev); if (!idev) evict_nocarrier = true; else { evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) && READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier); in6_dev_put(idev); } change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&nd_tbl, dev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block ndisc_netdev_notifier = { .notifier_call = ndisc_netdev_event, .priority = ADDRCONF_NOTIFY_PRIORITY - 5, }; #ifdef CONFIG_SYSCTL static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { strcpy(warncomm, current->comm); pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, dev_name, ctl->procname); warned++; } } int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; int ret; if ((strcmp(ctl->procname, "retrans_time") == 0) || (strcmp(ctl->procname, "base_reachable_time") == 0)) ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); else ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) idev->nd_parms->reachable_time = neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } return ret; } #endif static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; int err; err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { ND_PRINTK(0, err, "NDISC: Failed to initialize the control socket (err %d)\n", err); return err; } net->ipv6.ndisc_sk = sk; np = inet6_sk(sk); np->hop_limit = 255; /* Do not loopback ndisc messages */ inet6_clear_bit(MC6_LOOP, sk); return 0; } static void __net_exit ndisc_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.ndisc_sk); } static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, }; int __init ndisc_init(void) { int err; err = register_pernet_subsys(&ndisc_net_ops); if (err) return err; /* * Initialize the neighbour table */ neigh_table_init(NEIGH_ND_TABLE, &nd_tbl); #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; out: #endif return err; #ifdef CONFIG_SYSCTL out_unregister_pernet: unregister_pernet_subsys(&ndisc_net_ops); goto out; #endif } int __init ndisc_late_init(void) { return register_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_cleanup(void) { #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl); unregister_pernet_subsys(&ndisc_net_ops); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2013 Davidlohr Bueso <davidlohr.bueso@hp.com> * * Based on the shift-and-subtract algorithm for computing integer * square root from Guy L. Steele. */ #include <linux/export.h> #include <linux/bitops.h> #include <linux/limits.h> #include <linux/math.h> /** * int_sqrt - computes the integer square root * @x: integer of which to calculate the sqrt * * Computes: floor(sqrt(x)) */ unsigned long int_sqrt(unsigned long x) { unsigned long b, m, y = 0; if (x <= 1) return x; m = 1UL << (__fls(x) & ~1UL); while (m != 0) { b = y + m; y >>= 1; if (x >= b) { x -= b; y += m; } m >>= 2; } return y; } EXPORT_SYMBOL(int_sqrt); #if BITS_PER_LONG < 64 /** * int_sqrt64 - strongly typed int_sqrt function when minimum 64 bit input * is expected. * @x: 64bit integer of which to calculate the sqrt */ u32 int_sqrt64(u64 x) { u64 b, m, y = 0; if (x <= ULONG_MAX) return int_sqrt((unsigned long) x); m = 1ULL << ((fls64(x) - 1) & ~1ULL); while (m != 0) { b = y + m; y >>= 1; if (x >= b) { x -= b; y += m; } m >>= 2; } return y; } EXPORT_SYMBOL(int_sqrt64); #endif |
| 49 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Virtio PCI driver - common functionality for all device versions * * This module allows virtio devices to be used over a virtual PCI device. * This can be used with QEMU based VMMs like KVM or Xen. * * Copyright IBM Corp. 2007 * Copyright Red Hat, Inc. 2014 * * Authors: * Anthony Liguori <aliguori@us.ibm.com> * Rusty Russell <rusty@rustcorp.com.au> * Michael S. Tsirkin <mst@redhat.com> */ #include "virtio_pci_common.h" static bool force_legacy = false; #if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY) module_param(force_legacy, bool, 0444); MODULE_PARM_DESC(force_legacy, "Force legacy mode for transitional virtio 1 devices"); #endif /* wait for pending irq handlers */ void vp_synchronize_vectors(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i; if (vp_dev->intx_enabled) synchronize_irq(vp_dev->pci_dev->irq); for (i = 0; i < vp_dev->msix_vectors; ++i) synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i)); } /* the notify function used when creating a virt queue */ bool vp_notify(struct virtqueue *vq) { /* we write the queue's selector into the notification register to * signal the other end */ iowrite16(vq->index, (void __iomem *)vq->priv); return true; } /* Notify all slow path virtqueues on an interrupt. */ static void vp_vring_slow_path_interrupt(int irq, struct virtio_pci_device *vp_dev) { struct virtio_pci_vq_info *info; unsigned long flags; spin_lock_irqsave(&vp_dev->lock, flags); list_for_each_entry(info, &vp_dev->slow_virtqueues, node) vring_interrupt(irq, info->vq); spin_unlock_irqrestore(&vp_dev->lock, flags); } /* Handle a configuration change: Tell driver if it wants to know. */ static irqreturn_t vp_config_changed(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; virtio_config_changed(&vp_dev->vdev); vp_vring_slow_path_interrupt(irq, vp_dev); return IRQ_HANDLED; } /* Notify all virtqueues on an interrupt. */ static irqreturn_t vp_vring_interrupt(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; struct virtio_pci_vq_info *info; irqreturn_t ret = IRQ_NONE; unsigned long flags; spin_lock_irqsave(&vp_dev->lock, flags); list_for_each_entry(info, &vp_dev->virtqueues, node) { if (vring_interrupt(irq, info->vq) == IRQ_HANDLED) ret = IRQ_HANDLED; } spin_unlock_irqrestore(&vp_dev->lock, flags); return ret; } /* A small wrapper to also acknowledge the interrupt when it's handled. * I really need an EIO hook for the vring so I can ack the interrupt once we * know that we'll be handling the IRQ but before we invoke the callback since * the callback may notify the host which results in the host attempting to * raise an interrupt that we would then mask once we acknowledged the * interrupt. */ static irqreturn_t vp_interrupt(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; u8 isr; /* reading the ISR has the effect of also clearing it so it's very * important to save off the value. */ isr = ioread8(vp_dev->isr); /* It's definitely not us if the ISR was not high */ if (!isr) return IRQ_NONE; /* Configuration change? Tell driver if it wants to know. */ if (isr & VIRTIO_PCI_ISR_CONFIG) vp_config_changed(irq, opaque); return vp_vring_interrupt(irq, opaque); } static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, bool per_vq_vectors, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); const char *name = dev_name(&vp_dev->vdev.dev); unsigned int flags = PCI_IRQ_MSIX; unsigned int i, v; int err = -ENOMEM; vp_dev->msix_vectors = nvectors; vp_dev->msix_names = kmalloc_array(nvectors, sizeof(*vp_dev->msix_names), GFP_KERNEL); if (!vp_dev->msix_names) goto error; vp_dev->msix_affinity_masks = kcalloc(nvectors, sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL); if (!vp_dev->msix_affinity_masks) goto error; for (i = 0; i < nvectors; ++i) if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], GFP_KERNEL)) goto error; if (!per_vq_vectors) desc = NULL; if (desc) { flags |= PCI_IRQ_AFFINITY; desc->pre_vectors++; /* virtio config vector */ } err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors, nvectors, flags, desc); if (err < 0) goto error; vp_dev->msix_enabled = 1; /* Set the vector used for configuration */ v = vp_dev->msix_used_vectors; snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, "%s-config", name); err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), vp_config_changed, 0, vp_dev->msix_names[v], vp_dev); if (err) goto error; ++vp_dev->msix_used_vectors; v = vp_dev->config_vector(vp_dev, v); /* Verify we had enough resources to assign the vector */ if (v == VIRTIO_MSI_NO_VECTOR) { err = -EBUSY; goto error; } if (!per_vq_vectors) { /* Shared vector for all VQs */ v = vp_dev->msix_used_vectors; snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, "%s-virtqueues", name); err = request_irq(pci_irq_vector(vp_dev->pci_dev, v), vp_vring_interrupt, 0, vp_dev->msix_names[v], vp_dev); if (err) goto error; ++vp_dev->msix_used_vectors; } return 0; error: return err; } static bool vp_is_slow_path_vector(u16 msix_vec) { return msix_vec == VP_MSIX_CONFIG_VECTOR; } static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned int index, void (*callback)(struct virtqueue *vq), const char *name, bool ctx, u16 msix_vec, struct virtio_pci_vq_info **p_info) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL); struct virtqueue *vq; unsigned long flags; /* fill out our structure that represents an active queue */ if (!info) return ERR_PTR(-ENOMEM); vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx, msix_vec); if (IS_ERR(vq)) goto out_info; info->vq = vq; if (callback) { spin_lock_irqsave(&vp_dev->lock, flags); if (!vp_is_slow_path_vector(msix_vec)) list_add(&info->node, &vp_dev->virtqueues); else list_add(&info->node, &vp_dev->slow_virtqueues); spin_unlock_irqrestore(&vp_dev->lock, flags); } else { INIT_LIST_HEAD(&info->node); } *p_info = info; return vq; out_info: kfree(info); return vq; } static void vp_del_vq(struct virtqueue *vq) { struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; unsigned long flags; /* * If it fails during re-enable reset vq. This way we won't rejoin * info->node to the queue. Prevent unexpected irqs. */ if (!vq->reset) { spin_lock_irqsave(&vp_dev->lock, flags); list_del(&info->node); spin_unlock_irqrestore(&vp_dev->lock, flags); } vp_dev->del_vq(info); kfree(info); } /* the config->del_vqs() implementation */ void vp_del_vqs(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtqueue *vq, *n; int i; list_for_each_entry_safe(vq, n, &vdev->vqs, list) { if (vp_dev->per_vq_vectors) { int v = vp_dev->vqs[vq->index]->msix_vector; if (v != VIRTIO_MSI_NO_VECTOR && !vp_is_slow_path_vector(v)) { int irq = pci_irq_vector(vp_dev->pci_dev, v); irq_update_affinity_hint(irq, NULL); free_irq(irq, vq); } } vp_del_vq(vq); } vp_dev->per_vq_vectors = false; if (vp_dev->intx_enabled) { free_irq(vp_dev->pci_dev->irq, vp_dev); vp_dev->intx_enabled = 0; } for (i = 0; i < vp_dev->msix_used_vectors; ++i) free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev); if (vp_dev->msix_affinity_masks) { for (i = 0; i < vp_dev->msix_vectors; i++) free_cpumask_var(vp_dev->msix_affinity_masks[i]); } if (vp_dev->msix_enabled) { /* Disable the vector used for configuration */ vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); pci_free_irq_vectors(vp_dev->pci_dev); vp_dev->msix_enabled = 0; } vp_dev->msix_vectors = 0; vp_dev->msix_used_vectors = 0; kfree(vp_dev->msix_names); vp_dev->msix_names = NULL; kfree(vp_dev->msix_affinity_masks); vp_dev->msix_affinity_masks = NULL; kfree(vp_dev->vqs); vp_dev->vqs = NULL; } enum vp_vq_vector_policy { VP_VQ_VECTOR_POLICY_EACH, VP_VQ_VECTOR_POLICY_SHARED_SLOW, VP_VQ_VECTOR_POLICY_SHARED, }; static struct virtqueue * vp_find_one_vq_msix(struct virtio_device *vdev, int queue_idx, vq_callback_t *callback, const char *name, bool ctx, bool slow_path, int *allocated_vectors, enum vp_vq_vector_policy vector_policy, struct virtio_pci_vq_info **p_info) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtqueue *vq; u16 msix_vec; int err; if (!callback) msix_vec = VIRTIO_MSI_NO_VECTOR; else if (vector_policy == VP_VQ_VECTOR_POLICY_EACH || (vector_policy == VP_VQ_VECTOR_POLICY_SHARED_SLOW && !slow_path)) msix_vec = (*allocated_vectors)++; else if (vector_policy != VP_VQ_VECTOR_POLICY_EACH && slow_path) msix_vec = VP_MSIX_CONFIG_VECTOR; else msix_vec = VP_MSIX_VQ_VECTOR; vq = vp_setup_vq(vdev, queue_idx, callback, name, ctx, msix_vec, p_info); if (IS_ERR(vq)) return vq; if (vector_policy == VP_VQ_VECTOR_POLICY_SHARED || msix_vec == VIRTIO_MSI_NO_VECTOR || vp_is_slow_path_vector(msix_vec)) return vq; /* allocate per-vq irq if available and necessary */ snprintf(vp_dev->msix_names[msix_vec], sizeof(*vp_dev->msix_names), "%s-%s", dev_name(&vp_dev->vdev.dev), name); err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), vring_interrupt, 0, vp_dev->msix_names[msix_vec], vq); if (err) { vp_del_vq(vq); return ERR_PTR(err); } return vq; } static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], struct virtqueue_info vqs_info[], enum vp_vq_vector_policy vector_policy, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; struct virtqueue_info *vqi; int i, err, nvectors, allocated_vectors, queue_idx = 0; struct virtqueue *vq; bool per_vq_vectors; u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; if (vp_dev->avq_index) { err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); if (err) goto error_find; } per_vq_vectors = vector_policy != VP_VQ_VECTOR_POLICY_SHARED; if (per_vq_vectors) { /* Best option: one for change interrupt, one per vq. */ nvectors = 1; for (i = 0; i < nvqs; ++i) { vqi = &vqs_info[i]; if (vqi->name && vqi->callback) ++nvectors; } if (avq_num && vector_policy == VP_VQ_VECTOR_POLICY_EACH) ++nvectors; } else { /* Second best: one for change, shared for all vqs. */ nvectors = 2; } err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors, desc); if (err) goto error_find; vp_dev->per_vq_vectors = per_vq_vectors; allocated_vectors = vp_dev->msix_used_vectors; for (i = 0; i < nvqs; ++i) { vqi = &vqs_info[i]; if (!vqi->name) { vqs[i] = NULL; continue; } vqs[i] = vp_find_one_vq_msix(vdev, queue_idx++, vqi->callback, vqi->name, vqi->ctx, false, &allocated_vectors, vector_policy, &vp_dev->vqs[i]); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); goto error_find; } } if (!avq_num) return 0; sprintf(avq->name, "avq.%u", avq->vq_index); vq = vp_find_one_vq_msix(vdev, avq->vq_index, vp_modern_avq_done, avq->name, false, true, &allocated_vectors, vector_policy, &vp_dev->admin_vq.info); if (IS_ERR(vq)) { err = PTR_ERR(vq); goto error_find; } return 0; error_find: vp_del_vqs(vdev); return err; } static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], struct virtqueue_info vqs_info[]) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; int i, err, queue_idx = 0; struct virtqueue *vq; u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; if (vp_dev->avq_index) { err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); if (err) goto out_del_vqs; } err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vp_dev); if (err) goto out_del_vqs; vp_dev->intx_enabled = 1; vp_dev->per_vq_vectors = false; for (i = 0; i < nvqs; ++i) { struct virtqueue_info *vqi = &vqs_info[i]; if (!vqi->name) { vqs[i] = NULL; continue; } vqs[i] = vp_setup_vq(vdev, queue_idx++, vqi->callback, vqi->name, vqi->ctx, VIRTIO_MSI_NO_VECTOR, &vp_dev->vqs[i]); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); goto out_del_vqs; } } if (!avq_num) return 0; sprintf(avq->name, "avq.%u", avq->vq_index); vq = vp_setup_vq(vdev, queue_idx++, vp_modern_avq_done, avq->name, false, VIRTIO_MSI_NO_VECTOR, &vp_dev->admin_vq.info); if (IS_ERR(vq)) { err = PTR_ERR(vq); goto out_del_vqs; } return 0; out_del_vqs: vp_del_vqs(vdev); return err; } /* the config->find_vqs() implementation */ int vp_find_vqs(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], struct virtqueue_info vqs_info[], struct irq_affinity *desc) { int err; /* Try MSI-X with one vector per queue. */ err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, VP_VQ_VECTOR_POLICY_EACH, desc); if (!err) return 0; /* Fallback: MSI-X with one shared vector for config and * slow path queues, one vector per queue for the rest. */ err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, VP_VQ_VECTOR_POLICY_SHARED_SLOW, desc); if (!err) return 0; /* Fallback: MSI-X with one vector for config, one shared for queues. */ err = vp_find_vqs_msix(vdev, nvqs, vqs, vqs_info, VP_VQ_VECTOR_POLICY_SHARED, desc); if (!err) return 0; /* Is there an interrupt? If not give up. */ if (!(to_vp_device(vdev)->pci_dev->irq)) return err; /* Finally fall back to regular interrupts. */ return vp_find_vqs_intx(vdev, nvqs, vqs, vqs_info); } const char *vp_bus_name(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); return pci_name(vp_dev->pci_dev); } /* Setup the affinity for a virtqueue: * - force the affinity for per vq vector * - OR over all affinities for shared MSI * - ignore the affinity request if we're using INTX */ int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask) { struct virtio_device *vdev = vq->vdev; struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; struct cpumask *mask; unsigned int irq; if (!vq->callback) return -EINVAL; if (vp_dev->msix_enabled) { mask = vp_dev->msix_affinity_masks[info->msix_vector]; irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector); if (!cpu_mask) irq_update_affinity_hint(irq, NULL); else { cpumask_copy(mask, cpu_mask); irq_set_affinity_and_hint(irq, mask); } } return 0; } const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); if (!vp_dev->per_vq_vectors || vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR || vp_is_slow_path_vector(vp_dev->vqs[index]->msix_vector)) return NULL; return pci_irq_get_affinity(vp_dev->pci_dev, vp_dev->vqs[index]->msix_vector); } #ifdef CONFIG_PM_SLEEP static int virtio_pci_freeze(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); int ret; ret = virtio_device_freeze(&vp_dev->vdev); if (!ret) pci_disable_device(pci_dev); return ret; } static int virtio_pci_restore(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); int ret; ret = pci_enable_device(pci_dev); if (ret) return ret; pci_set_master(pci_dev); return virtio_device_restore(&vp_dev->vdev); } static bool vp_supports_pm_no_reset(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); u16 pmcsr; if (!pci_dev->pm_cap) return false; pci_read_config_word(pci_dev, pci_dev->pm_cap + PCI_PM_CTRL, &pmcsr); if (PCI_POSSIBLE_ERROR(pmcsr)) { dev_err(dev, "Unable to query pmcsr"); return false; } return pmcsr & PCI_PM_CTRL_NO_SOFT_RESET; } static int virtio_pci_suspend(struct device *dev) { return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_freeze(dev); } static int virtio_pci_resume(struct device *dev) { return vp_supports_pm_no_reset(dev) ? 0 : virtio_pci_restore(dev); } static const struct dev_pm_ops virtio_pci_pm_ops = { .suspend = virtio_pci_suspend, .resume = virtio_pci_resume, .freeze = virtio_pci_freeze, .thaw = virtio_pci_restore, .poweroff = virtio_pci_freeze, .restore = virtio_pci_restore, }; #endif /* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */ static const struct pci_device_id virtio_pci_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_REDHAT_QUMRANET, PCI_ANY_ID) }, { 0 } }; MODULE_DEVICE_TABLE(pci, virtio_pci_id_table); static void virtio_pci_release_dev(struct device *_d) { struct virtio_device *vdev = dev_to_virtio(_d); struct virtio_pci_device *vp_dev = to_vp_device(vdev); /* As struct device is a kobject, it's not safe to * free the memory (including the reference counter itself) * until it's release callback. */ kfree(vp_dev); } static int virtio_pci_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) { struct virtio_pci_device *vp_dev, *reg_dev = NULL; int rc; /* allocate our structure and fill it out */ vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL); if (!vp_dev) return -ENOMEM; pci_set_drvdata(pci_dev, vp_dev); vp_dev->vdev.dev.parent = &pci_dev->dev; vp_dev->vdev.dev.release = virtio_pci_release_dev; vp_dev->pci_dev = pci_dev; INIT_LIST_HEAD(&vp_dev->virtqueues); INIT_LIST_HEAD(&vp_dev->slow_virtqueues); spin_lock_init(&vp_dev->lock); /* enable the device */ rc = pci_enable_device(pci_dev); if (rc) goto err_enable_device; if (force_legacy) { rc = virtio_pci_legacy_probe(vp_dev); /* Also try modern mode if we can't map BAR0 (no IO space). */ if (rc == -ENODEV || rc == -ENOMEM) rc = virtio_pci_modern_probe(vp_dev); if (rc) goto err_probe; } else { rc = virtio_pci_modern_probe(vp_dev); if (rc == -ENODEV) rc = virtio_pci_legacy_probe(vp_dev); if (rc) goto err_probe; } pci_set_master(pci_dev); rc = register_virtio_device(&vp_dev->vdev); reg_dev = vp_dev; if (rc) goto err_register; return 0; err_register: if (vp_dev->is_legacy) virtio_pci_legacy_remove(vp_dev); else virtio_pci_modern_remove(vp_dev); err_probe: pci_disable_device(pci_dev); err_enable_device: if (reg_dev) put_device(&vp_dev->vdev.dev); else kfree(vp_dev); return rc; } static void virtio_pci_remove(struct pci_dev *pci_dev) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct device *dev = get_device(&vp_dev->vdev.dev); /* * Device is marked broken on surprise removal so that virtio upper * layers can abort any ongoing operation. */ if (!pci_device_is_present(pci_dev)) virtio_break_device(&vp_dev->vdev); pci_disable_sriov(pci_dev); unregister_virtio_device(&vp_dev->vdev); if (vp_dev->is_legacy) virtio_pci_legacy_remove(vp_dev); else virtio_pci_modern_remove(vp_dev); pci_disable_device(pci_dev); put_device(dev); } static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct virtio_device *vdev = &vp_dev->vdev; int ret; if (!(vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_DRIVER_OK)) return -EBUSY; if (!__virtio_test_bit(vdev, VIRTIO_F_SR_IOV)) return -EINVAL; if (pci_vfs_assigned(pci_dev)) return -EPERM; if (num_vfs == 0) { pci_disable_sriov(pci_dev); return 0; } ret = pci_enable_sriov(pci_dev, num_vfs); if (ret < 0) return ret; return num_vfs; } static struct pci_driver virtio_pci_driver = { .name = "virtio-pci", .id_table = virtio_pci_id_table, .probe = virtio_pci_probe, .remove = virtio_pci_remove, #ifdef CONFIG_PM_SLEEP .driver.pm = &virtio_pci_pm_ops, #endif .sriov_configure = virtio_pci_sriov_configure, }; struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev) { struct virtio_pci_device *pf_vp_dev; pf_vp_dev = pci_iov_get_pf_drvdata(pdev, &virtio_pci_driver); if (IS_ERR(pf_vp_dev)) return NULL; return &pf_vp_dev->vdev; } module_pci_driver(virtio_pci_driver); MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>"); MODULE_DESCRIPTION("virtio-pci"); MODULE_LICENSE("GPL"); MODULE_VERSION("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 | // SPDX-License-Identifier: GPL-2.0 /* * udc.c - Core UDC Framework * * Copyright (C) 2010 Texas Instruments * Author: Felipe Balbi <balbi@ti.com> */ #define pr_fmt(fmt) "UDC core: " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/err.h> #include <linux/dma-mapping.h> #include <linux/sched/task_stack.h> #include <linux/workqueue.h> #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> #include <linux/usb.h> #include "trace.h" static DEFINE_IDA(gadget_id_numbers); static const struct bus_type gadget_bus_type; /** * struct usb_udc - describes one usb device controller * @driver: the gadget driver pointer. For use by the class code * @dev: the child device to the actual controller * @gadget: the gadget. For use by the class code * @list: for use by the udc class driver * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. * @allow_connect: Indicates whether UDC is allowed to be pulled up. * Set/cleared by gadget_(un)bind_driver() after gadget driver is bound or * unbound. * @vbus_work: work routine to handle VBUS status change notifications. * @connect_lock: protects udc->started, gadget->connect, * gadget->allow_connect and gadget->deactivate. The routines * usb_gadget_connect_locked(), usb_gadget_disconnect_locked(), * usb_udc_connect_control_locked(), usb_gadget_udc_start_locked() and * usb_gadget_udc_stop_locked() are called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. */ struct usb_udc { struct usb_gadget_driver *driver; struct usb_gadget *gadget; struct device dev; struct list_head list; bool vbus; bool started; bool allow_connect; struct work_struct vbus_work; struct mutex connect_lock; }; static const struct class udc_class; static LIST_HEAD(udc_list); /* Protects udc_list, udc->driver, driver->is_bound, and related calls */ static DEFINE_MUTEX(udc_lock); /* ------------------------------------------------------------------------- */ /** * usb_ep_set_maxpacket_limit - set maximum packet size limit for endpoint * @ep:the endpoint being configured * @maxpacket_limit:value of maximum packet size limit * * This function should be used only in UDC drivers to initialize endpoint * (usually in probe function). */ void usb_ep_set_maxpacket_limit(struct usb_ep *ep, unsigned maxpacket_limit) { ep->maxpacket_limit = maxpacket_limit; ep->maxpacket = maxpacket_limit; trace_usb_ep_set_maxpacket_limit(ep, 0); } EXPORT_SYMBOL_GPL(usb_ep_set_maxpacket_limit); /** * usb_ep_enable - configure endpoint, making it usable * @ep:the endpoint being configured. may not be the endpoint named "ep0". * drivers discover endpoints through the ep_list of a usb_gadget. * * When configurations are set, or when interface settings change, the driver * will enable or disable the relevant endpoints. while it is enabled, an * endpoint may be used for i/o until the driver receives a disconnect() from * the host or until the endpoint is disabled. * * the ep0 implementation (which calls this routine) must ensure that the * hardware capabilities of each endpoint match the descriptor provided * for it. for example, an endpoint named "ep2in-bulk" would be usable * for interrupt transfers as well as bulk, but it likely couldn't be used * for iso transfers or for endpoint 14. some endpoints are fully * configurable, with more generic names like "ep-a". (remember that for * USB, "in" means "towards the USB host".) * * This routine may be called in an atomic (interrupt) context. * * returns zero, or a negative error code. */ int usb_ep_enable(struct usb_ep *ep) { int ret = 0; if (ep->enabled) goto out; /* UDC drivers can't handle endpoints with maxpacket size 0 */ if (!ep->desc || usb_endpoint_maxp(ep->desc) == 0) { WARN_ONCE(1, "%s: ep%d (%s) has %s\n", __func__, ep->address, ep->name, (!ep->desc) ? "NULL descriptor" : "maxpacket 0"); ret = -EINVAL; goto out; } ret = ep->ops->enable(ep, ep->desc); if (ret) goto out; ep->enabled = true; out: trace_usb_ep_enable(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_enable); /** * usb_ep_disable - endpoint is no longer usable * @ep:the endpoint being unconfigured. may not be the endpoint named "ep0". * * no other task may be using this endpoint when this is called. * any pending and uncompleted requests will complete with status * indicating disconnect (-ESHUTDOWN) before this call returns. * gadget drivers must call usb_ep_enable() again before queueing * requests to the endpoint. * * This routine may be called in an atomic (interrupt) context. * * returns zero, or a negative error code. */ int usb_ep_disable(struct usb_ep *ep) { int ret = 0; if (!ep->enabled) goto out; ret = ep->ops->disable(ep); if (ret) goto out; ep->enabled = false; out: trace_usb_ep_disable(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_disable); /** * usb_ep_alloc_request - allocate a request object to use with this endpoint * @ep:the endpoint to be used with with the request * @gfp_flags:GFP_* flags to use * * Request objects must be allocated with this call, since they normally * need controller-specific setup and may even need endpoint-specific * resources such as allocation of DMA descriptors. * Requests may be submitted with usb_ep_queue(), and receive a single * completion callback. Free requests with usb_ep_free_request(), when * they are no longer needed. * * Returns the request, or null if one could not be allocated. */ struct usb_request *usb_ep_alloc_request(struct usb_ep *ep, gfp_t gfp_flags) { struct usb_request *req = NULL; req = ep->ops->alloc_request(ep, gfp_flags); trace_usb_ep_alloc_request(ep, req, req ? 0 : -ENOMEM); return req; } EXPORT_SYMBOL_GPL(usb_ep_alloc_request); /** * usb_ep_free_request - frees a request object * @ep:the endpoint associated with the request * @req:the request being freed * * Reverses the effect of usb_ep_alloc_request(). * Caller guarantees the request is not queued, and that it will * no longer be requeued (or otherwise used). */ void usb_ep_free_request(struct usb_ep *ep, struct usb_request *req) { trace_usb_ep_free_request(ep, req, 0); ep->ops->free_request(ep, req); } EXPORT_SYMBOL_GPL(usb_ep_free_request); /** * usb_ep_queue - queues (submits) an I/O request to an endpoint. * @ep:the endpoint associated with the request * @req:the request being submitted * @gfp_flags: GFP_* flags to use in case the lower level driver couldn't * pre-allocate all necessary memory with the request. * * This tells the device controller to perform the specified request through * that endpoint (reading or writing a buffer). When the request completes, * including being canceled by usb_ep_dequeue(), the request's completion * routine is called to return the request to the driver. Any endpoint * (except control endpoints like ep0) may have more than one transfer * request queued; they complete in FIFO order. Once a gadget driver * submits a request, that request may not be examined or modified until it * is given back to that driver through the completion callback. * * Each request is turned into one or more packets. The controller driver * never merges adjacent requests into the same packet. OUT transfers * will sometimes use data that's already buffered in the hardware. * Drivers can rely on the fact that the first byte of the request's buffer * always corresponds to the first byte of some USB packet, for both * IN and OUT transfers. * * Bulk endpoints can queue any amount of data; the transfer is packetized * automatically. The last packet will be short if the request doesn't fill it * out completely. Zero length packets (ZLPs) should be avoided in portable * protocols since not all usb hardware can successfully handle zero length * packets. (ZLPs may be explicitly written, and may be implicitly written if * the request 'zero' flag is set.) Bulk endpoints may also be used * for interrupt transfers; but the reverse is not true, and some endpoints * won't support every interrupt transfer. (Such as 768 byte packets.) * * Interrupt-only endpoints are less functional than bulk endpoints, for * example by not supporting queueing or not handling buffers that are * larger than the endpoint's maxpacket size. They may also treat data * toggle differently. * * Control endpoints ... after getting a setup() callback, the driver queues * one response (even if it would be zero length). That enables the * status ack, after transferring data as specified in the response. Setup * functions may return negative error codes to generate protocol stalls. * (Note that some USB device controllers disallow protocol stall responses * in some cases.) When control responses are deferred (the response is * written after the setup callback returns), then usb_ep_set_halt() may be * used on ep0 to trigger protocol stalls. Depending on the controller, * it may not be possible to trigger a status-stage protocol stall when the * data stage is over, that is, from within the response's completion * routine. * * For periodic endpoints, like interrupt or isochronous ones, the usb host * arranges to poll once per interval, and the gadget driver usually will * have queued some data to transfer at that time. * * Note that @req's ->complete() callback must never be called from * within usb_ep_queue() as that can create deadlock situations. * * This routine may be called in interrupt context. * * Returns zero, or a negative error code. Endpoints that are not enabled * report errors; errors will also be * reported when the usb peripheral is disconnected. * * If and only if @req is successfully queued (the return value is zero), * @req->complete() will be called exactly once, when the Gadget core and * UDC are finished with the request. When the completion function is called, * control of the request is returned to the device driver which submitted it. * The completion handler may then immediately free or reuse @req. */ int usb_ep_queue(struct usb_ep *ep, struct usb_request *req, gfp_t gfp_flags) { int ret = 0; if (!ep->enabled && ep->address) { pr_debug("USB gadget: queue request to disabled ep 0x%x (%s)\n", ep->address, ep->name); ret = -ESHUTDOWN; goto out; } ret = ep->ops->queue(ep, req, gfp_flags); out: trace_usb_ep_queue(ep, req, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_queue); /** * usb_ep_dequeue - dequeues (cancels, unlinks) an I/O request from an endpoint * @ep:the endpoint associated with the request * @req:the request being canceled * * If the request is still active on the endpoint, it is dequeued and * eventually its completion routine is called (with status -ECONNRESET); * else a negative error code is returned. This routine is asynchronous, * that is, it may return before the completion routine runs. * * Note that some hardware can't clear out write fifos (to unlink the request * at the head of the queue) except as part of disconnecting from usb. Such * restrictions prevent drivers from supporting configuration changes, * even to configuration zero (a "chapter 9" requirement). * * This routine may be called in interrupt context. */ int usb_ep_dequeue(struct usb_ep *ep, struct usb_request *req) { int ret; ret = ep->ops->dequeue(ep, req); trace_usb_ep_dequeue(ep, req, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_dequeue); /** * usb_ep_set_halt - sets the endpoint halt feature. * @ep: the non-isochronous endpoint being stalled * * Use this to stall an endpoint, perhaps as an error report. * Except for control endpoints, * the endpoint stays halted (will not stream any data) until the host * clears this feature; drivers may need to empty the endpoint's request * queue first, to make sure no inappropriate transfers happen. * * Note that while an endpoint CLEAR_FEATURE will be invisible to the * gadget driver, a SET_INTERFACE will not be. To reset endpoints for the * current altsetting, see usb_ep_clear_halt(). When switching altsettings, * it's simplest to use usb_ep_enable() or usb_ep_disable() for the endpoints. * * This routine may be called in interrupt context. * * Returns zero, or a negative error code. On success, this call sets * underlying hardware state that blocks data transfers. * Attempts to halt IN endpoints will fail (returning -EAGAIN) if any * transfer requests are still queued, or if the controller hardware * (usually a FIFO) still holds bytes that the host hasn't collected. */ int usb_ep_set_halt(struct usb_ep *ep) { int ret; ret = ep->ops->set_halt(ep, 1); trace_usb_ep_set_halt(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_set_halt); /** * usb_ep_clear_halt - clears endpoint halt, and resets toggle * @ep:the bulk or interrupt endpoint being reset * * Use this when responding to the standard usb "set interface" request, * for endpoints that aren't reconfigured, after clearing any other state * in the endpoint's i/o queue. * * This routine may be called in interrupt context. * * Returns zero, or a negative error code. On success, this call clears * the underlying hardware state reflecting endpoint halt and data toggle. * Note that some hardware can't support this request (like pxa2xx_udc), * and accordingly can't correctly implement interface altsettings. */ int usb_ep_clear_halt(struct usb_ep *ep) { int ret; ret = ep->ops->set_halt(ep, 0); trace_usb_ep_clear_halt(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_clear_halt); /** * usb_ep_set_wedge - sets the halt feature and ignores clear requests * @ep: the endpoint being wedged * * Use this to stall an endpoint and ignore CLEAR_FEATURE(HALT_ENDPOINT) * requests. If the gadget driver clears the halt status, it will * automatically unwedge the endpoint. * * This routine may be called in interrupt context. * * Returns zero on success, else negative errno. */ int usb_ep_set_wedge(struct usb_ep *ep) { int ret; if (ep->ops->set_wedge) ret = ep->ops->set_wedge(ep); else ret = ep->ops->set_halt(ep, 1); trace_usb_ep_set_wedge(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_set_wedge); /** * usb_ep_fifo_status - returns number of bytes in fifo, or error * @ep: the endpoint whose fifo status is being checked. * * FIFO endpoints may have "unclaimed data" in them in certain cases, * such as after aborted transfers. Hosts may not have collected all * the IN data written by the gadget driver (and reported by a request * completion). The gadget driver may not have collected all the data * written OUT to it by the host. Drivers that need precise handling for * fault reporting or recovery may need to use this call. * * This routine may be called in interrupt context. * * This returns the number of such bytes in the fifo, or a negative * errno if the endpoint doesn't use a FIFO or doesn't support such * precise handling. */ int usb_ep_fifo_status(struct usb_ep *ep) { int ret; if (ep->ops->fifo_status) ret = ep->ops->fifo_status(ep); else ret = -EOPNOTSUPP; trace_usb_ep_fifo_status(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_fifo_status); /** * usb_ep_fifo_flush - flushes contents of a fifo * @ep: the endpoint whose fifo is being flushed. * * This call may be used to flush the "unclaimed data" that may exist in * an endpoint fifo after abnormal transaction terminations. The call * must never be used except when endpoint is not being used for any * protocol translation. * * This routine may be called in interrupt context. */ void usb_ep_fifo_flush(struct usb_ep *ep) { if (ep->ops->fifo_flush) ep->ops->fifo_flush(ep); trace_usb_ep_fifo_flush(ep, 0); } EXPORT_SYMBOL_GPL(usb_ep_fifo_flush); /* ------------------------------------------------------------------------- */ /** * usb_gadget_frame_number - returns the current frame number * @gadget: controller that reports the frame number * * Returns the usb frame number, normally eleven bits from a SOF packet, * or negative errno if this device doesn't support this capability. */ int usb_gadget_frame_number(struct usb_gadget *gadget) { int ret; ret = gadget->ops->get_frame(gadget); trace_usb_gadget_frame_number(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_frame_number); /** * usb_gadget_wakeup - tries to wake up the host connected to this gadget * @gadget: controller used to wake up the host * * Returns zero on success, else negative error code if the hardware * doesn't support such attempts, or its support has not been enabled * by the usb host. Drivers must return device descriptors that report * their ability to support this, or hosts won't enable it. * * This may also try to use SRP to wake the host and start enumeration, * even if OTG isn't otherwise in use. OTG devices may also start * remote wakeup even when hosts don't explicitly enable it. */ int usb_gadget_wakeup(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->wakeup) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->wakeup(gadget); out: trace_usb_gadget_wakeup(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_wakeup); /** * usb_gadget_set_remote_wakeup - configures the device remote wakeup feature. * @gadget:the device being configured for remote wakeup * @set:value to be configured. * * set to one to enable remote wakeup feature and zero to disable it. * * returns zero on success, else negative errno. */ int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) { int ret = 0; if (!gadget->ops->set_remote_wakeup) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->set_remote_wakeup(gadget, set); out: trace_usb_gadget_set_remote_wakeup(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_set_remote_wakeup); /** * usb_gadget_set_selfpowered - sets the device selfpowered feature. * @gadget:the device being declared as self-powered * * this affects the device status reported by the hardware driver * to reflect that it now has a local power supply. * * returns zero on success, else negative errno. */ int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->set_selfpowered) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->set_selfpowered(gadget, 1); out: trace_usb_gadget_set_selfpowered(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_set_selfpowered); /** * usb_gadget_clear_selfpowered - clear the device selfpowered feature. * @gadget:the device being declared as bus-powered * * this affects the device status reported by the hardware driver. * some hardware may not support bus-powered operation, in which * case this feature's value can never change. * * returns zero on success, else negative errno. */ int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->set_selfpowered) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->set_selfpowered(gadget, 0); out: trace_usb_gadget_clear_selfpowered(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_clear_selfpowered); /** * usb_gadget_vbus_connect - Notify controller that VBUS is powered * @gadget:The device which now has VBUS power. * Context: can sleep * * This call is used by a driver for an external transceiver (or GPIO) * that detects a VBUS power session starting. Common responses include * resuming the controller, activating the D+ (or D-) pullup to let the * host detect that a USB device is attached, and starting to draw power * (8mA or possibly more, especially after SET_CONFIGURATION). * * Returns zero on success, else negative errno. */ int usb_gadget_vbus_connect(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->vbus_session) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->vbus_session(gadget, 1); out: trace_usb_gadget_vbus_connect(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_vbus_connect); /** * usb_gadget_vbus_draw - constrain controller's VBUS power usage * @gadget:The device whose VBUS usage is being described * @mA:How much current to draw, in milliAmperes. This should be twice * the value listed in the configuration descriptor bMaxPower field. * * This call is used by gadget drivers during SET_CONFIGURATION calls, * reporting how much power the device may consume. For example, this * could affect how quickly batteries are recharged. * * Returns zero on success, else negative errno. */ int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) { int ret = 0; if (!gadget->ops->vbus_draw) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->vbus_draw(gadget, mA); if (!ret) gadget->mA = mA; out: trace_usb_gadget_vbus_draw(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_vbus_draw); /** * usb_gadget_vbus_disconnect - notify controller about VBUS session end * @gadget:the device whose VBUS supply is being described * Context: can sleep * * This call is used by a driver for an external transceiver (or GPIO) * that detects a VBUS power session ending. Common responses include * reversing everything done in usb_gadget_vbus_connect(). * * Returns zero on success, else negative errno. */ int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->vbus_session) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->vbus_session(gadget, 0); out: trace_usb_gadget_vbus_disconnect(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); static int usb_gadget_connect_locked(struct usb_gadget *gadget) __must_hold(&gadget->udc->connect_lock) { int ret = 0; if (!gadget->ops->pullup) { ret = -EOPNOTSUPP; goto out; } if (gadget->deactivated || !gadget->udc->allow_connect || !gadget->udc->started) { /* * If the gadget isn't usable (because it is deactivated, * unbound, or not yet started), we only save the new state. * The gadget will be connected automatically when it is * activated/bound/started. */ gadget->connected = true; goto out; } ret = gadget->ops->pullup(gadget, 1); if (!ret) gadget->connected = 1; out: trace_usb_gadget_connect(gadget, ret); return ret; } /** * usb_gadget_connect - software-controlled connect to USB host * @gadget:the peripheral being connected * * Enables the D+ (or potentially D-) pullup. The host will start * enumerating this gadget when the pullup is active and a VBUS session * is active (the link is powered). * * Returns zero on success, else negative errno. */ int usb_gadget_connect(struct usb_gadget *gadget) { int ret; mutex_lock(&gadget->udc->connect_lock); ret = usb_gadget_connect_locked(gadget); mutex_unlock(&gadget->udc->connect_lock); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_connect); static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) __must_hold(&gadget->udc->connect_lock) { int ret = 0; if (!gadget->ops->pullup) { ret = -EOPNOTSUPP; goto out; } if (!gadget->connected) goto out; if (gadget->deactivated || !gadget->udc->started) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. */ gadget->connected = false; goto out; } ret = gadget->ops->pullup(gadget, 0); if (!ret) gadget->connected = 0; mutex_lock(&udc_lock); if (gadget->udc->driver) gadget->udc->driver->disconnect(gadget); mutex_unlock(&udc_lock); out: trace_usb_gadget_disconnect(gadget, ret); return ret; } /** * usb_gadget_disconnect - software-controlled disconnect from USB host * @gadget:the peripheral being disconnected * * Disables the D+ (or potentially D-) pullup, which the host may see * as a disconnect (when a VBUS session is active). Not all systems * support software pullup controls. * * Following a successful disconnect, invoke the ->disconnect() callback * for the current gadget driver so that UDC drivers don't need to. * * Returns zero on success, else negative errno. */ int usb_gadget_disconnect(struct usb_gadget *gadget) { int ret; mutex_lock(&gadget->udc->connect_lock); ret = usb_gadget_disconnect_locked(gadget); mutex_unlock(&gadget->udc->connect_lock); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** * usb_gadget_deactivate - deactivate function which is not ready to work * @gadget: the peripheral being deactivated * * This routine may be used during the gadget driver bind() call to prevent * the peripheral from ever being visible to the USB host, unless later * usb_gadget_activate() is called. For example, user mode components may * need to be activated before the system can talk to hosts. * * This routine may sleep; it must not be called in interrupt context * (such as from within a gadget driver's disconnect() callback). * * Returns zero on success, else negative errno. */ int usb_gadget_deactivate(struct usb_gadget *gadget) { int ret = 0; mutex_lock(&gadget->udc->connect_lock); if (gadget->deactivated) goto unlock; if (gadget->connected) { ret = usb_gadget_disconnect_locked(gadget); if (ret) goto unlock; /* * If gadget was being connected before deactivation, we want * to reconnect it in usb_gadget_activate(). */ gadget->connected = true; } gadget->deactivated = true; unlock: mutex_unlock(&gadget->udc->connect_lock); trace_usb_gadget_deactivate(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_deactivate); /** * usb_gadget_activate - activate function which is not ready to work * @gadget: the peripheral being activated * * This routine activates gadget which was previously deactivated with * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. * * This routine may sleep; it must not be called in interrupt context. * * Returns zero on success, else negative errno. */ int usb_gadget_activate(struct usb_gadget *gadget) { int ret = 0; mutex_lock(&gadget->udc->connect_lock); if (!gadget->deactivated) goto unlock; gadget->deactivated = false; /* * If gadget has been connected before deactivation, or became connected * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) ret = usb_gadget_connect_locked(gadget); unlock: mutex_unlock(&gadget->udc->connect_lock); trace_usb_gadget_activate(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_activate); /* ------------------------------------------------------------------------- */ #ifdef CONFIG_HAS_DMA int usb_gadget_map_request_by_dev(struct device *dev, struct usb_request *req, int is_in) { if (req->length == 0) return 0; if (req->sg_was_mapped) { req->num_mapped_sgs = req->num_sgs; return 0; } if (req->num_sgs) { int mapped; mapped = dma_map_sg(dev, req->sg, req->num_sgs, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); if (mapped == 0) { dev_err(dev, "failed to map SGs\n"); return -EFAULT; } req->num_mapped_sgs = mapped; } else { if (is_vmalloc_addr(req->buf)) { dev_err(dev, "buffer is not dma capable\n"); return -EFAULT; } else if (object_is_on_stack(req->buf)) { dev_err(dev, "buffer is on stack\n"); return -EFAULT; } req->dma = dma_map_single(dev, req->buf, req->length, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); if (dma_mapping_error(dev, req->dma)) { dev_err(dev, "failed to map buffer\n"); return -EFAULT; } req->dma_mapped = 1; } return 0; } EXPORT_SYMBOL_GPL(usb_gadget_map_request_by_dev); int usb_gadget_map_request(struct usb_gadget *gadget, struct usb_request *req, int is_in) { return usb_gadget_map_request_by_dev(gadget->dev.parent, req, is_in); } EXPORT_SYMBOL_GPL(usb_gadget_map_request); void usb_gadget_unmap_request_by_dev(struct device *dev, struct usb_request *req, int is_in) { if (req->length == 0 || req->sg_was_mapped) return; if (req->num_mapped_sgs) { dma_unmap_sg(dev, req->sg, req->num_sgs, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); req->num_mapped_sgs = 0; } else if (req->dma_mapped) { dma_unmap_single(dev, req->dma, req->length, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); req->dma_mapped = 0; } } EXPORT_SYMBOL_GPL(usb_gadget_unmap_request_by_dev); void usb_gadget_unmap_request(struct usb_gadget *gadget, struct usb_request *req, int is_in) { usb_gadget_unmap_request_by_dev(gadget->dev.parent, req, is_in); } EXPORT_SYMBOL_GPL(usb_gadget_unmap_request); #endif /* CONFIG_HAS_DMA */ /* ------------------------------------------------------------------------- */ /** * usb_gadget_giveback_request - give the request back to the gadget layer * @ep: the endpoint to be used with with the request * @req: the request being given back * * This is called by device controller drivers in order to return the * completed request back to the gadget layer. */ void usb_gadget_giveback_request(struct usb_ep *ep, struct usb_request *req) { if (likely(req->status == 0)) usb_led_activity(USB_LED_EVENT_GADGET); trace_usb_gadget_giveback_request(ep, req, 0); req->complete(ep, req); } EXPORT_SYMBOL_GPL(usb_gadget_giveback_request); /* ------------------------------------------------------------------------- */ /** * gadget_find_ep_by_name - returns ep whose name is the same as sting passed * in second parameter or NULL if searched endpoint not found * @g: controller to check for quirk * @name: name of searched endpoint */ struct usb_ep *gadget_find_ep_by_name(struct usb_gadget *g, const char *name) { struct usb_ep *ep; gadget_for_each_ep(ep, g) { if (!strcmp(ep->name, name)) return ep; } return NULL; } EXPORT_SYMBOL_GPL(gadget_find_ep_by_name); /* ------------------------------------------------------------------------- */ int usb_gadget_ep_match_desc(struct usb_gadget *gadget, struct usb_ep *ep, struct usb_endpoint_descriptor *desc, struct usb_ss_ep_comp_descriptor *ep_comp) { u8 type; u16 max; int num_req_streams = 0; /* endpoint already claimed? */ if (ep->claimed) return 0; type = usb_endpoint_type(desc); max = usb_endpoint_maxp(desc); if (usb_endpoint_dir_in(desc) && !ep->caps.dir_in) return 0; if (usb_endpoint_dir_out(desc) && !ep->caps.dir_out) return 0; if (max > ep->maxpacket_limit) return 0; /* "high bandwidth" works only at high speed */ if (!gadget_is_dualspeed(gadget) && usb_endpoint_maxp_mult(desc) > 1) return 0; switch (type) { case USB_ENDPOINT_XFER_CONTROL: /* only support ep0 for portable CONTROL traffic */ return 0; case USB_ENDPOINT_XFER_ISOC: if (!ep->caps.type_iso) return 0; /* ISO: limit 1023 bytes full speed, 1024 high/super speed */ if (!gadget_is_dualspeed(gadget) && max > 1023) return 0; break; case USB_ENDPOINT_XFER_BULK: if (!ep->caps.type_bulk) return 0; if (ep_comp && gadget_is_superspeed(gadget)) { /* Get the number of required streams from the * EP companion descriptor and see if the EP * matches it */ num_req_streams = ep_comp->bmAttributes & 0x1f; if (num_req_streams > ep->max_streams) return 0; } break; case USB_ENDPOINT_XFER_INT: /* Bulk endpoints handle interrupt transfers, * except the toggle-quirky iso-synch kind */ if (!ep->caps.type_int && !ep->caps.type_bulk) return 0; /* INT: limit 64 bytes full speed, 1024 high/super speed */ if (!gadget_is_dualspeed(gadget) && max > 64) return 0; break; } return 1; } EXPORT_SYMBOL_GPL(usb_gadget_ep_match_desc); /** * usb_gadget_check_config - checks if the UDC can support the binded * configuration * @gadget: controller to check the USB configuration * * Ensure that a UDC is able to support the requested resources by a * configuration, and that there are no resource limitations, such as * internal memory allocated to all requested endpoints. * * Returns zero on success, else a negative errno. */ int usb_gadget_check_config(struct usb_gadget *gadget) { if (gadget->ops->check_config) return gadget->ops->check_config(gadget); return 0; } EXPORT_SYMBOL_GPL(usb_gadget_check_config); /* ------------------------------------------------------------------------- */ static void usb_gadget_state_work(struct work_struct *work) { struct usb_gadget *gadget = work_to_gadget(work); struct usb_udc *udc = gadget->udc; if (udc) sysfs_notify(&udc->dev.kobj, NULL, "state"); } void usb_gadget_set_state(struct usb_gadget *gadget, enum usb_device_state state) { gadget->state = state; schedule_work(&gadget->work); } EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ /* Acquire connect_lock before calling this function. */ static int usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) { if (udc->vbus) return usb_gadget_connect_locked(udc->gadget); else return usb_gadget_disconnect_locked(udc->gadget); } static void vbus_event_work(struct work_struct *work) { struct usb_udc *udc = container_of(work, struct usb_udc, vbus_work); mutex_lock(&udc->connect_lock); usb_udc_connect_control_locked(udc); mutex_unlock(&udc->connect_lock); } /** * usb_udc_vbus_handler - updates the udc core vbus status, and try to * connect or disconnect gadget * @gadget: The gadget which vbus change occurs * @status: The vbus status * * The udc driver calls it when it wants to connect or disconnect gadget * according to vbus status. * * This function can be invoked from interrupt context by irq handlers of * the gadget drivers, however, usb_udc_connect_control() has to run in * non-atomic context due to the following: * a. Some of the gadget driver implementations expect the ->pullup * callback to be invoked in non-atomic context. * b. usb_gadget_disconnect() acquires udc_lock which is a mutex. * Hence offload invocation of usb_udc_connect_control() to workqueue. */ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; if (udc) { udc->vbus = status; schedule_work(&udc->vbus_work); } } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); /** * usb_gadget_udc_reset - notifies the udc core that bus reset occurs * @gadget: The gadget which bus reset occurs * @driver: The gadget driver we want to notify * * If the udc driver has bus reset handler, it needs to call this when the bus * reset occurs, it notifies the gadget driver that the bus reset occurs as * well as updates gadget state. */ void usb_gadget_udc_reset(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { driver->reset(gadget); usb_gadget_set_state(gadget, USB_STATE_DEFAULT); } EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** * usb_gadget_udc_start_locked - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about * to register a gadget driver to the device controller, before * calling gadget driver's bind() method. * * It allows the controller to be powered off until strictly * necessary to have it powered on. * * Returns zero on success, else negative errno. * * Caller should acquire connect_lock before invoking this function. */ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) { int ret; if (udc->started) { dev_err(&udc->dev, "UDC had already started\n"); return -EBUSY; } ret = udc->gadget->ops->udc_start(udc->gadget, udc->driver); if (!ret) udc->started = true; return ret; } /** * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling * gadget driver's unbind() method. * * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. * * Caller should acquire connect lock before invoking this function. */ static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); return; } udc->gadget->ops->udc_stop(udc->gadget); udc->started = false; } /** * usb_gadget_udc_set_speed - tells usb device controller speed supported by * current driver * @udc: The device we want to set maximum speed * @speed: The maximum speed to allowed to run * * This call is issued by the UDC Class driver before calling * usb_gadget_udc_start() in order to make sure that we don't try to * connect on speeds the gadget driver doesn't support. */ static inline void usb_gadget_udc_set_speed(struct usb_udc *udc, enum usb_device_speed speed) { struct usb_gadget *gadget = udc->gadget; enum usb_device_speed s; if (speed == USB_SPEED_UNKNOWN) s = gadget->max_speed; else s = min(speed, gadget->max_speed); if (s == USB_SPEED_SUPER_PLUS && gadget->ops->udc_set_ssp_rate) gadget->ops->udc_set_ssp_rate(gadget, gadget->max_ssp_rate); else if (gadget->ops->udc_set_speed) gadget->ops->udc_set_speed(gadget, s); } /** * usb_gadget_enable_async_callbacks - tell usb device controller to enable asynchronous callbacks * @udc: The UDC which should enable async callbacks * * This routine is used when binding gadget drivers. It undoes the effect * of usb_gadget_disable_async_callbacks(); the UDC driver should enable IRQs * (if necessary) and resume issuing callbacks. * * This routine will always be called in process context. */ static inline void usb_gadget_enable_async_callbacks(struct usb_udc *udc) { struct usb_gadget *gadget = udc->gadget; if (gadget->ops->udc_async_callbacks) gadget->ops->udc_async_callbacks(gadget, true); } /** * usb_gadget_disable_async_callbacks - tell usb device controller to disable asynchronous callbacks * @udc: The UDC which should disable async callbacks * * This routine is used when unbinding gadget drivers. It prevents a race: * The UDC driver doesn't know when the gadget driver's ->unbind callback * runs, so unless it is told to disable asynchronous callbacks, it might * issue a callback (such as ->disconnect) after the unbind has completed. * * After this function runs, the UDC driver must suppress all ->suspend, * ->resume, ->disconnect, ->reset, and ->setup callbacks to the gadget driver * until async callbacks are again enabled. A simple-minded but effective * way to accomplish this is to tell the UDC hardware not to generate any * more IRQs. * * Request completion callbacks must still be issued. However, it's okay * to defer them until the request is cancelled, since the pull-up will be * turned off during the time period when async callbacks are disabled. * * This routine will always be called in process context. */ static inline void usb_gadget_disable_async_callbacks(struct usb_udc *udc) { struct usb_gadget *gadget = udc->gadget; if (gadget->ops->udc_async_callbacks) gadget->ops->udc_async_callbacks(gadget, false); } /** * usb_udc_release - release the usb_udc struct * @dev: the dev member within usb_udc * * This is called by driver's core in order to free memory once the last * reference is released. */ static void usb_udc_release(struct device *dev) { struct usb_udc *udc; udc = container_of(dev, struct usb_udc, dev); dev_dbg(dev, "releasing '%s'\n", dev_name(dev)); kfree(udc); } static const struct attribute_group *usb_udc_attr_groups[]; static void usb_udc_nop_release(struct device *dev) { dev_vdbg(dev, "%s\n", __func__); } /** * usb_initialize_gadget - initialize a gadget and its embedded struct device * @parent: the parent device to this udc. Usually the controller driver's * device. * @gadget: the gadget to be initialized. * @release: a gadget release function. */ void usb_initialize_gadget(struct device *parent, struct usb_gadget *gadget, void (*release)(struct device *dev)) { INIT_WORK(&gadget->work, usb_gadget_state_work); gadget->dev.parent = parent; if (release) gadget->dev.release = release; else gadget->dev.release = usb_udc_nop_release; device_initialize(&gadget->dev); gadget->dev.bus = &gadget_bus_type; } EXPORT_SYMBOL_GPL(usb_initialize_gadget); /** * usb_add_gadget - adds a new gadget to the udc class driver list * @gadget: the gadget to be added to the list. * * Returns zero on success, negative errno otherwise. * Does not do a final usb_put_gadget() if an error occurs. */ int usb_add_gadget(struct usb_gadget *gadget) { struct usb_udc *udc; int ret = -ENOMEM; udc = kzalloc(sizeof(*udc), GFP_KERNEL); if (!udc) goto error; device_initialize(&udc->dev); udc->dev.release = usb_udc_release; udc->dev.class = &udc_class; udc->dev.groups = usb_udc_attr_groups; udc->dev.parent = gadget->dev.parent; ret = dev_set_name(&udc->dev, "%s", kobject_name(&gadget->dev.parent->kobj)); if (ret) goto err_put_udc; udc->gadget = gadget; gadget->udc = udc; mutex_init(&udc->connect_lock); udc->started = false; mutex_lock(&udc_lock); list_add_tail(&udc->list, &udc_list); mutex_unlock(&udc_lock); INIT_WORK(&udc->vbus_work, vbus_event_work); ret = device_add(&udc->dev); if (ret) goto err_unlist_udc; usb_gadget_set_state(gadget, USB_STATE_NOTATTACHED); udc->vbus = true; ret = ida_alloc(&gadget_id_numbers, GFP_KERNEL); if (ret < 0) goto err_del_udc; gadget->id_number = ret; dev_set_name(&gadget->dev, "gadget.%d", ret); ret = device_add(&gadget->dev); if (ret) goto err_free_id; ret = sysfs_create_link(&udc->dev.kobj, &gadget->dev.kobj, "gadget"); if (ret) goto err_del_gadget; return 0; err_del_gadget: device_del(&gadget->dev); err_free_id: ida_free(&gadget_id_numbers, gadget->id_number); err_del_udc: flush_work(&gadget->work); device_del(&udc->dev); err_unlist_udc: mutex_lock(&udc_lock); list_del(&udc->list); mutex_unlock(&udc_lock); err_put_udc: put_device(&udc->dev); error: return ret; } EXPORT_SYMBOL_GPL(usb_add_gadget); /** * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list * @parent: the parent device to this udc. Usually the controller driver's * device. * @gadget: the gadget to be added to the list. * @release: a gadget release function. * * Returns zero on success, negative errno otherwise. * Calls the gadget release function in the latter case. */ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, void (*release)(struct device *dev)) { int ret; usb_initialize_gadget(parent, gadget, release); ret = usb_add_gadget(gadget); if (ret) usb_put_gadget(gadget); return ret; } EXPORT_SYMBOL_GPL(usb_add_gadget_udc_release); /** * usb_get_gadget_udc_name - get the name of the first UDC controller * This functions returns the name of the first UDC controller in the system. * Please note that this interface is usefull only for legacy drivers which * assume that there is only one UDC controller in the system and they need to * get its name before initialization. There is no guarantee that the UDC * of the returned name will be still available, when gadget driver registers * itself. * * Returns pointer to string with UDC controller name on success, NULL * otherwise. Caller should kfree() returned string. */ char *usb_get_gadget_udc_name(void) { struct usb_udc *udc; char *name = NULL; /* For now we take the first available UDC */ mutex_lock(&udc_lock); list_for_each_entry(udc, &udc_list, list) { if (!udc->driver) { name = kstrdup(udc->gadget->name, GFP_KERNEL); break; } } mutex_unlock(&udc_lock); return name; } EXPORT_SYMBOL_GPL(usb_get_gadget_udc_name); /** * usb_add_gadget_udc - adds a new gadget to the udc class driver list * @parent: the parent device to this udc. Usually the controller * driver's device. * @gadget: the gadget to be added to the list * * Returns zero on success, negative errno otherwise. */ int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget) { return usb_add_gadget_udc_release(parent, gadget, NULL); } EXPORT_SYMBOL_GPL(usb_add_gadget_udc); /** * usb_del_gadget - deletes a gadget and unregisters its udc * @gadget: the gadget to be deleted. * * This will unbind @gadget, if it is bound. * It will not do a final usb_put_gadget(). */ void usb_del_gadget(struct usb_gadget *gadget) { struct usb_udc *udc = gadget->udc; if (!udc) return; dev_vdbg(gadget->dev.parent, "unregistering gadget\n"); mutex_lock(&udc_lock); list_del(&udc->list); mutex_unlock(&udc_lock); kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE); sysfs_remove_link(&udc->dev.kobj, "gadget"); flush_work(&gadget->work); device_del(&gadget->dev); ida_free(&gadget_id_numbers, gadget->id_number); cancel_work_sync(&udc->vbus_work); device_unregister(&udc->dev); } EXPORT_SYMBOL_GPL(usb_del_gadget); /** * usb_del_gadget_udc - unregisters a gadget * @gadget: the gadget to be unregistered. * * Calls usb_del_gadget() and does a final usb_put_gadget(). */ void usb_del_gadget_udc(struct usb_gadget *gadget) { usb_del_gadget(gadget); usb_put_gadget(gadget); } EXPORT_SYMBOL_GPL(usb_del_gadget_udc); /* ------------------------------------------------------------------------- */ static int gadget_match_driver(struct device *dev, const struct device_driver *drv) { struct usb_gadget *gadget = dev_to_usb_gadget(dev); struct usb_udc *udc = gadget->udc; struct usb_gadget_driver *driver = container_of(drv, struct usb_gadget_driver, driver); /* If the driver specifies a udc_name, it must match the UDC's name */ if (driver->udc_name && strcmp(driver->udc_name, dev_name(&udc->dev)) != 0) return 0; /* If the driver is already bound to a gadget, it doesn't match */ if (driver->is_bound) return 0; /* Otherwise any gadget driver matches any UDC */ return 1; } static int gadget_bind_driver(struct device *dev) { struct usb_gadget *gadget = dev_to_usb_gadget(dev); struct usb_udc *udc = gadget->udc; struct usb_gadget_driver *driver = container_of(dev->driver, struct usb_gadget_driver, driver); int ret = 0; mutex_lock(&udc_lock); if (driver->is_bound) { mutex_unlock(&udc_lock); return -ENXIO; /* Driver binds to only one gadget */ } driver->is_bound = true; udc->driver = driver; mutex_unlock(&udc_lock); dev_dbg(&udc->dev, "binding gadget driver [%s]\n", driver->function); usb_gadget_udc_set_speed(udc, driver->max_speed); ret = driver->bind(udc->gadget, driver); if (ret) goto err_bind; mutex_lock(&udc->connect_lock); ret = usb_gadget_udc_start_locked(udc); if (ret) { mutex_unlock(&udc->connect_lock); goto err_start; } usb_gadget_enable_async_callbacks(udc); udc->allow_connect = true; ret = usb_udc_connect_control_locked(udc); if (ret) goto err_connect_control; mutex_unlock(&udc->connect_lock); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; err_connect_control: udc->allow_connect = false; usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); usb_gadget_udc_stop_locked(udc); mutex_unlock(&udc->connect_lock); err_start: driver->unbind(udc->gadget); err_bind: if (ret != -EISNAM) dev_err(&udc->dev, "failed to start %s: %d\n", driver->function, ret); mutex_lock(&udc_lock); udc->driver = NULL; driver->is_bound = false; mutex_unlock(&udc_lock); return ret; } static void gadget_unbind_driver(struct device *dev) { struct usb_gadget *gadget = dev_to_usb_gadget(dev); struct usb_udc *udc = gadget->udc; struct usb_gadget_driver *driver = udc->driver; dev_dbg(&udc->dev, "unbinding gadget driver [%s]\n", driver->function); udc->allow_connect = false; cancel_work_sync(&udc->vbus_work); mutex_lock(&udc->connect_lock); usb_gadget_disconnect_locked(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); mutex_unlock(&udc->connect_lock); udc->driver->unbind(gadget); mutex_lock(&udc->connect_lock); usb_gadget_udc_stop_locked(udc); mutex_unlock(&udc->connect_lock); mutex_lock(&udc_lock); driver->is_bound = false; udc->driver = NULL; mutex_unlock(&udc_lock); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); } /* ------------------------------------------------------------------------- */ int usb_gadget_register_driver_owner(struct usb_gadget_driver *driver, struct module *owner, const char *mod_name) { int ret; if (!driver || !driver->bind || !driver->setup) return -EINVAL; driver->driver.bus = &gadget_bus_type; driver->driver.owner = owner; driver->driver.mod_name = mod_name; ret = driver_register(&driver->driver); if (ret) { pr_warn("%s: driver registration failed: %d\n", driver->function, ret); return ret; } mutex_lock(&udc_lock); if (!driver->is_bound) { if (driver->match_existing_only) { pr_warn("%s: couldn't find an available UDC or it's busy\n", driver->function); ret = -EBUSY; } else { pr_info("%s: couldn't find an available UDC\n", driver->function); ret = 0; } } mutex_unlock(&udc_lock); if (ret) driver_unregister(&driver->driver); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_register_driver_owner); int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) { if (!driver || !driver->unbind) return -EINVAL; driver_unregister(&driver->driver); return 0; } EXPORT_SYMBOL_GPL(usb_gadget_unregister_driver); /* ------------------------------------------------------------------------- */ static ssize_t srp_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); if (sysfs_streq(buf, "1")) usb_gadget_wakeup(udc->gadget); return n; } static DEVICE_ATTR_WO(srp); static ssize_t soft_connect_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); ssize_t ret; device_lock(&udc->gadget->dev); if (!udc->driver) { dev_err(dev, "soft-connect without a gadget driver\n"); ret = -EOPNOTSUPP; goto out; } if (sysfs_streq(buf, "connect")) { mutex_lock(&udc->connect_lock); usb_gadget_udc_start_locked(udc); usb_gadget_connect_locked(udc->gadget); mutex_unlock(&udc->connect_lock); } else if (sysfs_streq(buf, "disconnect")) { mutex_lock(&udc->connect_lock); usb_gadget_disconnect_locked(udc->gadget); usb_gadget_udc_stop_locked(udc); mutex_unlock(&udc->connect_lock); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; goto out; } ret = n; out: device_unlock(&udc->gadget->dev); return ret; } static DEVICE_ATTR_WO(soft_connect); static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); struct usb_gadget *gadget = udc->gadget; return sprintf(buf, "%s\n", usb_state_string(gadget->state)); } static DEVICE_ATTR_RO(state); static ssize_t function_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); struct usb_gadget_driver *drv; int rc = 0; mutex_lock(&udc_lock); drv = udc->driver; if (drv && drv->function) rc = scnprintf(buf, PAGE_SIZE, "%s\n", drv->function); mutex_unlock(&udc_lock); return rc; } static DEVICE_ATTR_RO(function); #define USB_UDC_SPEED_ATTR(name, param) \ ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ return scnprintf(buf, PAGE_SIZE, "%s\n", \ usb_speed_string(udc->gadget->param)); \ } \ static DEVICE_ATTR_RO(name) static USB_UDC_SPEED_ATTR(current_speed, speed); static USB_UDC_SPEED_ATTR(maximum_speed, max_speed); #define USB_UDC_ATTR(name) \ ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ struct usb_gadget *gadget = udc->gadget; \ \ return scnprintf(buf, PAGE_SIZE, "%d\n", gadget->name); \ } \ static DEVICE_ATTR_RO(name) static USB_UDC_ATTR(is_otg); static USB_UDC_ATTR(is_a_peripheral); static USB_UDC_ATTR(b_hnp_enable); static USB_UDC_ATTR(a_hnp_support); static USB_UDC_ATTR(a_alt_hnp_support); static USB_UDC_ATTR(is_selfpowered); static struct attribute *usb_udc_attrs[] = { &dev_attr_srp.attr, &dev_attr_soft_connect.attr, &dev_attr_state.attr, &dev_attr_function.attr, &dev_attr_current_speed.attr, &dev_attr_maximum_speed.attr, &dev_attr_is_otg.attr, &dev_attr_is_a_peripheral.attr, &dev_attr_b_hnp_enable.attr, &dev_attr_a_hnp_support.attr, &dev_attr_a_alt_hnp_support.attr, &dev_attr_is_selfpowered.attr, NULL, }; static const struct attribute_group usb_udc_attr_group = { .attrs = usb_udc_attrs, }; static const struct attribute_group *usb_udc_attr_groups[] = { &usb_udc_attr_group, NULL, }; static int usb_udc_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct usb_udc *udc = container_of(dev, struct usb_udc, dev); int ret; ret = add_uevent_var(env, "USB_UDC_NAME=%s", udc->gadget->name); if (ret) { dev_err(dev, "failed to add uevent USB_UDC_NAME\n"); return ret; } mutex_lock(&udc_lock); if (udc->driver) ret = add_uevent_var(env, "USB_UDC_DRIVER=%s", udc->driver->function); mutex_unlock(&udc_lock); if (ret) { dev_err(dev, "failed to add uevent USB_UDC_DRIVER\n"); return ret; } return 0; } static const struct class udc_class = { .name = "udc", .dev_uevent = usb_udc_uevent, }; static const struct bus_type gadget_bus_type = { .name = "gadget", .probe = gadget_bind_driver, .remove = gadget_unbind_driver, .match = gadget_match_driver, }; static int __init usb_udc_init(void) { int rc; rc = class_register(&udc_class); if (rc) return rc; rc = bus_register(&gadget_bus_type); if (rc) class_unregister(&udc_class); return rc; } subsys_initcall(usb_udc_init); static void __exit usb_udc_exit(void) { bus_unregister(&gadget_bus_type); class_unregister(&udc_class); } module_exit(usb_udc_exit); MODULE_DESCRIPTION("UDC Framework"); MODULE_AUTHOR("Felipe Balbi <balbi@ti.com>"); MODULE_LICENSE("GPL v2"); |
| 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* gw.c - CAN frame Gateway/Router/Bridge with netlink interface * * Copyright (c) 2019 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/gw.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS(CAN_GW_NAME); #define CGW_MIN_HOPS 1 #define CGW_MAX_HOPS 6 #define CGW_DEFAULT_HOPS 1 static unsigned int max_hops __read_mostly = CGW_DEFAULT_HOPS; module_param(max_hops, uint, 0444); MODULE_PARM_DESC(max_hops, "maximum " CAN_GW_NAME " routing hops for CAN frames " "(valid values: " __stringify(CGW_MIN_HOPS) "-" __stringify(CGW_MAX_HOPS) " hops, " "default: " __stringify(CGW_DEFAULT_HOPS) ")"); static struct notifier_block notifier; static struct kmem_cache *cgw_cache __read_mostly; /* structure that contains the (on-the-fly) CAN frame modifications */ struct cf_mod { struct { struct canfd_frame and; struct canfd_frame or; struct canfd_frame xor; struct canfd_frame set; } modframe; struct { u8 and; u8 or; u8 xor; u8 set; } modtype; void (*modfunc[MAX_MODFUNCTIONS])(struct canfd_frame *cf, struct cf_mod *mod); /* CAN frame checksum calculation after CAN frame modifications */ struct { struct cgw_csum_xor xor; struct cgw_csum_crc8 crc8; } csum; struct { void (*xor)(struct canfd_frame *cf, struct cgw_csum_xor *xor); void (*crc8)(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8); } csumfunc; u32 uid; }; /* So far we just support CAN -> CAN routing and frame modifications. * * The internal can_can_gw structure contains data and attributes for * a CAN -> CAN gateway job. */ struct can_can_gw { struct can_filter filter; int src_idx; int dst_idx; }; /* list entry for CAN gateways jobs */ struct cgw_job { struct hlist_node list; struct rcu_head rcu; u32 handled_frames; u32 dropped_frames; u32 deleted_frames; struct cf_mod mod; union { /* CAN frame data source */ struct net_device *dev; } src; union { /* CAN frame data destination */ struct net_device *dev; } dst; union { struct can_can_gw ccgw; /* tbc */ }; u8 gwtype; u8 limit_hops; u16 flags; }; /* modification functions that are invoked in the hot path in can_can_gw_rcv */ #define MODFUNC(func, op) static void func(struct canfd_frame *cf, \ struct cf_mod *mod) { op ; } MODFUNC(mod_and_id, cf->can_id &= mod->modframe.and.can_id) MODFUNC(mod_and_len, cf->len &= mod->modframe.and.len) MODFUNC(mod_and_flags, cf->flags &= mod->modframe.and.flags) MODFUNC(mod_and_data, *(u64 *)cf->data &= *(u64 *)mod->modframe.and.data) MODFUNC(mod_or_id, cf->can_id |= mod->modframe.or.can_id) MODFUNC(mod_or_len, cf->len |= mod->modframe.or.len) MODFUNC(mod_or_flags, cf->flags |= mod->modframe.or.flags) MODFUNC(mod_or_data, *(u64 *)cf->data |= *(u64 *)mod->modframe.or.data) MODFUNC(mod_xor_id, cf->can_id ^= mod->modframe.xor.can_id) MODFUNC(mod_xor_len, cf->len ^= mod->modframe.xor.len) MODFUNC(mod_xor_flags, cf->flags ^= mod->modframe.xor.flags) MODFUNC(mod_xor_data, *(u64 *)cf->data ^= *(u64 *)mod->modframe.xor.data) MODFUNC(mod_set_id, cf->can_id = mod->modframe.set.can_id) MODFUNC(mod_set_len, cf->len = mod->modframe.set.len) MODFUNC(mod_set_flags, cf->flags = mod->modframe.set.flags) MODFUNC(mod_set_data, *(u64 *)cf->data = *(u64 *)mod->modframe.set.data) static void mod_and_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) &= *(u64 *)(mod->modframe.and.data + i); } static void mod_or_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) |= *(u64 *)(mod->modframe.or.data + i); } static void mod_xor_fddata(struct canfd_frame *cf, struct cf_mod *mod) { int i; for (i = 0; i < CANFD_MAX_DLEN; i += 8) *(u64 *)(cf->data + i) ^= *(u64 *)(mod->modframe.xor.data + i); } static void mod_set_fddata(struct canfd_frame *cf, struct cf_mod *mod) { memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN); } /* retrieve valid CC DLC value and store it into 'len' */ static void mod_retrieve_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* len8_dlc is only valid if len == CAN_MAX_DLEN */ if (ccf->len != CAN_MAX_DLEN) return; /* do we have a valid len8_dlc value from 9 .. 15 ? */ if (ccf->len8_dlc > CAN_MAX_DLEN && ccf->len8_dlc <= CAN_MAX_RAW_DLC) ccf->len = ccf->len8_dlc; } /* convert valid CC DLC value in 'len' into struct can_frame elements */ static void mod_store_ccdlc(struct canfd_frame *cf) { struct can_frame *ccf = (struct can_frame *)cf; /* clear potential leftovers */ ccf->len8_dlc = 0; /* plain data length 0 .. 8 - that was easy */ if (ccf->len <= CAN_MAX_DLEN) return; /* potentially broken values are caught in can_can_gw_rcv() */ if (ccf->len > CAN_MAX_RAW_DLC) return; /* we have a valid dlc value from 9 .. 15 in ccf->len */ ccf->len8_dlc = ccf->len; ccf->len = CAN_MAX_DLEN; } static void mod_and_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_and_len(cf, mod); mod_store_ccdlc(cf); } static void mod_or_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_or_len(cf, mod); mod_store_ccdlc(cf); } static void mod_xor_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_retrieve_ccdlc(cf); mod_xor_len(cf, mod); mod_store_ccdlc(cf); } static void mod_set_ccdlc(struct canfd_frame *cf, struct cf_mod *mod) { mod_set_len(cf, mod); mod_store_ccdlc(cf); } static void canframecpy(struct canfd_frame *dst, struct can_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 3 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->len = src->len; *(u64 *)dst->data = *(u64 *)src->data; } static void canfdframecpy(struct canfd_frame *dst, struct canfd_frame *src) { /* Copy the struct members separately to ensure that no uninitialized * data are copied in the 2 bytes hole of the struct. This is needed * to make easy compares of the data in the struct cf_mod. */ dst->can_id = src->can_id; dst->flags = src->flags; dst->len = src->len; memcpy(dst->data, src->data, CANFD_MAX_DLEN); } static int cgw_chk_csum_parms(s8 fr, s8 to, s8 re, struct rtcanmsg *r) { s8 dlen = CAN_MAX_DLEN; if (r->flags & CGW_FLAGS_CAN_FD) dlen = CANFD_MAX_DLEN; /* absolute dlc values 0 .. 7 => 0 .. 7, e.g. data [0] * relative to received dlc -1 .. -8 : * e.g. for received dlc = 8 * -1 => index = 7 (data[7]) * -3 => index = 5 (data[5]) * -8 => index = 0 (data[0]) */ if (fr >= -dlen && fr < dlen && to >= -dlen && to < dlen && re >= -dlen && re < dlen) return 0; else return -EINVAL; } static inline int calc_idx(int idx, int rx_len) { if (idx < 0) return rx_len + idx; else return idx; } static void cgw_csum_xor_rel(struct canfd_frame *cf, struct cgw_csum_xor *xor) { int from = calc_idx(xor->from_idx, cf->len); int to = calc_idx(xor->to_idx, cf->len); int res = calc_idx(xor->result_idx, cf->len); u8 val = xor->init_xor_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = from; i <= to; i++) val ^= cf->data[i]; } else { for (i = from; i >= to; i--) val ^= cf->data[i]; } cf->data[res] = val; } static void cgw_csum_xor_pos(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i <= xor->to_idx; i++) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_xor_neg(struct canfd_frame *cf, struct cgw_csum_xor *xor) { u8 val = xor->init_xor_val; int i; for (i = xor->from_idx; i >= xor->to_idx; i--) val ^= cf->data[i]; cf->data[xor->result_idx] = val; } static void cgw_csum_crc8_rel(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { int from = calc_idx(crc8->from_idx, cf->len); int to = calc_idx(crc8->to_idx, cf->len); int res = calc_idx(crc8->result_idx, cf->len); u8 crc = crc8->init_crc_val; int i; if (from < 0 || to < 0 || res < 0) return; if (from <= to) { for (i = crc8->from_idx; i <= crc8->to_idx; i++) crc = crc8->crctab[crc ^ cf->data[i]]; } else { for (i = crc8->from_idx; i >= crc8->to_idx; i--) crc = crc8->crctab[crc ^ cf->data[i]]; } switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_pos(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i <= crc8->to_idx; i++) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } static void cgw_csum_crc8_neg(struct canfd_frame *cf, struct cgw_csum_crc8 *crc8) { u8 crc = crc8->init_crc_val; int i; for (i = crc8->from_idx; i >= crc8->to_idx; i--) crc = crc8->crctab[crc ^ cf->data[i]]; switch (crc8->profile) { case CGW_CRC8PRF_1U8: crc = crc8->crctab[crc ^ crc8->profile_data[0]]; break; case CGW_CRC8PRF_16U8: crc = crc8->crctab[crc ^ crc8->profile_data[cf->data[1] & 0xF]]; break; case CGW_CRC8PRF_SFFID_XOR: crc = crc8->crctab[crc ^ (cf->can_id & 0xFF) ^ (cf->can_id >> 8 & 0xFF)]; break; } cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val; } /* the receive & process & send function */ static void can_can_gw_rcv(struct sk_buff *skb, void *data) { struct cgw_job *gwj = (struct cgw_job *)data; struct canfd_frame *cf; struct sk_buff *nskb; int modidx = 0; /* process strictly Classic CAN or CAN FD frames */ if (gwj->flags & CGW_FLAGS_CAN_FD) { if (!can_is_canfd_skb(skb)) return; } else { if (!can_is_can_skb(skb)) return; } /* Do not handle CAN frames routed more than 'max_hops' times. * In general we should never catch this delimiter which is intended * to cover a misconfiguration protection (e.g. circular CAN routes). * * The Controller Area Network controllers only accept CAN frames with * correct CRCs - which are not visible in the controller registers. * According to skbuff.h documentation the csum_start element for IP * checksums is undefined/unused when ip_summed == CHECKSUM_UNNECESSARY. * Only CAN skbs can be processed here which already have this property. */ #define cgw_hops(skb) ((skb)->csum_start) BUG_ON(skb->ip_summed != CHECKSUM_UNNECESSARY); if (cgw_hops(skb) >= max_hops) { /* indicate deleted frames due to misconfiguration */ gwj->deleted_frames++; return; } if (!(gwj->dst.dev->flags & IFF_UP)) { gwj->dropped_frames++; return; } /* is sending the skb back to the incoming interface not allowed? */ if (!(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK) && can_skb_prv(skb)->ifindex == gwj->dst.dev->ifindex) return; /* clone the given skb, which has not been done in can_rcv() * * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. */ if (gwj->mod.modfunc[0]) nskb = skb_copy(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) { gwj->dropped_frames++; return; } /* put the incremented hop counter in the cloned skb */ cgw_hops(nskb) = cgw_hops(skb) + 1; /* first processing of this CAN frame -> adjust to private hop limit */ if (gwj->limit_hops && cgw_hops(nskb) == 1) cgw_hops(nskb) = max_hops - gwj->limit_hops + 1; nskb->dev = gwj->dst.dev; /* pointer to modifiable CAN frame */ cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); /* Has the CAN frame been modified? */ if (modidx) { /* get available space for the processed CAN frame type */ int max_len = nskb->len - offsetof(struct canfd_frame, data); /* dlc may have changed, make sure it fits to the CAN frame */ if (cf->len > max_len) { /* delete frame due to misconfiguration */ gwj->deleted_frames++; kfree_skb(nskb); return; } /* check for checksum updates */ if (gwj->mod.csumfunc.crc8) (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); } /* clear the skb timestamp if not configured the other way */ if (!(gwj->flags & CGW_FLAGS_CAN_SRC_TSTAMP)) nskb->tstamp = 0; /* send to netdevice */ if (can_send(nskb, gwj->flags & CGW_FLAGS_CAN_ECHO)) gwj->dropped_frames++; else gwj->handled_frames++; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) { return can_rx_register(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj, "gw", NULL); } static inline void cgw_unregister_filter(struct net *net, struct cgw_job *gwj) { can_rx_unregister(net, gwj->src.dev, gwj->ccgw.filter.can_id, gwj->ccgw.filter.can_mask, can_can_gw_rcv, gwj); } static void cgw_job_free_rcu(struct rcu_head *rcu_head) { struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu); kmem_cache_free(cgw_cache, gwj); } static int cgw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg == NETDEV_UNREGISTER) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } } return NOTIFY_DONE; } static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, u32 pid, u32 seq, int flags) { struct rtcanmsg *rtcan; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) return -EMSGSIZE; rtcan = nlmsg_data(nlh); rtcan->can_family = AF_CAN; rtcan->gwtype = gwj->gwtype; rtcan->flags = gwj->flags; /* add statistics if available */ if (gwj->handled_frames) { if (nla_put_u32(skb, CGW_HANDLED, gwj->handled_frames) < 0) goto cancel; } if (gwj->dropped_frames) { if (nla_put_u32(skb, CGW_DROPPED, gwj->dropped_frames) < 0) goto cancel; } if (gwj->deleted_frames) { if (nla_put_u32(skb, CGW_DELETED, gwj->deleted_frames) < 0) goto cancel; } /* check non default settings of attributes */ if (gwj->limit_hops) { if (nla_put_u8(skb, CGW_LIM_HOPS, gwj->limit_hops) < 0) goto cancel; } if (gwj->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (gwj->mod.modtype.and) { memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.and; if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.or) { memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.or; if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.xor) { memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.xor; if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.set) { memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.set; if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } else { struct cgw_frame_mod mb; if (gwj->mod.modtype.and) { memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.or) { memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.xor) { memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } if (gwj->mod.modtype.set) { memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); mb.modtype = gwj->mod.modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } if (gwj->mod.uid) { if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0) goto cancel; } if (gwj->mod.csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, &gwj->mod.csum.crc8) < 0) goto cancel; } if (gwj->mod.csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, &gwj->mod.csum.xor) < 0) goto cancel; } if (gwj->gwtype == CGW_TYPE_CAN_CAN) { if (gwj->ccgw.filter.can_id || gwj->ccgw.filter.can_mask) { if (nla_put(skb, CGW_FILTER, sizeof(struct can_filter), &gwj->ccgw.filter) < 0) goto cancel; } if (nla_put_u32(skb, CGW_SRC_IF, gwj->ccgw.src_idx) < 0) goto cancel; if (nla_put_u32(skb, CGW_DST_IF, gwj->ccgw.dst_idx) < 0) goto cancel; } nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } /* Dump information about all CAN gateway jobs, in response to RTM_GETROUTE */ static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; int idx = 0; int s_idx = cb->args[0]; rcu_read_lock(); hlist_for_each_entry_rcu(gwj, &net->can.cgw_list, list) { if (idx < s_idx) goto cont; if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) break; cont: idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static const struct nla_policy cgw_policy[CGW_MAX + 1] = { [CGW_MOD_AND] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_OR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_XOR] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_MOD_SET] = { .len = sizeof(struct cgw_frame_mod) }, [CGW_CS_XOR] = { .len = sizeof(struct cgw_csum_xor) }, [CGW_CS_CRC8] = { .len = sizeof(struct cgw_csum_crc8) }, [CGW_SRC_IF] = { .type = NLA_U32 }, [CGW_DST_IF] = { .type = NLA_U32 }, [CGW_FILTER] = { .len = sizeof(struct can_filter) }, [CGW_LIM_HOPS] = { .type = NLA_U8 }, [CGW_MOD_UID] = { .type = NLA_U32 }, [CGW_FDMOD_AND] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_OR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_XOR] = { .len = sizeof(struct cgw_fdframe_mod) }, [CGW_FDMOD_SET] = { .len = sizeof(struct cgw_fdframe_mod) }, }; /* check for common and gwtype specific attributes */ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod, u8 gwtype, void *gwtypeattr, u8 *limhops) { struct nlattr *tb[CGW_MAX + 1]; struct rtcanmsg *r = nlmsg_data(nlh); int modidx = 0; int err = 0; /* initialize modification & checksum data space */ memset(mod, 0, sizeof(*mod)); err = nlmsg_parse_deprecated(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX, cgw_policy, NULL); if (err < 0) return err; if (tb[CGW_LIM_HOPS]) { *limhops = nla_get_u8(tb[CGW_LIM_HOPS]); if (*limhops < 1 || *limhops > max_hops) return -EINVAL; } /* check for AND/OR/XOR/SET modifications */ if (r->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; if (tb[CGW_FDMOD_AND]) { nla_memcpy(&mb, tb[CGW_FDMOD_AND], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_and_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_and_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_fddata; } if (tb[CGW_FDMOD_OR]) { nla_memcpy(&mb, tb[CGW_FDMOD_OR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_or_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_or_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_fddata; } if (tb[CGW_FDMOD_XOR]) { nla_memcpy(&mb, tb[CGW_FDMOD_XOR], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_xor_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_xor_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_fddata; } if (tb[CGW_FDMOD_SET]) { nla_memcpy(&mb, tb[CGW_FDMOD_SET], CGW_FDMODATTR_LEN); canfdframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_LEN) mod->modfunc[modidx++] = mod_set_len; if (mb.modtype & CGW_MOD_FLAGS) mod->modfunc[modidx++] = mod_set_flags; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_fddata; } } else { struct cgw_frame_mod mb; if (tb[CGW_MOD_AND]) { nla_memcpy(&mb, tb[CGW_MOD_AND], CGW_MODATTR_LEN); canframecpy(&mod->modframe.and, &mb.cf); mod->modtype.and = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_and_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_and_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_and_data; } if (tb[CGW_MOD_OR]) { nla_memcpy(&mb, tb[CGW_MOD_OR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.or, &mb.cf); mod->modtype.or = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_or_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_or_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_or_data; } if (tb[CGW_MOD_XOR]) { nla_memcpy(&mb, tb[CGW_MOD_XOR], CGW_MODATTR_LEN); canframecpy(&mod->modframe.xor, &mb.cf); mod->modtype.xor = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_xor_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_xor_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_xor_data; } if (tb[CGW_MOD_SET]) { nla_memcpy(&mb, tb[CGW_MOD_SET], CGW_MODATTR_LEN); canframecpy(&mod->modframe.set, &mb.cf); mod->modtype.set = mb.modtype; if (mb.modtype & CGW_MOD_ID) mod->modfunc[modidx++] = mod_set_id; if (mb.modtype & CGW_MOD_DLC) mod->modfunc[modidx++] = mod_set_ccdlc; if (mb.modtype & CGW_MOD_DATA) mod->modfunc[modidx++] = mod_set_data; } } /* check for checksum operations after CAN frame modifications */ if (modidx) { if (tb[CGW_CS_CRC8]) { struct cgw_csum_crc8 *c = nla_data(tb[CGW_CS_CRC8]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.crc8, tb[CGW_CS_CRC8], CGW_CS_CRC8_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.crc8 = cgw_csum_crc8_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.crc8 = cgw_csum_crc8_pos; else mod->csumfunc.crc8 = cgw_csum_crc8_neg; } if (tb[CGW_CS_XOR]) { struct cgw_csum_xor *c = nla_data(tb[CGW_CS_XOR]); err = cgw_chk_csum_parms(c->from_idx, c->to_idx, c->result_idx, r); if (err) return err; nla_memcpy(&mod->csum.xor, tb[CGW_CS_XOR], CGW_CS_XOR_LEN); /* select dedicated processing function to reduce * runtime operations in receive hot path. */ if (c->from_idx < 0 || c->to_idx < 0 || c->result_idx < 0) mod->csumfunc.xor = cgw_csum_xor_rel; else if (c->from_idx <= c->to_idx) mod->csumfunc.xor = cgw_csum_xor_pos; else mod->csumfunc.xor = cgw_csum_xor_neg; } if (tb[CGW_MOD_UID]) nla_memcpy(&mod->uid, tb[CGW_MOD_UID], sizeof(u32)); } if (gwtype == CGW_TYPE_CAN_CAN) { /* check CGW_TYPE_CAN_CAN specific attributes */ struct can_can_gw *ccgw = (struct can_can_gw *)gwtypeattr; memset(ccgw, 0, sizeof(*ccgw)); /* check for can_filter in attributes */ if (tb[CGW_FILTER]) nla_memcpy(&ccgw->filter, tb[CGW_FILTER], sizeof(struct can_filter)); err = -ENODEV; /* specifying two interfaces is mandatory */ if (!tb[CGW_SRC_IF] || !tb[CGW_DST_IF]) return err; ccgw->src_idx = nla_get_u32(tb[CGW_SRC_IF]); ccgw->dst_idx = nla_get_u32(tb[CGW_DST_IF]); /* both indices set to 0 for flushing all routing entries */ if (!ccgw->src_idx && !ccgw->dst_idx) return 0; /* only one index set to 0 is an error */ if (!ccgw->src_idx || !ccgw->dst_idx) return err; } /* add the checks for other gwtypes here */ return 0; } static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct rtcanmsg *r; struct cgw_job *gwj; struct cf_mod mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) return err; if (mod.uid) { ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { if (gwj->mod.uid != mod.uid) continue; /* interfaces & filters must be identical */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) return -EINVAL; /* update modifications with disabled softirq & quit */ local_bh_disable(); memcpy(&gwj->mod, &mod, sizeof(mod)); local_bh_enable(); return 0; } } /* ifindex == 0 is not allowed for job creation */ if (!ccgw.src_idx || !ccgw.dst_idx) return -ENODEV; gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); if (!gwj) return -ENOMEM; gwj->handled_frames = 0; gwj->dropped_frames = 0; gwj->deleted_frames = 0; gwj->flags = r->flags; gwj->gwtype = r->gwtype; gwj->limit_hops = limhops; /* insert already parsed information */ memcpy(&gwj->mod, &mod, sizeof(mod)); memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw)); err = -ENODEV; gwj->src.dev = __dev_get_by_index(net, gwj->ccgw.src_idx); if (!gwj->src.dev) goto out; if (gwj->src.dev->type != ARPHRD_CAN) goto out; gwj->dst.dev = __dev_get_by_index(net, gwj->ccgw.dst_idx); if (!gwj->dst.dev) goto out; if (gwj->dst.dev->type != ARPHRD_CAN) goto out; /* is sending the skb back to the incoming interface intended? */ if (gwj->src.dev == gwj->dst.dev && !(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK)) { err = -EINVAL; goto out; } ASSERT_RTNL(); err = cgw_register_filter(net, gwj); if (!err) hlist_add_head_rcu(&gwj->list, &net->can.cgw_list); out: if (err) kmem_cache_free(cgw_cache, gwj); return err; } static void cgw_remove_all_jobs(struct net *net) { struct cgw_job *gwj = NULL; struct hlist_node *nx; ASSERT_RTNL(); hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); } } static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct cgw_job *gwj = NULL; struct hlist_node *nx; struct rtcanmsg *r; struct cf_mod mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (nlmsg_len(nlh) < sizeof(*r)) return -EINVAL; r = nlmsg_data(nlh); if (r->can_family != AF_CAN) return -EPFNOSUPPORT; /* so far we only support CAN -> CAN routings */ if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) return err; /* two interface indices both set to 0 => remove all entries */ if (!ccgw.src_idx && !ccgw.dst_idx) { cgw_remove_all_jobs(net); return 0; } err = -EINVAL; ASSERT_RTNL(); /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { if (gwj->flags != r->flags) continue; if (gwj->limit_hops != limhops) continue; /* we have a match when uid is enabled and identical */ if (gwj->mod.uid || mod.uid) { if (gwj->mod.uid != mod.uid) continue; } else { /* no uid => check for identical modifications */ if (memcmp(&gwj->mod, &mod, sizeof(mod))) continue; } /* if (r->gwtype == CGW_TYPE_CAN_CAN) - is made sure here */ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) continue; hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); call_rcu(&gwj->rcu, cgw_job_free_rcu); err = 0; break; } return err; } static int __net_init cangw_pernet_init(struct net *net) { INIT_HLIST_HEAD(&net->can.cgw_list); return 0; } static void __net_exit cangw_pernet_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) cgw_remove_all_jobs(net); rtnl_unlock(); } static struct pernet_operations cangw_pernet_ops = { .init = cangw_pernet_init, .exit_batch = cangw_pernet_exit_batch, }; static __init int cgw_module_init(void) { int ret; /* sanitize given module parameter */ max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS); pr_info("can: netlink gateway - max_hops=%d\n", max_hops); ret = register_pernet_subsys(&cangw_pernet_ops); if (ret) return ret; ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); if (!cgw_cache) goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; ret = register_netdevice_notifier(¬ifier); if (ret) goto out_register_notifier; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0); if (ret) goto out_rtnl_register1; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, cgw_create_job, NULL, 0); if (ret) goto out_rtnl_register2; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, cgw_remove_job, NULL, 0); if (ret) goto out_rtnl_register3; return 0; out_rtnl_register3: rtnl_unregister(PF_CAN, RTM_NEWROUTE); out_rtnl_register2: rtnl_unregister(PF_CAN, RTM_GETROUTE); out_rtnl_register1: unregister_netdevice_notifier(¬ifier); out_register_notifier: kmem_cache_destroy(cgw_cache); out_cache_create: unregister_pernet_subsys(&cangw_pernet_ops); return ret; } static __exit void cgw_module_exit(void) { rtnl_unregister_all(PF_CAN); unregister_netdevice_notifier(¬ifier); unregister_pernet_subsys(&cangw_pernet_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ kmem_cache_destroy(cgw_cache); } module_init(cgw_module_init); module_exit(cgw_module_exit); |
| 67 113 113 6 66 63 7 7 113 12 141 12 12 7 7 11 149 31 30 30 30 31 31 1 1 1 1 1 1 1 1 1 31 31 30 31 31 2 30 30 30 30 31 31 31 30 2 30 93 50 10 10 10 10 131 150 148 154 145 145 8 8 8 115 127 127 115 131 131 2 131 131 9 131 3 131 117 117 117 117 117 117 117 1 5 110 115 115 127 127 126 31 30 2 81 53 31 107 81 29 187 66 54 47 3 118 1 5 2 39 36 2 3 3 3 39 33 1 5 2 7 28 28 26 10 5 2 13 119 38 23 23 22 22 3 1 5 13 12 13 24 5 1 4 23 22 23 23 1 1 2 24 24 24 24 24 24 13 9 9 13 5 146 25 141 54 35 24 34 53 70 58 15 130 130 128 128 95 2 29 47 3 35 2 37 35 35 130 128 92 2 130 25 21 39 16 18 5 37 37 37 38 15 16 16 44 5 18 41 44 16 27 22 21 30 127 102 3 21 31 15 5 20 29 3 1 11 1 11 6 6 49 49 44 4 44 44 44 49 44 44 49 49 42 25 33 1 133 8 5 16 130 110 42 101 46 92 4 89 62 3 36 73 28 81 76 1 2 36 36 12 2 9 7 3 9 6 2 7 6 2 9 6 3 5 3 3 6 2 3 143 3 3 143 79 70 117 36 113 92 46 82 82 77 9 9 21 94 111 116 17 64 79 22 56 37 93 17 17 24 24 12 3 17 17 17 17 5 17 1 1 24 24 12 1 17 24 23 17 7 147 32 139 143 5 1 146 29 4 134 10 7 3 85 15 49 7 7 28 110 24 117 37 92 110 29 29 49 25 109 60 136 24 25 137 5 143 139 2 24 23 14 14 17 17 7 1 8 2 1 2 1 8 9 95 5 4 95 102 95 8 8 8 8 8 8 154 3 150 3 148 3 62 78 12 85 22 99 3 8 100 143 148 25 17 2 2 6 5 46 11 37 5 34 9 5 1 12 12 7 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2008 Oracle. All rights reserved. */ #include <linux/sched.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/list_sort.h> #include <linux/iversion.h> #include "misc.h" #include "ctree.h" #include "tree-log.h" #include "disk-io.h" #include "locking.h" #include "backref.h" #include "compression.h" #include "qgroup.h" #include "block-group.h" #include "space-info.h" #include "inode-item.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "root-tree.h" #include "dir-item.h" #include "file-item.h" #include "file.h" #include "orphan.h" #include "tree-checker.h" #define MAX_CONFLICT_INODES 10 /* magic values for the inode_only field in btrfs_log_inode: * * LOG_INODE_ALL means to log everything * LOG_INODE_EXISTS means to log just enough to recreate the inode * during log replay */ enum { LOG_INODE_ALL, LOG_INODE_EXISTS, }; /* * directory trouble cases * * 1) on rename or unlink, if the inode being unlinked isn't in the fsync * log, we must force a full commit before doing an fsync of the directory * where the unlink was done. * ---> record transid of last unlink/rename per directory * * mkdir foo/some_dir * normal commit * rename foo/some_dir foo2/some_dir * mkdir foo/some_dir * fsync foo/some_dir/some_file * * The fsync above will unlink the original some_dir without recording * it in its new location (foo2). After a crash, some_dir will be gone * unless the fsync of some_file forces a full commit * * 2) we must log any new names for any file or dir that is in the fsync * log. ---> check inode while renaming/linking. * * 2a) we must log any new names for any file or dir during rename * when the directory they are being removed from was logged. * ---> check inode and old parent dir during rename * * 2a is actually the more important variant. With the extra logging * a crash might unlink the old name without recreating the new one * * 3) after a crash, we must go through any directories with a link count * of zero and redo the rm -rf * * mkdir f1/foo * normal commit * rm -rf f1/foo * fsync(f1) * * The directory f1 was fully removed from the FS, but fsync was never * called on f1, only its parent dir. After a crash the rm -rf must * be replayed. This must be able to recurse down the entire * directory tree. The inode link count fixup code takes care of the * ugly details. */ /* * stages for the tree walking. The first * stage (0) is to only pin down the blocks we find * the second stage (1) is to make sure that all the inodes * we find in the log are created in the subvolume. * * The last stage is to deal with directories and links and extents * and all the other fun semantics */ enum { LOG_WALK_PIN_ONLY, LOG_WALK_REPLAY_INODES, LOG_WALK_REPLAY_DIR_INDEX, LOG_WALK_REPLAY_ALL, }; static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, int inode_only, struct btrfs_log_ctx *ctx); static int link_to_fixup_dir(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 objectid); static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, int del_all); static void wait_log_commit(struct btrfs_root *root, int transid); /* * tree logging is a special write ahead log used to make sure that * fsyncs and O_SYNCs can happen without doing full tree commits. * * Full tree commits are expensive because they require commonly * modified blocks to be recowed, creating many dirty pages in the * extent tree an 4x-6x higher write load than ext3. * * Instead of doing a tree commit on every fsync, we use the * key ranges and transaction ids to find items for a given file or directory * that have changed in this transaction. Those items are copied into * a special tree (one per subvolume root), that tree is written to disk * and then the fsync is considered complete. * * After a crash, items are copied out of the log-tree back into the * subvolume tree. Any file data extents found are recorded in the extent * allocation tree, and the log-tree freed. * * The log tree is read three times, once to pin down all the extents it is * using in ram and once, once to create all the inodes logged in the tree * and once to do all the other items. */ static struct inode *btrfs_iget_logging(u64 objectid, struct btrfs_root *root) { unsigned int nofs_flag; struct inode *inode; /* * We're holding a transaction handle whether we are logging or * replaying a log tree, so we must make sure NOFS semantics apply * because btrfs_alloc_inode() may be triggered and it uses GFP_KERNEL * to allocate an inode, which can recurse back into the filesystem and * attempt a transaction commit, resulting in a deadlock. */ nofs_flag = memalloc_nofs_save(); inode = btrfs_iget(objectid, root); memalloc_nofs_restore(nofs_flag); return inode; } /* * start a sub transaction and setup the log tree * this increments the log tree writer count to make the people * syncing the tree wait for us to finish */ static int start_log_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *tree_root = fs_info->tree_root; const bool zoned = btrfs_is_zoned(fs_info); int ret = 0; bool created = false; /* * First check if the log root tree was already created. If not, create * it before locking the root's log_mutex, just to keep lockdep happy. */ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state)) { mutex_lock(&tree_root->log_mutex); if (!fs_info->log_root_tree) { ret = btrfs_init_log_root_tree(trans, fs_info); if (!ret) { set_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state); created = true; } } mutex_unlock(&tree_root->log_mutex); if (ret) return ret; } mutex_lock(&root->log_mutex); again: if (root->log_root) { int index = (root->log_transid + 1) % 2; if (btrfs_need_log_full_commit(trans)) { ret = BTRFS_LOG_FORCE_COMMIT; goto out; } if (zoned && atomic_read(&root->log_commit[index])) { wait_log_commit(root, root->log_transid - 1); goto again; } if (!root->log_start_pid) { clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } else if (root->log_start_pid != current->pid) { set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); } } else { /* * This means fs_info->log_root_tree was already created * for some other FS trees. Do the full commit not to mix * nodes from multiple log transactions to do sequential * writing. */ if (zoned && !created) { ret = BTRFS_LOG_FORCE_COMMIT; goto out; } ret = btrfs_add_log_tree(trans, root); if (ret) goto out; set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } atomic_inc(&root->log_writers); if (!ctx->logging_new_name) { int index = root->log_transid % 2; list_add_tail(&ctx->list, &root->log_ctxs[index]); ctx->log_transid = root->log_transid; } out: mutex_unlock(&root->log_mutex); return ret; } /* * returns 0 if there was a log transaction running and we were able * to join, or returns -ENOENT if there were not transactions * in progress */ static int join_running_log_trans(struct btrfs_root *root) { const bool zoned = btrfs_is_zoned(root->fs_info); int ret = -ENOENT; if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) return ret; mutex_lock(&root->log_mutex); again: if (root->log_root) { int index = (root->log_transid + 1) % 2; ret = 0; if (zoned && atomic_read(&root->log_commit[index])) { wait_log_commit(root, root->log_transid - 1); goto again; } atomic_inc(&root->log_writers); } mutex_unlock(&root->log_mutex); return ret; } /* * This either makes the current running log transaction wait * until you call btrfs_end_log_trans() or it makes any future * log transactions wait until you call btrfs_end_log_trans() */ void btrfs_pin_log_trans(struct btrfs_root *root) { atomic_inc(&root->log_writers); } /* * indicate we're done making changes to the log tree * and wake up anyone waiting to do a sync */ void btrfs_end_log_trans(struct btrfs_root *root) { if (atomic_dec_and_test(&root->log_writers)) { /* atomic_dec_and_test implies a barrier */ cond_wake_up_nomb(&root->log_writer_wait); } } /* * the walk control struct is used to pass state down the chain when * processing the log tree. The stage field tells us which part * of the log tree processing we are currently doing. The others * are state fields used for that specific part */ struct walk_control { /* should we free the extent on disk when done? This is used * at transaction commit time while freeing a log tree */ int free; /* pin only walk, we record which extents on disk belong to the * log trees */ int pin; /* what stage of the replay code we're currently in */ int stage; /* * Ignore any items from the inode currently being processed. Needs * to be set every time we find a BTRFS_INODE_ITEM_KEY and we are in * the LOG_WALK_REPLAY_INODES stage. */ bool ignore_cur_inode; /* the root we are currently replaying */ struct btrfs_root *replay_dest; /* the trans handle for the current replay */ struct btrfs_trans_handle *trans; /* the function that gets used to process blocks we find in the * tree. Note the extent_buffer might not be up to date when it is * passed in, and it must be checked or read if you need the data * inside it */ int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level); }; /* * process_func used to pin down extents, write them or wait on them */ static int process_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level) { struct btrfs_fs_info *fs_info = log->fs_info; int ret = 0; /* * If this fs is mixed then we need to be able to process the leaves to * pin down any logged extents, so we have to read the block. */ if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) { struct btrfs_tree_parent_check check = { .level = level, .transid = gen }; ret = btrfs_read_extent_buffer(eb, &check); if (ret) return ret; } if (wc->pin) { ret = btrfs_pin_extent_for_log_replay(wc->trans, eb); if (ret) return ret; if (btrfs_buffer_uptodate(eb, gen, 0) && btrfs_header_level(eb) == 0) ret = btrfs_exclude_logged_extents(eb); } return ret; } /* * Item overwrite used by replay and tree logging. eb, slot and key all refer * to the src data we are copying out. * * root is the tree we are copying into, and path is a scratch * path for use in this function (it should be released on entry and * will be released on exit). * * If the key is already in the destination tree the existing item is * overwritten. If the existing item isn't big enough, it is extended. * If it is too large, it is truncated. * * If the key isn't in the destination yet, a new item is inserted. */ static int overwrite_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { int ret; u32 item_size; u64 saved_i_size = 0; int save_old_i_size = 0; unsigned long src_ptr; unsigned long dst_ptr; bool inode_item = key->type == BTRFS_INODE_ITEM_KEY; /* * This is only used during log replay, so the root is always from a * fs/subvolume tree. In case we ever need to support a log root, then * we'll have to clone the leaf in the path, release the path and use * the leaf before writing into the log tree. See the comments at * copy_items() for more details. */ ASSERT(btrfs_root_id(root) != BTRFS_TREE_LOG_OBJECTID); item_size = btrfs_item_size(eb, slot); src_ptr = btrfs_item_ptr_offset(eb, slot); /* Look for the key in the destination tree. */ ret = btrfs_search_slot(NULL, root, key, path, 0, 0); if (ret < 0) return ret; if (ret == 0) { char *src_copy; char *dst_copy; u32 dst_size = btrfs_item_size(path->nodes[0], path->slots[0]); if (dst_size != item_size) goto insert; if (item_size == 0) { btrfs_release_path(path); return 0; } dst_copy = kmalloc(item_size, GFP_NOFS); src_copy = kmalloc(item_size, GFP_NOFS); if (!dst_copy || !src_copy) { btrfs_release_path(path); kfree(dst_copy); kfree(src_copy); return -ENOMEM; } read_extent_buffer(eb, src_copy, src_ptr, item_size); dst_ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); read_extent_buffer(path->nodes[0], dst_copy, dst_ptr, item_size); ret = memcmp(dst_copy, src_copy, item_size); kfree(dst_copy); kfree(src_copy); /* * they have the same contents, just return, this saves * us from cowing blocks in the destination tree and doing * extra writes that may not have been done by a previous * sync */ if (ret == 0) { btrfs_release_path(path); return 0; } /* * We need to load the old nbytes into the inode so when we * replay the extents we've logged we get the right nbytes. */ if (inode_item) { struct btrfs_inode_item *item; u64 nbytes; u32 mode; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); nbytes = btrfs_inode_nbytes(path->nodes[0], item); item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, nbytes); /* * If this is a directory we need to reset the i_size to * 0 so that we can set it up properly when replaying * the rest of the items in this log. */ mode = btrfs_inode_mode(eb, item); if (S_ISDIR(mode)) btrfs_set_inode_size(eb, item, 0); } } else if (inode_item) { struct btrfs_inode_item *item; u32 mode; /* * New inode, set nbytes to 0 so that the nbytes comes out * properly when we replay the extents. */ item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, 0); /* * If this is a directory we need to reset the i_size to 0 so * that we can set it up properly when replaying the rest of * the items in this log. */ mode = btrfs_inode_mode(eb, item); if (S_ISDIR(mode)) btrfs_set_inode_size(eb, item, 0); } insert: btrfs_release_path(path); /* try to insert the key into the destination tree */ path->skip_release_on_error = 1; ret = btrfs_insert_empty_item(trans, root, path, key, item_size); path->skip_release_on_error = 0; /* make sure any existing item is the correct size */ if (ret == -EEXIST || ret == -EOVERFLOW) { u32 found_size; found_size = btrfs_item_size(path->nodes[0], path->slots[0]); if (found_size > item_size) btrfs_truncate_item(trans, path, item_size, 1); else if (found_size < item_size) btrfs_extend_item(trans, path, item_size - found_size); } else if (ret) { return ret; } dst_ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); /* don't overwrite an existing inode if the generation number * was logged as zero. This is done when the tree logging code * is just logging an inode to make sure it exists after recovery. * * Also, don't overwrite i_size on directories during replay. * log replay inserts and removes directory items based on the * state of the tree found in the subvolume, and i_size is modified * as it goes */ if (key->type == BTRFS_INODE_ITEM_KEY && ret == -EEXIST) { struct btrfs_inode_item *src_item; struct btrfs_inode_item *dst_item; src_item = (struct btrfs_inode_item *)src_ptr; dst_item = (struct btrfs_inode_item *)dst_ptr; if (btrfs_inode_generation(eb, src_item) == 0) { struct extent_buffer *dst_eb = path->nodes[0]; const u64 ino_size = btrfs_inode_size(eb, src_item); /* * For regular files an ino_size == 0 is used only when * logging that an inode exists, as part of a directory * fsync, and the inode wasn't fsynced before. In this * case don't set the size of the inode in the fs/subvol * tree, otherwise we would be throwing valid data away. */ if (S_ISREG(btrfs_inode_mode(eb, src_item)) && S_ISREG(btrfs_inode_mode(dst_eb, dst_item)) && ino_size != 0) btrfs_set_inode_size(dst_eb, dst_item, ino_size); goto no_copy; } if (S_ISDIR(btrfs_inode_mode(eb, src_item)) && S_ISDIR(btrfs_inode_mode(path->nodes[0], dst_item))) { save_old_i_size = 1; saved_i_size = btrfs_inode_size(path->nodes[0], dst_item); } } copy_extent_buffer(path->nodes[0], eb, dst_ptr, src_ptr, item_size); if (save_old_i_size) { struct btrfs_inode_item *dst_item; dst_item = (struct btrfs_inode_item *)dst_ptr; btrfs_set_inode_size(path->nodes[0], dst_item, saved_i_size); } /* make sure the generation is filled in */ if (key->type == BTRFS_INODE_ITEM_KEY) { struct btrfs_inode_item *dst_item; dst_item = (struct btrfs_inode_item *)dst_ptr; if (btrfs_inode_generation(path->nodes[0], dst_item) == 0) { btrfs_set_inode_generation(path->nodes[0], dst_item, trans->transid); } } no_copy: btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } static int read_alloc_one_name(struct extent_buffer *eb, void *start, int len, struct fscrypt_str *name) { char *buf; buf = kmalloc(len, GFP_NOFS); if (!buf) return -ENOMEM; read_extent_buffer(eb, buf, (unsigned long)start, len); name->name = buf; name->len = len; return 0; } /* * simple helper to read an inode off the disk from a given root * This can only be called for subvolume roots and not for the log */ static noinline struct inode *read_one_inode(struct btrfs_root *root, u64 objectid) { struct inode *inode; inode = btrfs_iget_logging(objectid, root); if (IS_ERR(inode)) inode = NULL; return inode; } /* replays a single extent in 'eb' at 'slot' with 'key' into the * subvolume 'root'. path is released on entry and should be released * on exit. * * extents in the log tree have not been allocated out of the extent * tree yet. So, this completes the allocation, taking a reference * as required if the extent already exists or creating a new extent * if it isn't in the extent allocation tree yet. * * The extent is inserted into the file, dropping any existing extents * from the file that overlap the new one. */ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_fs_info *fs_info = root->fs_info; int found_type; u64 extent_end; u64 start = key->offset; u64 nbytes = 0; struct btrfs_file_extent_item *item; struct inode *inode = NULL; unsigned long size; int ret = 0; item = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); found_type = btrfs_file_extent_type(eb, item); if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { nbytes = btrfs_file_extent_num_bytes(eb, item); extent_end = start + nbytes; /* * We don't add to the inodes nbytes if we are prealloc or a * hole. */ if (btrfs_file_extent_disk_bytenr(eb, item) == 0) nbytes = 0; } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { size = btrfs_file_extent_ram_bytes(eb, item); nbytes = btrfs_file_extent_ram_bytes(eb, item); extent_end = ALIGN(start + size, fs_info->sectorsize); } else { ret = 0; goto out; } inode = read_one_inode(root, key->objectid); if (!inode) { ret = -EIO; goto out; } /* * first check to see if we already have this extent in the * file. This must be done before the btrfs_drop_extents run * so we don't try to drop this extent. */ ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(BTRFS_I(inode)), start, 0); if (ret == 0 && (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC)) { struct btrfs_file_extent_item cmp1; struct btrfs_file_extent_item cmp2; struct btrfs_file_extent_item *existing; struct extent_buffer *leaf; leaf = path->nodes[0]; existing = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); read_extent_buffer(eb, &cmp1, (unsigned long)item, sizeof(cmp1)); read_extent_buffer(leaf, &cmp2, (unsigned long)existing, sizeof(cmp2)); /* * we already have a pointer to this exact extent, * we don't have to do anything */ if (memcmp(&cmp1, &cmp2, sizeof(cmp1)) == 0) { btrfs_release_path(path); goto out; } } btrfs_release_path(path); /* drop any overlapping extents */ drop_args.start = start; drop_args.end = extent_end; drop_args.drop_cache = true; ret = btrfs_drop_extents(trans, root, BTRFS_I(inode), &drop_args); if (ret) goto out; if (found_type == BTRFS_FILE_EXTENT_REG || found_type == BTRFS_FILE_EXTENT_PREALLOC) { u64 offset; unsigned long dest_offset; struct btrfs_key ins; if (btrfs_file_extent_disk_bytenr(eb, item) == 0 && btrfs_fs_incompat(fs_info, NO_HOLES)) goto update_inode; ret = btrfs_insert_empty_item(trans, root, path, key, sizeof(*item)); if (ret) goto out; dest_offset = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); copy_extent_buffer(path->nodes[0], eb, dest_offset, (unsigned long)item, sizeof(*item)); ins.objectid = btrfs_file_extent_disk_bytenr(eb, item); ins.offset = btrfs_file_extent_disk_num_bytes(eb, item); ins.type = BTRFS_EXTENT_ITEM_KEY; offset = key->offset - btrfs_file_extent_offset(eb, item); /* * Manually record dirty extent, as here we did a shallow * file extent item copy and skip normal backref update, * but modifying extent tree all by ourselves. * So need to manually record dirty extent for qgroup, * as the owner of the file extent changed from log tree * (doesn't affect qgroup) to fs/file tree(affects qgroup) */ ret = btrfs_qgroup_trace_extent(trans, btrfs_file_extent_disk_bytenr(eb, item), btrfs_file_extent_disk_num_bytes(eb, item)); if (ret < 0) goto out; if (ins.objectid > 0) { u64 csum_start; u64 csum_end; LIST_HEAD(ordered_sums); /* * is this extent already allocated in the extent * allocation tree? If so, just add a reference */ ret = btrfs_lookup_data_extent(fs_info, ins.objectid, ins.offset); if (ret < 0) { goto out; } else if (ret == 0) { struct btrfs_ref ref = { .action = BTRFS_ADD_DELAYED_REF, .bytenr = ins.objectid, .num_bytes = ins.offset, .owning_root = btrfs_root_id(root), .ref_root = btrfs_root_id(root), }; btrfs_init_data_ref(&ref, key->objectid, offset, 0, false); ret = btrfs_inc_extent_ref(trans, &ref); if (ret) goto out; } else { /* * insert the extent pointer in the extent * allocation tree */ ret = btrfs_alloc_logged_file_extent(trans, btrfs_root_id(root), key->objectid, offset, &ins); if (ret) goto out; } btrfs_release_path(path); if (btrfs_file_extent_compression(eb, item)) { csum_start = ins.objectid; csum_end = csum_start + ins.offset; } else { csum_start = ins.objectid + btrfs_file_extent_offset(eb, item); csum_end = csum_start + btrfs_file_extent_num_bytes(eb, item); } ret = btrfs_lookup_csums_list(root->log_root, csum_start, csum_end - 1, &ordered_sums, false); if (ret < 0) goto out; ret = 0; /* * Now delete all existing cums in the csum root that * cover our range. We do this because we can have an * extent that is completely referenced by one file * extent item and partially referenced by another * file extent item (like after using the clone or * extent_same ioctls). In this case if we end up doing * the replay of the one that partially references the * extent first, and we do not do the csum deletion * below, we can get 2 csum items in the csum tree that * overlap each other. For example, imagine our log has * the two following file extent items: * * key (257 EXTENT_DATA 409600) * extent data disk byte 12845056 nr 102400 * extent data offset 20480 nr 20480 ram 102400 * * key (257 EXTENT_DATA 819200) * extent data disk byte 12845056 nr 102400 * extent data offset 0 nr 102400 ram 102400 * * Where the second one fully references the 100K extent * that starts at disk byte 12845056, and the log tree * has a single csum item that covers the entire range * of the extent: * * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100 * * After the first file extent item is replayed, the * csum tree gets the following csum item: * * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20 * * Which covers the 20K sub-range starting at offset 20K * of our extent. Now when we replay the second file * extent item, if we do not delete existing csum items * that cover any of its blocks, we end up getting two * csum items in our csum tree that overlap each other: * * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100 * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20 * * Which is a problem, because after this anyone trying * to lookup up for the checksum of any block of our * extent starting at an offset of 40K or higher, will * end up looking at the second csum item only, which * does not contain the checksum for any block starting * at offset 40K or higher of our extent. */ while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums; struct btrfs_root *csum_root; sums = list_entry(ordered_sums.next, struct btrfs_ordered_sum, list); csum_root = btrfs_csum_root(fs_info, sums->logical); if (!ret) ret = btrfs_del_csums(trans, csum_root, sums->logical, sums->len); if (!ret) ret = btrfs_csum_file_blocks(trans, csum_root, sums); list_del(&sums->list); kfree(sums); } if (ret) goto out; } else { btrfs_release_path(path); } } else if (found_type == BTRFS_FILE_EXTENT_INLINE) { /* inline extents are easy, we just overwrite them */ ret = overwrite_item(trans, root, path, eb, slot, key); if (ret) goto out; } ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), start, extent_end - start); if (ret) goto out; update_inode: btrfs_update_inode_bytes(BTRFS_I(inode), nbytes, drop_args.bytes_found); ret = btrfs_update_inode(trans, BTRFS_I(inode)); out: iput(inode); return ret; } static int unlink_inode_for_log_replay(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, const struct fscrypt_str *name) { int ret; ret = btrfs_unlink_inode(trans, dir, inode, name); if (ret) return ret; /* * Whenever we need to check if a name exists or not, we check the * fs/subvolume tree. So after an unlink we must run delayed items, so * that future checks for a name during log replay see that the name * does not exists anymore. */ return btrfs_run_delayed_items(trans); } /* * when cleaning up conflicts between the directory names in the * subvolume, directory names in the log and directory names in the * inode back references, we may have to unlink inodes from directories. * * This is a helper function to do the unlink of a specific directory * item */ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_inode *dir, struct btrfs_dir_item *di) { struct btrfs_root *root = dir->root; struct inode *inode; struct fscrypt_str name; struct extent_buffer *leaf; struct btrfs_key location; int ret; leaf = path->nodes[0]; btrfs_dir_item_key_to_cpu(leaf, di, &location); ret = read_alloc_one_name(leaf, di + 1, btrfs_dir_name_len(leaf, di), &name); if (ret) return -ENOMEM; btrfs_release_path(path); inode = read_one_inode(root, location.objectid); if (!inode) { ret = -EIO; goto out; } ret = link_to_fixup_dir(trans, root, path, location.objectid); if (ret) goto out; ret = unlink_inode_for_log_replay(trans, dir, BTRFS_I(inode), &name); out: kfree(name.name); iput(inode); return ret; } /* * See if a given name and sequence number found in an inode back reference are * already in a directory and correctly point to this inode. * * Returns: < 0 on error, 0 if the directory entry does not exists and 1 if it * exists. */ static noinline int inode_in_dir(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 objectid, u64 index, struct fscrypt_str *name) { struct btrfs_dir_item *di; struct btrfs_key location; int ret = 0; di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid != objectid) goto out; } else { goto out; } btrfs_release_path(path); di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, 0); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid == objectid) ret = 1; } out: btrfs_release_path(path); return ret; } /* * helper function to check a log tree for a named back reference in * an inode. This is used to decide if a back reference that is * found in the subvolume conflicts with what we find in the log. * * inode backreferences may have multiple refs in a single item, * during replay we process one reference at a time, and we don't * want to delete valid links to a file from the subvolume if that * link is also in the log. */ static noinline int backref_in_log(struct btrfs_root *log, struct btrfs_key *key, u64 ref_objectid, const struct fscrypt_str *name) { struct btrfs_path *path; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = btrfs_search_slot(NULL, log, key, path, 0, 0); if (ret < 0) { goto out; } else if (ret == 1) { ret = 0; goto out; } if (key->type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], ref_objectid, name); else ret = !!btrfs_find_name_in_backref(path->nodes[0], path->slots[0], name); out: btrfs_free_path(path); return ret; } static inline int __add_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_root *log_root, struct btrfs_inode *dir, struct btrfs_inode *inode, u64 inode_objectid, u64 parent_objectid, u64 ref_index, struct fscrypt_str *name) { int ret; struct extent_buffer *leaf; struct btrfs_dir_item *di; struct btrfs_key search_key; struct btrfs_inode_extref *extref; again: /* Search old style refs */ search_key.objectid = inode_objectid; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = parent_objectid; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret == 0) { struct btrfs_inode_ref *victim_ref; unsigned long ptr; unsigned long ptr_end; leaf = path->nodes[0]; /* are we trying to overwrite a back ref for the root directory * if so, just jump out, we're done */ if (search_key.objectid == search_key.offset) return 1; /* check all the names in this back reference to see * if they are in the log. if so, we allow them to stay * otherwise they must be unlinked as a conflict */ ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); ptr_end = ptr + btrfs_item_size(leaf, path->slots[0]); while (ptr < ptr_end) { struct fscrypt_str victim_name; victim_ref = (struct btrfs_inode_ref *)ptr; ret = read_alloc_one_name(leaf, (victim_ref + 1), btrfs_inode_ref_name_len(leaf, victim_ref), &victim_name); if (ret) return ret; ret = backref_in_log(log_root, &search_key, parent_objectid, &victim_name); if (ret < 0) { kfree(victim_name.name); return ret; } else if (!ret) { inc_nlink(&inode->vfs_inode); btrfs_release_path(path); ret = unlink_inode_for_log_replay(trans, dir, inode, &victim_name); kfree(victim_name.name); if (ret) return ret; goto again; } kfree(victim_name.name); ptr = (unsigned long)(victim_ref + 1) + victim_name.len; } } btrfs_release_path(path); /* Same search but for extended refs */ extref = btrfs_lookup_inode_extref(NULL, root, path, name, inode_objectid, parent_objectid, 0, 0); if (IS_ERR(extref)) { return PTR_ERR(extref); } else if (extref) { u32 item_size; u32 cur_offset = 0; unsigned long base; struct inode *victim_parent; leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); base = btrfs_item_ptr_offset(leaf, path->slots[0]); while (cur_offset < item_size) { struct fscrypt_str victim_name; extref = (struct btrfs_inode_extref *)(base + cur_offset); if (btrfs_inode_extref_parent(leaf, extref) != parent_objectid) goto next; ret = read_alloc_one_name(leaf, &extref->name, btrfs_inode_extref_name_len(leaf, extref), &victim_name); if (ret) return ret; search_key.objectid = inode_objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; search_key.offset = btrfs_extref_hash(parent_objectid, victim_name.name, victim_name.len); ret = backref_in_log(log_root, &search_key, parent_objectid, &victim_name); if (ret < 0) { kfree(victim_name.name); return ret; } else if (!ret) { ret = -ENOENT; victim_parent = read_one_inode(root, parent_objectid); if (victim_parent) { inc_nlink(&inode->vfs_inode); btrfs_release_path(path); ret = unlink_inode_for_log_replay(trans, BTRFS_I(victim_parent), inode, &victim_name); } iput(victim_parent); kfree(victim_name.name); if (ret) return ret; goto again; } kfree(victim_name.name); next: cur_offset += victim_name.len + sizeof(*extref); } } btrfs_release_path(path); /* look for a conflicting sequence number */ di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), ref_index, name, 0); if (IS_ERR(di)) { return PTR_ERR(di); } else if (di) { ret = drop_one_dir_item(trans, path, dir, di); if (ret) return ret; } btrfs_release_path(path); /* look for a conflicting name */ di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), name, 0); if (IS_ERR(di)) { return PTR_ERR(di); } else if (di) { ret = drop_one_dir_item(trans, path, dir, di); if (ret) return ret; } btrfs_release_path(path); return 0; } static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, struct fscrypt_str *name, u64 *index, u64 *parent_objectid) { struct btrfs_inode_extref *extref; int ret; extref = (struct btrfs_inode_extref *)ref_ptr; ret = read_alloc_one_name(eb, &extref->name, btrfs_inode_extref_name_len(eb, extref), name); if (ret) return ret; if (index) *index = btrfs_inode_extref_index(eb, extref); if (parent_objectid) *parent_objectid = btrfs_inode_extref_parent(eb, extref); return 0; } static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, struct fscrypt_str *name, u64 *index) { struct btrfs_inode_ref *ref; int ret; ref = (struct btrfs_inode_ref *)ref_ptr; ret = read_alloc_one_name(eb, ref + 1, btrfs_inode_ref_name_len(eb, ref), name); if (ret) return ret; if (index) *index = btrfs_inode_ref_index(eb, ref); return 0; } /* * Take an inode reference item from the log tree and iterate all names from the * inode reference item in the subvolume tree with the same key (if it exists). * For any name that is not in the inode reference item from the log tree, do a * proper unlink of that name (that is, remove its entry from the inode * reference item and both dir index keys). */ static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_inode *inode, struct extent_buffer *log_eb, int log_slot, struct btrfs_key *key) { int ret; unsigned long ref_ptr; unsigned long ref_end; struct extent_buffer *eb; again: btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, key, path, 0, 0); if (ret > 0) { ret = 0; goto out; } if (ret < 0) goto out; eb = path->nodes[0]; ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]); ref_end = ref_ptr + btrfs_item_size(eb, path->slots[0]); while (ref_ptr < ref_end) { struct fscrypt_str name; u64 parent_id; if (key->type == BTRFS_INODE_EXTREF_KEY) { ret = extref_get_fields(eb, ref_ptr, &name, NULL, &parent_id); } else { parent_id = key->offset; ret = ref_get_fields(eb, ref_ptr, &name, NULL); } if (ret) goto out; if (key->type == BTRFS_INODE_EXTREF_KEY) ret = !!btrfs_find_name_in_ext_backref(log_eb, log_slot, parent_id, &name); else ret = !!btrfs_find_name_in_backref(log_eb, log_slot, &name); if (!ret) { struct inode *dir; btrfs_release_path(path); dir = read_one_inode(root, parent_id); if (!dir) { ret = -ENOENT; kfree(name.name); goto out; } ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), inode, &name); kfree(name.name); iput(dir); if (ret) goto out; goto again; } kfree(name.name); ref_ptr += name.len; if (key->type == BTRFS_INODE_EXTREF_KEY) ref_ptr += sizeof(struct btrfs_inode_extref); else ref_ptr += sizeof(struct btrfs_inode_ref); } ret = 0; out: btrfs_release_path(path); return ret; } /* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. * root is the destination we are replaying into, and path is for temp * use by this function. (it should be released on return). */ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { struct inode *dir = NULL; struct inode *inode = NULL; unsigned long ref_ptr; unsigned long ref_end; struct fscrypt_str name; int ret; int log_ref_ver = 0; u64 parent_objectid; u64 inode_objectid; u64 ref_index = 0; int ref_struct_size; ref_ptr = btrfs_item_ptr_offset(eb, slot); ref_end = ref_ptr + btrfs_item_size(eb, slot); if (key->type == BTRFS_INODE_EXTREF_KEY) { struct btrfs_inode_extref *r; ref_struct_size = sizeof(struct btrfs_inode_extref); log_ref_ver = 1; r = (struct btrfs_inode_extref *)ref_ptr; parent_objectid = btrfs_inode_extref_parent(eb, r); } else { ref_struct_size = sizeof(struct btrfs_inode_ref); parent_objectid = key->offset; } inode_objectid = key->objectid; /* * it is possible that we didn't log all the parent directories * for a given inode. If we don't find the dir, just don't * copy the back ref in. The link count fixup code will take * care of the rest */ dir = read_one_inode(root, parent_objectid); if (!dir) { ret = -ENOENT; goto out; } inode = read_one_inode(root, inode_objectid); if (!inode) { ret = -EIO; goto out; } while (ref_ptr < ref_end) { if (log_ref_ver) { ret = extref_get_fields(eb, ref_ptr, &name, &ref_index, &parent_objectid); /* * parent object can change from one array * item to another. */ if (!dir) dir = read_one_inode(root, parent_objectid); if (!dir) { ret = -ENOENT; goto out; } } else { ret = ref_get_fields(eb, ref_ptr, &name, &ref_index); } if (ret) goto out; ret = inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), btrfs_ino(BTRFS_I(inode)), ref_index, &name); if (ret < 0) { goto out; } else if (ret == 0) { /* * look for a conflicting back reference in the * metadata. if we find one we have to unlink that name * of the file before we add our new link. Later on, we * overwrite any existing back reference, and we don't * want to create dangling pointers in the directory. */ ret = __add_inode_ref(trans, root, path, log, BTRFS_I(dir), BTRFS_I(inode), inode_objectid, parent_objectid, ref_index, &name); if (ret) { if (ret == 1) ret = 0; goto out; } /* insert our name */ ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), &name, 0, ref_index); if (ret) goto out; ret = btrfs_update_inode(trans, BTRFS_I(inode)); if (ret) goto out; } /* Else, ret == 1, we already have a perfect match, we're done. */ ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + name.len; kfree(name.name); name.name = NULL; if (log_ref_ver) { iput(dir); dir = NULL; } } /* * Before we overwrite the inode reference item in the subvolume tree * with the item from the log tree, we must unlink all names from the * parent directory that are in the subvolume's tree inode reference * item, otherwise we end up with an inconsistent subvolume tree where * dir index entries exist for a name but there is no inode reference * item with the same name. */ ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot, key); if (ret) goto out; /* finally write the back reference in the inode */ ret = overwrite_item(trans, root, path, eb, slot, key); out: btrfs_release_path(path); kfree(name.name); iput(dir); iput(inode); return ret; } static int count_inode_extrefs(struct btrfs_inode *inode, struct btrfs_path *path) { int ret = 0; int name_len; unsigned int nlink = 0; u32 item_size; u32 cur_offset = 0; u64 inode_objectid = btrfs_ino(inode); u64 offset = 0; unsigned long ptr; struct btrfs_inode_extref *extref; struct extent_buffer *leaf; while (1) { ret = btrfs_find_one_extref(inode->root, inode_objectid, offset, path, &extref, &offset); if (ret) break; leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); cur_offset = 0; while (cur_offset < item_size) { extref = (struct btrfs_inode_extref *) (ptr + cur_offset); name_len = btrfs_inode_extref_name_len(leaf, extref); nlink++; cur_offset += name_len + sizeof(*extref); } offset++; btrfs_release_path(path); } btrfs_release_path(path); if (ret < 0 && ret != -ENOENT) return ret; return nlink; } static int count_inode_refs(struct btrfs_inode *inode, struct btrfs_path *path) { int ret; struct btrfs_key key; unsigned int nlink = 0; unsigned long ptr; unsigned long ptr_end; int name_len; u64 ino = btrfs_ino(inode); key.objectid = ino; key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0); if (ret < 0) break; if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } process_slot: btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_INODE_REF_KEY) break; ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); ptr_end = ptr + btrfs_item_size(path->nodes[0], path->slots[0]); while (ptr < ptr_end) { struct btrfs_inode_ref *ref; ref = (struct btrfs_inode_ref *)ptr; name_len = btrfs_inode_ref_name_len(path->nodes[0], ref); ptr = (unsigned long)(ref + 1) + name_len; nlink++; } if (key.offset == 0) break; if (path->slots[0] > 0) { path->slots[0]--; goto process_slot; } key.offset--; btrfs_release_path(path); } btrfs_release_path(path); return nlink; } /* * There are a few corners where the link count of the file can't * be properly maintained during replay. So, instead of adding * lots of complexity to the log code, we just scan the backrefs * for any file that has been through replay. * * The scan will update the link count on the inode to reflect the * number of back refs found. If it goes down to zero, the iput * will free the inode. */ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, struct inode *inode) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; int ret; u64 nlink = 0; u64 ino = btrfs_ino(BTRFS_I(inode)); path = btrfs_alloc_path(); if (!path) return -ENOMEM; ret = count_inode_refs(BTRFS_I(inode), path); if (ret < 0) goto out; nlink = ret; ret = count_inode_extrefs(BTRFS_I(inode), path); if (ret < 0) goto out; nlink += ret; ret = 0; if (nlink != inode->i_nlink) { set_nlink(inode, nlink); ret = btrfs_update_inode(trans, BTRFS_I(inode)); if (ret) goto out; } if (S_ISDIR(inode->i_mode)) BTRFS_I(inode)->index_cnt = (u64)-1; if (inode->i_nlink == 0) { if (S_ISDIR(inode->i_mode)) { ret = replay_dir_deletes(trans, root, NULL, path, ino, 1); if (ret) goto out; } ret = btrfs_insert_orphan_item(trans, root, ino); if (ret == -EEXIST) ret = 0; } out: btrfs_free_path(path); return ret; } static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path) { int ret; struct btrfs_key key; struct inode *inode; key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) break; if (ret == 1) { ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid != BTRFS_TREE_LOG_FIXUP_OBJECTID || key.type != BTRFS_ORPHAN_ITEM_KEY) break; ret = btrfs_del_item(trans, root, path); if (ret) break; btrfs_release_path(path); inode = read_one_inode(root, key.offset); if (!inode) { ret = -EIO; break; } ret = fixup_inode_link_count(trans, inode); iput(inode); if (ret) break; /* * fixup on a directory may create new entries, * make sure we always look for the highset possible * offset */ key.offset = (u64)-1; } btrfs_release_path(path); return ret; } /* * record a given inode in the fixup dir so we can check its link * count when replay is done. The link count is incremented here * so the inode won't go away until we check it */ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 objectid) { struct btrfs_key key; int ret = 0; struct inode *inode; inode = read_one_inode(root, objectid); if (!inode) return -EIO; key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID; key.type = BTRFS_ORPHAN_ITEM_KEY; key.offset = objectid; ret = btrfs_insert_empty_item(trans, root, path, &key, 0); btrfs_release_path(path); if (ret == 0) { if (!inode->i_nlink) set_nlink(inode, 1); else inc_nlink(inode); ret = btrfs_update_inode(trans, BTRFS_I(inode)); } else if (ret == -EEXIST) { ret = 0; } iput(inode); return ret; } /* * when replaying the log for a directory, we only insert names * for inodes that actually exist. This means an fsync on a directory * does not implicitly fsync all the new files in it */ static noinline int insert_one_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 dirid, u64 index, const struct fscrypt_str *name, struct btrfs_key *location) { struct inode *inode; struct inode *dir; int ret; inode = read_one_inode(root, location->objectid); if (!inode) return -ENOENT; dir = read_one_inode(root, dirid); if (!dir) { iput(inode); return -EIO; } ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name, 1, index); /* FIXME, put inode into FIXUP list */ iput(inode); iput(dir); return ret; } static int delete_conflicting_dir_entry(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_path *path, struct btrfs_dir_item *dst_di, const struct btrfs_key *log_key, u8 log_flags, bool exists) { struct btrfs_key found_key; btrfs_dir_item_key_to_cpu(path->nodes[0], dst_di, &found_key); /* The existing dentry points to the same inode, don't delete it. */ if (found_key.objectid == log_key->objectid && found_key.type == log_key->type && found_key.offset == log_key->offset && btrfs_dir_flags(path->nodes[0], dst_di) == log_flags) return 1; /* * Don't drop the conflicting directory entry if the inode for the new * entry doesn't exist. */ if (!exists) return 0; return drop_one_dir_item(trans, path, dir, dst_di); } /* * take a single entry in a log directory item and replay it into * the subvolume. * * if a conflicting item exists in the subdirectory already, * the inode it points to is unlinked and put into the link count * fix up tree. * * If a name from the log points to a file or directory that does * not exist in the FS, it is skipped. fsyncs on directories * do not force down inodes inside that directory, just changes to the * names or unlinks in a directory. * * Returns < 0 on error, 0 if the name wasn't replayed (dentry points to a * non-existing inode) and 1 if the name was replayed. */ static noinline int replay_one_name(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, struct btrfs_dir_item *di, struct btrfs_key *key) { struct fscrypt_str name; struct btrfs_dir_item *dir_dst_di; struct btrfs_dir_item *index_dst_di; bool dir_dst_matches = false; bool index_dst_matches = false; struct btrfs_key log_key; struct btrfs_key search_key; struct inode *dir; u8 log_flags; bool exists; int ret; bool update_size = true; bool name_added = false; dir = read_one_inode(root, key->objectid); if (!dir) return -EIO; ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name); if (ret) goto out; log_flags = btrfs_dir_flags(eb, di); btrfs_dir_item_key_to_cpu(eb, di, &log_key); ret = btrfs_lookup_inode(trans, root, path, &log_key, 0); btrfs_release_path(path); if (ret < 0) goto out; exists = (ret == 0); ret = 0; dir_dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid, &name, 1); if (IS_ERR(dir_dst_di)) { ret = PTR_ERR(dir_dst_di); goto out; } else if (dir_dst_di) { ret = delete_conflicting_dir_entry(trans, BTRFS_I(dir), path, dir_dst_di, &log_key, log_flags, exists); if (ret < 0) goto out; dir_dst_matches = (ret == 1); } btrfs_release_path(path); index_dst_di = btrfs_lookup_dir_index_item(trans, root, path, key->objectid, key->offset, &name, 1); if (IS_ERR(index_dst_di)) { ret = PTR_ERR(index_dst_di); goto out; } else if (index_dst_di) { ret = delete_conflicting_dir_entry(trans, BTRFS_I(dir), path, index_dst_di, &log_key, log_flags, exists); if (ret < 0) goto out; index_dst_matches = (ret == 1); } btrfs_release_path(path); if (dir_dst_matches && index_dst_matches) { ret = 0; update_size = false; goto out; } /* * Check if the inode reference exists in the log for the given name, * inode and parent inode */ search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = key->objectid; ret = backref_in_log(root->log_root, &search_key, 0, &name); if (ret < 0) { goto out; } else if (ret) { /* The dentry will be added later. */ ret = 0; update_size = false; goto out; } search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; search_key.offset = key->objectid; ret = backref_in_log(root->log_root, &search_key, key->objectid, &name); if (ret < 0) { goto out; } else if (ret) { /* The dentry will be added later. */ ret = 0; update_size = false; goto out; } btrfs_release_path(path); ret = insert_one_name(trans, root, key->objectid, key->offset, &name, &log_key); if (ret && ret != -ENOENT && ret != -EEXIST) goto out; if (!ret) name_added = true; update_size = false; ret = 0; out: if (!ret && update_size) { btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name.len * 2); ret = btrfs_update_inode(trans, BTRFS_I(dir)); } kfree(name.name); iput(dir); if (!ret && name_added) ret = 1; return ret; } /* Replay one dir item from a BTRFS_DIR_INDEX_KEY key. */ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct extent_buffer *eb, int slot, struct btrfs_key *key) { int ret; struct btrfs_dir_item *di; /* We only log dir index keys, which only contain a single dir item. */ ASSERT(key->type == BTRFS_DIR_INDEX_KEY); di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); ret = replay_one_name(trans, root, path, eb, di, key); if (ret < 0) return ret; /* * If this entry refers to a non-directory (directories can not have a * link count > 1) and it was added in the transaction that was not * committed, make sure we fixup the link count of the inode the entry * points to. Otherwise something like the following would result in a * directory pointing to an inode with a wrong link that does not account * for this dir entry: * * mkdir testdir * touch testdir/foo * touch testdir/bar * sync * * ln testdir/bar testdir/bar_link * ln testdir/foo testdir/foo_link * xfs_io -c "fsync" testdir/bar * * <power failure> * * mount fs, log replay happens * * File foo would remain with a link count of 1 when it has two entries * pointing to it in the directory testdir. This would make it impossible * to ever delete the parent directory has it would result in stale * dentries that can never be deleted. */ if (ret == 1 && btrfs_dir_ftype(eb, di) != BTRFS_FT_DIR) { struct btrfs_path *fixup_path; struct btrfs_key di_key; fixup_path = btrfs_alloc_path(); if (!fixup_path) return -ENOMEM; btrfs_dir_item_key_to_cpu(eb, di, &di_key); ret = link_to_fixup_dir(trans, root, fixup_path, di_key.objectid); btrfs_free_path(fixup_path); } return ret; } /* * directory replay has two parts. There are the standard directory * items in the log copied from the subvolume, and range items * created in the log while the subvolume was logged. * * The range items tell us which parts of the key space the log * is authoritative for. During replay, if a key in the subvolume * directory is in a logged range item, but not actually in the log * that means it was deleted from the directory before the fsync * and should be removed. */ static noinline int find_dir_range(struct btrfs_root *root, struct btrfs_path *path, u64 dirid, u64 *start_ret, u64 *end_ret) { struct btrfs_key key; u64 found_end; struct btrfs_dir_log_item *item; int ret; int nritems; if (*start_ret == (u64)-1) return 1; key.objectid = dirid; key.type = BTRFS_DIR_LOG_INDEX_KEY; key.offset = *start_ret; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; if (ret > 0) { if (path->slots[0] == 0) goto out; path->slots[0]--; } if (ret != 0) btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto next; } item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); found_end = btrfs_dir_log_end(path->nodes[0], item); if (*start_ret >= key.offset && *start_ret <= found_end) { ret = 0; *start_ret = key.offset; *end_ret = found_end; goto out; } ret = 1; next: /* check the next slot in the tree to see if it is a valid item */ nritems = btrfs_header_nritems(path->nodes[0]); path->slots[0]++; if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret) goto out; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_DIR_LOG_INDEX_KEY || key.objectid != dirid) { ret = 1; goto out; } item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); found_end = btrfs_dir_log_end(path->nodes[0], item); *start_ret = key.offset; *end_ret = found_end; ret = 0; out: btrfs_release_path(path); return ret; } /* * this looks for a given directory item in the log. If the directory * item is not in the log, the item is removed and the inode it points * to is unlinked */ static noinline int check_item_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_path *log_path, struct inode *dir, struct btrfs_key *dir_key) { struct btrfs_root *root = BTRFS_I(dir)->root; int ret; struct extent_buffer *eb; int slot; struct btrfs_dir_item *di; struct fscrypt_str name; struct inode *inode = NULL; struct btrfs_key location; /* * Currently we only log dir index keys. Even if we replay a log created * by an older kernel that logged both dir index and dir item keys, all * we need to do is process the dir index keys, we (and our caller) can * safely ignore dir item keys (key type BTRFS_DIR_ITEM_KEY). */ ASSERT(dir_key->type == BTRFS_DIR_INDEX_KEY); eb = path->nodes[0]; slot = path->slots[0]; di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item); ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name); if (ret) goto out; if (log) { struct btrfs_dir_item *log_di; log_di = btrfs_lookup_dir_index_item(trans, log, log_path, dir_key->objectid, dir_key->offset, &name, 0); if (IS_ERR(log_di)) { ret = PTR_ERR(log_di); goto out; } else if (log_di) { /* The dentry exists in the log, we have nothing to do. */ ret = 0; goto out; } } btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(path); btrfs_release_path(log_path); inode = read_one_inode(root, location.objectid); if (!inode) { ret = -EIO; goto out; } ret = link_to_fixup_dir(trans, root, path, location.objectid); if (ret) goto out; inc_nlink(inode); ret = unlink_inode_for_log_replay(trans, BTRFS_I(dir), BTRFS_I(inode), &name); /* * Unlike dir item keys, dir index keys can only have one name (entry) in * them, as there are no key collisions since each key has a unique offset * (an index number), so we're done. */ out: btrfs_release_path(path); btrfs_release_path(log_path); kfree(name.name); iput(inode); return ret; } static int replay_xattr_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, const u64 ino) { struct btrfs_key search_key; struct btrfs_path *log_path; int i; int nritems; int ret; log_path = btrfs_alloc_path(); if (!log_path) return -ENOMEM; search_key.objectid = ino; search_key.type = BTRFS_XATTR_ITEM_KEY; search_key.offset = 0; again: ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) goto out; process_leaf: nritems = btrfs_header_nritems(path->nodes[0]); for (i = path->slots[0]; i < nritems; i++) { struct btrfs_key key; struct btrfs_dir_item *di; struct btrfs_dir_item *log_di; u32 total_size; u32 cur; btrfs_item_key_to_cpu(path->nodes[0], &key, i); if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) { ret = 0; goto out; } di = btrfs_item_ptr(path->nodes[0], i, struct btrfs_dir_item); total_size = btrfs_item_size(path->nodes[0], i); cur = 0; while (cur < total_size) { u16 name_len = btrfs_dir_name_len(path->nodes[0], di); u16 data_len = btrfs_dir_data_len(path->nodes[0], di); u32 this_len = sizeof(*di) + name_len + data_len; char *name; name = kmalloc(name_len, GFP_NOFS); if (!name) { ret = -ENOMEM; goto out; } read_extent_buffer(path->nodes[0], name, (unsigned long)(di + 1), name_len); log_di = btrfs_lookup_xattr(NULL, log, log_path, ino, name, name_len, 0); btrfs_release_path(log_path); if (!log_di) { /* Doesn't exist in log tree, so delete it. */ btrfs_release_path(path); di = btrfs_lookup_xattr(trans, root, path, ino, name, name_len, -1); kfree(name); if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } ASSERT(di); ret = btrfs_delete_one_dir_name(trans, root, path, di); if (ret) goto out; btrfs_release_path(path); search_key = key; goto again; } kfree(name); if (IS_ERR(log_di)) { ret = PTR_ERR(log_di); goto out; } cur += this_len; di = (struct btrfs_dir_item *)((char *)di + this_len); } } ret = btrfs_next_leaf(root, path); if (ret > 0) ret = 0; else if (ret == 0) goto process_leaf; out: btrfs_free_path(log_path); btrfs_release_path(path); return ret; } /* * deletion replay happens before we copy any new directory items * out of the log or out of backreferences from inodes. It * scans the log to find ranges of keys that log is authoritative for, * and then scans the directory to find items in those ranges that are * not present in the log. * * Anything we don't find in the log is unlinked and removed from the * directory. */ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, int del_all) { u64 range_start; u64 range_end; int ret = 0; struct btrfs_key dir_key; struct btrfs_key found_key; struct btrfs_path *log_path; struct inode *dir; dir_key.objectid = dirid; dir_key.type = BTRFS_DIR_INDEX_KEY; log_path = btrfs_alloc_path(); if (!log_path) return -ENOMEM; dir = read_one_inode(root, dirid); /* it isn't an error if the inode isn't there, that can happen * because we replay the deletes before we copy in the inode item * from the log */ if (!dir) { btrfs_free_path(log_path); return 0; } range_start = 0; range_end = 0; while (1) { if (del_all) range_end = (u64)-1; else { ret = find_dir_range(log, path, dirid, &range_start, &range_end); if (ret < 0) goto out; else if (ret > 0) break; } dir_key.offset = range_start; while (1) { int nritems; ret = btrfs_search_slot(NULL, root, &dir_key, path, 0, 0); if (ret < 0) goto out; nritems = btrfs_header_nritems(path->nodes[0]); if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret == 1) break; else if (ret < 0) goto out; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); if (found_key.objectid != dirid || found_key.type != dir_key.type) { ret = 0; goto out; } if (found_key.offset > range_end) break; ret = check_item_in_log(trans, log, path, log_path, dir, &found_key); if (ret) goto out; if (found_key.offset == (u64)-1) break; dir_key.offset = found_key.offset + 1; } btrfs_release_path(path); if (range_end == (u64)-1) break; range_start = range_end + 1; } ret = 0; out: btrfs_release_path(path); btrfs_free_path(log_path); iput(dir); return ret; } /* * the process_func used to replay items from the log tree. This * gets called in two different stages. The first stage just looks * for inodes and makes sure they are all copied into the subvolume. * * The second stage copies all the other item types from the log into * the subvolume. The two stage approach is slower, but gets rid of * lots of complexity around inodes referencing other inodes that exist * only in the log (references come from either directory items or inode * back refs). */ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level) { int nritems; struct btrfs_tree_parent_check check = { .transid = gen, .level = level }; struct btrfs_path *path; struct btrfs_root *root = wc->replay_dest; struct btrfs_key key; int i; int ret; ret = btrfs_read_extent_buffer(eb, &check); if (ret) return ret; level = btrfs_header_level(eb); if (level != 0) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; nritems = btrfs_header_nritems(eb); for (i = 0; i < nritems; i++) { btrfs_item_key_to_cpu(eb, &key, i); /* inode keys are done during the first stage */ if (key.type == BTRFS_INODE_ITEM_KEY && wc->stage == LOG_WALK_REPLAY_INODES) { struct btrfs_inode_item *inode_item; u32 mode; inode_item = btrfs_item_ptr(eb, i, struct btrfs_inode_item); /* * If we have a tmpfile (O_TMPFILE) that got fsync'ed * and never got linked before the fsync, skip it, as * replaying it is pointless since it would be deleted * later. We skip logging tmpfiles, but it's always * possible we are replaying a log created with a kernel * that used to log tmpfiles. */ if (btrfs_inode_nlink(eb, inode_item) == 0) { wc->ignore_cur_inode = true; continue; } else { wc->ignore_cur_inode = false; } ret = replay_xattr_deletes(wc->trans, root, log, path, key.objectid); if (ret) break; mode = btrfs_inode_mode(eb, inode_item); if (S_ISDIR(mode)) { ret = replay_dir_deletes(wc->trans, root, log, path, key.objectid, 0); if (ret) break; } ret = overwrite_item(wc->trans, root, path, eb, i, &key); if (ret) break; /* * Before replaying extents, truncate the inode to its * size. We need to do it now and not after log replay * because before an fsync we can have prealloc extents * added beyond the inode's i_size. If we did it after, * through orphan cleanup for example, we would drop * those prealloc extents just after replaying them. */ if (S_ISREG(mode)) { struct btrfs_drop_extents_args drop_args = { 0 }; struct inode *inode; u64 from; inode = read_one_inode(root, key.objectid); if (!inode) { ret = -EIO; break; } from = ALIGN(i_size_read(inode), root->fs_info->sectorsize); drop_args.start = from; drop_args.end = (u64)-1; drop_args.drop_cache = true; ret = btrfs_drop_extents(wc->trans, root, BTRFS_I(inode), &drop_args); if (!ret) { inode_sub_bytes(inode, drop_args.bytes_found); /* Update the inode's nbytes. */ ret = btrfs_update_inode(wc->trans, BTRFS_I(inode)); } iput(inode); if (ret) break; } ret = link_to_fixup_dir(wc->trans, root, path, key.objectid); if (ret) break; } if (wc->ignore_cur_inode) continue; if (key.type == BTRFS_DIR_INDEX_KEY && wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { ret = replay_one_dir_item(wc->trans, root, path, eb, i, &key); if (ret) break; } if (wc->stage < LOG_WALK_REPLAY_ALL) continue; /* these keys are simply copied */ if (key.type == BTRFS_XATTR_ITEM_KEY) { ret = overwrite_item(wc->trans, root, path, eb, i, &key); if (ret) break; } else if (key.type == BTRFS_INODE_REF_KEY || key.type == BTRFS_INODE_EXTREF_KEY) { ret = add_inode_ref(wc->trans, root, log, path, eb, i, &key); if (ret && ret != -ENOENT) break; ret = 0; } else if (key.type == BTRFS_EXTENT_DATA_KEY) { ret = replay_one_extent(wc->trans, root, path, eb, i, &key); if (ret) break; } /* * We don't log BTRFS_DIR_ITEM_KEY keys anymore, only the * BTRFS_DIR_INDEX_KEY items which we use to derive the * BTRFS_DIR_ITEM_KEY items. If we are replaying a log from an * older kernel with such keys, ignore them. */ } btrfs_free_path(path); return ret; } /* * Correctly adjust the reserved bytes occupied by a log tree extent buffer */ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); if (!cache) { btrfs_err(fs_info, "unable to find block group for %llu", start); return; } spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); cache->reserved -= fs_info->nodesize; cache->space_info->bytes_reserved -= fs_info->nodesize; spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); btrfs_put_block_group(cache); } static int clean_log_buffer(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { int ret; btrfs_tree_lock(eb); btrfs_clear_buffer_dirty(trans, eb); wait_on_extent_buffer_writeback(eb); btrfs_tree_unlock(eb); if (trans) { ret = btrfs_pin_reserved_extent(trans, eb); if (ret) return ret; } else { unaccount_log_buffer(eb->fs_info, eb->start); } return 0; } static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int *level, struct walk_control *wc) { struct btrfs_fs_info *fs_info = root->fs_info; u64 bytenr; u64 ptr_gen; struct extent_buffer *next; struct extent_buffer *cur; int ret = 0; while (*level > 0) { struct btrfs_tree_parent_check check = { 0 }; cur = path->nodes[*level]; WARN_ON(btrfs_header_level(cur) != *level); if (path->slots[*level] >= btrfs_header_nritems(cur)) break; bytenr = btrfs_node_blockptr(cur, path->slots[*level]); ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]); check.transid = ptr_gen; check.level = *level - 1; check.has_first_key = true; btrfs_node_key_to_cpu(cur, &check.first_key, path->slots[*level]); next = btrfs_find_create_tree_block(fs_info, bytenr, btrfs_header_owner(cur), *level - 1); if (IS_ERR(next)) return PTR_ERR(next); if (*level == 1) { ret = wc->process_func(root, next, wc, ptr_gen, *level - 1); if (ret) { free_extent_buffer(next); return ret; } path->slots[*level]++; if (wc->free) { ret = btrfs_read_extent_buffer(next, &check); if (ret) { free_extent_buffer(next); return ret; } ret = clean_log_buffer(trans, next); if (ret) { free_extent_buffer(next); return ret; } } free_extent_buffer(next); continue; } ret = btrfs_read_extent_buffer(next, &check); if (ret) { free_extent_buffer(next); return ret; } if (path->nodes[*level-1]) free_extent_buffer(path->nodes[*level-1]); path->nodes[*level-1] = next; *level = btrfs_header_level(next); path->slots[*level] = 0; cond_resched(); } path->slots[*level] = btrfs_header_nritems(path->nodes[*level]); cond_resched(); return 0; } static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int *level, struct walk_control *wc) { int i; int slot; int ret; for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) { slot = path->slots[i]; if (slot + 1 < btrfs_header_nritems(path->nodes[i])) { path->slots[i]++; *level = i; WARN_ON(*level == 0); return 0; } else { ret = wc->process_func(root, path->nodes[*level], wc, btrfs_header_generation(path->nodes[*level]), *level); if (ret) return ret; if (wc->free) { ret = clean_log_buffer(trans, path->nodes[*level]); if (ret) return ret; } free_extent_buffer(path->nodes[*level]); path->nodes[*level] = NULL; *level = i + 1; } } return 1; } /* * drop the reference count on the tree rooted at 'snap'. This traverses * the tree freeing any blocks that have a ref count of zero after being * decremented. */ static int walk_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct walk_control *wc) { int ret = 0; int wret; int level; struct btrfs_path *path; int orig_level; path = btrfs_alloc_path(); if (!path) return -ENOMEM; level = btrfs_header_level(log->node); orig_level = level; path->nodes[level] = log->node; atomic_inc(&log->node->refs); path->slots[level] = 0; while (1) { wret = walk_down_log_tree(trans, log, path, &level, wc); if (wret > 0) break; if (wret < 0) { ret = wret; goto out; } wret = walk_up_log_tree(trans, log, path, &level, wc); if (wret > 0) break; if (wret < 0) { ret = wret; goto out; } } /* was the root node processed? if not, catch it here */ if (path->nodes[orig_level]) { ret = wc->process_func(log, path->nodes[orig_level], wc, btrfs_header_generation(path->nodes[orig_level]), orig_level); if (ret) goto out; if (wc->free) ret = clean_log_buffer(trans, path->nodes[orig_level]); } out: btrfs_free_path(path); return ret; } /* * helper function to update the item for a given subvolumes log root * in the tree of log roots */ static int update_log_root(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_root_item *root_item) { struct btrfs_fs_info *fs_info = log->fs_info; int ret; if (log->log_transid == 1) { /* insert root item on the first sync */ ret = btrfs_insert_root(trans, fs_info->log_root_tree, &log->root_key, root_item); } else { ret = btrfs_update_root(trans, fs_info->log_root_tree, &log->root_key, root_item); } return ret; } static void wait_log_commit(struct btrfs_root *root, int transid) { DEFINE_WAIT(wait); int index = transid % 2; /* * we only allow two pending log transactions at a time, * so we know that if ours is more than 2 older than the * current transaction, we're done */ for (;;) { prepare_to_wait(&root->log_commit_wait[index], &wait, TASK_UNINTERRUPTIBLE); if (!(root->log_transid_committed < transid && atomic_read(&root->log_commit[index]))) break; mutex_unlock(&root->log_mutex); schedule(); mutex_lock(&root->log_mutex); } finish_wait(&root->log_commit_wait[index], &wait); } static void wait_for_writer(struct btrfs_root *root) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&root->log_writer_wait, &wait, TASK_UNINTERRUPTIBLE); if (!atomic_read(&root->log_writers)) break; mutex_unlock(&root->log_mutex); schedule(); mutex_lock(&root->log_mutex); } finish_wait(&root->log_writer_wait, &wait); } void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, struct btrfs_inode *inode) { ctx->log_ret = 0; ctx->log_transid = 0; ctx->log_new_dentries = false; ctx->logging_new_name = false; ctx->logging_new_delayed_dentries = false; ctx->logged_before = false; ctx->inode = inode; INIT_LIST_HEAD(&ctx->list); INIT_LIST_HEAD(&ctx->ordered_extents); INIT_LIST_HEAD(&ctx->conflict_inodes); ctx->num_conflict_inodes = 0; ctx->logging_conflict_inodes = false; ctx->scratch_eb = NULL; } void btrfs_init_log_ctx_scratch_eb(struct btrfs_log_ctx *ctx) { struct btrfs_inode *inode = ctx->inode; if (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) && !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) return; /* * Don't care about allocation failure. This is just for optimization, * if we fail to allocate here, we will try again later if needed. */ ctx->scratch_eb = alloc_dummy_extent_buffer(inode->root->fs_info, 0); } void btrfs_release_log_ctx_extents(struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_ordered_extent *tmp; ASSERT(inode_is_locked(&ctx->inode->vfs_inode)); list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) { list_del_init(&ordered->log_list); btrfs_put_ordered_extent(ordered); } } static inline void btrfs_remove_log_ctx(struct btrfs_root *root, struct btrfs_log_ctx *ctx) { mutex_lock(&root->log_mutex); list_del_init(&ctx->list); mutex_unlock(&root->log_mutex); } /* * Invoked in log mutex context, or be sure there is no other task which * can access the list. */ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; struct btrfs_log_ctx *safe; list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { list_del_init(&ctx->list); ctx->log_ret = error; } } /* * Sends a given tree log down to the disk and updates the super blocks to * record it. When this call is done, you know that any inodes previously * logged are safely on disk only if it returns 0. * * Any other return value means you need to call btrfs_commit_transaction. * Some of the edge cases for fsyncing directories that have had unlinks * or renames done in the past mean that sometimes the only safe * fsync is to commit the whole FS. When btrfs_sync_log returns -EAGAIN, * that has happened. */ int btrfs_sync_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { int index1; int index2; int mark; int ret; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_root *log = root->log_root; struct btrfs_root *log_root_tree = fs_info->log_root_tree; struct btrfs_root_item new_root_item; int log_transid = 0; struct btrfs_log_ctx root_log_ctx; struct blk_plug plug; u64 log_root_start; u64 log_root_level; mutex_lock(&root->log_mutex); log_transid = ctx->log_transid; if (root->log_transid_committed >= log_transid) { mutex_unlock(&root->log_mutex); return ctx->log_ret; } index1 = log_transid % 2; if (atomic_read(&root->log_commit[index1])) { wait_log_commit(root, log_transid); mutex_unlock(&root->log_mutex); return ctx->log_ret; } ASSERT(log_transid == root->log_transid); atomic_set(&root->log_commit[index1], 1); /* wait for previous tree log sync to complete */ if (atomic_read(&root->log_commit[(index1 + 1) % 2])) wait_log_commit(root, log_transid - 1); while (1) { int batch = atomic_read(&root->log_batch); /* when we're on an ssd, just kick the log commit out */ if (!btrfs_test_opt(fs_info, SSD) && test_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state)) { mutex_unlock(&root->log_mutex); schedule_timeout_uninterruptible(1); mutex_lock(&root->log_mutex); } wait_for_writer(root); if (batch == atomic_read(&root->log_batch)) break; } /* bail out if we need to do a full commit */ if (btrfs_need_log_full_commit(trans)) { ret = BTRFS_LOG_FORCE_COMMIT; mutex_unlock(&root->log_mutex); goto out; } if (log_transid % 2 == 0) mark = EXTENT_DIRTY; else mark = EXTENT_NEW; /* we start IO on all the marked extents here, but we don't actually * wait for them until later. */ blk_start_plug(&plug); ret = btrfs_write_marked_extents(fs_info, &log->dirty_log_pages, mark); /* * -EAGAIN happens when someone, e.g., a concurrent transaction * commit, writes a dirty extent in this tree-log commit. This * concurrent write will create a hole writing out the extents, * and we cannot proceed on a zoned filesystem, requiring * sequential writing. While we can bail out to a full commit * here, but we can continue hoping the concurrent writing fills * the hole. */ if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) ret = 0; if (ret) { blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); mutex_unlock(&root->log_mutex); goto out; } /* * We _must_ update under the root->log_mutex in order to make sure we * have a consistent view of the log root we are trying to commit at * this moment. * * We _must_ copy this into a local copy, because we are not holding the * log_root_tree->log_mutex yet. This is important because when we * commit the log_root_tree we must have a consistent view of the * log_root_tree when we update the super block to point at the * log_root_tree bytenr. If we update the log_root_tree here we'll race * with the commit and possibly point at the new block which we may not * have written out. */ btrfs_set_root_node(&log->root_item, log->node); memcpy(&new_root_item, &log->root_item, sizeof(new_root_item)); btrfs_set_root_log_transid(root, root->log_transid + 1); log->log_transid = root->log_transid; root->log_start_pid = 0; /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. */ mutex_unlock(&root->log_mutex); if (btrfs_is_zoned(fs_info)) { mutex_lock(&fs_info->tree_root->log_mutex); if (!log_root_tree->node) { ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { mutex_unlock(&fs_info->tree_root->log_mutex); blk_finish_plug(&plug); goto out; } } mutex_unlock(&fs_info->tree_root->log_mutex); } btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); index2 = log_root_tree->log_transid % 2; list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); root_log_ctx.log_transid = log_root_tree->log_transid; /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit * open until we drop the log_mutex. */ ret = update_log_root(trans, log, &new_root_item); if (ret) { list_del_init(&root_log_ctx.list); blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); if (ret != -ENOSPC) btrfs_err(fs_info, "failed to update log for root %llu ret %d", btrfs_root_id(root), ret); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); goto out; } if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { blk_finish_plug(&plug); list_del_init(&root_log_ctx.list); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; } if (atomic_read(&log_root_tree->log_commit[index2])) { blk_finish_plug(&plug); ret = btrfs_wait_tree_log_extents(log, mark); wait_log_commit(log_root_tree, root_log_ctx.log_transid); mutex_unlock(&log_root_tree->log_mutex); if (!ret) ret = root_log_ctx.log_ret; goto out; } ASSERT(root_log_ctx.log_transid == log_root_tree->log_transid); atomic_set(&log_root_tree->log_commit[index2], 1); if (atomic_read(&log_root_tree->log_commit[(index2 + 1) % 2])) { wait_log_commit(log_root_tree, root_log_ctx.log_transid - 1); } /* * now that we've moved on to the tree of log tree roots, * check the full commit flag again */ if (btrfs_need_log_full_commit(trans)) { blk_finish_plug(&plug); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); ret = BTRFS_LOG_FORCE_COMMIT; goto out_wake_log_root; } ret = btrfs_write_marked_extents(fs_info, &log_root_tree->dirty_log_pages, EXTENT_DIRTY | EXTENT_NEW); blk_finish_plug(&plug); /* * As described above, -EAGAIN indicates a hole in the extents. We * cannot wait for these write outs since the waiting cause a * deadlock. Bail out to the full commit instead. */ if (ret == -EAGAIN && btrfs_is_zoned(fs_info)) { btrfs_set_log_full_commit(trans); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } else if (ret) { btrfs_set_log_full_commit(trans); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } ret = btrfs_wait_tree_log_extents(log, mark); if (!ret) ret = btrfs_wait_tree_log_extents(log_root_tree, EXTENT_NEW | EXTENT_DIRTY); if (ret) { btrfs_set_log_full_commit(trans); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } log_root_start = log_root_tree->node->start; log_root_level = btrfs_header_level(log_root_tree->node); log_root_tree->log_transid++; mutex_unlock(&log_root_tree->log_mutex); /* * Here we are guaranteed that nobody is going to write the superblock * for the current transaction before us and that neither we do write * our superblock before the previous transaction finishes its commit * and writes its superblock, because: * * 1) We are holding a handle on the current transaction, so no body * can commit it until we release the handle; * * 2) Before writing our superblock we acquire the tree_log_mutex, so * if the previous transaction is still committing, and hasn't yet * written its superblock, we wait for it to do it, because a * transaction commit acquires the tree_log_mutex when the commit * begins and releases it only after writing its superblock. */ mutex_lock(&fs_info->tree_log_mutex); /* * The previous transaction writeout phase could have failed, and thus * marked the fs in an error state. We must not commit here, as we * could have updated our generation in the super_for_commit and * writing the super here would result in transid mismatches. If there * is an error here just bail. */ if (BTRFS_FS_ERROR(fs_info)) { ret = -EIO; btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); mutex_unlock(&fs_info->tree_log_mutex); goto out_wake_log_root; } btrfs_set_super_log_root(fs_info->super_for_commit, log_root_start); btrfs_set_super_log_root_level(fs_info->super_for_commit, log_root_level); ret = write_all_supers(fs_info, 1); mutex_unlock(&fs_info->tree_log_mutex); if (ret) { btrfs_set_log_full_commit(trans); btrfs_abort_transaction(trans, ret); goto out_wake_log_root; } /* * We know there can only be one task here, since we have not yet set * root->log_commit[index1] to 0 and any task attempting to sync the * log must wait for the previous log transaction to commit if it's * still in progress or wait for the current log transaction commit if * someone else already started it. We use <= and not < because the * first log transaction has an ID of 0. */ ASSERT(btrfs_get_root_last_log_commit(root) <= log_transid); btrfs_set_root_last_log_commit(root, log_transid); out_wake_log_root: mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); /* * The barrier before waitqueue_active (in cond_wake_up) is needed so * all the updates above are seen by the woken threads. It might not be * necessary, but proving that seems to be hard. */ cond_wake_up(&log_root_tree->log_commit_wait[index2]); out: mutex_lock(&root->log_mutex); btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); /* * The barrier before waitqueue_active (in cond_wake_up) is needed so * all the updates above are seen by the woken threads. It might not be * necessary, but proving that seems to be hard. */ cond_wake_up(&root->log_commit_wait[index1]); return ret; } static void free_log_tree(struct btrfs_trans_handle *trans, struct btrfs_root *log) { int ret; struct walk_control wc = { .free = 1, .process_func = process_one_buffer }; if (log->node) { ret = walk_log_tree(trans, log, &wc); if (ret) { /* * We weren't able to traverse the entire log tree, the * typical scenario is getting an -EIO when reading an * extent buffer of the tree, due to a previous writeback * failure of it. */ set_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, &log->fs_info->fs_state); /* * Some extent buffers of the log tree may still be dirty * and not yet written back to storage, because we may * have updates to a log tree without syncing a log tree, * such as during rename and link operations. So flush * them out and wait for their writeback to complete, so * that we properly cleanup their state and pages. */ btrfs_write_marked_extents(log->fs_info, &log->dirty_log_pages, EXTENT_DIRTY | EXTENT_NEW); btrfs_wait_tree_log_extents(log, EXTENT_DIRTY | EXTENT_NEW); if (trans) btrfs_abort_transaction(trans, ret); else btrfs_handle_fs_error(log->fs_info, ret, NULL); } } extent_io_tree_release(&log->dirty_log_pages); extent_io_tree_release(&log->log_csum_range); btrfs_put_root(log); } /* * free all the extents used by the tree log. This should be called * at commit time of the full transaction */ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root) { if (root->log_root) { free_log_tree(trans, root->log_root); root->log_root = NULL; clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); } return 0; } int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { if (fs_info->log_root_tree) { free_log_tree(trans, fs_info->log_root_tree); fs_info->log_root_tree = NULL; clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &fs_info->tree_root->state); } return 0; } /* * Check if an inode was logged in the current transaction. This correctly deals * with the case where the inode was logged but has a logged_trans of 0, which * happens if the inode is evicted and loaded again, as logged_trans is an in * memory only field (not persisted). * * Returns 1 if the inode was logged before in the transaction, 0 if it was not, * and < 0 on error. */ static int inode_logged(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path_in) { struct btrfs_path *path = path_in; struct btrfs_key key; int ret; if (inode->logged_trans == trans->transid) return 1; /* * If logged_trans is not 0, then we know the inode logged was not logged * in this transaction, so we can return false right away. */ if (inode->logged_trans > 0) return 0; /* * If no log tree was created for this root in this transaction, then * the inode can not have been logged in this transaction. In that case * set logged_trans to anything greater than 0 and less than the current * transaction's ID, to avoid the search below in a future call in case * a log tree gets created after this. */ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state)) { inode->logged_trans = trans->transid - 1; return 0; } /* * We have a log tree and the inode's logged_trans is 0. We can't tell * for sure if the inode was logged before in this transaction by looking * only at logged_trans. We could be pessimistic and assume it was, but * that can lead to unnecessarily logging an inode during rename and link * operations, and then further updating the log in followup rename and * link operations, specially if it's a directory, which adds latency * visible to applications doing a series of rename or link operations. * * A logged_trans of 0 here can mean several things: * * 1) The inode was never logged since the filesystem was mounted, and may * or may have not been evicted and loaded again; * * 2) The inode was logged in a previous transaction, then evicted and * then loaded again; * * 3) The inode was logged in the current transaction, then evicted and * then loaded again. * * For cases 1) and 2) we don't want to return true, but we need to detect * case 3) and return true. So we do a search in the log root for the inode * item. */ key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; if (!path) { path = btrfs_alloc_path(); if (!path) return -ENOMEM; } ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); if (path_in) btrfs_release_path(path); else btrfs_free_path(path); /* * Logging an inode always results in logging its inode item. So if we * did not find the item we know the inode was not logged for sure. */ if (ret < 0) { return ret; } else if (ret > 0) { /* * Set logged_trans to a value greater than 0 and less then the * current transaction to avoid doing the search in future calls. */ inode->logged_trans = trans->transid - 1; return 0; } /* * The inode was previously logged and then evicted, set logged_trans to * the current transacion's ID, to avoid future tree searches as long as * the inode is not evicted again. */ inode->logged_trans = trans->transid; /* * If it's a directory, then we must set last_dir_index_offset to the * maximum possible value, so that the next attempt to log the inode does * not skip checking if dir index keys found in modified subvolume tree * leaves have been logged before, otherwise it would result in attempts * to insert duplicate dir index keys in the log tree. This must be done * because last_dir_index_offset is an in-memory only field, not persisted * in the inode item or any other on-disk structure, so its value is lost * once the inode is evicted. */ if (S_ISDIR(inode->vfs_inode.i_mode)) inode->last_dir_index_offset = (u64)-1; return 1; } /* * Delete a directory entry from the log if it exists. * * Returns < 0 on error * 1 if the entry does not exists * 0 if the entry existed and was successfully deleted */ static int del_logged_dentry(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dir_ino, const struct fscrypt_str *name, u64 index) { struct btrfs_dir_item *di; /* * We only log dir index items of a directory, so we don't need to look * for dir item keys. */ di = btrfs_lookup_dir_index_item(trans, log, path, dir_ino, index, name, -1); if (IS_ERR(di)) return PTR_ERR(di); else if (!di) return 1; /* * We do not need to update the size field of the directory's * inode item because on log replay we update the field to reflect * all existing entries in the directory (see overwrite_item()). */ return btrfs_delete_one_dir_name(trans, log, path, di); } /* * If both a file and directory are logged, and unlinks or renames are * mixed in, we have a few interesting corners: * * create file X in dir Y * link file X to X.link in dir Y * fsync file X * unlink file X but leave X.link * fsync dir Y * * After a crash we would expect only X.link to exist. But file X * didn't get fsync'd again so the log has back refs for X and X.link. * * We solve this by removing directory entries and inode backrefs from the * log when a file that was logged in the current transaction is * unlinked. Any later fsync will include the updated log entries, and * we'll be able to reconstruct the proper directory items from backrefs. * * This optimizations allows us to avoid relogging the entire inode * or the entire directory. */ void btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *dir, u64 index) { struct btrfs_path *path; int ret; ret = inode_logged(trans, dir, NULL); if (ret == 0) return; else if (ret < 0) { btrfs_set_log_full_commit(trans); return; } ret = join_running_log_trans(root); if (ret) return; mutex_lock(&dir->log_mutex); path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out_unlock; } ret = del_logged_dentry(trans, root->log_root, path, btrfs_ino(dir), name, index); btrfs_free_path(path); out_unlock: mutex_unlock(&dir->log_mutex); if (ret < 0) btrfs_set_log_full_commit(trans); btrfs_end_log_trans(root); } /* see comments for btrfs_del_dir_entries_in_log */ void btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct fscrypt_str *name, struct btrfs_inode *inode, u64 dirid) { struct btrfs_root *log; u64 index; int ret; ret = inode_logged(trans, inode, NULL); if (ret == 0) return; else if (ret < 0) { btrfs_set_log_full_commit(trans); return; } ret = join_running_log_trans(root); if (ret) return; log = root->log_root; mutex_lock(&inode->log_mutex); ret = btrfs_del_inode_ref(trans, log, name, btrfs_ino(inode), dirid, &index); mutex_unlock(&inode->log_mutex); if (ret < 0 && ret != -ENOENT) btrfs_set_log_full_commit(trans); btrfs_end_log_trans(root); } /* * creates a range item in the log for 'dirid'. first_offset and * last_offset tell us which parts of the key space the log should * be considered authoritative for. */ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, u64 dirid, u64 first_offset, u64 last_offset) { int ret; struct btrfs_key key; struct btrfs_dir_log_item *item; key.objectid = dirid; key.offset = first_offset; key.type = BTRFS_DIR_LOG_INDEX_KEY; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item)); /* * -EEXIST is fine and can happen sporadically when we are logging a * directory and have concurrent insertions in the subvolume's tree for * items from other inodes and that result in pushing off some dir items * from one leaf to another in order to accommodate for the new items. * This results in logging the same dir index range key. */ if (ret && ret != -EEXIST) return ret; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); if (ret == -EEXIST) { const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item); /* * btrfs_del_dir_entries_in_log() might have been called during * an unlink between the initial insertion of this key and the * current update, or we might be logging a single entry deletion * during a rename, so set the new last_offset to the max value. */ last_offset = max(last_offset, curr_end); } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } static int flush_dir_items_batch(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct extent_buffer *src, struct btrfs_path *dst_path, int start_slot, int count) { struct btrfs_root *log = inode->root->log_root; char *ins_data = NULL; struct btrfs_item_batch batch; struct extent_buffer *dst; unsigned long src_offset; unsigned long dst_offset; u64 last_index; struct btrfs_key key; u32 item_size; int ret; int i; ASSERT(count > 0); batch.nr = count; if (count == 1) { btrfs_item_key_to_cpu(src, &key, start_slot); item_size = btrfs_item_size(src, start_slot); batch.keys = &key; batch.data_sizes = &item_size; batch.total_data_size = item_size; } else { struct btrfs_key *ins_keys; u32 *ins_sizes; ins_data = kmalloc(count * sizeof(u32) + count * sizeof(struct btrfs_key), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; ins_keys = (struct btrfs_key *)(ins_data + count * sizeof(u32)); batch.keys = ins_keys; batch.data_sizes = ins_sizes; batch.total_data_size = 0; for (i = 0; i < count; i++) { const int slot = start_slot + i; btrfs_item_key_to_cpu(src, &ins_keys[i], slot); ins_sizes[i] = btrfs_item_size(src, slot); batch.total_data_size += ins_sizes[i]; } } ret = btrfs_insert_empty_items(trans, log, dst_path, &batch); if (ret) goto out; dst = dst_path->nodes[0]; /* * Copy all the items in bulk, in a single copy operation. Item data is * organized such that it's placed at the end of a leaf and from right * to left. For example, the data for the second item ends at an offset * that matches the offset where the data for the first item starts, the * data for the third item ends at an offset that matches the offset * where the data of the second items starts, and so on. * Therefore our source and destination start offsets for copy match the * offsets of the last items (highest slots). */ dst_offset = btrfs_item_ptr_offset(dst, dst_path->slots[0] + count - 1); src_offset = btrfs_item_ptr_offset(src, start_slot + count - 1); copy_extent_buffer(dst, src, dst_offset, src_offset, batch.total_data_size); btrfs_release_path(dst_path); last_index = batch.keys[count - 1].offset; ASSERT(last_index > inode->last_dir_index_offset); /* * If for some unexpected reason the last item's index is not greater * than the last index we logged, warn and force a transaction commit. */ if (WARN_ON(last_index <= inode->last_dir_index_offset)) ret = BTRFS_LOG_FORCE_COMMIT; else inode->last_dir_index_offset = last_index; if (btrfs_get_first_dir_index_to_log(inode) == 0) btrfs_set_first_dir_index_to_log(inode, batch.keys[0].offset); out: kfree(ins_data); return ret; } static int clone_leaf(struct btrfs_path *path, struct btrfs_log_ctx *ctx) { const int slot = path->slots[0]; if (ctx->scratch_eb) { copy_extent_buffer_full(ctx->scratch_eb, path->nodes[0]); } else { ctx->scratch_eb = btrfs_clone_extent_buffer(path->nodes[0]); if (!ctx->scratch_eb) return -ENOMEM; } btrfs_release_path(path); path->nodes[0] = ctx->scratch_eb; path->slots[0] = slot; /* * Add extra ref to scratch eb so that it is not freed when callers * release the path, so we can reuse it later if needed. */ atomic_inc(&ctx->scratch_eb->refs); return 0; } static int process_dir_items_leaf(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx, u64 *last_old_dentry_offset) { struct btrfs_root *log = inode->root->log_root; struct extent_buffer *src; const int nritems = btrfs_header_nritems(path->nodes[0]); const u64 ino = btrfs_ino(inode); bool last_found = false; int batch_start = 0; int batch_size = 0; int ret; /* * We need to clone the leaf, release the read lock on it, and use the * clone before modifying the log tree. See the comment at copy_items() * about why we need to do this. */ ret = clone_leaf(path, ctx); if (ret < 0) return ret; src = path->nodes[0]; for (int i = path->slots[0]; i < nritems; i++) { struct btrfs_dir_item *di; struct btrfs_key key; int ret; btrfs_item_key_to_cpu(src, &key, i); if (key.objectid != ino || key.type != BTRFS_DIR_INDEX_KEY) { last_found = true; break; } di = btrfs_item_ptr(src, i, struct btrfs_dir_item); /* * Skip ranges of items that consist only of dir item keys created * in past transactions. However if we find a gap, we must log a * dir index range item for that gap, so that index keys in that * gap are deleted during log replay. */ if (btrfs_dir_transid(src, di) < trans->transid) { if (key.offset > *last_old_dentry_offset + 1) { ret = insert_dir_log_key(trans, log, dst_path, ino, *last_old_dentry_offset + 1, key.offset - 1); if (ret < 0) return ret; } *last_old_dentry_offset = key.offset; continue; } /* If we logged this dir index item before, we can skip it. */ if (key.offset <= inode->last_dir_index_offset) continue; /* * We must make sure that when we log a directory entry, the * corresponding inode, after log replay, has a matching link * count. For example: * * touch foo * mkdir mydir * sync * ln foo mydir/bar * xfs_io -c "fsync" mydir * <crash> * <mount fs and log replay> * * Would result in a fsync log that when replayed, our file inode * would have a link count of 1, but we get two directory entries * pointing to the same inode. After removing one of the names, * it would not be possible to remove the other name, which * resulted always in stale file handle errors, and would not be * possible to rmdir the parent directory, since its i_size could * never be decremented to the value BTRFS_EMPTY_DIR_SIZE, * resulting in -ENOTEMPTY errors. */ if (!ctx->log_new_dentries) { struct btrfs_key di_key; btrfs_dir_item_key_to_cpu(src, di, &di_key); if (di_key.type != BTRFS_ROOT_ITEM_KEY) ctx->log_new_dentries = true; } if (batch_size == 0) batch_start = i; batch_size++; } if (batch_size > 0) { int ret; ret = flush_dir_items_batch(trans, inode, src, dst_path, batch_start, batch_size); if (ret < 0) return ret; } return last_found ? 1 : 0; } /* * log all the items included in the current transaction for a given * directory. This also creates the range items in the log tree required * to replay anything deleted before the fsync */ static noinline int log_dir_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx, u64 min_offset, u64 *last_offset_ret) { struct btrfs_key min_key; struct btrfs_root *root = inode->root; struct btrfs_root *log = root->log_root; int ret; u64 last_old_dentry_offset = min_offset - 1; u64 last_offset = (u64)-1; u64 ino = btrfs_ino(inode); min_key.objectid = ino; min_key.type = BTRFS_DIR_INDEX_KEY; min_key.offset = min_offset; ret = btrfs_search_forward(root, &min_key, path, trans->transid); /* * we didn't find anything from this transaction, see if there * is anything at all */ if (ret != 0 || min_key.objectid != ino || min_key.type != BTRFS_DIR_INDEX_KEY) { min_key.objectid = ino; min_key.type = BTRFS_DIR_INDEX_KEY; min_key.offset = (u64)-1; btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret < 0) { btrfs_release_path(path); return ret; } ret = btrfs_previous_item(root, path, ino, BTRFS_DIR_INDEX_KEY); /* if ret == 0 there are items for this type, * create a range to tell us the last key of this type. * otherwise, there are no items in this directory after * *min_offset, and we create a range to indicate that. */ if (ret == 0) { struct btrfs_key tmp; btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]); if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; } else if (ret > 0) { ret = 0; } goto done; } /* go backward to find any previous key */ ret = btrfs_previous_item(root, path, ino, BTRFS_DIR_INDEX_KEY); if (ret == 0) { struct btrfs_key tmp; btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]); /* * The dir index key before the first one we found that needs to * be logged might be in a previous leaf, and there might be a * gap between these keys, meaning that we had deletions that * happened. So the key range item we log (key type * BTRFS_DIR_LOG_INDEX_KEY) must cover a range that starts at the * previous key's offset plus 1, so that those deletes are replayed. */ if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; } else if (ret < 0) { goto done; } btrfs_release_path(path); /* * Find the first key from this transaction again or the one we were at * in the loop below in case we had to reschedule. We may be logging the * directory without holding its VFS lock, which happen when logging new * dentries (through log_new_dir_dentries()) or in some cases when we * need to log the parent directory of an inode. This means a dir index * key might be deleted from the inode's root, and therefore we may not * find it anymore. If we can't find it, just move to the next key. We * can not bail out and ignore, because if we do that we will simply * not log dir index keys that come after the one that was just deleted * and we can end up logging a dir index range that ends at (u64)-1 * (@last_offset is initialized to that), resulting in removing dir * entries we should not remove at log replay time. */ search: ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); if (ret > 0) { ret = btrfs_next_item(root, path); if (ret > 0) { /* There are no more keys in the inode's root. */ ret = 0; goto done; } } if (ret < 0) goto done; /* * we have a block from this transaction, log every item in it * from our directory */ while (1) { ret = process_dir_items_leaf(trans, inode, path, dst_path, ctx, &last_old_dentry_offset); if (ret != 0) { if (ret > 0) ret = 0; goto done; } path->slots[0] = btrfs_header_nritems(path->nodes[0]); /* * look ahead to the next item and see if it is also * from this directory and from this transaction */ ret = btrfs_next_leaf(root, path); if (ret) { if (ret == 1) { last_offset = (u64)-1; ret = 0; } goto done; } btrfs_item_key_to_cpu(path->nodes[0], &min_key, path->slots[0]); if (min_key.objectid != ino || min_key.type != BTRFS_DIR_INDEX_KEY) { last_offset = (u64)-1; goto done; } if (btrfs_header_generation(path->nodes[0]) != trans->transid) { /* * The next leaf was not changed in the current transaction * and has at least one dir index key. * We check for the next key because there might have been * one or more deletions between the last key we logged and * that next key. So the key range item we log (key type * BTRFS_DIR_LOG_INDEX_KEY) must end at the next key's * offset minus 1, so that those deletes are replayed. */ last_offset = min_key.offset - 1; goto done; } if (need_resched()) { btrfs_release_path(path); cond_resched(); goto search; } } done: btrfs_release_path(path); btrfs_release_path(dst_path); if (ret == 0) { *last_offset_ret = last_offset; /* * In case the leaf was changed in the current transaction but * all its dir items are from a past transaction, the last item * in the leaf is a dir item and there's no gap between that last * dir item and the first one on the next leaf (which did not * change in the current transaction), then we don't need to log * a range, last_old_dentry_offset is == to last_offset. */ ASSERT(last_old_dentry_offset <= last_offset); if (last_old_dentry_offset < last_offset) ret = insert_dir_log_key(trans, log, path, ino, last_old_dentry_offset + 1, last_offset); } return ret; } /* * If the inode was logged before and it was evicted, then its * last_dir_index_offset is (u64)-1, so we don't the value of the last index * key offset. If that's the case, search for it and update the inode. This * is to avoid lookups in the log tree every time we try to insert a dir index * key from a leaf changed in the current transaction, and to allow us to always * do batch insertions of dir index keys. */ static int update_last_dir_index_offset(struct btrfs_inode *inode, struct btrfs_path *path, const struct btrfs_log_ctx *ctx) { const u64 ino = btrfs_ino(inode); struct btrfs_key key; int ret; lockdep_assert_held(&inode->log_mutex); if (inode->last_dir_index_offset != (u64)-1) return 0; if (!ctx->logged_before) { inode->last_dir_index_offset = BTRFS_DIR_START_INDEX - 1; return 0; } key.objectid = ino; key.type = BTRFS_DIR_INDEX_KEY; key.offset = (u64)-1; ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); /* * An error happened or we actually have an index key with an offset * value of (u64)-1. Bail out, we're done. */ if (ret <= 0) goto out; ret = 0; inode->last_dir_index_offset = BTRFS_DIR_START_INDEX - 1; /* * No dir index items, bail out and leave last_dir_index_offset with * the value right before the first valid index value. */ if (path->slots[0] == 0) goto out; /* * btrfs_search_slot() left us at one slot beyond the slot with the last * index key, or beyond the last key of the directory that is not an * index key. If we have an index key before, set last_dir_index_offset * to its offset value, otherwise leave it with a value right before the * first valid index value, as it means we have an empty directory. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0] - 1); if (key.objectid == ino && key.type == BTRFS_DIR_INDEX_KEY) inode->last_dir_index_offset = key.offset; out: btrfs_release_path(path); return ret; } /* * logging directories is very similar to logging inodes, We find all the items * from the current transaction and write them to the log. * * The recovery code scans the directory in the subvolume, and if it finds a * key in the range logged that is not present in the log tree, then it means * that dir entry was unlinked during the transaction. * * In order for that scan to work, we must include one key smaller than * the smallest logged by this transaction and one key larger than the largest * key logged by this transaction. */ static noinline int log_directory_changes(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx) { u64 min_key; u64 max_key; int ret; ret = update_last_dir_index_offset(inode, path, ctx); if (ret) return ret; min_key = BTRFS_DIR_START_INDEX; max_key = 0; while (1) { ret = log_dir_items(trans, inode, path, dst_path, ctx, min_key, &max_key); if (ret) return ret; if (max_key == (u64)-1) break; min_key = max_key + 1; } return 0; } /* * a helper function to drop items from the log before we relog an * inode. max_key_type indicates the highest item type to remove. * This cannot be run for file data extents because it does not * free the extents they point to. */ static int drop_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_inode *inode, int max_key_type) { int ret; struct btrfs_key key; struct btrfs_key found_key; int start_slot; key.objectid = btrfs_ino(inode); key.type = max_key_type; key.offset = (u64)-1; while (1) { ret = btrfs_search_slot(trans, log, &key, path, -1, 1); if (ret < 0) { break; } else if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); if (found_key.objectid != key.objectid) break; found_key.offset = 0; found_key.type = 0; ret = btrfs_bin_search(path->nodes[0], 0, &found_key, &start_slot); if (ret < 0) break; ret = btrfs_del_items(trans, log, path, start_slot, path->slots[0] - start_slot + 1); /* * If start slot isn't 0 then we don't need to re-search, we've * found the last guy with the objectid in this tree. */ if (ret || start_slot != 0) break; btrfs_release_path(path); } btrfs_release_path(path); if (ret > 0) ret = 0; return ret; } static int truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_root *log_root, struct btrfs_inode *inode, u64 new_size, u32 min_type) { struct btrfs_truncate_control control = { .new_size = new_size, .ino = btrfs_ino(inode), .min_type = min_type, .skip_ref_updates = true, }; return btrfs_truncate_inode_items(trans, log_root, &control); } static void fill_inode_item(struct btrfs_trans_handle *trans, struct extent_buffer *leaf, struct btrfs_inode_item *item, struct inode *inode, int log_inode_only, u64 logged_isize) { struct btrfs_map_token token; u64 flags; btrfs_init_map_token(&token, leaf); if (log_inode_only) { /* set the generation to zero so the recover code * can tell the difference between an logging * just to say 'this inode exists' and a logging * to say 'update this inode with these values' */ btrfs_set_token_inode_generation(&token, item, 0); btrfs_set_token_inode_size(&token, item, logged_isize); } else { btrfs_set_token_inode_generation(&token, item, BTRFS_I(inode)->generation); btrfs_set_token_inode_size(&token, item, inode->i_size); } btrfs_set_token_inode_uid(&token, item, i_uid_read(inode)); btrfs_set_token_inode_gid(&token, item, i_gid_read(inode)); btrfs_set_token_inode_mode(&token, item, inode->i_mode); btrfs_set_token_inode_nlink(&token, item, inode->i_nlink); btrfs_set_token_timespec_sec(&token, &item->atime, inode_get_atime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->atime, inode_get_atime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->mtime, inode_get_mtime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->mtime, inode_get_mtime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->ctime, inode_get_ctime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->ctime, inode_get_ctime_nsec(inode)); /* * We do not need to set the nbytes field, in fact during a fast fsync * its value may not even be correct, since a fast fsync does not wait * for ordered extent completion, which is where we update nbytes, it * only waits for writeback to complete. During log replay as we find * file extent items and replay them, we adjust the nbytes field of the * inode item in subvolume tree as needed (see overwrite_item()). */ btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode)); btrfs_set_token_inode_transid(&token, item, trans->transid); btrfs_set_token_inode_rdev(&token, item, inode->i_rdev); flags = btrfs_inode_combine_flags(BTRFS_I(inode)->flags, BTRFS_I(inode)->ro_flags); btrfs_set_token_inode_flags(&token, item, flags); btrfs_set_token_inode_block_group(&token, item, 0); } static int log_inode_item(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, struct btrfs_inode *inode, bool inode_item_dropped) { struct btrfs_inode_item *inode_item; struct btrfs_key key; int ret; btrfs_get_inode_key(inode, &key); /* * If we are doing a fast fsync and the inode was logged before in the * current transaction, then we know the inode was previously logged and * it exists in the log tree. For performance reasons, in this case use * btrfs_search_slot() directly with ins_len set to 0 so that we never * attempt a write lock on the leaf's parent, which adds unnecessary lock * contention in case there are concurrent fsyncs for other inodes of the * same subvolume. Using btrfs_insert_empty_item() when the inode item * already exists can also result in unnecessarily splitting a leaf. */ if (!inode_item_dropped && inode->logged_trans == trans->transid) { ret = btrfs_search_slot(trans, log, &key, path, 0, 1); ASSERT(ret <= 0); if (ret > 0) ret = -ENOENT; } else { /* * This means it is the first fsync in the current transaction, * so the inode item is not in the log and we need to insert it. * We can never get -EEXIST because we are only called for a fast * fsync and in case an inode eviction happens after the inode was * logged before in the current transaction, when we load again * the inode, we set BTRFS_INODE_NEEDS_FULL_SYNC on its runtime * flags and set ->logged_trans to 0. */ ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*inode_item)); ASSERT(ret != -EEXIST); } if (ret) return ret; inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); fill_inode_item(trans, path->nodes[0], inode_item, &inode->vfs_inode, 0, 0); btrfs_release_path(path); return 0; } static int log_csums(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_root *log_root, struct btrfs_ordered_sum *sums) { const u64 lock_end = sums->logical + sums->len - 1; struct extent_state *cached_state = NULL; int ret; /* * If this inode was not used for reflink operations in the current * transaction with new extents, then do the fast path, no need to * worry about logging checksum items with overlapping ranges. */ if (inode->last_reflink_trans < trans->transid) return btrfs_csum_file_blocks(trans, log_root, sums); /* * Serialize logging for checksums. This is to avoid racing with the * same checksum being logged by another task that is logging another * file which happens to refer to the same extent as well. Such races * can leave checksum items in the log with overlapping ranges. */ ret = lock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); if (ret) return ret; /* * Due to extent cloning, we might have logged a csum item that covers a * subrange of a cloned extent, and later we can end up logging a csum * item for a larger subrange of the same extent or the entire range. * This would leave csum items in the log tree that cover the same range * and break the searches for checksums in the log tree, resulting in * some checksums missing in the fs/subvolume tree. So just delete (or * trim and adjust) any existing csum items in the log for this range. */ ret = btrfs_del_csums(trans, log_root, sums->logical, sums->len); if (!ret) ret = btrfs_csum_file_blocks(trans, log_root, sums); unlock_extent(&log_root->log_csum_range, sums->logical, lock_end, &cached_state); return ret; } static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, struct btrfs_path *src_path, int start_slot, int nr, int inode_only, u64 logged_isize, struct btrfs_log_ctx *ctx) { struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item *extent; struct extent_buffer *src; int ret; struct btrfs_key *ins_keys; u32 *ins_sizes; struct btrfs_item_batch batch; char *ins_data; int dst_index; const bool skip_csum = (inode->flags & BTRFS_INODE_NODATASUM); const u64 i_size = i_size_read(&inode->vfs_inode); /* * To keep lockdep happy and avoid deadlocks, clone the source leaf and * use the clone. This is because otherwise we would be changing the log * tree, to insert items from the subvolume tree or insert csum items, * while holding a read lock on a leaf from the subvolume tree, which * creates a nasty lock dependency when COWing log tree nodes/leaves: * * 1) Modifying the log tree triggers an extent buffer allocation while * holding a write lock on a parent extent buffer from the log tree. * Allocating the pages for an extent buffer, or the extent buffer * struct, can trigger inode eviction and finally the inode eviction * will trigger a release/remove of a delayed node, which requires * taking the delayed node's mutex; * * 2) Allocating a metadata extent for a log tree can trigger the async * reclaim thread and make us wait for it to release enough space and * unblock our reservation ticket. The reclaim thread can start * flushing delayed items, and that in turn results in the need to * lock delayed node mutexes and in the need to write lock extent * buffers of a subvolume tree - all this while holding a write lock * on the parent extent buffer in the log tree. * * So one task in scenario 1) running in parallel with another task in * scenario 2) could lead to a deadlock, one wanting to lock a delayed * node mutex while having a read lock on a leaf from the subvolume, * while the other is holding the delayed node's mutex and wants to * write lock the same subvolume leaf for flushing delayed items. */ ret = clone_leaf(src_path, ctx); if (ret < 0) return ret; src = src_path->nodes[0]; ins_data = kmalloc(nr * sizeof(struct btrfs_key) + nr * sizeof(u32), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32)); batch.keys = ins_keys; batch.data_sizes = ins_sizes; batch.total_data_size = 0; batch.nr = 0; dst_index = 0; for (int i = 0; i < nr; i++) { const int src_slot = start_slot + i; struct btrfs_root *csum_root; struct btrfs_ordered_sum *sums; struct btrfs_ordered_sum *sums_next; LIST_HEAD(ordered_sums); u64 disk_bytenr; u64 disk_num_bytes; u64 extent_offset; u64 extent_num_bytes; bool is_old_extent; btrfs_item_key_to_cpu(src, &ins_keys[dst_index], src_slot); if (ins_keys[dst_index].type != BTRFS_EXTENT_DATA_KEY) goto add_to_batch; extent = btrfs_item_ptr(src, src_slot, struct btrfs_file_extent_item); is_old_extent = (btrfs_file_extent_generation(src, extent) < trans->transid); /* * Don't copy extents from past generations. That would make us * log a lot more metadata for common cases like doing only a * few random writes into a file and then fsync it for the first * time or after the full sync flag is set on the inode. We can * get leaves full of extent items, most of which are from past * generations, so we can skip them - as long as the inode has * not been the target of a reflink operation in this transaction, * as in that case it might have had file extent items with old * generations copied into it. We also must always log prealloc * extents that start at or beyond eof, otherwise we would lose * them on log replay. */ if (is_old_extent && ins_keys[dst_index].offset < i_size && inode->last_reflink_trans < trans->transid) continue; if (skip_csum) goto add_to_batch; /* Only regular extents have checksums. */ if (btrfs_file_extent_type(src, extent) != BTRFS_FILE_EXTENT_REG) goto add_to_batch; /* * If it's an extent created in a past transaction, then its * checksums are already accessible from the committed csum tree, * no need to log them. */ if (is_old_extent) goto add_to_batch; disk_bytenr = btrfs_file_extent_disk_bytenr(src, extent); /* If it's an explicit hole, there are no checksums. */ if (disk_bytenr == 0) goto add_to_batch; disk_num_bytes = btrfs_file_extent_disk_num_bytes(src, extent); if (btrfs_file_extent_compression(src, extent)) { extent_offset = 0; extent_num_bytes = disk_num_bytes; } else { extent_offset = btrfs_file_extent_offset(src, extent); extent_num_bytes = btrfs_file_extent_num_bytes(src, extent); } csum_root = btrfs_csum_root(trans->fs_info, disk_bytenr); disk_bytenr += extent_offset; ret = btrfs_lookup_csums_list(csum_root, disk_bytenr, disk_bytenr + extent_num_bytes - 1, &ordered_sums, false); if (ret < 0) goto out; ret = 0; list_for_each_entry_safe(sums, sums_next, &ordered_sums, list) { if (!ret) ret = log_csums(trans, inode, log, sums); list_del(&sums->list); kfree(sums); } if (ret) goto out; add_to_batch: ins_sizes[dst_index] = btrfs_item_size(src, src_slot); batch.total_data_size += ins_sizes[dst_index]; batch.nr++; dst_index++; } /* * We have a leaf full of old extent items that don't need to be logged, * so we don't need to do anything. */ if (batch.nr == 0) goto out; ret = btrfs_insert_empty_items(trans, log, dst_path, &batch); if (ret) goto out; dst_index = 0; for (int i = 0; i < nr; i++) { const int src_slot = start_slot + i; const int dst_slot = dst_path->slots[0] + dst_index; struct btrfs_key key; unsigned long src_offset; unsigned long dst_offset; /* * We're done, all the remaining items in the source leaf * correspond to old file extent items. */ if (dst_index >= batch.nr) break; btrfs_item_key_to_cpu(src, &key, src_slot); if (key.type != BTRFS_EXTENT_DATA_KEY) goto copy_item; extent = btrfs_item_ptr(src, src_slot, struct btrfs_file_extent_item); /* See the comment in the previous loop, same logic. */ if (btrfs_file_extent_generation(src, extent) < trans->transid && key.offset < i_size && inode->last_reflink_trans < trans->transid) continue; copy_item: dst_offset = btrfs_item_ptr_offset(dst_path->nodes[0], dst_slot); src_offset = btrfs_item_ptr_offset(src, src_slot); if (key.type == BTRFS_INODE_ITEM_KEY) { struct btrfs_inode_item *inode_item; inode_item = btrfs_item_ptr(dst_path->nodes[0], dst_slot, struct btrfs_inode_item); fill_inode_item(trans, dst_path->nodes[0], inode_item, &inode->vfs_inode, inode_only == LOG_INODE_EXISTS, logged_isize); } else { copy_extent_buffer(dst_path->nodes[0], src, dst_offset, src_offset, ins_sizes[dst_index]); } dst_index++; } btrfs_mark_buffer_dirty(trans, dst_path->nodes[0]); btrfs_release_path(dst_path); out: kfree(ins_data); return ret; } static int extent_cmp(void *priv, const struct list_head *a, const struct list_head *b) { const struct extent_map *em1, *em2; em1 = list_entry(a, struct extent_map, list); em2 = list_entry(b, struct extent_map, list); if (em1->start < em2->start) return -1; else if (em1->start > em2->start) return 1; return 0; } static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_root *log_root, const struct extent_map *em, struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_root *csum_root; u64 block_start; u64 csum_offset; u64 csum_len; u64 mod_start = em->start; u64 mod_len = em->len; LIST_HEAD(ordered_sums); int ret = 0; if (inode->flags & BTRFS_INODE_NODATASUM || (em->flags & EXTENT_FLAG_PREALLOC) || em->disk_bytenr == EXTENT_MAP_HOLE) return 0; list_for_each_entry(ordered, &ctx->ordered_extents, log_list) { const u64 ordered_end = ordered->file_offset + ordered->num_bytes; const u64 mod_end = mod_start + mod_len; struct btrfs_ordered_sum *sums; if (mod_len == 0) break; if (ordered_end <= mod_start) continue; if (mod_end <= ordered->file_offset) break; /* * We are going to copy all the csums on this ordered extent, so * go ahead and adjust mod_start and mod_len in case this ordered * extent has already been logged. */ if (ordered->file_offset > mod_start) { if (ordered_end >= mod_end) mod_len = ordered->file_offset - mod_start; /* * If we have this case * * |--------- logged extent ---------| * |----- ordered extent ----| * * Just don't mess with mod_start and mod_len, we'll * just end up logging more csums than we need and it * will be ok. */ } else { if (ordered_end < mod_end) { mod_len = mod_end - ordered_end; mod_start = ordered_end; } else { mod_len = 0; } } /* * To keep us from looping for the above case of an ordered * extent that falls inside of the logged extent. */ if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM, &ordered->flags)) continue; list_for_each_entry(sums, &ordered->list, list) { ret = log_csums(trans, inode, log_root, sums); if (ret) return ret; } } /* We're done, found all csums in the ordered extents. */ if (mod_len == 0) return 0; /* If we're compressed we have to save the entire range of csums. */ if (extent_map_is_compressed(em)) { csum_offset = 0; csum_len = em->disk_num_bytes; } else { csum_offset = mod_start - em->start; csum_len = mod_len; } /* block start is already adjusted for the file extent offset. */ block_start = extent_map_block_start(em); csum_root = btrfs_csum_root(trans->fs_info, block_start); ret = btrfs_lookup_csums_list(csum_root, block_start + csum_offset, block_start + csum_offset + csum_len - 1, &ordered_sums, false); if (ret < 0) return ret; ret = 0; while (!list_empty(&ordered_sums)) { struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next, struct btrfs_ordered_sum, list); if (!ret) ret = log_csums(trans, inode, log_root, sums); list_del(&sums->list); kfree(sums); } return ret; } static int log_one_extent(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, const struct extent_map *em, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item fi = { 0 }; struct extent_buffer *leaf; struct btrfs_key key; enum btrfs_compression_type compress_type; u64 extent_offset = em->offset; u64 block_start = extent_map_block_start(em); u64 block_len; int ret; btrfs_set_stack_file_extent_generation(&fi, trans->transid); if (em->flags & EXTENT_FLAG_PREALLOC) btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_PREALLOC); else btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_REG); block_len = em->disk_num_bytes; compress_type = extent_map_compression(em); if (compress_type != BTRFS_COMPRESS_NONE) { btrfs_set_stack_file_extent_disk_bytenr(&fi, block_start); btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len); } else if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) { btrfs_set_stack_file_extent_disk_bytenr(&fi, block_start - extent_offset); btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len); } btrfs_set_stack_file_extent_offset(&fi, extent_offset); btrfs_set_stack_file_extent_num_bytes(&fi, em->len); btrfs_set_stack_file_extent_ram_bytes(&fi, em->ram_bytes); btrfs_set_stack_file_extent_compression(&fi, compress_type); ret = log_extent_csums(trans, inode, log, em, ctx); if (ret) return ret; /* * If this is the first time we are logging the inode in the current * transaction, we can avoid btrfs_drop_extents(), which is expensive * because it does a deletion search, which always acquires write locks * for extent buffers at levels 2, 1 and 0. This not only wastes time * but also adds significant contention in a log tree, since log trees * are small, with a root at level 2 or 3 at most, due to their short * life span. */ if (ctx->logged_before) { drop_args.path = path; drop_args.start = em->start; drop_args.end = em->start + em->len; drop_args.replace_extent = true; drop_args.extent_item_size = sizeof(fi); ret = btrfs_drop_extents(trans, log, inode, &drop_args); if (ret) return ret; } if (!drop_args.extent_inserted) { key.objectid = btrfs_ino(inode); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = em->start; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(fi)); if (ret) return ret; } leaf = path->nodes[0]; write_extent_buffer(leaf, &fi, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(fi)); btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return ret; } /* * Log all prealloc extents beyond the inode's i_size to make sure we do not * lose them after doing a full/fast fsync and replaying the log. We scan the * subvolume's root instead of iterating the inode's extent map tree because * otherwise we can log incorrect extent items based on extent map conversion. * That can happen due to the fact that extent maps are merged when they * are not in the extent map tree's list of modified extents. */ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct btrfs_key key; const u64 i_size = i_size_read(&inode->vfs_inode); const u64 ino = btrfs_ino(inode); struct btrfs_path *dst_path = NULL; bool dropped_extents = false; u64 truncate_offset = i_size; struct extent_buffer *leaf; int slot; int ins_nr = 0; int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) return 0; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = i_size; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; /* * We must check if there is a prealloc extent that starts before the * i_size and crosses the i_size boundary. This is to ensure later we * truncate down to the end of that extent and not to the i_size, as * otherwise we end up losing part of the prealloc extent after a log * replay and with an implicit hole if there is another prealloc extent * that starts at an offset beyond i_size. */ ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY); if (ret < 0) goto out; if (ret == 0) { struct btrfs_file_extent_item *ei; leaf = path->nodes[0]; slot = path->slots[0]; ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_PREALLOC) { u64 extent_end; btrfs_item_key_to_cpu(leaf, &key, slot); extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, ei); if (extent_end > i_size) truncate_offset = extent_end; } } else { ret = 0; } while (true) { leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) goto out; ins_nr = 0; } ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; if (ret > 0) { ret = 0; break; } continue; } btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid > ino) break; if (WARN_ON_ONCE(key.objectid < ino) || key.type < BTRFS_EXTENT_DATA_KEY || key.offset < i_size) { path->slots[0]++; continue; } /* * Avoid overlapping items in the log tree. The first time we * get here, get rid of everything from a past fsync. After * that, if the current extent starts before the end of the last * extent we copied, truncate the last one. This can happen if * an ordered extent completion modifies the subvolume tree * while btrfs_next_leaf() has the tree unlocked. */ if (!dropped_extents || key.offset < truncate_offset) { ret = truncate_inode_items(trans, root->log_root, inode, min(key.offset, truncate_offset), BTRFS_EXTENT_DATA_KEY); if (ret) goto out; dropped_extents = true; } truncate_offset = btrfs_file_extent_end(path); if (ins_nr == 0) start_slot = slot; ins_nr++; path->slots[0]++; if (!dst_path) { dst_path = btrfs_alloc_path(); if (!dst_path) { ret = -ENOMEM; goto out; } } } if (ins_nr > 0) ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); out: btrfs_release_path(path); btrfs_free_path(dst_path); return ret; } static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_ordered_extent *ordered; struct btrfs_ordered_extent *tmp; struct extent_map *em, *n; LIST_HEAD(extents); struct extent_map_tree *tree = &inode->extent_tree; int ret = 0; int num = 0; write_lock(&tree->lock); list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we * have a bunch of extents we just want to commit since it will * be faster. */ if (++num > 32768) { list_del_init(&tree->modified_extents); ret = -EFBIG; goto process; } if (em->generation < trans->transid) continue; /* We log prealloc extents beyond eof later. */ if ((em->flags & EXTENT_FLAG_PREALLOC) && em->start >= i_size_read(&inode->vfs_inode)) continue; /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); em->flags |= EXTENT_FLAG_LOGGING; list_add_tail(&em->list, &extents); num++; } list_sort(NULL, &extents, extent_cmp); process: while (!list_empty(&extents)) { em = list_entry(extents.next, struct extent_map, list); list_del_init(&em->list); /* * If we had an error we just need to delete everybody from our * private list. */ if (ret) { clear_em_logging(inode, em); free_extent_map(em); continue; } write_unlock(&tree->lock); ret = log_one_extent(trans, inode, em, path, ctx); write_lock(&tree->lock); clear_em_logging(inode, em); free_extent_map(em); } WARN_ON(!list_empty(&extents)); write_unlock(&tree->lock); if (!ret) ret = btrfs_log_prealloc_extents(trans, inode, path, ctx); if (ret) return ret; /* * We have logged all extents successfully, now make sure the commit of * the current transaction waits for the ordered extents to complete * before it commits and wipes out the log trees, otherwise we would * lose data if an ordered extents completes after the transaction * commits and a power failure happens after the transaction commit. */ list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) { list_del_init(&ordered->log_list); set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags); if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { spin_lock_irq(&inode->ordered_tree_lock); if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) { set_bit(BTRFS_ORDERED_PENDING, &ordered->flags); atomic_inc(&trans->transaction->pending_ordered); } spin_unlock_irq(&inode->ordered_tree_lock); } btrfs_put_ordered_extent(ordered); } return 0; } static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, struct btrfs_path *path, u64 *size_ret) { struct btrfs_key key; int ret; key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, log, &key, path, 0, 0); if (ret < 0) { return ret; } else if (ret > 0) { *size_ret = 0; } else { struct btrfs_inode_item *item; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); *size_ret = btrfs_inode_size(path->nodes[0], item); /* * If the in-memory inode's i_size is smaller then the inode * size stored in the btree, return the inode's i_size, so * that we get a correct inode size after replaying the log * when before a power failure we had a shrinking truncate * followed by addition of a new name (rename / new hard link). * Otherwise return the inode size from the btree, to avoid * data loss when replaying a log due to previously doing a * write that expands the inode's size and logging a new name * immediately after. */ if (*size_ret > inode->vfs_inode.i_size) *size_ret = inode->vfs_inode.i_size; } btrfs_release_path(path); return 0; } /* * At the moment we always log all xattrs. This is to figure out at log replay * time which xattrs must have their deletion replayed. If a xattr is missing * in the log tree and exists in the fs/subvol tree, we delete it. This is * because if a xattr is deleted, the inode is fsynced and a power failure * happens, causing the log to be replayed the next time the fs is mounted, * we want the xattr to not exist anymore (same behaviour as other filesystems * with a journal, ext3/4, xfs, f2fs, etc). */ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_path *dst_path, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; int ret; struct btrfs_key key; const u64 ino = btrfs_ino(inode); int ins_nr = 0; int start_slot = 0; bool found_xattrs = false; if (test_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags)) return 0; key.objectid = ino; key.type = BTRFS_XATTR_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (true) { int slot = path->slots[0]; struct extent_buffer *leaf = path->nodes[0]; int nritems = btrfs_header_nritems(leaf); if (slot >= nritems) { if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) return ret; ins_nr = 0; } ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; else if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) break; if (ins_nr == 0) start_slot = slot; ins_nr++; path->slots[0]++; found_xattrs = true; cond_resched(); } if (ins_nr > 0) { ret = copy_items(trans, inode, dst_path, path, start_slot, ins_nr, 1, 0, ctx); if (ret < 0) return ret; } if (!found_xattrs) set_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags); return 0; } /* * When using the NO_HOLES feature if we punched a hole that causes the * deletion of entire leafs or all the extent items of the first leaf (the one * that contains the inode item and references) we may end up not processing * any extents, because there are no leafs with a generation matching the * current transaction that have extent items for our inode. So we need to find * if any holes exist and then log them. We also need to log holes after any * truncate operation that changes the inode's size. */ static int btrfs_log_holes(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; const u64 ino = btrfs_ino(inode); const u64 i_size = i_size_read(&inode->vfs_inode); u64 prev_extent_end = 0; int ret; if (!btrfs_fs_incompat(fs_info, NO_HOLES) || i_size == 0) return 0; key.objectid = ino; key.type = BTRFS_EXTENT_DATA_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (true) { struct extent_buffer *leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; if (ret > 0) { ret = 0; break; } leaf = path->nodes[0]; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) break; /* We have a hole, log it. */ if (prev_extent_end < key.offset) { const u64 hole_len = key.offset - prev_extent_end; /* * Release the path to avoid deadlocks with other code * paths that search the root while holding locks on * leafs from the log root. */ btrfs_release_path(path); ret = btrfs_insert_hole_extent(trans, root->log_root, ino, prev_extent_end, hole_len); if (ret < 0) return ret; /* * Search for the same key again in the root. Since it's * an extent item and we are holding the inode lock, the * key must still exist. If it doesn't just emit warning * and return an error to fall back to a transaction * commit. */ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; if (WARN_ON(ret > 0)) return -ENOENT; leaf = path->nodes[0]; } prev_extent_end = btrfs_file_extent_end(path); path->slots[0]++; cond_resched(); } if (prev_extent_end < i_size) { u64 hole_len; btrfs_release_path(path); hole_len = ALIGN(i_size - prev_extent_end, fs_info->sectorsize); ret = btrfs_insert_hole_extent(trans, root->log_root, ino, prev_extent_end, hole_len); if (ret < 0) return ret; } return 0; } /* * When we are logging a new inode X, check if it doesn't have a reference that * matches the reference from some other inode Y created in a past transaction * and that was renamed in the current transaction. If we don't do this, then at * log replay time we can lose inode Y (and all its files if it's a directory): * * mkdir /mnt/x * echo "hello world" > /mnt/x/foobar * sync * mv /mnt/x /mnt/y * mkdir /mnt/x # or touch /mnt/x * xfs_io -c fsync /mnt/x * <power fail> * mount fs, trigger log replay * * After the log replay procedure, we would lose the first directory and all its * files (file foobar). * For the case where inode Y is not a directory we simply end up losing it: * * echo "123" > /mnt/foo * sync * mv /mnt/foo /mnt/bar * echo "abc" > /mnt/foo * xfs_io -c fsync /mnt/foo * <power fail> * * We also need this for cases where a snapshot entry is replaced by some other * entry (file or directory) otherwise we end up with an unreplayable log due to * attempts to delete the snapshot entry (entry of type BTRFS_ROOT_ITEM_KEY) as * if it were a regular entry: * * mkdir /mnt/x * btrfs subvolume snapshot /mnt /mnt/x/snap * btrfs subvolume delete /mnt/x/snap * rmdir /mnt/x * mkdir /mnt/x * fsync /mnt/x or fsync some new file inside it * <power fail> * * The snapshot delete, rmdir of x, mkdir of a new x and the fsync all happen in * the same transaction. */ static int btrfs_check_ref_name_override(struct extent_buffer *eb, const int slot, const struct btrfs_key *key, struct btrfs_inode *inode, u64 *other_ino, u64 *other_parent) { int ret; struct btrfs_path *search_path; char *name = NULL; u32 name_len = 0; u32 item_size = btrfs_item_size(eb, slot); u32 cur_offset = 0; unsigned long ptr = btrfs_item_ptr_offset(eb, slot); search_path = btrfs_alloc_path(); if (!search_path) return -ENOMEM; search_path->search_commit_root = 1; search_path->skip_locking = 1; while (cur_offset < item_size) { u64 parent; u32 this_name_len; u32 this_len; unsigned long name_ptr; struct btrfs_dir_item *di; struct fscrypt_str name_str; if (key->type == BTRFS_INODE_REF_KEY) { struct btrfs_inode_ref *iref; iref = (struct btrfs_inode_ref *)(ptr + cur_offset); parent = key->offset; this_name_len = btrfs_inode_ref_name_len(eb, iref); name_ptr = (unsigned long)(iref + 1); this_len = sizeof(*iref) + this_name_len; } else { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *)(ptr + cur_offset); parent = btrfs_inode_extref_parent(eb, extref); this_name_len = btrfs_inode_extref_name_len(eb, extref); name_ptr = (unsigned long)&extref->name; this_len = sizeof(*extref) + this_name_len; } if (this_name_len > name_len) { char *new_name; new_name = krealloc(name, this_name_len, GFP_NOFS); if (!new_name) { ret = -ENOMEM; goto out; } name_len = this_name_len; name = new_name; } read_extent_buffer(eb, name, name_ptr, this_name_len); name_str.name = name; name_str.len = this_name_len; di = btrfs_lookup_dir_item(NULL, inode->root, search_path, parent, &name_str, 0); if (di && !IS_ERR(di)) { struct btrfs_key di_key; btrfs_dir_item_key_to_cpu(search_path->nodes[0], di, &di_key); if (di_key.type == BTRFS_INODE_ITEM_KEY) { if (di_key.objectid != key->objectid) { ret = 1; *other_ino = di_key.objectid; *other_parent = parent; } else { ret = 0; } } else { ret = -EAGAIN; } goto out; } else if (IS_ERR(di)) { ret = PTR_ERR(di); goto out; } btrfs_release_path(search_path); cur_offset += this_len; } ret = 0; out: btrfs_free_path(search_path); kfree(name); return ret; } /* * Check if we need to log an inode. This is used in contexts where while * logging an inode we need to log another inode (either that it exists or in * full mode). This is used instead of btrfs_inode_in_log() because the later * requires the inode to be in the log and have the log transaction committed, * while here we do not care if the log transaction was already committed - our * caller will commit the log later - and we want to avoid logging an inode * multiple times when multiple tasks have joined the same log transaction. */ static bool need_log_inode(const struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { /* * If a directory was not modified, no dentries added or removed, we can * and should avoid logging it. */ if (S_ISDIR(inode->vfs_inode.i_mode) && inode->last_trans < trans->transid) return false; /* * If this inode does not have new/updated/deleted xattrs since the last * time it was logged and is flagged as logged in the current transaction, * we can skip logging it. As for new/deleted names, those are updated in * the log by link/unlink/rename operations. * In case the inode was logged and then evicted and reloaded, its * logged_trans will be 0, in which case we have to fully log it since * logged_trans is a transient field, not persisted. */ if (inode_logged(trans, inode, NULL) == 1 && !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags)) return false; return true; } struct btrfs_dir_list { u64 ino; struct list_head list; }; /* * Log the inodes of the new dentries of a directory. * See process_dir_items_leaf() for details about why it is needed. * This is a recursive operation - if an existing dentry corresponds to a * directory, that directory's new entries are logged too (same behaviour as * ext3/4, xfs, f2fs, reiserfs, nilfs2). Note that when logging the inodes * the dentries point to we do not acquire their VFS lock, otherwise lockdep * complains about the following circular lock dependency / possible deadlock: * * CPU0 CPU1 * ---- ---- * lock(&type->i_mutex_dir_key#3/2); * lock(sb_internal#2); * lock(&type->i_mutex_dir_key#3/2); * lock(&sb->s_type->i_mutex_key#14); * * Where sb_internal is the lock (a counter that works as a lock) acquired by * sb_start_intwrite() in btrfs_start_transaction(). * Not acquiring the VFS lock of the inodes is still safe because: * * 1) For regular files we log with a mode of LOG_INODE_EXISTS. It's possible * that while logging the inode new references (names) are added or removed * from the inode, leaving the logged inode item with a link count that does * not match the number of logged inode reference items. This is fine because * at log replay time we compute the real number of links and correct the * link count in the inode item (see replay_one_buffer() and * link_to_fixup_dir()); * * 2) For directories we log with a mode of LOG_INODE_ALL. It's possible that * while logging the inode's items new index items (key type * BTRFS_DIR_INDEX_KEY) are added to fs/subvol tree and the logged inode item * has a size that doesn't match the sum of the lengths of all the logged * names - this is ok, not a problem, because at log replay time we set the * directory's i_size to the correct value (see replay_one_name() and * overwrite_item()). */ static int log_new_dir_dentries(struct btrfs_trans_handle *trans, struct btrfs_inode *start_inode, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = start_inode->root; struct btrfs_path *path; LIST_HEAD(dir_list); struct btrfs_dir_list *dir_elem; u64 ino = btrfs_ino(start_inode); struct btrfs_inode *curr_inode = start_inode; int ret = 0; /* * If we are logging a new name, as part of a link or rename operation, * don't bother logging new dentries, as we just want to log the names * of an inode and that any new parents exist. */ if (ctx->logging_new_name) return 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* Pairs with btrfs_add_delayed_iput below. */ ihold(&curr_inode->vfs_inode); while (true) { struct inode *vfs_inode; struct btrfs_key key; struct btrfs_key found_key; u64 next_index; bool continue_curr_inode = true; int iter_ret; key.objectid = ino; key.type = BTRFS_DIR_INDEX_KEY; key.offset = btrfs_get_first_dir_index_to_log(curr_inode); next_index = key.offset; again: btrfs_for_each_slot(root->log_root, &key, &found_key, path, iter_ret) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_dir_item *di; struct btrfs_key di_key; struct inode *di_inode; int log_mode = LOG_INODE_EXISTS; int type; if (found_key.objectid != ino || found_key.type != BTRFS_DIR_INDEX_KEY) { continue_curr_inode = false; break; } next_index = found_key.offset + 1; di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); type = btrfs_dir_ftype(leaf, di); if (btrfs_dir_transid(leaf, di) < trans->transid) continue; btrfs_dir_item_key_to_cpu(leaf, di, &di_key); if (di_key.type == BTRFS_ROOT_ITEM_KEY) continue; btrfs_release_path(path); di_inode = btrfs_iget_logging(di_key.objectid, root); if (IS_ERR(di_inode)) { ret = PTR_ERR(di_inode); goto out; } if (!need_log_inode(trans, BTRFS_I(di_inode))) { btrfs_add_delayed_iput(BTRFS_I(di_inode)); break; } ctx->log_new_dentries = false; if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, BTRFS_I(di_inode), log_mode, ctx); btrfs_add_delayed_iput(BTRFS_I(di_inode)); if (ret) goto out; if (ctx->log_new_dentries) { dir_elem = kmalloc(sizeof(*dir_elem), GFP_NOFS); if (!dir_elem) { ret = -ENOMEM; goto out; } dir_elem->ino = di_key.objectid; list_add_tail(&dir_elem->list, &dir_list); } break; } btrfs_release_path(path); if (iter_ret < 0) { ret = iter_ret; goto out; } else if (iter_ret > 0) { continue_curr_inode = false; } else { key = found_key; } if (continue_curr_inode && key.offset < (u64)-1) { key.offset++; goto again; } btrfs_set_first_dir_index_to_log(curr_inode, next_index); if (list_empty(&dir_list)) break; dir_elem = list_first_entry(&dir_list, struct btrfs_dir_list, list); ino = dir_elem->ino; list_del(&dir_elem->list); kfree(dir_elem); btrfs_add_delayed_iput(curr_inode); curr_inode = NULL; vfs_inode = btrfs_iget_logging(ino, root); if (IS_ERR(vfs_inode)) { ret = PTR_ERR(vfs_inode); break; } curr_inode = BTRFS_I(vfs_inode); } out: btrfs_free_path(path); if (curr_inode) btrfs_add_delayed_iput(curr_inode); if (ret) { struct btrfs_dir_list *next; list_for_each_entry_safe(dir_elem, next, &dir_list, list) kfree(dir_elem); } return ret; } struct btrfs_ino_list { u64 ino; u64 parent; struct list_head list; }; static void free_conflicting_inodes(struct btrfs_log_ctx *ctx) { struct btrfs_ino_list *curr; struct btrfs_ino_list *next; list_for_each_entry_safe(curr, next, &ctx->conflict_inodes, list) { list_del(&curr->list); kfree(curr); } } static int conflicting_inode_is_dir(struct btrfs_root *root, u64 ino, struct btrfs_path *path) { struct btrfs_key key; int ret; key.objectid = ino; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; path->search_commit_root = 1; path->skip_locking = 1; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (WARN_ON_ONCE(ret > 0)) { /* * We have previously found the inode through the commit root * so this should not happen. If it does, just error out and * fallback to a transaction commit. */ ret = -ENOENT; } else if (ret == 0) { struct btrfs_inode_item *item; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); if (S_ISDIR(btrfs_inode_mode(path->nodes[0], item))) ret = 1; } btrfs_release_path(path); path->search_commit_root = 0; path->skip_locking = 0; return ret; } static int add_conflicting_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 ino, u64 parent, struct btrfs_log_ctx *ctx) { struct btrfs_ino_list *ino_elem; struct inode *inode; /* * It's rare to have a lot of conflicting inodes, in practice it is not * common to have more than 1 or 2. We don't want to collect too many, * as we could end up logging too many inodes (even if only in * LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction * commits. */ if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) return BTRFS_LOG_FORCE_COMMIT; inode = btrfs_iget_logging(ino, root); /* * If the other inode that had a conflicting dir entry was deleted in * the current transaction then we either: * * 1) Log the parent directory (later after adding it to the list) if * the inode is a directory. This is because it may be a deleted * subvolume/snapshot or it may be a regular directory that had * deleted subvolumes/snapshots (or subdirectories that had them), * and at the moment we can't deal with dropping subvolumes/snapshots * during log replay. So we just log the parent, which will result in * a fallback to a transaction commit if we are dealing with those * cases (last_unlink_trans will match the current transaction); * * 2) Do nothing if it's not a directory. During log replay we simply * unlink the conflicting dentry from the parent directory and then * add the dentry for our inode. Like this we can avoid logging the * parent directory (and maybe fallback to a transaction commit in * case it has a last_unlink_trans == trans->transid, due to moving * some inode from it to some other directory). */ if (IS_ERR(inode)) { int ret = PTR_ERR(inode); if (ret != -ENOENT) return ret; ret = conflicting_inode_is_dir(root, ino, path); /* Not a directory or we got an error. */ if (ret <= 0) return ret; /* Conflicting inode is a directory, so we'll log its parent. */ ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); if (!ino_elem) return -ENOMEM; ino_elem->ino = ino; ino_elem->parent = parent; list_add_tail(&ino_elem->list, &ctx->conflict_inodes); ctx->num_conflict_inodes++; return 0; } /* * If the inode was already logged skip it - otherwise we can hit an * infinite loop. Example: * * From the commit root (previous transaction) we have the following * inodes: * * inode 257 a directory * inode 258 with references "zz" and "zz_link" on inode 257 * inode 259 with reference "a" on inode 257 * * And in the current (uncommitted) transaction we have: * * inode 257 a directory, unchanged * inode 258 with references "a" and "a2" on inode 257 * inode 259 with reference "zz_link" on inode 257 * inode 261 with reference "zz" on inode 257 * * When logging inode 261 the following infinite loop could * happen if we don't skip already logged inodes: * * - we detect inode 258 as a conflicting inode, with inode 261 * on reference "zz", and log it; * * - we detect inode 259 as a conflicting inode, with inode 258 * on reference "a", and log it; * * - we detect inode 258 as a conflicting inode, with inode 259 * on reference "zz_link", and log it - again! After this we * repeat the above steps forever. * * Here we can use need_log_inode() because we only need to log the * inode in LOG_INODE_EXISTS mode and rename operations update the log, * so that the log ends up with the new name and without the old name. */ if (!need_log_inode(trans, BTRFS_I(inode))) { btrfs_add_delayed_iput(BTRFS_I(inode)); return 0; } btrfs_add_delayed_iput(BTRFS_I(inode)); ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); if (!ino_elem) return -ENOMEM; ino_elem->ino = ino; ino_elem->parent = parent; list_add_tail(&ino_elem->list, &ctx->conflict_inodes); ctx->num_conflict_inodes++; return 0; } static int log_conflicting_inodes(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_log_ctx *ctx) { int ret = 0; /* * Conflicting inodes are logged by the first call to btrfs_log_inode(), * otherwise we could have unbounded recursion of btrfs_log_inode() * calls. This check guarantees we can have only 1 level of recursion. */ if (ctx->logging_conflict_inodes) return 0; ctx->logging_conflict_inodes = true; /* * New conflicting inodes may be found and added to the list while we * are logging a conflicting inode, so keep iterating while the list is * not empty. */ while (!list_empty(&ctx->conflict_inodes)) { struct btrfs_ino_list *curr; struct inode *inode; u64 ino; u64 parent; curr = list_first_entry(&ctx->conflict_inodes, struct btrfs_ino_list, list); ino = curr->ino; parent = curr->parent; list_del(&curr->list); kfree(curr); inode = btrfs_iget_logging(ino, root); /* * If the other inode that had a conflicting dir entry was * deleted in the current transaction, we need to log its parent * directory. See the comment at add_conflicting_inode(). */ if (IS_ERR(inode)) { ret = PTR_ERR(inode); if (ret != -ENOENT) break; inode = btrfs_iget_logging(parent, root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); break; } /* * Always log the directory, we cannot make this * conditional on need_log_inode() because the directory * might have been logged in LOG_INODE_EXISTS mode or * the dir index of the conflicting inode is not in a * dir index key range logged for the directory. So we * must make sure the deletion is recorded. */ ret = btrfs_log_inode(trans, BTRFS_I(inode), LOG_INODE_ALL, ctx); btrfs_add_delayed_iput(BTRFS_I(inode)); if (ret) break; continue; } /* * Here we can use need_log_inode() because we only need to log * the inode in LOG_INODE_EXISTS mode and rename operations * update the log, so that the log ends up with the new name and * without the old name. * * We did this check at add_conflicting_inode(), but here we do * it again because if some other task logged the inode after * that, we can avoid doing it again. */ if (!need_log_inode(trans, BTRFS_I(inode))) { btrfs_add_delayed_iput(BTRFS_I(inode)); continue; } /* * We are safe logging the other inode without acquiring its * lock as long as we log with the LOG_INODE_EXISTS mode. We * are safe against concurrent renames of the other inode as * well because during a rename we pin the log and update the * log with the new name before we unpin it. */ ret = btrfs_log_inode(trans, BTRFS_I(inode), LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(BTRFS_I(inode)); if (ret) break; } ctx->logging_conflict_inodes = false; if (ret) free_conflicting_inodes(ctx); return ret; } static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_key *min_key, const struct btrfs_key *max_key, struct btrfs_path *path, struct btrfs_path *dst_path, const u64 logged_isize, const int inode_only, struct btrfs_log_ctx *ctx, bool *need_log_inode_item) { const u64 i_size = i_size_read(&inode->vfs_inode); struct btrfs_root *root = inode->root; int ins_start_slot = 0; int ins_nr = 0; int ret; while (1) { ret = btrfs_search_forward(root, min_key, path, trans->transid); if (ret < 0) return ret; if (ret > 0) { ret = 0; break; } again: /* Note, ins_nr might be > 0 here, cleanup outside the loop */ if (min_key->objectid != max_key->objectid) break; if (min_key->type > max_key->type) break; if (min_key->type == BTRFS_INODE_ITEM_KEY) { *need_log_inode_item = false; } else if (min_key->type == BTRFS_EXTENT_DATA_KEY && min_key->offset >= i_size) { /* * Extents at and beyond eof are logged with * btrfs_log_prealloc_extents(). * Only regular files have BTRFS_EXTENT_DATA_KEY keys, * and no keys greater than that, so bail out. */ break; } else if ((min_key->type == BTRFS_INODE_REF_KEY || min_key->type == BTRFS_INODE_EXTREF_KEY) && (inode->generation == trans->transid || ctx->logging_conflict_inodes)) { u64 other_ino = 0; u64 other_parent = 0; ret = btrfs_check_ref_name_override(path->nodes[0], path->slots[0], min_key, inode, &other_ino, &other_parent); if (ret < 0) { return ret; } else if (ret > 0 && other_ino != btrfs_ino(ctx->inode)) { if (ins_nr > 0) { ins_nr++; } else { ins_nr = 1; ins_start_slot = path->slots[0]; } ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; btrfs_release_path(path); ret = add_conflicting_inode(trans, root, path, other_ino, other_parent, ctx); if (ret) return ret; goto next_key; } } else if (min_key->type == BTRFS_XATTR_ITEM_KEY) { /* Skip xattrs, logged later with btrfs_log_all_xattrs() */ if (ins_nr == 0) goto next_slot; ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; goto next_slot; } if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { ins_nr++; goto next_slot; } else if (!ins_nr) { ins_start_slot = path->slots[0]; ins_nr = 1; goto next_slot; } ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 1; ins_start_slot = path->slots[0]; next_slot: path->slots[0]++; if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { btrfs_item_key_to_cpu(path->nodes[0], min_key, path->slots[0]); goto again; } if (ins_nr) { ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret < 0) return ret; ins_nr = 0; } btrfs_release_path(path); next_key: if (min_key->offset < (u64)-1) { min_key->offset++; } else if (min_key->type < max_key->type) { min_key->type++; min_key->offset = 0; } else { break; } /* * We may process many leaves full of items for our inode, so * avoid monopolizing a cpu for too long by rescheduling while * not holding locks on any tree. */ cond_resched(); } if (ins_nr) { ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize, ctx); if (ret) return ret; } if (inode_only == LOG_INODE_ALL && S_ISREG(inode->vfs_inode.i_mode)) { /* * Release the path because otherwise we might attempt to double * lock the same leaf with btrfs_log_prealloc_extents() below. */ btrfs_release_path(path); ret = btrfs_log_prealloc_extents(trans, inode, dst_path, ctx); } return ret; } static int insert_delayed_items_batch(struct btrfs_trans_handle *trans, struct btrfs_root *log, struct btrfs_path *path, const struct btrfs_item_batch *batch, const struct btrfs_delayed_item *first_item) { const struct btrfs_delayed_item *curr = first_item; int ret; ret = btrfs_insert_empty_items(trans, log, path, batch); if (ret) return ret; for (int i = 0; i < batch->nr; i++) { char *data_ptr; data_ptr = btrfs_item_ptr(path->nodes[0], path->slots[0], char); write_extent_buffer(path->nodes[0], &curr->data, (unsigned long)data_ptr, curr->data_len); curr = list_next_entry(curr, log_list); path->slots[0]++; } btrfs_release_path(path); return 0; } static int log_delayed_insertion_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_ins_list, struct btrfs_log_ctx *ctx) { /* 195 (4095 bytes of keys and sizes) fits in a single 4K page. */ const int max_batch_size = 195; const int leaf_data_size = BTRFS_LEAF_DATA_SIZE(trans->fs_info); const u64 ino = btrfs_ino(inode); struct btrfs_root *log = inode->root->log_root; struct btrfs_item_batch batch = { .nr = 0, .total_data_size = 0, }; const struct btrfs_delayed_item *first = NULL; const struct btrfs_delayed_item *curr; char *ins_data; struct btrfs_key *ins_keys; u32 *ins_sizes; u64 curr_batch_size = 0; int batch_idx = 0; int ret; /* We are adding dir index items to the log tree. */ lockdep_assert_held(&inode->log_mutex); /* * We collect delayed items before copying index keys from the subvolume * to the log tree. However just after we collected them, they may have * been flushed (all of them or just some of them), and therefore we * could have copied them from the subvolume tree to the log tree. * So find the first delayed item that was not yet logged (they are * sorted by index number). */ list_for_each_entry(curr, delayed_ins_list, log_list) { if (curr->index > inode->last_dir_index_offset) { first = curr; break; } } /* Empty list or all delayed items were already logged. */ if (!first) return 0; ins_data = kmalloc(max_batch_size * sizeof(u32) + max_batch_size * sizeof(struct btrfs_key), GFP_NOFS); if (!ins_data) return -ENOMEM; ins_sizes = (u32 *)ins_data; batch.data_sizes = ins_sizes; ins_keys = (struct btrfs_key *)(ins_data + max_batch_size * sizeof(u32)); batch.keys = ins_keys; curr = first; while (!list_entry_is_head(curr, delayed_ins_list, log_list)) { const u32 curr_size = curr->data_len + sizeof(struct btrfs_item); if (curr_batch_size + curr_size > leaf_data_size || batch.nr == max_batch_size) { ret = insert_delayed_items_batch(trans, log, path, &batch, first); if (ret) goto out; batch_idx = 0; batch.nr = 0; batch.total_data_size = 0; curr_batch_size = 0; first = curr; } ins_sizes[batch_idx] = curr->data_len; ins_keys[batch_idx].objectid = ino; ins_keys[batch_idx].type = BTRFS_DIR_INDEX_KEY; ins_keys[batch_idx].offset = curr->index; curr_batch_size += curr_size; batch.total_data_size += curr->data_len; batch.nr++; batch_idx++; curr = list_next_entry(curr, log_list); } ASSERT(batch.nr >= 1); ret = insert_delayed_items_batch(trans, log, path, &batch, first); curr = list_last_entry(delayed_ins_list, struct btrfs_delayed_item, log_list); inode->last_dir_index_offset = curr->index; out: kfree(ins_data); return ret; } static int log_delayed_deletions_full(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { const u64 ino = btrfs_ino(inode); const struct btrfs_delayed_item *curr; curr = list_first_entry(delayed_del_list, struct btrfs_delayed_item, log_list); while (!list_entry_is_head(curr, delayed_del_list, log_list)) { u64 first_dir_index = curr->index; u64 last_dir_index; const struct btrfs_delayed_item *next; int ret; /* * Find a range of consecutive dir index items to delete. Like * this we log a single dir range item spanning several contiguous * dir items instead of logging one range item per dir index item. */ next = list_next_entry(curr, log_list); while (!list_entry_is_head(next, delayed_del_list, log_list)) { if (next->index != curr->index + 1) break; curr = next; next = list_next_entry(next, log_list); } last_dir_index = curr->index; ASSERT(last_dir_index >= first_dir_index); ret = insert_dir_log_key(trans, inode->root->log_root, path, ino, first_dir_index, last_dir_index); if (ret) return ret; curr = list_next_entry(curr, log_list); } return 0; } static int batch_delete_dir_index_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, struct btrfs_log_ctx *ctx, const struct list_head *delayed_del_list, const struct btrfs_delayed_item *first, const struct btrfs_delayed_item **last_ret) { const struct btrfs_delayed_item *next; struct extent_buffer *leaf = path->nodes[0]; const int last_slot = btrfs_header_nritems(leaf) - 1; int slot = path->slots[0] + 1; const u64 ino = btrfs_ino(inode); next = list_next_entry(first, log_list); while (slot < last_slot && !list_entry_is_head(next, delayed_del_list, log_list)) { struct btrfs_key key; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ino || key.type != BTRFS_DIR_INDEX_KEY || key.offset != next->index) break; slot++; *last_ret = next; next = list_next_entry(next, log_list); } return btrfs_del_items(trans, inode->root->log_root, path, path->slots[0], slot - path->slots[0]); } static int log_delayed_deletions_incremental(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { struct btrfs_root *log = inode->root->log_root; const struct btrfs_delayed_item *curr; u64 last_range_start = 0; u64 last_range_end = 0; struct btrfs_key key; key.objectid = btrfs_ino(inode); key.type = BTRFS_DIR_INDEX_KEY; curr = list_first_entry(delayed_del_list, struct btrfs_delayed_item, log_list); while (!list_entry_is_head(curr, delayed_del_list, log_list)) { const struct btrfs_delayed_item *last = curr; u64 first_dir_index = curr->index; u64 last_dir_index; bool deleted_items = false; int ret; key.offset = curr->index; ret = btrfs_search_slot(trans, log, &key, path, -1, 1); if (ret < 0) { return ret; } else if (ret == 0) { ret = batch_delete_dir_index_items(trans, inode, path, ctx, delayed_del_list, curr, &last); if (ret) return ret; deleted_items = true; } btrfs_release_path(path); /* * If we deleted items from the leaf, it means we have a range * item logging their range, so no need to add one or update an * existing one. Otherwise we have to log a dir range item. */ if (deleted_items) goto next_batch; last_dir_index = last->index; ASSERT(last_dir_index >= first_dir_index); /* * If this range starts right after where the previous one ends, * then we want to reuse the previous range item and change its * end offset to the end of this range. This is just to minimize * leaf space usage, by avoiding adding a new range item. */ if (last_range_end != 0 && first_dir_index == last_range_end + 1) first_dir_index = last_range_start; ret = insert_dir_log_key(trans, log, path, key.objectid, first_dir_index, last_dir_index); if (ret) return ret; last_range_start = first_dir_index; last_range_end = last_dir_index; next_batch: curr = list_next_entry(last, log_list); } return 0; } static int log_delayed_deletion_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *path, const struct list_head *delayed_del_list, struct btrfs_log_ctx *ctx) { /* * We are deleting dir index items from the log tree or adding range * items to it. */ lockdep_assert_held(&inode->log_mutex); if (list_empty(delayed_del_list)) return 0; if (ctx->logged_before) return log_delayed_deletions_incremental(trans, inode, path, delayed_del_list, ctx); return log_delayed_deletions_full(trans, inode, path, delayed_del_list, ctx); } /* * Similar logic as for log_new_dir_dentries(), but it iterates over the delayed * items instead of the subvolume tree. */ static int log_new_delayed_dentries(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, const struct list_head *delayed_ins_list, struct btrfs_log_ctx *ctx) { const bool orig_log_new_dentries = ctx->log_new_dentries; struct btrfs_delayed_item *item; int ret = 0; /* * No need for the log mutex, plus to avoid potential deadlocks or * lockdep annotations due to nesting of delayed inode mutexes and log * mutexes. */ lockdep_assert_not_held(&inode->log_mutex); ASSERT(!ctx->logging_new_delayed_dentries); ctx->logging_new_delayed_dentries = true; list_for_each_entry(item, delayed_ins_list, log_list) { struct btrfs_dir_item *dir_item; struct inode *di_inode; struct btrfs_key key; int log_mode = LOG_INODE_EXISTS; dir_item = (struct btrfs_dir_item *)item->data; btrfs_disk_key_to_cpu(&key, &dir_item->location); if (key.type == BTRFS_ROOT_ITEM_KEY) continue; di_inode = btrfs_iget_logging(key.objectid, inode->root); if (IS_ERR(di_inode)) { ret = PTR_ERR(di_inode); break; } if (!need_log_inode(trans, BTRFS_I(di_inode))) { btrfs_add_delayed_iput(BTRFS_I(di_inode)); continue; } if (btrfs_stack_dir_ftype(dir_item) == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, BTRFS_I(di_inode), log_mode, ctx); if (!ret && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, BTRFS_I(di_inode), ctx); btrfs_add_delayed_iput(BTRFS_I(di_inode)); if (ret) break; } ctx->log_new_dentries = orig_log_new_dentries; ctx->logging_new_delayed_dentries = false; return ret; } /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. * * Any items from this inode changed by the current transaction are copied * to the log tree. An extra reference is taken on any extents in this * file, allowing us to avoid a whole pile of corner cases around logging * blocks that have been removed from the tree. * * See LOG_INODE_ALL and related defines for a description of what inode_only * does. * * This handles both files and directories. */ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, int inode_only, struct btrfs_log_ctx *ctx) { struct btrfs_path *path; struct btrfs_path *dst_path; struct btrfs_key min_key; struct btrfs_key max_key; struct btrfs_root *log = inode->root->log_root; int ret; bool fast_search = false; u64 ino = btrfs_ino(inode); struct extent_map_tree *em_tree = &inode->extent_tree; u64 logged_isize = 0; bool need_log_inode_item = true; bool xattrs_logged = false; bool inode_item_dropped = true; bool full_dir_logging = false; LIST_HEAD(delayed_ins_list); LIST_HEAD(delayed_del_list); path = btrfs_alloc_path(); if (!path) return -ENOMEM; dst_path = btrfs_alloc_path(); if (!dst_path) { btrfs_free_path(path); return -ENOMEM; } min_key.objectid = ino; min_key.type = BTRFS_INODE_ITEM_KEY; min_key.offset = 0; max_key.objectid = ino; /* today the code can only do partial logging of directories */ if (S_ISDIR(inode->vfs_inode.i_mode) || (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) && inode_only >= LOG_INODE_EXISTS)) max_key.type = BTRFS_XATTR_ITEM_KEY; else max_key.type = (u8)-1; max_key.offset = (u64)-1; if (S_ISDIR(inode->vfs_inode.i_mode) && inode_only == LOG_INODE_ALL) full_dir_logging = true; /* * If we are logging a directory while we are logging dentries of the * delayed items of some other inode, then we need to flush the delayed * items of this directory and not log the delayed items directly. This * is to prevent more than one level of recursion into btrfs_log_inode() * by having something like this: * * $ mkdir -p a/b/c/d/e/f/g/h/... * $ xfs_io -c "fsync" a * * Where all directories in the path did not exist before and are * created in the current transaction. * So in such a case we directly log the delayed items of the main * directory ("a") without flushing them first, while for each of its * subdirectories we flush their delayed items before logging them. * This prevents a potential unbounded recursion like this: * * btrfs_log_inode() * log_new_delayed_dentries() * btrfs_log_inode() * log_new_delayed_dentries() * btrfs_log_inode() * log_new_delayed_dentries() * (...) * * We have thresholds for the maximum number of delayed items to have in * memory, and once they are hit, the items are flushed asynchronously. * However the limit is quite high, so lets prevent deep levels of * recursion to happen by limiting the maximum depth to be 1. */ if (full_dir_logging && ctx->logging_new_delayed_dentries) { ret = btrfs_commit_inode_delayed_items(trans, inode); if (ret) goto out; } mutex_lock(&inode->log_mutex); /* * For symlinks, we must always log their content, which is stored in an * inline extent, otherwise we could end up with an empty symlink after * log replay, which is invalid on linux (symlink(2) returns -ENOENT if * one attempts to create an empty symlink). * We don't need to worry about flushing delalloc, because when we create * the inline extent when the symlink is created (we never have delalloc * for symlinks). */ if (S_ISLNK(inode->vfs_inode.i_mode)) inode_only = LOG_INODE_ALL; /* * Before logging the inode item, cache the value returned by * inode_logged(), because after that we have the need to figure out if * the inode was previously logged in this transaction. */ ret = inode_logged(trans, inode, path); if (ret < 0) goto out_unlock; ctx->logged_before = (ret == 1); ret = 0; /* * This is for cases where logging a directory could result in losing a * a file after replaying the log. For example, if we move a file from a * directory A to a directory B, then fsync directory A, we have no way * to known the file was moved from A to B, so logging just A would * result in losing the file after a log replay. */ if (full_dir_logging && inode->last_unlink_trans >= trans->transid) { ret = BTRFS_LOG_FORCE_COMMIT; goto out_unlock; } /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ if (S_ISDIR(inode->vfs_inode.i_mode)) { clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, BTRFS_XATTR_ITEM_KEY); } else { if (inode_only == LOG_INODE_EXISTS && ctx->logged_before) { /* * Make sure the new inode item we write to the log has * the same isize as the current one (if it exists). * This is necessary to prevent data loss after log * replay, and also to prevent doing a wrong expanding * truncate - for e.g. create file, write 4K into offset * 0, fsync, write 4K into offset 4096, add hard link, * fsync some other file (to sync log), power fail - if * we use the inode's current i_size, after log replay * we get a 8Kb file, with the last 4Kb extent as a hole * (zeroes), as if an expanding truncate happened, * instead of getting a file of 4Kb only. */ ret = logged_inode_size(log, inode, path, &logged_isize); if (ret) goto out_unlock; } if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) { if (inode_only == LOG_INODE_EXISTS) { max_key.type = BTRFS_XATTR_ITEM_KEY; if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, max_key.type); } else { clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags); clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); if (ctx->logged_before) ret = truncate_inode_items(trans, log, inode, 0, 0); } } else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags) || inode_only == LOG_INODE_EXISTS) { if (inode_only == LOG_INODE_ALL) fast_search = true; max_key.type = BTRFS_XATTR_ITEM_KEY; if (ctx->logged_before) ret = drop_inode_items(trans, log, path, inode, max_key.type); } else { if (inode_only == LOG_INODE_ALL) fast_search = true; inode_item_dropped = false; goto log_extents; } } if (ret) goto out_unlock; /* * If we are logging a directory in full mode, collect the delayed items * before iterating the subvolume tree, so that we don't miss any new * dir index items in case they get flushed while or right after we are * iterating the subvolume tree. */ if (full_dir_logging && !ctx->logging_new_delayed_dentries) btrfs_log_get_delayed_items(inode, &delayed_ins_list, &delayed_del_list); ret = copy_inode_items_to_log(trans, inode, &min_key, &max_key, path, dst_path, logged_isize, inode_only, ctx, &need_log_inode_item); if (ret) goto out_unlock; btrfs_release_path(path); btrfs_release_path(dst_path); ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; xattrs_logged = true; if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) { btrfs_release_path(path); btrfs_release_path(dst_path); ret = btrfs_log_holes(trans, inode, path); if (ret) goto out_unlock; } log_extents: btrfs_release_path(path); btrfs_release_path(dst_path); if (need_log_inode_item) { ret = log_inode_item(trans, log, dst_path, inode, inode_item_dropped); if (ret) goto out_unlock; /* * If we are doing a fast fsync and the inode was logged before * in this transaction, we don't need to log the xattrs because * they were logged before. If xattrs were added, changed or * deleted since the last time we logged the inode, then we have * already logged them because the inode had the runtime flag * BTRFS_INODE_COPY_EVERYTHING set. */ if (!xattrs_logged && inode->logged_trans < trans->transid) { ret = btrfs_log_all_xattrs(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; btrfs_release_path(path); } } if (fast_search) { ret = btrfs_log_changed_extents(trans, inode, dst_path, ctx); if (ret) goto out_unlock; } else if (inode_only == LOG_INODE_ALL) { struct extent_map *em, *n; write_lock(&em_tree->lock); list_for_each_entry_safe(em, n, &em_tree->modified_extents, list) list_del_init(&em->list); write_unlock(&em_tree->lock); } if (full_dir_logging) { ret = log_directory_changes(trans, inode, path, dst_path, ctx); if (ret) goto out_unlock; ret = log_delayed_insertion_items(trans, inode, path, &delayed_ins_list, ctx); if (ret) goto out_unlock; ret = log_delayed_deletion_items(trans, inode, path, &delayed_del_list, ctx); if (ret) goto out_unlock; } spin_lock(&inode->lock); inode->logged_trans = trans->transid; /* * Don't update last_log_commit if we logged that an inode exists. * We do this for three reasons: * * 1) We might have had buffered writes to this inode that were * flushed and had their ordered extents completed in this * transaction, but we did not previously log the inode with * LOG_INODE_ALL. Later the inode was evicted and after that * it was loaded again and this LOG_INODE_EXISTS log operation * happened. We must make sure that if an explicit fsync against * the inode is performed later, it logs the new extents, an * updated inode item, etc, and syncs the log. The same logic * applies to direct IO writes instead of buffered writes. * * 2) When we log the inode with LOG_INODE_EXISTS, its inode item * is logged with an i_size of 0 or whatever value was logged * before. If later the i_size of the inode is increased by a * truncate operation, the log is synced through an fsync of * some other inode and then finally an explicit fsync against * this inode is made, we must make sure this fsync logs the * inode with the new i_size, the hole between old i_size and * the new i_size, and syncs the log. * * 3) If we are logging that an ancestor inode exists as part of * logging a new name from a link or rename operation, don't update * its last_log_commit - otherwise if an explicit fsync is made * against an ancestor, the fsync considers the inode in the log * and doesn't sync the log, resulting in the ancestor missing after * a power failure unless the log was synced as part of an fsync * against any other unrelated inode. */ if (inode_only != LOG_INODE_EXISTS) inode->last_log_commit = inode->last_sub_trans; spin_unlock(&inode->lock); /* * Reset the last_reflink_trans so that the next fsync does not need to * go through the slower path when logging extents and their checksums. */ if (inode_only == LOG_INODE_ALL) inode->last_reflink_trans = 0; out_unlock: mutex_unlock(&inode->log_mutex); out: btrfs_free_path(path); btrfs_free_path(dst_path); if (ret) free_conflicting_inodes(ctx); else ret = log_conflicting_inodes(trans, inode->root, ctx); if (full_dir_logging && !ctx->logging_new_delayed_dentries) { if (!ret) ret = log_new_delayed_dentries(trans, inode, &delayed_ins_list, ctx); btrfs_log_put_delayed_items(inode, &delayed_ins_list, &delayed_del_list); } return ret; } static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_log_ctx *ctx) { int ret; struct btrfs_path *path; struct btrfs_key key; struct btrfs_root *root = inode->root; const u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); if (!path) return -ENOMEM; path->skip_locking = 1; path->search_commit_root = 1; key.objectid = ino; key.type = BTRFS_INODE_REF_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; while (true) { struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; u32 cur_offset = 0; u32 item_size; unsigned long ptr; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; else if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &key, slot); /* BTRFS_INODE_EXTREF_KEY is BTRFS_INODE_REF_KEY + 1 */ if (key.objectid != ino || key.type > BTRFS_INODE_EXTREF_KEY) break; item_size = btrfs_item_size(leaf, slot); ptr = btrfs_item_ptr_offset(leaf, slot); while (cur_offset < item_size) { struct btrfs_key inode_key; struct inode *dir_inode; inode_key.type = BTRFS_INODE_ITEM_KEY; inode_key.offset = 0; if (key.type == BTRFS_INODE_EXTREF_KEY) { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *) (ptr + cur_offset); inode_key.objectid = btrfs_inode_extref_parent( leaf, extref); cur_offset += sizeof(*extref); cur_offset += btrfs_inode_extref_name_len(leaf, extref); } else { inode_key.objectid = key.offset; cur_offset = item_size; } dir_inode = btrfs_iget_logging(inode_key.objectid, root); /* * If the parent inode was deleted, return an error to * fallback to a transaction commit. This is to prevent * getting an inode that was moved from one parent A to * a parent B, got its former parent A deleted and then * it got fsync'ed, from existing at both parents after * a log replay (and the old parent still existing). * Example: * * mkdir /mnt/A * mkdir /mnt/B * touch /mnt/B/bar * sync * mv /mnt/B/bar /mnt/A/bar * mv -T /mnt/A /mnt/B * fsync /mnt/B/bar * <power fail> * * If we ignore the old parent B which got deleted, * after a log replay we would have file bar linked * at both parents and the old parent B would still * exist. */ if (IS_ERR(dir_inode)) { ret = PTR_ERR(dir_inode); goto out; } if (!need_log_inode(trans, BTRFS_I(dir_inode))) { btrfs_add_delayed_iput(BTRFS_I(dir_inode)); continue; } ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, BTRFS_I(dir_inode), LOG_INODE_ALL, ctx); if (!ret && ctx->log_new_dentries) ret = log_new_dir_dentries(trans, BTRFS_I(dir_inode), ctx); btrfs_add_delayed_iput(BTRFS_I(dir_inode)); if (ret) goto out; } path->slots[0]++; } ret = 0; out: btrfs_free_path(path); return ret; } static int log_new_ancestors(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_log_ctx *ctx) { struct btrfs_key found_key; btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); while (true) { struct extent_buffer *leaf; int slot; struct btrfs_key search_key; struct inode *inode; u64 ino; int ret = 0; btrfs_release_path(path); ino = found_key.offset; search_key.objectid = found_key.offset; search_key.type = BTRFS_INODE_ITEM_KEY; search_key.offset = 0; inode = btrfs_iget_logging(ino, root); if (IS_ERR(inode)) return PTR_ERR(inode); if (BTRFS_I(inode)->generation >= trans->transid && need_log_inode(trans, BTRFS_I(inode))) ret = btrfs_log_inode(trans, BTRFS_I(inode), LOG_INODE_EXISTS, ctx); btrfs_add_delayed_iput(BTRFS_I(inode)); if (ret) return ret; if (search_key.objectid == BTRFS_FIRST_FREE_OBJECTID) break; search_key.type = BTRFS_INODE_REF_KEY; ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) return ret; leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) return ret; else if (ret > 0) return -ENOENT; leaf = path->nodes[0]; slot = path->slots[0]; } btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != search_key.objectid || found_key.type != BTRFS_INODE_REF_KEY) return -ENOENT; } return 0; } static int log_new_ancestors_fast(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct dentry *old_parent = NULL; struct super_block *sb = inode->vfs_inode.i_sb; int ret = 0; while (true) { if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; inode = BTRFS_I(d_inode(parent)); if (root != inode->root) break; if (inode->generation >= trans->transid && need_log_inode(trans, inode)) { ret = btrfs_log_inode(trans, inode, LOG_INODE_EXISTS, ctx); if (ret) break; } if (IS_ROOT(parent)) break; parent = dget_parent(parent); dput(old_parent); old_parent = parent; } dput(old_parent); return ret; } static int log_all_new_ancestors(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; const u64 ino = btrfs_ino(inode); struct btrfs_path *path; struct btrfs_key search_key; int ret; /* * For a single hard link case, go through a fast path that does not * need to iterate the fs/subvolume tree. */ if (inode->vfs_inode.i_nlink < 2) return log_new_ancestors_fast(trans, inode, parent, ctx); path = btrfs_alloc_path(); if (!path) return -ENOMEM; search_key.objectid = ino; search_key.type = BTRFS_INODE_REF_KEY; search_key.offset = 0; again: ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); if (ret < 0) goto out; if (ret == 0) path->slots[0]++; while (true) { struct extent_buffer *leaf = path->nodes[0]; int slot = path->slots[0]; struct btrfs_key found_key; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; else if (ret > 0) break; continue; } btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != ino || found_key.type > BTRFS_INODE_EXTREF_KEY) break; /* * Don't deal with extended references because they are rare * cases and too complex to deal with (we would need to keep * track of which subitem we are processing for each item in * this loop, etc). So just return some error to fallback to * a transaction commit. */ if (found_key.type == BTRFS_INODE_EXTREF_KEY) { ret = -EMLINK; goto out; } /* * Logging ancestors needs to do more searches on the fs/subvol * tree, so it releases the path as needed to avoid deadlocks. * Keep track of the last inode ref key and resume from that key * after logging all new ancestors for the current hard link. */ memcpy(&search_key, &found_key, sizeof(search_key)); ret = log_new_ancestors(trans, root, path, ctx); if (ret) goto out; btrfs_release_path(path); goto again; } ret = 0; out: btrfs_free_path(path); return ret; } /* * helper function around btrfs_log_inode to make sure newly created * parent directories also end up in the log. A minimal inode and backref * only logging is done of any parent directories that are older than * the last committed transaction */ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct dentry *parent, int inode_only, struct btrfs_log_ctx *ctx) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; int ret = 0; bool log_dentries = false; if (btrfs_test_opt(fs_info, NOTREELOG)) { ret = BTRFS_LOG_FORCE_COMMIT; goto end_no_trans; } if (btrfs_root_refs(&root->root_item) == 0) { ret = BTRFS_LOG_FORCE_COMMIT; goto end_no_trans; } /* * If we're logging an inode from a subvolume created in the current * transaction we must force a commit since the root is not persisted. */ if (btrfs_root_generation(&root->root_item) == trans->transid) { ret = BTRFS_LOG_FORCE_COMMIT; goto end_no_trans; } /* * Skip already logged inodes or inodes corresponding to tmpfiles * (since logging them is pointless, a link count of 0 means they * will never be accessible). */ if ((btrfs_inode_in_log(inode, trans->transid) && list_empty(&ctx->ordered_extents)) || inode->vfs_inode.i_nlink == 0) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; } ret = start_log_trans(trans, root, ctx); if (ret) goto end_no_trans; ret = btrfs_log_inode(trans, inode, inode_only, ctx); if (ret) goto end_trans; /* * for regular files, if its inode is already on disk, we don't * have to worry about the parents at all. This is because * we can use the last_unlink_trans field to record renames * and other fun in this file. */ if (S_ISREG(inode->vfs_inode.i_mode) && inode->generation < trans->transid && inode->last_unlink_trans < trans->transid) { ret = 0; goto end_trans; } if (S_ISDIR(inode->vfs_inode.i_mode) && ctx->log_new_dentries) log_dentries = true; /* * On unlink we must make sure all our current and old parent directory * inodes are fully logged. This is to prevent leaving dangling * directory index entries in directories that were our parents but are * not anymore. Not doing this results in old parent directory being * impossible to delete after log replay (rmdir will always fail with * error -ENOTEMPTY). * * Example 1: * * mkdir testdir * touch testdir/foo * ln testdir/foo testdir/bar * sync * unlink testdir/bar * xfs_io -c fsync testdir/foo * <power failure> * mount fs, triggers log replay * * If we don't log the parent directory (testdir), after log replay the * directory still has an entry pointing to the file inode using the bar * name, but a matching BTRFS_INODE_[REF|EXTREF]_KEY does not exist and * the file inode has a link count of 1. * * Example 2: * * mkdir testdir * touch foo * ln foo testdir/foo2 * ln foo testdir/foo3 * sync * unlink testdir/foo3 * xfs_io -c fsync foo * <power failure> * mount fs, triggers log replay * * Similar as the first example, after log replay the parent directory * testdir still has an entry pointing to the inode file with name foo3 * but the file inode does not have a matching BTRFS_INODE_REF_KEY item * and has a link count of 2. */ if (inode->last_unlink_trans >= trans->transid) { ret = btrfs_log_all_parents(trans, inode, ctx); if (ret) goto end_trans; } ret = log_all_new_ancestors(trans, inode, parent, ctx); if (ret) goto end_trans; if (log_dentries) ret = log_new_dir_dentries(trans, inode, ctx); else ret = 0; end_trans: if (ret < 0) { btrfs_set_log_full_commit(trans); ret = BTRFS_LOG_FORCE_COMMIT; } if (ret) btrfs_remove_log_ctx(root, ctx); btrfs_end_log_trans(root); end_no_trans: return ret; } /* * it is not safe to log dentry if the chunk root has added new * chunks. This returns 0 if the dentry was logged, and 1 otherwise. * If this returns 1, you must commit the transaction to safely get your * data on disk. */ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct dentry *dentry, struct btrfs_log_ctx *ctx) { struct dentry *parent = dget_parent(dentry); int ret; ret = btrfs_log_inode_parent(trans, BTRFS_I(d_inode(dentry)), parent, LOG_INODE_ALL, ctx); dput(parent); return ret; } /* * should be called during mount to recover any replay any log trees * from the FS */ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) { int ret; struct btrfs_path *path; struct btrfs_trans_handle *trans; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_root *log; struct btrfs_fs_info *fs_info = log_root_tree->fs_info; struct walk_control wc = { .process_func = process_one_buffer, .stage = LOG_WALK_PIN_ONLY, }; path = btrfs_alloc_path(); if (!path) return -ENOMEM; set_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); trans = btrfs_start_transaction(fs_info->tree_root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto error; } wc.trans = trans; wc.pin = 1; ret = walk_log_tree(trans, log_root_tree, &wc); if (ret) { btrfs_abort_transaction(trans, ret); goto error; } again: key.objectid = BTRFS_TREE_LOG_OBJECTID; key.offset = (u64)-1; key.type = BTRFS_ROOT_ITEM_KEY; while (1) { ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0); if (ret < 0) { btrfs_abort_transaction(trans, ret); goto error; } if (ret > 0) { if (path->slots[0] == 0) break; path->slots[0]--; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); btrfs_release_path(path); if (found_key.objectid != BTRFS_TREE_LOG_OBJECTID) break; log = btrfs_read_tree_root(log_root_tree, &found_key); if (IS_ERR(log)) { ret = PTR_ERR(log); btrfs_abort_transaction(trans, ret); goto error; } wc.replay_dest = btrfs_get_fs_root(fs_info, found_key.offset, true); if (IS_ERR(wc.replay_dest)) { ret = PTR_ERR(wc.replay_dest); /* * We didn't find the subvol, likely because it was * deleted. This is ok, simply skip this log and go to * the next one. * * We need to exclude the root because we can't have * other log replays overwriting this log as we'll read * it back in a few more times. This will keep our * block from being modified, and we'll just bail for * each subsequent pass. */ if (ret == -ENOENT) ret = btrfs_pin_extent_for_log_replay(trans, log->node); btrfs_put_root(log); if (!ret) goto next; btrfs_abort_transaction(trans, ret); goto error; } wc.replay_dest->log_root = log; ret = btrfs_record_root_in_trans(trans, wc.replay_dest); if (ret) /* The loop needs to continue due to the root refs */ btrfs_abort_transaction(trans, ret); else ret = walk_log_tree(trans, log, &wc); if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) { ret = fixup_inode_link_counts(trans, wc.replay_dest, path); if (ret) btrfs_abort_transaction(trans, ret); } if (!ret && wc.stage == LOG_WALK_REPLAY_ALL) { struct btrfs_root *root = wc.replay_dest; btrfs_release_path(path); /* * We have just replayed everything, and the highest * objectid of fs roots probably has changed in case * some inode_item's got replayed. * * root->objectid_mutex is not acquired as log replay * could only happen during mount. */ ret = btrfs_init_root_free_objectid(root); if (ret) btrfs_abort_transaction(trans, ret); } wc.replay_dest->log_root = NULL; btrfs_put_root(wc.replay_dest); btrfs_put_root(log); if (ret) goto error; next: if (found_key.offset == 0) break; key.offset = found_key.offset - 1; } btrfs_release_path(path); /* step one is to pin it all, step two is to replay just inodes */ if (wc.pin) { wc.pin = 0; wc.process_func = replay_one_buffer; wc.stage = LOG_WALK_REPLAY_INODES; goto again; } /* step three is to replay everything */ if (wc.stage < LOG_WALK_REPLAY_ALL) { wc.stage++; goto again; } btrfs_free_path(path); /* step 4: commit the transaction, which also unpins the blocks */ ret = btrfs_commit_transaction(trans); if (ret) return ret; log_root_tree->log_root = NULL; clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); btrfs_put_root(log_root_tree); return 0; error: if (wc.trans) btrfs_end_transaction(wc.trans); clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); btrfs_free_path(path); return ret; } /* * there are some corner cases where we want to force a full * commit instead of allowing a directory to be logged. * * They revolve around files there were unlinked from the directory, and * this function updates the parent directory so that a full commit is * properly done if it is fsync'd later after the unlinks are done. * * Must be called before the unlink operations (updates to the subvolume tree, * inodes, etc) are done. */ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, struct btrfs_inode *dir, struct btrfs_inode *inode, bool for_rename) { /* * when we're logging a file, if it hasn't been renamed * or unlinked, and its inode is fully committed on disk, * we don't have to worry about walking up the directory chain * to log its parents. * * So, we use the last_unlink_trans field to put this transid * into the file. When the file is logged we check it and * don't log the parents if the file is fully on disk. */ mutex_lock(&inode->log_mutex); inode->last_unlink_trans = trans->transid; mutex_unlock(&inode->log_mutex); if (!for_rename) return; /* * If this directory was already logged, any new names will be logged * with btrfs_log_new_name() and old names will be deleted from the log * tree with btrfs_del_dir_entries_in_log() or with * btrfs_del_inode_ref_in_log(). */ if (inode_logged(trans, dir, NULL) == 1) return; /* * If the inode we're about to unlink was logged before, the log will be * properly updated with the new name with btrfs_log_new_name() and the * old name removed with btrfs_del_dir_entries_in_log() or with * btrfs_del_inode_ref_in_log(). */ if (inode_logged(trans, inode, NULL) == 1) return; /* * when renaming files across directories, if the directory * there we're unlinking from gets fsync'd later on, there's * no way to find the destination directory later and fsync it * properly. So, we have to be conservative and force commits * so the new name gets discovered. */ mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Make sure that if someone attempts to fsync the parent directory of a deleted * snapshot, it ends up triggering a transaction commit. This is to guarantee * that after replaying the log tree of the parent directory's root we will not * see the snapshot anymore and at log replay time we will not see any log tree * corresponding to the deleted snapshot's root, which could lead to replaying * it after replaying the log tree of the parent directory (which would replay * the snapshot delete operation). * * Must be called before the actual snapshot destroy operation (updates to the * parent root and tree of tree roots trees, etc) are done. */ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir) { mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Call this when creating a subvolume in a directory. * Because we don't commit a transaction when creating a subvolume, we can't * allow the directory pointing to the subvolume to be logged with an entry that * points to an unpersisted root if we are still in the transaction used to * create the subvolume, so make any attempt to log the directory to result in a * full log sync. * Also we don't need to worry with renames, since btrfs_rename() marks the log * for full commit when renaming a subvolume. */ void btrfs_record_new_subvolume(const struct btrfs_trans_handle *trans, struct btrfs_inode *dir) { mutex_lock(&dir->log_mutex); dir->last_unlink_trans = trans->transid; mutex_unlock(&dir->log_mutex); } /* * Update the log after adding a new name for an inode. * * @trans: Transaction handle. * @old_dentry: The dentry associated with the old name and the old * parent directory. * @old_dir: The inode of the previous parent directory for the case * of a rename. For a link operation, it must be NULL. * @old_dir_index: The index number associated with the old name, meaningful * only for rename operations (when @old_dir is not NULL). * Ignored for link operations. * @parent: The dentry associated with the directory under which the * new name is located. * * Call this after adding a new name for an inode, as a result of a link or * rename operation, and it will properly update the log to reflect the new name. */ void btrfs_log_new_name(struct btrfs_trans_handle *trans, struct dentry *old_dentry, struct btrfs_inode *old_dir, u64 old_dir_index, struct dentry *parent) { struct btrfs_inode *inode = BTRFS_I(d_inode(old_dentry)); struct btrfs_root *root = inode->root; struct btrfs_log_ctx ctx; bool log_pinned = false; int ret; /* * this will force the logging code to walk the dentry chain * up for the file */ if (!S_ISDIR(inode->vfs_inode.i_mode)) inode->last_unlink_trans = trans->transid; /* * if this inode hasn't been logged and directory we're renaming it * from hasn't been logged, we don't need to log it */ ret = inode_logged(trans, inode, NULL); if (ret < 0) { goto out; } else if (ret == 0) { if (!old_dir) return; /* * If the inode was not logged and we are doing a rename (old_dir is not * NULL), check if old_dir was logged - if it was not we can return and * do nothing. */ ret = inode_logged(trans, old_dir, NULL); if (ret < 0) goto out; else if (ret == 0) return; } ret = 0; /* * If we are doing a rename (old_dir is not NULL) from a directory that * was previously logged, make sure that on log replay we get the old * dir entry deleted. This is needed because we will also log the new * name of the renamed inode, so we need to make sure that after log * replay we don't end up with both the new and old dir entries existing. */ if (old_dir && old_dir->logged_trans == trans->transid) { struct btrfs_root *log = old_dir->root->log_root; struct btrfs_path *path; struct fscrypt_name fname; ASSERT(old_dir_index >= BTRFS_DIR_START_INDEX); ret = fscrypt_setup_filename(&old_dir->vfs_inode, &old_dentry->d_name, 0, &fname); if (ret) goto out; /* * We have two inodes to update in the log, the old directory and * the inode that got renamed, so we must pin the log to prevent * anyone from syncing the log until we have updated both inodes * in the log. */ ret = join_running_log_trans(root); /* * At least one of the inodes was logged before, so this should * not fail, but if it does, it's not serious, just bail out and * mark the log for a full commit. */ if (WARN_ON_ONCE(ret < 0)) { fscrypt_free_filename(&fname); goto out; } log_pinned = true; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; fscrypt_free_filename(&fname); goto out; } /* * Other concurrent task might be logging the old directory, * as it can be triggered when logging other inode that had or * still has a dentry in the old directory. We lock the old * directory's log_mutex to ensure the deletion of the old * name is persisted, because during directory logging we * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of * the old name's dir index item is in the delayed items, so * it could be missed by an in progress directory logging. */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), &fname.disk_name, old_dir_index); if (ret > 0) { /* * The dentry does not exist in the log, so record its * deletion. */ btrfs_release_path(path); ret = insert_dir_log_key(trans, log, path, btrfs_ino(old_dir), old_dir_index, old_dir_index); } mutex_unlock(&old_dir->log_mutex); btrfs_free_path(path); fscrypt_free_filename(&fname); if (ret < 0) goto out; } btrfs_init_log_ctx(&ctx, inode); ctx.logging_new_name = true; btrfs_init_log_ctx_scratch_eb(&ctx); /* * We don't care about the return value. If we fail to log the new name * then we know the next attempt to sync the log will fallback to a full * transaction commit (due to a call to btrfs_set_log_full_commit()), so * we don't need to worry about getting a log committed that has an * inconsistent state after a rename operation. */ btrfs_log_inode_parent(trans, inode, parent, LOG_INODE_EXISTS, &ctx); free_extent_buffer(ctx.scratch_eb); ASSERT(list_empty(&ctx.conflict_inodes)); out: /* * If an error happened mark the log for a full commit because it's not * consistent and up to date or we couldn't find out if one of the * inodes was logged before in this transaction. Do it before unpinning * the log, to avoid any races with someone else trying to commit it. */ if (ret < 0) btrfs_set_log_full_commit(trans); if (log_pinned) btrfs_end_log_trans(root); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * z3fold.c * * Author: Vitaly Wool <vitaly.wool@konsulko.com> * Copyright (C) 2016, Sony Mobile Communications Inc. * * This implementation is based on zbud written by Seth Jennings. * * z3fold is an special purpose allocator for storing compressed pages. It * can store up to three compressed pages per page which improves the * compression ratio of zbud while retaining its main concepts (e. g. always * storing an integral number of objects per page) and simplicity. * It still has simple and deterministic reclaim properties that make it * preferable to a higher density approach (with no requirement on integral * number of object per page) when reclaim is used. * * As in zbud, pages are divided into "chunks". The size of the chunks is * fixed at compile time and is determined by NCHUNKS_ORDER below. * * z3fold doesn't export any API and is meant to be used via zpool API. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/atomic.h> #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/page-flags.h> #include <linux/migrate.h> #include <linux/node.h> #include <linux/compaction.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/zpool.h> #include <linux/kmemleak.h> /* * NCHUNKS_ORDER determines the internal allocation granularity, effectively * adjusting internal fragmentation. It also determines the number of * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the * allocation granularity will be in chunks of size PAGE_SIZE/64. Some chunks * in the beginning of an allocated page are occupied by z3fold header, so * NCHUNKS will be calculated to 63 (or 62 in case CONFIG_DEBUG_SPINLOCK=y), * which shows the max number of free chunks in z3fold page, also there will * be 63, or 62, respectively, freelists per pool. */ #define NCHUNKS_ORDER 6 #define CHUNK_SHIFT (PAGE_SHIFT - NCHUNKS_ORDER) #define CHUNK_SIZE (1 << CHUNK_SHIFT) #define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE) #define ZHDR_CHUNKS (ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT) #define TOTAL_CHUNKS (PAGE_SIZE >> CHUNK_SHIFT) #define NCHUNKS (TOTAL_CHUNKS - ZHDR_CHUNKS) #define BUDDY_MASK (0x3) #define BUDDY_SHIFT 2 #define SLOTS_ALIGN (0x40) /***************** * Structures *****************/ struct z3fold_pool; enum buddy { HEADLESS = 0, FIRST, MIDDLE, LAST, BUDDIES_MAX = LAST }; struct z3fold_buddy_slots { /* * we are using BUDDY_MASK in handle_to_buddy etc. so there should * be enough slots to hold all possible variants */ unsigned long slot[BUDDY_MASK + 1]; unsigned long pool; /* back link */ rwlock_t lock; }; #define HANDLE_FLAG_MASK (0x03) /* * struct z3fold_header - z3fold page metadata occupying first chunks of each * z3fold page, except for HEADLESS pages * @buddy: links the z3fold page into the relevant list in the * pool * @page_lock: per-page lock * @refcount: reference count for the z3fold page * @work: work_struct for page layout optimization * @slots: pointer to the structure holding buddy slots * @pool: pointer to the containing pool * @cpu: CPU which this page "belongs" to * @first_chunks: the size of the first buddy in chunks, 0 if free * @middle_chunks: the size of the middle buddy in chunks, 0 if free * @last_chunks: the size of the last buddy in chunks, 0 if free * @first_num: the starting number (for the first handle) * @mapped_count: the number of objects currently mapped */ struct z3fold_header { struct list_head buddy; spinlock_t page_lock; struct kref refcount; struct work_struct work; struct z3fold_buddy_slots *slots; struct z3fold_pool *pool; short cpu; unsigned short first_chunks; unsigned short middle_chunks; unsigned short last_chunks; unsigned short start_middle; unsigned short first_num:2; unsigned short mapped_count:2; unsigned short foreign_handles:2; }; /** * struct z3fold_pool - stores metadata for each z3fold pool * @name: pool name * @lock: protects pool unbuddied lists * @stale_lock: protects pool stale page list * @unbuddied: per-cpu array of lists tracking z3fold pages that contain 2- * buddies; the list each z3fold page is added to depends on * the size of its free region. * @stale: list of pages marked for freeing * @pages_nr: number of z3fold pages in the pool. * @c_handle: cache for z3fold_buddy_slots allocation * @compact_wq: workqueue for page layout background optimization * @release_wq: workqueue for safe page release * @work: work_struct for safe page release * * This structure is allocated at pool creation time and maintains metadata * pertaining to a particular z3fold pool. */ struct z3fold_pool { const char *name; spinlock_t lock; spinlock_t stale_lock; struct list_head *unbuddied; struct list_head stale; atomic64_t pages_nr; struct kmem_cache *c_handle; struct workqueue_struct *compact_wq; struct workqueue_struct *release_wq; struct work_struct work; }; /* * Internal z3fold page flags */ enum z3fold_page_flags { PAGE_HEADLESS = 0, MIDDLE_CHUNK_MAPPED, NEEDS_COMPACTING, PAGE_STALE, PAGE_CLAIMED, /* by either reclaim or free */ PAGE_MIGRATED, /* page is migrated and soon to be released */ }; /* * handle flags, go under HANDLE_FLAG_MASK */ enum z3fold_handle_flags { HANDLES_NOFREE = 0, }; /* * Forward declarations */ static struct z3fold_header *__z3fold_alloc(struct z3fold_pool *, size_t, bool); static void compact_page_work(struct work_struct *w); /***************** * Helpers *****************/ /* Converts an allocation size in bytes to size in z3fold chunks */ static int size_to_chunks(size_t size) { return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; } #define for_each_unbuddied_list(_iter, _begin) \ for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) static inline struct z3fold_buddy_slots *alloc_slots(struct z3fold_pool *pool, gfp_t gfp) { struct z3fold_buddy_slots *slots = kmem_cache_zalloc(pool->c_handle, gfp); if (slots) { /* It will be freed separately in free_handle(). */ kmemleak_not_leak(slots); slots->pool = (unsigned long)pool; rwlock_init(&slots->lock); } return slots; } static inline struct z3fold_pool *slots_to_pool(struct z3fold_buddy_slots *s) { return (struct z3fold_pool *)(s->pool & ~HANDLE_FLAG_MASK); } static inline struct z3fold_buddy_slots *handle_to_slots(unsigned long handle) { return (struct z3fold_buddy_slots *)(handle & ~(SLOTS_ALIGN - 1)); } /* Lock a z3fold page */ static inline void z3fold_page_lock(struct z3fold_header *zhdr) { spin_lock(&zhdr->page_lock); } /* Try to lock a z3fold page */ static inline int z3fold_page_trylock(struct z3fold_header *zhdr) { return spin_trylock(&zhdr->page_lock); } /* Unlock a z3fold page */ static inline void z3fold_page_unlock(struct z3fold_header *zhdr) { spin_unlock(&zhdr->page_lock); } /* return locked z3fold page if it's not headless */ static inline struct z3fold_header *get_z3fold_header(unsigned long handle) { struct z3fold_buddy_slots *slots; struct z3fold_header *zhdr; int locked = 0; if (!(handle & (1 << PAGE_HEADLESS))) { slots = handle_to_slots(handle); do { unsigned long addr; read_lock(&slots->lock); addr = *(unsigned long *)handle; zhdr = (struct z3fold_header *)(addr & PAGE_MASK); locked = z3fold_page_trylock(zhdr); read_unlock(&slots->lock); if (locked) { struct page *page = virt_to_page(zhdr); if (!test_bit(PAGE_MIGRATED, &page->private)) break; z3fold_page_unlock(zhdr); } cpu_relax(); } while (true); } else { zhdr = (struct z3fold_header *)(handle & PAGE_MASK); } return zhdr; } static inline void put_z3fold_header(struct z3fold_header *zhdr) { struct page *page = virt_to_page(zhdr); if (!test_bit(PAGE_HEADLESS, &page->private)) z3fold_page_unlock(zhdr); } static inline void free_handle(unsigned long handle, struct z3fold_header *zhdr) { struct z3fold_buddy_slots *slots; int i; bool is_free; if (WARN_ON(*(unsigned long *)handle == 0)) return; slots = handle_to_slots(handle); write_lock(&slots->lock); *(unsigned long *)handle = 0; if (test_bit(HANDLES_NOFREE, &slots->pool)) { write_unlock(&slots->lock); return; /* simple case, nothing else to do */ } if (zhdr->slots != slots) zhdr->foreign_handles--; is_free = true; for (i = 0; i <= BUDDY_MASK; i++) { if (slots->slot[i]) { is_free = false; break; } } write_unlock(&slots->lock); if (is_free) { struct z3fold_pool *pool = slots_to_pool(slots); if (zhdr->slots == slots) zhdr->slots = NULL; kmem_cache_free(pool->c_handle, slots); } } /* Initializes the z3fold header of a newly allocated z3fold page */ static struct z3fold_header *init_z3fold_page(struct page *page, bool headless, struct z3fold_pool *pool, gfp_t gfp) { struct z3fold_header *zhdr = page_address(page); struct z3fold_buddy_slots *slots; clear_bit(PAGE_HEADLESS, &page->private); clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); clear_bit(PAGE_STALE, &page->private); clear_bit(PAGE_CLAIMED, &page->private); clear_bit(PAGE_MIGRATED, &page->private); if (headless) return zhdr; slots = alloc_slots(pool, gfp); if (!slots) return NULL; memset(zhdr, 0, sizeof(*zhdr)); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); zhdr->cpu = -1; zhdr->slots = slots; zhdr->pool = pool; INIT_LIST_HEAD(&zhdr->buddy); INIT_WORK(&zhdr->work, compact_page_work); return zhdr; } /* Resets the struct page fields and frees the page */ static void free_z3fold_page(struct page *page, bool headless) { if (!headless) { lock_page(page); __ClearPageMovable(page); unlock_page(page); } __free_page(page); } /* Helper function to build the index */ static inline int __idx(struct z3fold_header *zhdr, enum buddy bud) { return (bud + zhdr->first_num) & BUDDY_MASK; } /* * Encodes the handle of a particular buddy within a z3fold page. * Zhdr->page_lock should be held as this function accesses first_num * if bud != HEADLESS. */ static unsigned long __encode_handle(struct z3fold_header *zhdr, struct z3fold_buddy_slots *slots, enum buddy bud) { unsigned long h = (unsigned long)zhdr; int idx = 0; /* * For a headless page, its handle is its pointer with the extra * PAGE_HEADLESS bit set */ if (bud == HEADLESS) return h | (1 << PAGE_HEADLESS); /* otherwise, return pointer to encoded handle */ idx = __idx(zhdr, bud); h += idx; if (bud == LAST) h |= (zhdr->last_chunks << BUDDY_SHIFT); write_lock(&slots->lock); slots->slot[idx] = h; write_unlock(&slots->lock); return (unsigned long)&slots->slot[idx]; } static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud) { return __encode_handle(zhdr, zhdr->slots, bud); } /* only for LAST bud, returns zero otherwise */ static unsigned short handle_to_chunks(unsigned long handle) { struct z3fold_buddy_slots *slots = handle_to_slots(handle); unsigned long addr; read_lock(&slots->lock); addr = *(unsigned long *)handle; read_unlock(&slots->lock); return (addr & ~PAGE_MASK) >> BUDDY_SHIFT; } /* * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle * but that doesn't matter. because the masking will result in the * correct buddy number. */ static enum buddy handle_to_buddy(unsigned long handle) { struct z3fold_header *zhdr; struct z3fold_buddy_slots *slots = handle_to_slots(handle); unsigned long addr; read_lock(&slots->lock); WARN_ON(handle & (1 << PAGE_HEADLESS)); addr = *(unsigned long *)handle; read_unlock(&slots->lock); zhdr = (struct z3fold_header *)(addr & PAGE_MASK); return (addr - zhdr->first_num) & BUDDY_MASK; } static inline struct z3fold_pool *zhdr_to_pool(struct z3fold_header *zhdr) { return zhdr->pool; } static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) { struct page *page = virt_to_page(zhdr); struct z3fold_pool *pool = zhdr_to_pool(zhdr); WARN_ON(!list_empty(&zhdr->buddy)); set_bit(PAGE_STALE, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); spin_lock(&pool->lock); spin_unlock(&pool->lock); if (locked) z3fold_page_unlock(zhdr); spin_lock(&pool->stale_lock); list_add(&zhdr->buddy, &pool->stale); queue_work(pool->release_wq, &pool->work); spin_unlock(&pool->stale_lock); atomic64_dec(&pool->pages_nr); } static void release_z3fold_page_locked(struct kref *ref) { struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, refcount); WARN_ON(z3fold_page_trylock(zhdr)); __release_z3fold_page(zhdr, true); } static void release_z3fold_page_locked_list(struct kref *ref) { struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, refcount); struct z3fold_pool *pool = zhdr_to_pool(zhdr); spin_lock(&pool->lock); list_del_init(&zhdr->buddy); spin_unlock(&pool->lock); WARN_ON(z3fold_page_trylock(zhdr)); __release_z3fold_page(zhdr, true); } static inline int put_z3fold_locked(struct z3fold_header *zhdr) { return kref_put(&zhdr->refcount, release_z3fold_page_locked); } static inline int put_z3fold_locked_list(struct z3fold_header *zhdr) { return kref_put(&zhdr->refcount, release_z3fold_page_locked_list); } static void free_pages_work(struct work_struct *w) { struct z3fold_pool *pool = container_of(w, struct z3fold_pool, work); spin_lock(&pool->stale_lock); while (!list_empty(&pool->stale)) { struct z3fold_header *zhdr = list_first_entry(&pool->stale, struct z3fold_header, buddy); struct page *page = virt_to_page(zhdr); list_del(&zhdr->buddy); if (WARN_ON(!test_bit(PAGE_STALE, &page->private))) continue; spin_unlock(&pool->stale_lock); cancel_work_sync(&zhdr->work); free_z3fold_page(page, false); cond_resched(); spin_lock(&pool->stale_lock); } spin_unlock(&pool->stale_lock); } /* * Returns the number of free chunks in a z3fold page. * NB: can't be used with HEADLESS pages. */ static int num_free_chunks(struct z3fold_header *zhdr) { int nfree; /* * If there is a middle object, pick up the bigger free space * either before or after it. Otherwise just subtract the number * of chunks occupied by the first and the last objects. */ if (zhdr->middle_chunks != 0) { int nfree_before = zhdr->first_chunks ? 0 : zhdr->start_middle - ZHDR_CHUNKS; int nfree_after = zhdr->last_chunks ? 0 : TOTAL_CHUNKS - (zhdr->start_middle + zhdr->middle_chunks); nfree = max(nfree_before, nfree_after); } else nfree = NCHUNKS - zhdr->first_chunks - zhdr->last_chunks; return nfree; } /* Add to the appropriate unbuddied list */ static inline void add_to_unbuddied(struct z3fold_pool *pool, struct z3fold_header *zhdr) { if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 || zhdr->middle_chunks == 0) { struct list_head *unbuddied; int freechunks = num_free_chunks(zhdr); migrate_disable(); unbuddied = this_cpu_ptr(pool->unbuddied); spin_lock(&pool->lock); list_add(&zhdr->buddy, &unbuddied[freechunks]); spin_unlock(&pool->lock); zhdr->cpu = smp_processor_id(); migrate_enable(); } } static inline enum buddy get_free_buddy(struct z3fold_header *zhdr, int chunks) { enum buddy bud = HEADLESS; if (zhdr->middle_chunks) { if (!zhdr->first_chunks && chunks <= zhdr->start_middle - ZHDR_CHUNKS) bud = FIRST; else if (!zhdr->last_chunks) bud = LAST; } else { if (!zhdr->first_chunks) bud = FIRST; else if (!zhdr->last_chunks) bud = LAST; else bud = MIDDLE; } return bud; } static inline void *mchunk_memmove(struct z3fold_header *zhdr, unsigned short dst_chunk) { void *beg = zhdr; return memmove(beg + (dst_chunk << CHUNK_SHIFT), beg + (zhdr->start_middle << CHUNK_SHIFT), zhdr->middle_chunks << CHUNK_SHIFT); } static inline bool buddy_single(struct z3fold_header *zhdr) { return !((zhdr->first_chunks && zhdr->middle_chunks) || (zhdr->first_chunks && zhdr->last_chunks) || (zhdr->middle_chunks && zhdr->last_chunks)); } static struct z3fold_header *compact_single_buddy(struct z3fold_header *zhdr) { struct z3fold_pool *pool = zhdr_to_pool(zhdr); void *p = zhdr; unsigned long old_handle = 0; size_t sz = 0; struct z3fold_header *new_zhdr = NULL; int first_idx = __idx(zhdr, FIRST); int middle_idx = __idx(zhdr, MIDDLE); int last_idx = __idx(zhdr, LAST); unsigned short *moved_chunks = NULL; /* * No need to protect slots here -- all the slots are "local" and * the page lock is already taken */ if (zhdr->first_chunks && zhdr->slots->slot[first_idx]) { p += ZHDR_SIZE_ALIGNED; sz = zhdr->first_chunks << CHUNK_SHIFT; old_handle = (unsigned long)&zhdr->slots->slot[first_idx]; moved_chunks = &zhdr->first_chunks; } else if (zhdr->middle_chunks && zhdr->slots->slot[middle_idx]) { p += zhdr->start_middle << CHUNK_SHIFT; sz = zhdr->middle_chunks << CHUNK_SHIFT; old_handle = (unsigned long)&zhdr->slots->slot[middle_idx]; moved_chunks = &zhdr->middle_chunks; } else if (zhdr->last_chunks && zhdr->slots->slot[last_idx]) { p += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); sz = zhdr->last_chunks << CHUNK_SHIFT; old_handle = (unsigned long)&zhdr->slots->slot[last_idx]; moved_chunks = &zhdr->last_chunks; } if (sz > 0) { enum buddy new_bud = HEADLESS; short chunks = size_to_chunks(sz); void *q; new_zhdr = __z3fold_alloc(pool, sz, false); if (!new_zhdr) return NULL; if (WARN_ON(new_zhdr == zhdr)) goto out_fail; new_bud = get_free_buddy(new_zhdr, chunks); q = new_zhdr; switch (new_bud) { case FIRST: new_zhdr->first_chunks = chunks; q += ZHDR_SIZE_ALIGNED; break; case MIDDLE: new_zhdr->middle_chunks = chunks; new_zhdr->start_middle = new_zhdr->first_chunks + ZHDR_CHUNKS; q += new_zhdr->start_middle << CHUNK_SHIFT; break; case LAST: new_zhdr->last_chunks = chunks; q += PAGE_SIZE - (new_zhdr->last_chunks << CHUNK_SHIFT); break; default: goto out_fail; } new_zhdr->foreign_handles++; memcpy(q, p, sz); write_lock(&zhdr->slots->lock); *(unsigned long *)old_handle = (unsigned long)new_zhdr + __idx(new_zhdr, new_bud); if (new_bud == LAST) *(unsigned long *)old_handle |= (new_zhdr->last_chunks << BUDDY_SHIFT); write_unlock(&zhdr->slots->lock); add_to_unbuddied(pool, new_zhdr); z3fold_page_unlock(new_zhdr); *moved_chunks = 0; } return new_zhdr; out_fail: if (new_zhdr && !put_z3fold_locked(new_zhdr)) { add_to_unbuddied(pool, new_zhdr); z3fold_page_unlock(new_zhdr); } return NULL; } #define BIG_CHUNK_GAP 3 /* Has to be called with lock held */ static int z3fold_compact_page(struct z3fold_header *zhdr) { struct page *page = virt_to_page(zhdr); if (test_bit(MIDDLE_CHUNK_MAPPED, &page->private)) return 0; /* can't move middle chunk, it's used */ if (unlikely(PageIsolated(page))) return 0; if (zhdr->middle_chunks == 0) return 0; /* nothing to compact */ if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { /* move to the beginning */ mchunk_memmove(zhdr, ZHDR_CHUNKS); zhdr->first_chunks = zhdr->middle_chunks; zhdr->middle_chunks = 0; zhdr->start_middle = 0; zhdr->first_num++; return 1; } /* * moving data is expensive, so let's only do that if * there's substantial gain (at least BIG_CHUNK_GAP chunks) */ if (zhdr->first_chunks != 0 && zhdr->last_chunks == 0 && zhdr->start_middle - (zhdr->first_chunks + ZHDR_CHUNKS) >= BIG_CHUNK_GAP) { mchunk_memmove(zhdr, zhdr->first_chunks + ZHDR_CHUNKS); zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS; return 1; } else if (zhdr->last_chunks != 0 && zhdr->first_chunks == 0 && TOTAL_CHUNKS - (zhdr->last_chunks + zhdr->start_middle + zhdr->middle_chunks) >= BIG_CHUNK_GAP) { unsigned short new_start = TOTAL_CHUNKS - zhdr->last_chunks - zhdr->middle_chunks; mchunk_memmove(zhdr, new_start); zhdr->start_middle = new_start; return 1; } return 0; } static void do_compact_page(struct z3fold_header *zhdr, bool locked) { struct z3fold_pool *pool = zhdr_to_pool(zhdr); struct page *page; page = virt_to_page(zhdr); if (locked) WARN_ON(z3fold_page_trylock(zhdr)); else z3fold_page_lock(zhdr); if (WARN_ON(!test_and_clear_bit(NEEDS_COMPACTING, &page->private))) { z3fold_page_unlock(zhdr); return; } spin_lock(&pool->lock); list_del_init(&zhdr->buddy); spin_unlock(&pool->lock); if (put_z3fold_locked(zhdr)) return; if (test_bit(PAGE_STALE, &page->private) || test_and_set_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); return; } if (!zhdr->foreign_handles && buddy_single(zhdr) && zhdr->mapped_count == 0 && compact_single_buddy(zhdr)) { if (!put_z3fold_locked(zhdr)) { clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); } return; } z3fold_compact_page(zhdr); add_to_unbuddied(pool, zhdr); clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); } static void compact_page_work(struct work_struct *w) { struct z3fold_header *zhdr = container_of(w, struct z3fold_header, work); do_compact_page(zhdr, false); } /* returns _locked_ z3fold page header or NULL */ static inline struct z3fold_header *__z3fold_alloc(struct z3fold_pool *pool, size_t size, bool can_sleep) { struct z3fold_header *zhdr = NULL; struct page *page; struct list_head *unbuddied; int chunks = size_to_chunks(size), i; lookup: migrate_disable(); /* First, try to find an unbuddied z3fold page. */ unbuddied = this_cpu_ptr(pool->unbuddied); for_each_unbuddied_list(i, chunks) { struct list_head *l = &unbuddied[i]; zhdr = list_first_entry_or_null(READ_ONCE(l), struct z3fold_header, buddy); if (!zhdr) continue; /* Re-check under lock. */ spin_lock(&pool->lock); if (unlikely(zhdr != list_first_entry(READ_ONCE(l), struct z3fold_header, buddy)) || !z3fold_page_trylock(zhdr)) { spin_unlock(&pool->lock); zhdr = NULL; migrate_enable(); if (can_sleep) cond_resched(); goto lookup; } list_del_init(&zhdr->buddy); zhdr->cpu = -1; spin_unlock(&pool->lock); page = virt_to_page(zhdr); if (test_bit(NEEDS_COMPACTING, &page->private) || test_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); zhdr = NULL; migrate_enable(); if (can_sleep) cond_resched(); goto lookup; } /* * this page could not be removed from its unbuddied * list while pool lock was held, and then we've taken * page lock so kref_put could not be called before * we got here, so it's safe to just call kref_get() */ kref_get(&zhdr->refcount); break; } migrate_enable(); if (!zhdr) { int cpu; /* look for _exact_ match on other cpus' lists */ for_each_online_cpu(cpu) { struct list_head *l; unbuddied = per_cpu_ptr(pool->unbuddied, cpu); spin_lock(&pool->lock); l = &unbuddied[chunks]; zhdr = list_first_entry_or_null(READ_ONCE(l), struct z3fold_header, buddy); if (!zhdr || !z3fold_page_trylock(zhdr)) { spin_unlock(&pool->lock); zhdr = NULL; continue; } list_del_init(&zhdr->buddy); zhdr->cpu = -1; spin_unlock(&pool->lock); page = virt_to_page(zhdr); if (test_bit(NEEDS_COMPACTING, &page->private) || test_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); zhdr = NULL; if (can_sleep) cond_resched(); continue; } kref_get(&zhdr->refcount); break; } } if (zhdr && !zhdr->slots) { zhdr->slots = alloc_slots(pool, GFP_ATOMIC); if (!zhdr->slots) goto out_fail; } return zhdr; out_fail: if (!put_z3fold_locked(zhdr)) { add_to_unbuddied(pool, zhdr); z3fold_page_unlock(zhdr); } return NULL; } /* * API Functions */ /** * z3fold_create_pool() - create a new z3fold pool * @name: pool name * @gfp: gfp flags when allocating the z3fold pool structure * * Return: pointer to the new z3fold pool or NULL if the metadata allocation * failed. */ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp) { struct z3fold_pool *pool = NULL; int i, cpu; pool = kzalloc(sizeof(struct z3fold_pool), gfp); if (!pool) goto out; pool->c_handle = kmem_cache_create("z3fold_handle", sizeof(struct z3fold_buddy_slots), SLOTS_ALIGN, 0, NULL); if (!pool->c_handle) goto out_c; spin_lock_init(&pool->lock); spin_lock_init(&pool->stale_lock); pool->unbuddied = __alloc_percpu(sizeof(struct list_head) * NCHUNKS, __alignof__(struct list_head)); if (!pool->unbuddied) goto out_pool; for_each_possible_cpu(cpu) { struct list_head *unbuddied = per_cpu_ptr(pool->unbuddied, cpu); for_each_unbuddied_list(i, 0) INIT_LIST_HEAD(&unbuddied[i]); } INIT_LIST_HEAD(&pool->stale); atomic64_set(&pool->pages_nr, 0); pool->name = name; pool->compact_wq = create_singlethread_workqueue(pool->name); if (!pool->compact_wq) goto out_unbuddied; pool->release_wq = create_singlethread_workqueue(pool->name); if (!pool->release_wq) goto out_wq; INIT_WORK(&pool->work, free_pages_work); return pool; out_wq: destroy_workqueue(pool->compact_wq); out_unbuddied: free_percpu(pool->unbuddied); out_pool: kmem_cache_destroy(pool->c_handle); out_c: kfree(pool); out: return NULL; } /** * z3fold_destroy_pool() - destroys an existing z3fold pool * @pool: the z3fold pool to be destroyed * * The pool should be emptied before this function is called. */ static void z3fold_destroy_pool(struct z3fold_pool *pool) { kmem_cache_destroy(pool->c_handle); /* * We need to destroy pool->compact_wq before pool->release_wq, * as any pending work on pool->compact_wq will call * queue_work(pool->release_wq, &pool->work). * * There are still outstanding pages until both workqueues are drained, * so we cannot unregister migration until then. */ destroy_workqueue(pool->compact_wq); destroy_workqueue(pool->release_wq); free_percpu(pool->unbuddied); kfree(pool); } static const struct movable_operations z3fold_mops; /** * z3fold_alloc() - allocates a region of a given size * @pool: z3fold pool from which to allocate * @size: size in bytes of the desired allocation * @gfp: gfp flags used if the pool needs to grow * @handle: handle of the new allocation * * This function will attempt to find a free region in the pool large enough to * satisfy the allocation request. A search of the unbuddied lists is * performed first. If no suitable free region is found, then a new page is * allocated and added to the pool to satisfy the request. * * Return: 0 if success and handle is set, otherwise -EINVAL if the size or * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate * a new page. */ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, unsigned long *handle) { int chunks = size_to_chunks(size); struct z3fold_header *zhdr = NULL; struct page *page = NULL; enum buddy bud; bool can_sleep = gfpflags_allow_blocking(gfp); if (!size || (gfp & __GFP_HIGHMEM)) return -EINVAL; if (size > PAGE_SIZE) return -ENOSPC; if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) bud = HEADLESS; else { retry: zhdr = __z3fold_alloc(pool, size, can_sleep); if (zhdr) { bud = get_free_buddy(zhdr, chunks); if (bud == HEADLESS) { if (!put_z3fold_locked(zhdr)) z3fold_page_unlock(zhdr); pr_err("No free chunks in unbuddied\n"); WARN_ON(1); goto retry; } page = virt_to_page(zhdr); goto found; } bud = FIRST; } page = alloc_page(gfp); if (!page) return -ENOMEM; zhdr = init_z3fold_page(page, bud == HEADLESS, pool, gfp); if (!zhdr) { __free_page(page); return -ENOMEM; } atomic64_inc(&pool->pages_nr); if (bud == HEADLESS) { set_bit(PAGE_HEADLESS, &page->private); goto headless; } if (can_sleep) { lock_page(page); __SetPageMovable(page, &z3fold_mops); unlock_page(page); } else { WARN_ON(!trylock_page(page)); __SetPageMovable(page, &z3fold_mops); unlock_page(page); } z3fold_page_lock(zhdr); found: if (bud == FIRST) zhdr->first_chunks = chunks; else if (bud == LAST) zhdr->last_chunks = chunks; else { zhdr->middle_chunks = chunks; zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS; } add_to_unbuddied(pool, zhdr); headless: spin_lock(&pool->lock); *handle = encode_handle(zhdr, bud); spin_unlock(&pool->lock); if (bud != HEADLESS) z3fold_page_unlock(zhdr); return 0; } /** * z3fold_free() - frees the allocation associated with the given handle * @pool: pool in which the allocation resided * @handle: handle associated with the allocation returned by z3fold_alloc() * * In the case that the z3fold page in which the allocation resides is under * reclaim, as indicated by the PAGE_CLAIMED flag being set, this function * only sets the first|middle|last_chunks to 0. The page is actually freed * once all buddies are evicted (see z3fold_reclaim_page() below). */ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) { struct z3fold_header *zhdr; struct page *page; enum buddy bud; bool page_claimed; zhdr = get_z3fold_header(handle); page = virt_to_page(zhdr); page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private); if (test_bit(PAGE_HEADLESS, &page->private)) { /* if a headless page is under reclaim, just leave. * NB: we use test_and_set_bit for a reason: if the bit * has not been set before, we release this page * immediately so we don't care about its value any more. */ if (!page_claimed) { put_z3fold_header(zhdr); free_z3fold_page(page, true); atomic64_dec(&pool->pages_nr); } return; } /* Non-headless case */ bud = handle_to_buddy(handle); switch (bud) { case FIRST: zhdr->first_chunks = 0; break; case MIDDLE: zhdr->middle_chunks = 0; break; case LAST: zhdr->last_chunks = 0; break; default: pr_err("%s: unknown bud %d\n", __func__, bud); WARN_ON(1); put_z3fold_header(zhdr); return; } if (!page_claimed) free_handle(handle, zhdr); if (put_z3fold_locked_list(zhdr)) return; if (page_claimed) { /* the page has not been claimed by us */ put_z3fold_header(zhdr); return; } if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) { clear_bit(PAGE_CLAIMED, &page->private); put_z3fold_header(zhdr); return; } if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) { zhdr->cpu = -1; kref_get(&zhdr->refcount); clear_bit(PAGE_CLAIMED, &page->private); do_compact_page(zhdr, true); return; } kref_get(&zhdr->refcount); clear_bit(PAGE_CLAIMED, &page->private); queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); put_z3fold_header(zhdr); } /** * z3fold_map() - maps the allocation associated with the given handle * @pool: pool in which the allocation resides * @handle: handle associated with the allocation to be mapped * * Extracts the buddy number from handle and constructs the pointer to the * correct starting chunk within the page. * * Returns: a pointer to the mapped allocation */ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) { struct z3fold_header *zhdr; struct page *page; void *addr; enum buddy buddy; zhdr = get_z3fold_header(handle); addr = zhdr; page = virt_to_page(zhdr); if (test_bit(PAGE_HEADLESS, &page->private)) goto out; buddy = handle_to_buddy(handle); switch (buddy) { case FIRST: addr += ZHDR_SIZE_ALIGNED; break; case MIDDLE: addr += zhdr->start_middle << CHUNK_SHIFT; set_bit(MIDDLE_CHUNK_MAPPED, &page->private); break; case LAST: addr += PAGE_SIZE - (handle_to_chunks(handle) << CHUNK_SHIFT); break; default: pr_err("unknown buddy id %d\n", buddy); WARN_ON(1); addr = NULL; break; } if (addr) zhdr->mapped_count++; out: put_z3fold_header(zhdr); return addr; } /** * z3fold_unmap() - unmaps the allocation associated with the given handle * @pool: pool in which the allocation resides * @handle: handle associated with the allocation to be unmapped */ static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle) { struct z3fold_header *zhdr; struct page *page; enum buddy buddy; zhdr = get_z3fold_header(handle); page = virt_to_page(zhdr); if (test_bit(PAGE_HEADLESS, &page->private)) return; buddy = handle_to_buddy(handle); if (buddy == MIDDLE) clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); zhdr->mapped_count--; put_z3fold_header(zhdr); } /** * z3fold_get_pool_pages() - gets the z3fold pool size in pages * @pool: pool whose size is being queried * * Returns: size in pages of the given pool. */ static u64 z3fold_get_pool_pages(struct z3fold_pool *pool) { return atomic64_read(&pool->pages_nr); } static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode) { struct z3fold_header *zhdr; struct z3fold_pool *pool; VM_BUG_ON_PAGE(PageIsolated(page), page); if (test_bit(PAGE_HEADLESS, &page->private)) return false; zhdr = page_address(page); z3fold_page_lock(zhdr); if (test_bit(NEEDS_COMPACTING, &page->private) || test_bit(PAGE_STALE, &page->private)) goto out; if (zhdr->mapped_count != 0 || zhdr->foreign_handles != 0) goto out; if (test_and_set_bit(PAGE_CLAIMED, &page->private)) goto out; pool = zhdr_to_pool(zhdr); spin_lock(&pool->lock); if (!list_empty(&zhdr->buddy)) list_del_init(&zhdr->buddy); spin_unlock(&pool->lock); kref_get(&zhdr->refcount); z3fold_page_unlock(zhdr); return true; out: z3fold_page_unlock(zhdr); return false; } static int z3fold_page_migrate(struct page *newpage, struct page *page, enum migrate_mode mode) { struct z3fold_header *zhdr, *new_zhdr; struct z3fold_pool *pool; VM_BUG_ON_PAGE(!PageIsolated(page), page); VM_BUG_ON_PAGE(!test_bit(PAGE_CLAIMED, &page->private), page); VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); zhdr = page_address(page); pool = zhdr_to_pool(zhdr); if (!z3fold_page_trylock(zhdr)) return -EAGAIN; if (zhdr->mapped_count != 0 || zhdr->foreign_handles != 0) { clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); return -EBUSY; } if (work_pending(&zhdr->work)) { z3fold_page_unlock(zhdr); return -EAGAIN; } new_zhdr = page_address(newpage); memcpy(new_zhdr, zhdr, PAGE_SIZE); newpage->private = page->private; set_bit(PAGE_MIGRATED, &page->private); z3fold_page_unlock(zhdr); spin_lock_init(&new_zhdr->page_lock); INIT_WORK(&new_zhdr->work, compact_page_work); /* * z3fold_page_isolate() ensures that new_zhdr->buddy is empty, * so we only have to reinitialize it. */ INIT_LIST_HEAD(&new_zhdr->buddy); __ClearPageMovable(page); get_page(newpage); z3fold_page_lock(new_zhdr); if (new_zhdr->first_chunks) encode_handle(new_zhdr, FIRST); if (new_zhdr->last_chunks) encode_handle(new_zhdr, LAST); if (new_zhdr->middle_chunks) encode_handle(new_zhdr, MIDDLE); set_bit(NEEDS_COMPACTING, &newpage->private); new_zhdr->cpu = smp_processor_id(); __SetPageMovable(newpage, &z3fold_mops); z3fold_page_unlock(new_zhdr); queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work); /* PAGE_CLAIMED and PAGE_MIGRATED are cleared now. */ page->private = 0; put_page(page); return 0; } static void z3fold_page_putback(struct page *page) { struct z3fold_header *zhdr; struct z3fold_pool *pool; zhdr = page_address(page); pool = zhdr_to_pool(zhdr); z3fold_page_lock(zhdr); if (!list_empty(&zhdr->buddy)) list_del_init(&zhdr->buddy); INIT_LIST_HEAD(&page->lru); if (put_z3fold_locked(zhdr)) return; if (list_empty(&zhdr->buddy)) add_to_unbuddied(pool, zhdr); clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); } static const struct movable_operations z3fold_mops = { .isolate_page = z3fold_page_isolate, .migrate_page = z3fold_page_migrate, .putback_page = z3fold_page_putback, }; /***************** * zpool ****************/ static void *z3fold_zpool_create(const char *name, gfp_t gfp) { return z3fold_create_pool(name, gfp); } static void z3fold_zpool_destroy(void *pool) { z3fold_destroy_pool(pool); } static int z3fold_zpool_malloc(void *pool, size_t size, gfp_t gfp, unsigned long *handle) { return z3fold_alloc(pool, size, gfp, handle); } static void z3fold_zpool_free(void *pool, unsigned long handle) { z3fold_free(pool, handle); } static void *z3fold_zpool_map(void *pool, unsigned long handle, enum zpool_mapmode mm) { return z3fold_map(pool, handle); } static void z3fold_zpool_unmap(void *pool, unsigned long handle) { z3fold_unmap(pool, handle); } static u64 z3fold_zpool_total_pages(void *pool) { return z3fold_get_pool_pages(pool); } static struct zpool_driver z3fold_zpool_driver = { .type = "z3fold", .sleep_mapped = true, .owner = THIS_MODULE, .create = z3fold_zpool_create, .destroy = z3fold_zpool_destroy, .malloc = z3fold_zpool_malloc, .free = z3fold_zpool_free, .map = z3fold_zpool_map, .unmap = z3fold_zpool_unmap, .total_pages = z3fold_zpool_total_pages, }; MODULE_ALIAS("zpool-z3fold"); static int __init init_z3fold(void) { /* * Make sure the z3fold header is not larger than the page size and * there has remaining spaces for its buddy. */ BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE - CHUNK_SIZE); zpool_register_driver(&z3fold_zpool_driver); return 0; } static void __exit exit_z3fold(void) { zpool_unregister_driver(&z3fold_zpool_driver); } module_init(init_z3fold); module_exit(exit_z3fold); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vitaly Wool <vitalywool@gmail.com>"); MODULE_DESCRIPTION("3-Fold Allocator for Compressed Pages"); |
| 39 15 35 35 32 8 24 24 24 15 15 15 15 15 7 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Minchan Kim <minchan@kernel.org> */ #include <linux/types.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/bio.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/cpumask.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "decompressor.h" #include "squashfs.h" /* * This file implements multi-threaded decompression in the * decompressor framework */ /* * The reason that multiply two is that a CPU can request new I/O * while it is waiting previous request. */ #define MAX_DECOMPRESSOR (num_online_cpus() * 2) static int squashfs_max_decompressors(void) { return MAX_DECOMPRESSOR; } struct squashfs_stream { void *comp_opts; struct list_head strm_list; struct mutex mutex; int avail_decomp; wait_queue_head_t wait; }; struct decomp_stream { void *stream; struct list_head list; }; static void put_decomp_stream(struct decomp_stream *decomp_strm, struct squashfs_stream *stream) { mutex_lock(&stream->mutex); list_add(&decomp_strm->list, &stream->strm_list); mutex_unlock(&stream->mutex); wake_up(&stream->wait); } static void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, void *comp_opts) { struct squashfs_stream *stream; struct decomp_stream *decomp_strm = NULL; int err = -ENOMEM; stream = kzalloc(sizeof(*stream), GFP_KERNEL); if (!stream) goto out; stream->comp_opts = comp_opts; mutex_init(&stream->mutex); INIT_LIST_HEAD(&stream->strm_list); init_waitqueue_head(&stream->wait); /* * We should have a decompressor at least as default * so if we fail to allocate new decompressor dynamically, * we could always fall back to default decompressor and * file system works. */ decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL); if (!decomp_strm) goto out; decomp_strm->stream = msblk->decompressor->init(msblk, stream->comp_opts); if (IS_ERR(decomp_strm->stream)) { err = PTR_ERR(decomp_strm->stream); goto out; } list_add(&decomp_strm->list, &stream->strm_list); stream->avail_decomp = 1; return stream; out: kfree(decomp_strm); kfree(stream); return ERR_PTR(err); } static void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) { struct squashfs_stream *stream = msblk->stream; if (stream) { struct decomp_stream *decomp_strm; while (!list_empty(&stream->strm_list)) { decomp_strm = list_entry(stream->strm_list.prev, struct decomp_stream, list); list_del(&decomp_strm->list); msblk->decompressor->free(decomp_strm->stream); kfree(decomp_strm); stream->avail_decomp--; } WARN_ON(stream->avail_decomp); kfree(stream->comp_opts); kfree(stream); } } static struct decomp_stream *get_decomp_stream(struct squashfs_sb_info *msblk, struct squashfs_stream *stream) { struct decomp_stream *decomp_strm; while (1) { mutex_lock(&stream->mutex); /* There is available decomp_stream */ if (!list_empty(&stream->strm_list)) { decomp_strm = list_entry(stream->strm_list.prev, struct decomp_stream, list); list_del(&decomp_strm->list); mutex_unlock(&stream->mutex); break; } /* * If there is no available decomp and already full, * let's wait for releasing decomp from other users. */ if (stream->avail_decomp >= msblk->max_thread_num) goto wait; /* Let's allocate new decomp */ decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL); if (!decomp_strm) goto wait; decomp_strm->stream = msblk->decompressor->init(msblk, stream->comp_opts); if (IS_ERR(decomp_strm->stream)) { kfree(decomp_strm); goto wait; } stream->avail_decomp++; WARN_ON(stream->avail_decomp > msblk->max_thread_num); mutex_unlock(&stream->mutex); break; wait: /* * If system memory is tough, let's for other's * releasing instead of hurting VM because it could * make page cache thrashing. */ mutex_unlock(&stream->mutex); wait_event(stream->wait, !list_empty(&stream->strm_list)); } return decomp_strm; } static int squashfs_decompress(struct squashfs_sb_info *msblk, struct bio *bio, int offset, int length, struct squashfs_page_actor *output) { int res; struct squashfs_stream *stream = msblk->stream; struct decomp_stream *decomp_stream = get_decomp_stream(msblk, stream); res = msblk->decompressor->decompress(msblk, decomp_stream->stream, bio, offset, length, output); put_decomp_stream(decomp_stream, stream); if (res < 0) ERROR("%s decompression failed, data probably corrupt\n", msblk->decompressor->name); return res; } const struct squashfs_decompressor_thread_ops squashfs_decompressor_multi = { .create = squashfs_decompressor_create, .destroy = squashfs_decompressor_destroy, .decompress = squashfs_decompress, .max_decompressors = squashfs_max_decompressors, }; |
| 32 27 32 42 | 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 | /* * linux/fs/nls/nls_iso8859-6.c * * Charset iso8859-6 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0660, 0x0661, 0x0662, 0x0663, 0x0664, 0x0665, 0x0666, 0x0667, 0x0668, 0x0669, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, /* 0x90*/ 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, /* 0xa0*/ 0x00a0, 0x0000, 0x0000, 0x0000, 0x00a4, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x060c, 0x00ad, 0x0000, 0x0000, /* 0xb0*/ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x061b, 0x0000, 0x0000, 0x0000, 0x061f, /* 0xc0*/ 0x0000, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627, 0x0628, 0x0629, 0x062a, 0x062b, 0x062c, 0x062d, 0x062e, 0x062f, /* 0xd0*/ 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x0637, 0x0638, 0x0639, 0x063a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, /* 0xe0*/ 0x0640, 0x0641, 0x0642, 0x0643, 0x0644, 0x0645, 0x0646, 0x0647, 0x0648, 0x0649, 0x064a, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, /* 0xf0*/ 0x0650, 0x0651, 0x0652, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0xad, 0x00, 0x00, /* 0xa8-0xaf */ }; static const unsigned char page06[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xac, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0x18-0x1f */ 0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0x20-0x27 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0x28-0x2f */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0x30-0x37 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x40-0x47 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x48-0x4f */ 0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x60-0x67 */ 0x38, 0x39, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, NULL, NULL, page06, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xac, 0xad, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0xb8-0xbf */ 0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xac, 0xad, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0xb8-0xbf */ 0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "iso8859-6", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_iso8859_6(void) { return register_nls(&table); } static void __exit exit_nls_iso8859_6(void) { unregister_nls(&table); } module_init(init_nls_iso8859_6) module_exit(exit_nls_iso8859_6) MODULE_DESCRIPTION("NLS ISO 8859-6 (Arabic)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 76 76 76 76 76 79 75 1 35 74 35 75 34 77 43 35 75 87 86 87 87 87 42 79 43 85 88 49 2 64 64 54 48 61 3 1 15 76 85 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * * block.c */ /* * This file implements the low-level routines to read and decompress * datablocks and metadata blocks. */ #include <linux/blkdev.h> #include <linux/fs.h> #include <linux/vfs.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/string.h> #include <linux/bio.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" #include "page_actor.h" /* * Returns the amount of bytes copied to the page actor. */ static int copy_bio_to_actor(struct bio *bio, struct squashfs_page_actor *actor, int offset, int req_length) { void *actor_addr; struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); int copied_bytes = 0; int actor_offset = 0; squashfs_actor_nobuff(actor); actor_addr = squashfs_first_page(actor); if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) return 0; while (copied_bytes < req_length) { int bytes_to_copy = min_t(int, bvec->bv_len - offset, PAGE_SIZE - actor_offset); bytes_to_copy = min_t(int, bytes_to_copy, req_length - copied_bytes); if (!IS_ERR(actor_addr)) memcpy(actor_addr + actor_offset, bvec_virt(bvec) + offset, bytes_to_copy); actor_offset += bytes_to_copy; copied_bytes += bytes_to_copy; offset += bytes_to_copy; if (actor_offset >= PAGE_SIZE) { actor_addr = squashfs_next_page(actor); if (!actor_addr) break; actor_offset = 0; } if (offset >= bvec->bv_len) { if (!bio_next_segment(bio, &iter_all)) break; offset = 0; } } squashfs_finish_page(actor); return copied_bytes; } static int squashfs_bio_read_cached(struct bio *fullbio, struct address_space *cache_mapping, u64 index, int length, u64 read_start, u64 read_end, int page_count) { struct page *head_to_cache = NULL, *tail_to_cache = NULL; struct block_device *bdev = fullbio->bi_bdev; int start_idx = 0, end_idx = 0; struct bvec_iter_all iter_all; struct bio *bio = NULL; struct bio_vec *bv; int idx = 0; int err = 0; bio_for_each_segment_all(bv, fullbio, iter_all) { struct page *page = bv->bv_page; if (page->mapping == cache_mapping) { idx++; continue; } /* * We only use this when the device block size is the same as * the page size, so read_start and read_end cover full pages. * * Compare these to the original required index and length to * only cache pages which were requested partially, since these * are the ones which are likely to be needed when reading * adjacent blocks. */ if (idx == 0 && index != read_start) head_to_cache = page; else if (idx == page_count - 1 && index + length != read_end) tail_to_cache = page; if (!bio || idx != end_idx) { struct bio *new = bio_alloc_clone(bdev, fullbio, GFP_NOIO, &fs_bio_set); if (bio) { bio_trim(bio, start_idx * PAGE_SECTORS, (end_idx - start_idx) * PAGE_SECTORS); bio_chain(bio, new); submit_bio(bio); } bio = new; start_idx = idx; } idx++; end_idx = idx; } if (bio) { bio_trim(bio, start_idx * PAGE_SECTORS, (end_idx - start_idx) * PAGE_SECTORS); err = submit_bio_wait(bio); bio_put(bio); } if (err) return err; if (head_to_cache) { int ret = add_to_page_cache_lru(head_to_cache, cache_mapping, read_start >> PAGE_SHIFT, GFP_NOIO); if (!ret) { SetPageUptodate(head_to_cache); unlock_page(head_to_cache); } } if (tail_to_cache) { int ret = add_to_page_cache_lru(tail_to_cache, cache_mapping, (read_end >> PAGE_SHIFT) - 1, GFP_NOIO); if (!ret) { SetPageUptodate(tail_to_cache); unlock_page(tail_to_cache); } } return 0; } static struct page *squashfs_get_cache_page(struct address_space *mapping, pgoff_t index) { struct page *page; if (!mapping) return NULL; page = find_get_page(mapping, index); if (!page) return NULL; if (!PageUptodate(page)) { put_page(page); return NULL; } return page; } static int squashfs_bio_read(struct super_block *sb, u64 index, int length, struct bio **biop, int *block_offset) { struct squashfs_sb_info *msblk = sb->s_fs_info; struct address_space *cache_mapping = msblk->cache_mapping; const u64 read_start = round_down(index, msblk->devblksize); const sector_t block = read_start >> msblk->devblksize_log2; const u64 read_end = round_up(index + length, msblk->devblksize); const sector_t block_end = read_end >> msblk->devblksize_log2; int offset = read_start - round_down(index, PAGE_SIZE); int total_len = (block_end - block) << msblk->devblksize_log2; const int page_count = DIV_ROUND_UP(total_len + offset, PAGE_SIZE); int error, i; struct bio *bio; bio = bio_kmalloc(page_count, GFP_NOIO); if (!bio) return -ENOMEM; bio_init(bio, sb->s_bdev, bio->bi_inline_vecs, page_count, REQ_OP_READ); bio->bi_iter.bi_sector = block * (msblk->devblksize >> SECTOR_SHIFT); for (i = 0; i < page_count; ++i) { unsigned int len = min_t(unsigned int, PAGE_SIZE - offset, total_len); pgoff_t index = (read_start >> PAGE_SHIFT) + i; struct page *page; page = squashfs_get_cache_page(cache_mapping, index); if (!page) page = alloc_page(GFP_NOIO); if (!page) { error = -ENOMEM; goto out_free_bio; } /* * Use the __ version to avoid merging since we need each page * to be separate when we check for and avoid cached pages. */ __bio_add_page(bio, page, len, offset); offset = 0; total_len -= len; } if (cache_mapping) error = squashfs_bio_read_cached(bio, cache_mapping, index, length, read_start, read_end, page_count); else error = submit_bio_wait(bio); if (error) goto out_free_bio; *biop = bio; *block_offset = index & ((1 << msblk->devblksize_log2) - 1); return 0; out_free_bio: bio_free_pages(bio); bio_uninit(bio); kfree(bio); return error; } /* * Read and decompress a metadata block or datablock. Length is non-zero * if a datablock is being read (the size is stored elsewhere in the * filesystem), otherwise the length is obtained from the first two bytes of * the metadata block. A bit in the length field indicates if the block * is stored uncompressed in the filesystem (usually because compression * generated a larger block - this does occasionally happen with compression * algorithms). */ int squashfs_read_data(struct super_block *sb, u64 index, int length, u64 *next_index, struct squashfs_page_actor *output) { struct squashfs_sb_info *msblk = sb->s_fs_info; struct bio *bio = NULL; int compressed; int res; int offset; if (length) { /* * Datablock. */ compressed = SQUASHFS_COMPRESSED_BLOCK(length); length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length); TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n", index, compressed ? "" : "un", length, output->length); } else { /* * Metadata block. */ const u8 *data; struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); if (index + 2 > msblk->bytes_used) { res = -EIO; goto out; } res = squashfs_bio_read(sb, index, 2, &bio, &offset); if (res) goto out; if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) { res = -EIO; goto out_free_bio; } /* Extract the length of the metadata block */ data = bvec_virt(bvec); length = data[offset]; if (offset < bvec->bv_len - 1) { length |= data[offset + 1] << 8; } else { if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) { res = -EIO; goto out_free_bio; } data = bvec_virt(bvec); length |= data[0] << 8; } bio_free_pages(bio); bio_uninit(bio); kfree(bio); compressed = SQUASHFS_COMPRESSED(length); length = SQUASHFS_COMPRESSED_SIZE(length); index += 2; TRACE("Block @ 0x%llx, %scompressed size %d\n", index - 2, compressed ? "" : "un", length); } if (length <= 0 || length > output->length || (index + length) > msblk->bytes_used) { res = -EIO; goto out; } if (next_index) *next_index = index + length; res = squashfs_bio_read(sb, index, length, &bio, &offset); if (res) goto out; if (compressed) { if (!msblk->stream) { res = -EIO; goto out_free_bio; } res = msblk->thread_ops->decompress(msblk, bio, offset, length, output); } else { res = copy_bio_to_actor(bio, output, offset, length); } out_free_bio: bio_free_pages(bio); bio_uninit(bio); kfree(bio); out: if (res < 0) { ERROR("Failed to read block 0x%llx: %d\n", index, res); if (msblk->panic_on_errors) panic("squashfs read failed"); } return res; } |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2003-2005 Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2015 Intel Deutschland GmbH * Copyright (C) 2021-2023 Intel Corporation */ #include <linux/kobject.h> #include <linux/slab.h> #include "ieee80211_i.h" #include "key.h" #include "debugfs.h" #include "debugfs_key.h" #define KEY_READ(name, prop, format_string) \ static ssize_t key_##name##_read(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ struct ieee80211_key *key = file->private_data; \ return mac80211_format_buffer(userbuf, count, ppos, \ format_string, key->prop); \ } #define KEY_READ_X(name) KEY_READ(name, name, "0x%x\n") #define KEY_OPS(name) \ static const struct file_operations key_ ##name## _ops = { \ .read = key_##name##_read, \ .open = simple_open, \ .llseek = generic_file_llseek, \ } #define KEY_OPS_W(name) \ static const struct file_operations key_ ##name## _ops = { \ .read = key_##name##_read, \ .write = key_##name##_write, \ .open = simple_open, \ .llseek = generic_file_llseek, \ } #define KEY_FILE(name, format) \ KEY_READ_##format(name) \ KEY_OPS(name) #define KEY_CONF_READ(name, format_string) \ KEY_READ(conf_##name, conf.name, format_string) #define KEY_CONF_READ_D(name) KEY_CONF_READ(name, "%d\n") #define KEY_CONF_OPS(name) \ static const struct file_operations key_ ##name## _ops = { \ .read = key_conf_##name##_read, \ .open = simple_open, \ .llseek = generic_file_llseek, \ } #define KEY_CONF_FILE(name, format) \ KEY_CONF_READ_##format(name) \ KEY_CONF_OPS(name) KEY_CONF_FILE(keylen, D); KEY_CONF_FILE(keyidx, D); KEY_CONF_FILE(hw_key_idx, D); KEY_FILE(flags, X); KEY_READ(ifindex, sdata->name, "%s\n"); KEY_OPS(ifindex); static ssize_t key_algorithm_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[15]; struct ieee80211_key *key = file->private_data; u32 c = key->conf.cipher; sprintf(buf, "%.2x-%.2x-%.2x:%d\n", c >> 24, (c >> 16) & 0xff, (c >> 8) & 0xff, c & 0xff); return simple_read_from_buffer(userbuf, count, ppos, buf, strlen(buf)); } KEY_OPS(algorithm); static ssize_t key_tx_spec_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; u64 pn; int ret; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: return -EINVAL; case WLAN_CIPHER_SUITE_TKIP: /* not supported yet */ return -EOPNOTSUPP; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: ret = kstrtou64_from_user(userbuf, count, 16, &pn); if (ret) return ret; /* PN is a 48-bit counter */ if (pn >= (1ULL << 48)) return -ERANGE; atomic64_set(&key->conf.tx_pn, pn); return count; default: return 0; } } static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { u64 pn; char buf[20]; int len; struct ieee80211_key *key = file->private_data; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: len = scnprintf(buf, sizeof(buf), "\n"); break; case WLAN_CIPHER_SUITE_TKIP: pn = atomic64_read(&key->conf.tx_pn); len = scnprintf(buf, sizeof(buf), "%08x %04x\n", TKIP_PN_TO_IV32(pn), TKIP_PN_TO_IV16(pn)); break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: pn = atomic64_read(&key->conf.tx_pn); len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS_W(tx_spec); static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[14*IEEE80211_NUM_TIDS+1], *p = buf; int i, len; const u8 *rpn; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: len = scnprintf(buf, sizeof(buf), "\n"); break; case WLAN_CIPHER_SUITE_TKIP: for (i = 0; i < IEEE80211_NUM_TIDS; i++) p += scnprintf(p, sizeof(buf)+buf-p, "%08x %04x\n", key->u.tkip.rx[i].iv32, key->u.tkip.rx[i].iv16); len = p - buf; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { rpn = key->u.ccmp.rx_pn[i]; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); } len = p - buf; break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: rpn = key->u.aes_cmac.rx_pn; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); len = p - buf; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: rpn = key->u.aes_gmac.rx_pn; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); len = p - buf; break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { rpn = key->u.gcmp.rx_pn[i]; p += scnprintf(p, sizeof(buf)+buf-p, "%02x%02x%02x%02x%02x%02x\n", rpn[0], rpn[1], rpn[2], rpn[3], rpn[4], rpn[5]); } len = p - buf; break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(rx_spec); static ssize_t key_replays_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[20]; int len; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.ccmp.replays); break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_cmac.replays); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_gmac.replays); break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.gcmp.replays); break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(replays); static ssize_t key_icverrors_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[20]; int len; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_cmac.icverrors); break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: len = scnprintf(buf, sizeof(buf), "%u\n", key->u.aes_gmac.icverrors); break; default: return 0; } return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(icverrors); static ssize_t key_mic_failures_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; char buf[20]; int len; if (key->conf.cipher != WLAN_CIPHER_SUITE_TKIP) return -EINVAL; len = scnprintf(buf, sizeof(buf), "%u\n", key->u.tkip.mic_failures); return simple_read_from_buffer(userbuf, count, ppos, buf, len); } KEY_OPS(mic_failures); static ssize_t key_key_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct ieee80211_key *key = file->private_data; int i, bufsize = 2 * key->conf.keylen + 2; char *buf = kmalloc(bufsize, GFP_KERNEL); char *p = buf; ssize_t res; if (!buf) return -ENOMEM; for (i = 0; i < key->conf.keylen; i++) p += scnprintf(p, bufsize + buf - p, "%02x", key->conf.key[i]); p += scnprintf(p, bufsize+buf-p, "\n"); res = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return res; } KEY_OPS(key); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, key->debugfs.dir, \ key, &key_##name##_ops) #define DEBUGFS_ADD_W(name) \ debugfs_create_file(#name, 0600, key->debugfs.dir, \ key, &key_##name##_ops); void ieee80211_debugfs_key_add(struct ieee80211_key *key) { static int keycount; char buf[100]; struct sta_info *sta; if (!key->local->debugfs.keys) return; sprintf(buf, "%d", keycount); key->debugfs.cnt = keycount; keycount++; key->debugfs.dir = debugfs_create_dir(buf, key->local->debugfs.keys); sta = key->sta; if (sta) { sprintf(buf, "../../netdev:%s/stations/%pM", sta->sdata->name, sta->sta.addr); key->debugfs.stalink = debugfs_create_symlink("station", key->debugfs.dir, buf); } DEBUGFS_ADD(keylen); DEBUGFS_ADD(flags); DEBUGFS_ADD(keyidx); DEBUGFS_ADD(hw_key_idx); DEBUGFS_ADD(algorithm); DEBUGFS_ADD_W(tx_spec); DEBUGFS_ADD(rx_spec); DEBUGFS_ADD(replays); DEBUGFS_ADD(icverrors); DEBUGFS_ADD(mic_failures); DEBUGFS_ADD(key); DEBUGFS_ADD(ifindex); }; void ieee80211_debugfs_key_remove(struct ieee80211_key *key) { if (!key) return; debugfs_remove_recursive(key->debugfs.dir); key->debugfs.dir = NULL; } void ieee80211_debugfs_key_update_default(struct ieee80211_sub_if_data *sdata) { char buf[50]; struct ieee80211_key *key; if (!sdata->vif.debugfs_dir) return; lockdep_assert_wiphy(sdata->local->hw.wiphy); debugfs_remove(sdata->debugfs.default_unicast_key); sdata->debugfs.default_unicast_key = NULL; if (sdata->default_unicast_key) { key = wiphy_dereference(sdata->local->hw.wiphy, sdata->default_unicast_key); sprintf(buf, "../keys/%d", key->debugfs.cnt); sdata->debugfs.default_unicast_key = debugfs_create_symlink("default_unicast_key", sdata->vif.debugfs_dir, buf); } debugfs_remove(sdata->debugfs.default_multicast_key); sdata->debugfs.default_multicast_key = NULL; if (sdata->deflink.default_multicast_key) { key = wiphy_dereference(sdata->local->hw.wiphy, sdata->deflink.default_multicast_key); sprintf(buf, "../keys/%d", key->debugfs.cnt); sdata->debugfs.default_multicast_key = debugfs_create_symlink("default_multicast_key", sdata->vif.debugfs_dir, buf); } } void ieee80211_debugfs_key_add_mgmt_default(struct ieee80211_sub_if_data *sdata) { char buf[50]; struct ieee80211_key *key; if (!sdata->vif.debugfs_dir) return; key = wiphy_dereference(sdata->local->hw.wiphy, sdata->deflink.default_mgmt_key); if (key) { sprintf(buf, "../keys/%d", key->debugfs.cnt); sdata->debugfs.default_mgmt_key = debugfs_create_symlink("default_mgmt_key", sdata->vif.debugfs_dir, buf); } else ieee80211_debugfs_key_remove_mgmt_default(sdata); } void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sdata) { if (!sdata) return; debugfs_remove(sdata->debugfs.default_mgmt_key); sdata->debugfs.default_mgmt_key = NULL; } void ieee80211_debugfs_key_add_beacon_default(struct ieee80211_sub_if_data *sdata) { char buf[50]; struct ieee80211_key *key; if (!sdata->vif.debugfs_dir) return; key = wiphy_dereference(sdata->local->hw.wiphy, sdata->deflink.default_beacon_key); if (key) { sprintf(buf, "../keys/%d", key->debugfs.cnt); sdata->debugfs.default_beacon_key = debugfs_create_symlink("default_beacon_key", sdata->vif.debugfs_dir, buf); } else { ieee80211_debugfs_key_remove_beacon_default(sdata); } } void ieee80211_debugfs_key_remove_beacon_default(struct ieee80211_sub_if_data *sdata) { if (!sdata) return; debugfs_remove(sdata->debugfs.default_beacon_key); sdata->debugfs.default_beacon_key = NULL; } void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta) { debugfs_remove(key->debugfs.stalink); key->debugfs.stalink = NULL; } |
| 27 27 2 1 1 8 6 2 2 2 3 1 11 2 12 76 76 46 26 32 2 4 1 4 3 22 1 23 31 11 1 2 11 11 12 2 11 11 12 1 1 12 1 13 3 11 13 5 5 1 4 4 25 18 18 17 9 9 5 4 1 1 1 1 1 1 1 1 1 1 1 5 1 4 1 2 2 2 1 3 2 1 2 4 5 3 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 | // SPDX-License-Identifier: GPL-2.0 /* * Filesystem-level keyring for fscrypt * * Copyright 2019 Google LLC */ /* * This file implements management of fscrypt master keys in the * filesystem-level keyring, including the ioctls: * * - FS_IOC_ADD_ENCRYPTION_KEY * - FS_IOC_REMOVE_ENCRYPTION_KEY * - FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS * - FS_IOC_GET_ENCRYPTION_KEY_STATUS * * See the "User API" section of Documentation/filesystems/fscrypt.rst for more * information about these ioctls. */ #include <asm/unaligned.h> #include <crypto/skcipher.h> #include <linux/key-type.h> #include <linux/random.h> #include <linux/seq_file.h> #include "fscrypt_private.h" /* The master encryption keys for a filesystem (->s_master_keys) */ struct fscrypt_keyring { /* * Lock that protects ->key_hashtable. It does *not* protect the * fscrypt_master_key structs themselves. */ spinlock_t lock; /* Hash table that maps fscrypt_key_specifier to fscrypt_master_key */ struct hlist_head key_hashtable[128]; }; static void wipe_master_key_secret(struct fscrypt_master_key_secret *secret) { fscrypt_destroy_hkdf(&secret->hkdf); memzero_explicit(secret, sizeof(*secret)); } static void move_master_key_secret(struct fscrypt_master_key_secret *dst, struct fscrypt_master_key_secret *src) { memcpy(dst, src, sizeof(*dst)); memzero_explicit(src, sizeof(*src)); } static void fscrypt_free_master_key(struct rcu_head *head) { struct fscrypt_master_key *mk = container_of(head, struct fscrypt_master_key, mk_rcu_head); /* * The master key secret and any embedded subkeys should have already * been wiped when the last active reference to the fscrypt_master_key * struct was dropped; doing it here would be unnecessarily late. * Nevertheless, use kfree_sensitive() in case anything was missed. */ kfree_sensitive(mk); } void fscrypt_put_master_key(struct fscrypt_master_key *mk) { if (!refcount_dec_and_test(&mk->mk_struct_refs)) return; /* * No structural references left, so free ->mk_users, and also free the * fscrypt_master_key struct itself after an RCU grace period ensures * that concurrent keyring lookups can no longer find it. */ WARN_ON_ONCE(refcount_read(&mk->mk_active_refs) != 0); if (mk->mk_users) { /* Clear the keyring so the quota gets released right away. */ keyring_clear(mk->mk_users); key_put(mk->mk_users); mk->mk_users = NULL; } call_rcu(&mk->mk_rcu_head, fscrypt_free_master_key); } void fscrypt_put_master_key_activeref(struct super_block *sb, struct fscrypt_master_key *mk) { size_t i; if (!refcount_dec_and_test(&mk->mk_active_refs)) return; /* * No active references left, so complete the full removal of this * fscrypt_master_key struct by removing it from the keyring and * destroying any subkeys embedded in it. */ if (WARN_ON_ONCE(!sb->s_master_keys)) return; spin_lock(&sb->s_master_keys->lock); hlist_del_rcu(&mk->mk_node); spin_unlock(&sb->s_master_keys->lock); /* * ->mk_active_refs == 0 implies that ->mk_present is false and * ->mk_decrypted_inodes is empty. */ WARN_ON_ONCE(mk->mk_present); WARN_ON_ONCE(!list_empty(&mk->mk_decrypted_inodes)); for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { fscrypt_destroy_prepared_key( sb, &mk->mk_direct_keys[i]); fscrypt_destroy_prepared_key( sb, &mk->mk_iv_ino_lblk_64_keys[i]); fscrypt_destroy_prepared_key( sb, &mk->mk_iv_ino_lblk_32_keys[i]); } memzero_explicit(&mk->mk_ino_hash_key, sizeof(mk->mk_ino_hash_key)); mk->mk_ino_hash_key_initialized = false; /* Drop the structural ref associated with the active refs. */ fscrypt_put_master_key(mk); } /* * This transitions the key state from present to incompletely removed, and then * potentially to absent (depending on whether inodes remain). */ static void fscrypt_initiate_key_removal(struct super_block *sb, struct fscrypt_master_key *mk) { WRITE_ONCE(mk->mk_present, false); wipe_master_key_secret(&mk->mk_secret); fscrypt_put_master_key_activeref(sb, mk); } static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec) { if (spec->__reserved) return false; return master_key_spec_len(spec) != 0; } static int fscrypt_user_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { /* * We just charge FSCRYPT_MAX_KEY_SIZE bytes to the user's key quota for * each key, regardless of the exact key size. The amount of memory * actually used is greater than the size of the raw key anyway. */ return key_payload_reserve(key, FSCRYPT_MAX_KEY_SIZE); } static void fscrypt_user_key_describe(const struct key *key, struct seq_file *m) { seq_puts(m, key->description); } /* * Type of key in ->mk_users. Each key of this type represents a particular * user who has added a particular master key. * * Note that the name of this key type really should be something like * ".fscrypt-user" instead of simply ".fscrypt". But the shorter name is chosen * mainly for simplicity of presentation in /proc/keys when read by a non-root * user. And it is expected to be rare that a key is actually added by multiple * users, since users should keep their encryption keys confidential. */ static struct key_type key_type_fscrypt_user = { .name = ".fscrypt", .instantiate = fscrypt_user_key_instantiate, .describe = fscrypt_user_key_describe, }; #define FSCRYPT_MK_USERS_DESCRIPTION_SIZE \ (CONST_STRLEN("fscrypt-") + 2 * FSCRYPT_KEY_IDENTIFIER_SIZE + \ CONST_STRLEN("-users") + 1) #define FSCRYPT_MK_USER_DESCRIPTION_SIZE \ (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + CONST_STRLEN(".uid.") + 10 + 1) static void format_mk_users_keyring_description( char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE], const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) { sprintf(description, "fscrypt-%*phN-users", FSCRYPT_KEY_IDENTIFIER_SIZE, mk_identifier); } static void format_mk_user_description( char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE], const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) { sprintf(description, "%*phN.uid.%u", FSCRYPT_KEY_IDENTIFIER_SIZE, mk_identifier, __kuid_val(current_fsuid())); } /* Create ->s_master_keys if needed. Synchronized by fscrypt_add_key_mutex. */ static int allocate_filesystem_keyring(struct super_block *sb) { struct fscrypt_keyring *keyring; if (sb->s_master_keys) return 0; keyring = kzalloc(sizeof(*keyring), GFP_KERNEL); if (!keyring) return -ENOMEM; spin_lock_init(&keyring->lock); /* * Pairs with the smp_load_acquire() in fscrypt_find_master_key(). * I.e., here we publish ->s_master_keys with a RELEASE barrier so that * concurrent tasks can ACQUIRE it. */ smp_store_release(&sb->s_master_keys, keyring); return 0; } /* * Release all encryption keys that have been added to the filesystem, along * with the keyring that contains them. * * This is called at unmount time, after all potentially-encrypted inodes have * been evicted. The filesystem's underlying block device(s) are still * available at this time; this is important because after user file accesses * have been allowed, this function may need to evict keys from the keyslots of * an inline crypto engine, which requires the block device(s). */ void fscrypt_destroy_keyring(struct super_block *sb) { struct fscrypt_keyring *keyring = sb->s_master_keys; size_t i; if (!keyring) return; for (i = 0; i < ARRAY_SIZE(keyring->key_hashtable); i++) { struct hlist_head *bucket = &keyring->key_hashtable[i]; struct fscrypt_master_key *mk; struct hlist_node *tmp; hlist_for_each_entry_safe(mk, tmp, bucket, mk_node) { /* * Since all potentially-encrypted inodes were already * evicted, every key remaining in the keyring should * have an empty inode list, and should only still be in * the keyring due to the single active ref associated * with ->mk_present. There should be no structural * refs beyond the one associated with the active ref. */ WARN_ON_ONCE(refcount_read(&mk->mk_active_refs) != 1); WARN_ON_ONCE(refcount_read(&mk->mk_struct_refs) != 1); WARN_ON_ONCE(!mk->mk_present); fscrypt_initiate_key_removal(sb, mk); } } kfree_sensitive(keyring); sb->s_master_keys = NULL; } static struct hlist_head * fscrypt_mk_hash_bucket(struct fscrypt_keyring *keyring, const struct fscrypt_key_specifier *mk_spec) { /* * Since key specifiers should be "random" values, it is sufficient to * use a trivial hash function that just takes the first several bits of * the key specifier. */ unsigned long i = get_unaligned((unsigned long *)&mk_spec->u); return &keyring->key_hashtable[i % ARRAY_SIZE(keyring->key_hashtable)]; } /* * Find the specified master key struct in ->s_master_keys and take a structural * ref to it. The structural ref guarantees that the key struct continues to * exist, but it does *not* guarantee that ->s_master_keys continues to contain * the key struct. The structural ref needs to be dropped by * fscrypt_put_master_key(). Returns NULL if the key struct is not found. */ struct fscrypt_master_key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec) { struct fscrypt_keyring *keyring; struct hlist_head *bucket; struct fscrypt_master_key *mk; /* * Pairs with the smp_store_release() in allocate_filesystem_keyring(). * I.e., another task can publish ->s_master_keys concurrently, * executing a RELEASE barrier. We need to use smp_load_acquire() here * to safely ACQUIRE the memory the other task published. */ keyring = smp_load_acquire(&sb->s_master_keys); if (keyring == NULL) return NULL; /* No keyring yet, so no keys yet. */ bucket = fscrypt_mk_hash_bucket(keyring, mk_spec); rcu_read_lock(); switch (mk_spec->type) { case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR: hlist_for_each_entry_rcu(mk, bucket, mk_node) { if (mk->mk_spec.type == FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && memcmp(mk->mk_spec.u.descriptor, mk_spec->u.descriptor, FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 && refcount_inc_not_zero(&mk->mk_struct_refs)) goto out; } break; case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER: hlist_for_each_entry_rcu(mk, bucket, mk_node) { if (mk->mk_spec.type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER && memcmp(mk->mk_spec.u.identifier, mk_spec->u.identifier, FSCRYPT_KEY_IDENTIFIER_SIZE) == 0 && refcount_inc_not_zero(&mk->mk_struct_refs)) goto out; } break; } mk = NULL; out: rcu_read_unlock(); return mk; } static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk) { char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE]; struct key *keyring; format_mk_users_keyring_description(description, mk->mk_spec.u.identifier); keyring = keyring_alloc(description, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), KEY_POS_SEARCH | KEY_USR_SEARCH | KEY_USR_READ | KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); if (IS_ERR(keyring)) return PTR_ERR(keyring); mk->mk_users = keyring; return 0; } /* * Find the current user's "key" in the master key's ->mk_users. * Returns ERR_PTR(-ENOKEY) if not found. */ static struct key *find_master_key_user(struct fscrypt_master_key *mk) { char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE]; key_ref_t keyref; format_mk_user_description(description, mk->mk_spec.u.identifier); /* * We need to mark the keyring reference as "possessed" so that we * acquire permission to search it, via the KEY_POS_SEARCH permission. */ keyref = keyring_search(make_key_ref(mk->mk_users, true /*possessed*/), &key_type_fscrypt_user, description, false); if (IS_ERR(keyref)) { if (PTR_ERR(keyref) == -EAGAIN || /* not found */ PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ keyref = ERR_PTR(-ENOKEY); return ERR_CAST(keyref); } return key_ref_to_ptr(keyref); } /* * Give the current user a "key" in ->mk_users. This charges the user's quota * and marks the master key as added by the current user, so that it cannot be * removed by another user with the key. Either ->mk_sem must be held for * write, or the master key must be still undergoing initialization. */ static int add_master_key_user(struct fscrypt_master_key *mk) { char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE]; struct key *mk_user; int err; format_mk_user_description(description, mk->mk_spec.u.identifier); mk_user = key_alloc(&key_type_fscrypt_user, description, current_fsuid(), current_gid(), current_cred(), KEY_POS_SEARCH | KEY_USR_VIEW, 0, NULL); if (IS_ERR(mk_user)) return PTR_ERR(mk_user); err = key_instantiate_and_link(mk_user, NULL, 0, mk->mk_users, NULL); key_put(mk_user); return err; } /* * Remove the current user's "key" from ->mk_users. * ->mk_sem must be held for write. * * Returns 0 if removed, -ENOKEY if not found, or another -errno code. */ static int remove_master_key_user(struct fscrypt_master_key *mk) { struct key *mk_user; int err; mk_user = find_master_key_user(mk); if (IS_ERR(mk_user)) return PTR_ERR(mk_user); err = key_unlink(mk->mk_users, mk_user); key_put(mk_user); return err; } /* * Allocate a new fscrypt_master_key, transfer the given secret over to it, and * insert it into sb->s_master_keys. */ static int add_new_master_key(struct super_block *sb, struct fscrypt_master_key_secret *secret, const struct fscrypt_key_specifier *mk_spec) { struct fscrypt_keyring *keyring = sb->s_master_keys; struct fscrypt_master_key *mk; int err; mk = kzalloc(sizeof(*mk), GFP_KERNEL); if (!mk) return -ENOMEM; init_rwsem(&mk->mk_sem); refcount_set(&mk->mk_struct_refs, 1); mk->mk_spec = *mk_spec; INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock); if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = allocate_master_key_users_keyring(mk); if (err) goto out_put; err = add_master_key_user(mk); if (err) goto out_put; } move_master_key_secret(&mk->mk_secret, secret); mk->mk_present = true; refcount_set(&mk->mk_active_refs, 1); /* ->mk_present is true */ spin_lock(&keyring->lock); hlist_add_head_rcu(&mk->mk_node, fscrypt_mk_hash_bucket(keyring, mk_spec)); spin_unlock(&keyring->lock); return 0; out_put: fscrypt_put_master_key(mk); return err; } #define KEY_DEAD 1 static int add_existing_master_key(struct fscrypt_master_key *mk, struct fscrypt_master_key_secret *secret) { int err; /* * If the current user is already in ->mk_users, then there's nothing to * do. Otherwise, we need to add the user to ->mk_users. (Neither is * applicable for v1 policy keys, which have NULL ->mk_users.) */ if (mk->mk_users) { struct key *mk_user = find_master_key_user(mk); if (mk_user != ERR_PTR(-ENOKEY)) { if (IS_ERR(mk_user)) return PTR_ERR(mk_user); key_put(mk_user); return 0; } err = add_master_key_user(mk); if (err) return err; } /* If the key is incompletely removed, make it present again. */ if (!mk->mk_present) { if (!refcount_inc_not_zero(&mk->mk_active_refs)) { /* * Raced with the last active ref being dropped, so the * key has become, or is about to become, "absent". * Therefore, we need to allocate a new key struct. */ return KEY_DEAD; } move_master_key_secret(&mk->mk_secret, secret); WRITE_ONCE(mk->mk_present, true); } return 0; } static int do_add_master_key(struct super_block *sb, struct fscrypt_master_key_secret *secret, const struct fscrypt_key_specifier *mk_spec) { static DEFINE_MUTEX(fscrypt_add_key_mutex); struct fscrypt_master_key *mk; int err; mutex_lock(&fscrypt_add_key_mutex); /* serialize find + link */ mk = fscrypt_find_master_key(sb, mk_spec); if (!mk) { /* Didn't find the key in ->s_master_keys. Add it. */ err = allocate_filesystem_keyring(sb); if (!err) err = add_new_master_key(sb, secret, mk_spec); } else { /* * Found the key in ->s_master_keys. Add the user to ->mk_users * if needed, and make the key "present" again if possible. */ down_write(&mk->mk_sem); err = add_existing_master_key(mk, secret); up_write(&mk->mk_sem); if (err == KEY_DEAD) { /* * We found a key struct, but it's already been fully * removed. Ignore the old struct and add a new one. * fscrypt_add_key_mutex means we don't need to worry * about concurrent adds. */ err = add_new_master_key(sb, secret, mk_spec); } fscrypt_put_master_key(mk); } mutex_unlock(&fscrypt_add_key_mutex); return err; } static int add_master_key(struct super_block *sb, struct fscrypt_master_key_secret *secret, struct fscrypt_key_specifier *key_spec) { int err; if (key_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = fscrypt_init_hkdf(&secret->hkdf, secret->raw, secret->size); if (err) return err; /* * Now that the HKDF context is initialized, the raw key is no * longer needed. */ memzero_explicit(secret->raw, secret->size); /* Calculate the key identifier */ err = fscrypt_hkdf_expand(&secret->hkdf, HKDF_CONTEXT_KEY_IDENTIFIER, NULL, 0, key_spec->u.identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); if (err) return err; } return do_add_master_key(sb, secret, key_spec); } static int fscrypt_provisioning_key_preparse(struct key_preparsed_payload *prep) { const struct fscrypt_provisioning_key_payload *payload = prep->data; if (prep->datalen < sizeof(*payload) + FSCRYPT_MIN_KEY_SIZE || prep->datalen > sizeof(*payload) + FSCRYPT_MAX_KEY_SIZE) return -EINVAL; if (payload->type != FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && payload->type != FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) return -EINVAL; if (payload->__reserved) return -EINVAL; prep->payload.data[0] = kmemdup(payload, prep->datalen, GFP_KERNEL); if (!prep->payload.data[0]) return -ENOMEM; prep->quotalen = prep->datalen; return 0; } static void fscrypt_provisioning_key_free_preparse( struct key_preparsed_payload *prep) { kfree_sensitive(prep->payload.data[0]); } static void fscrypt_provisioning_key_describe(const struct key *key, struct seq_file *m) { seq_puts(m, key->description); if (key_is_positive(key)) { const struct fscrypt_provisioning_key_payload *payload = key->payload.data[0]; seq_printf(m, ": %u [%u]", key->datalen, payload->type); } } static void fscrypt_provisioning_key_destroy(struct key *key) { kfree_sensitive(key->payload.data[0]); } static struct key_type key_type_fscrypt_provisioning = { .name = "fscrypt-provisioning", .preparse = fscrypt_provisioning_key_preparse, .free_preparse = fscrypt_provisioning_key_free_preparse, .instantiate = generic_key_instantiate, .describe = fscrypt_provisioning_key_describe, .destroy = fscrypt_provisioning_key_destroy, }; /* * Retrieve the raw key from the Linux keyring key specified by 'key_id', and * store it into 'secret'. * * The key must be of type "fscrypt-provisioning" and must have the field * fscrypt_provisioning_key_payload::type set to 'type', indicating that it's * only usable with fscrypt with the particular KDF version identified by * 'type'. We don't use the "logon" key type because there's no way to * completely restrict the use of such keys; they can be used by any kernel API * that accepts "logon" keys and doesn't require a specific service prefix. * * The ability to specify the key via Linux keyring key is intended for cases * where userspace needs to re-add keys after the filesystem is unmounted and * re-mounted. Most users should just provide the raw key directly instead. */ static int get_keyring_key(u32 key_id, u32 type, struct fscrypt_master_key_secret *secret) { key_ref_t ref; struct key *key; const struct fscrypt_provisioning_key_payload *payload; int err; ref = lookup_user_key(key_id, 0, KEY_NEED_SEARCH); if (IS_ERR(ref)) return PTR_ERR(ref); key = key_ref_to_ptr(ref); if (key->type != &key_type_fscrypt_provisioning) goto bad_key; payload = key->payload.data[0]; /* Don't allow fscrypt v1 keys to be used as v2 keys and vice versa. */ if (payload->type != type) goto bad_key; secret->size = key->datalen - sizeof(*payload); memcpy(secret->raw, payload->raw, secret->size); err = 0; goto out_put; bad_key: err = -EKEYREJECTED; out_put: key_ref_put(ref); return err; } /* * Add a master encryption key to the filesystem, causing all files which were * encrypted with it to appear "unlocked" (decrypted) when accessed. * * When adding a key for use by v1 encryption policies, this ioctl is * privileged, and userspace must provide the 'key_descriptor'. * * When adding a key for use by v2+ encryption policies, this ioctl is * unprivileged. This is needed, in general, to allow non-root users to use * encryption without encountering the visibility problems of process-subscribed * keyrings and the inability to properly remove keys. This works by having * each key identified by its cryptographically secure hash --- the * 'key_identifier'. The cryptographic hash ensures that a malicious user * cannot add the wrong key for a given identifier. Furthermore, each added key * is charged to the appropriate user's quota for the keyrings service, which * prevents a malicious user from adding too many keys. Finally, we forbid a * user from removing a key while other users have added it too, which prevents * a user who knows another user's key from causing a denial-of-service by * removing it at an inopportune time. (We tolerate that a user who knows a key * can prevent other users from removing it.) * * For more details, see the "FS_IOC_ADD_ENCRYPTION_KEY" section of * Documentation/filesystems/fscrypt.rst. */ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg) { struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_add_key_arg __user *uarg = _uarg; struct fscrypt_add_key_arg arg; struct fscrypt_master_key_secret secret; int err; if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; if (!valid_key_spec(&arg.key_spec)) return -EINVAL; if (memchr_inv(arg.__reserved, 0, sizeof(arg.__reserved))) return -EINVAL; /* * Only root can add keys that are identified by an arbitrary descriptor * rather than by a cryptographic hash --- since otherwise a malicious * user could add the wrong key. */ if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && !capable(CAP_SYS_ADMIN)) return -EACCES; memset(&secret, 0, sizeof(secret)); if (arg.key_id) { if (arg.raw_size != 0) return -EINVAL; err = get_keyring_key(arg.key_id, arg.key_spec.type, &secret); if (err) goto out_wipe_secret; } else { if (arg.raw_size < FSCRYPT_MIN_KEY_SIZE || arg.raw_size > FSCRYPT_MAX_KEY_SIZE) return -EINVAL; secret.size = arg.raw_size; err = -EFAULT; if (copy_from_user(secret.raw, uarg->raw, secret.size)) goto out_wipe_secret; } err = add_master_key(sb, &secret, &arg.key_spec); if (err) goto out_wipe_secret; /* Return the key identifier to userspace, if applicable */ err = -EFAULT; if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER && copy_to_user(uarg->key_spec.u.identifier, arg.key_spec.u.identifier, FSCRYPT_KEY_IDENTIFIER_SIZE)) goto out_wipe_secret; err = 0; out_wipe_secret: wipe_master_key_secret(&secret); return err; } EXPORT_SYMBOL_GPL(fscrypt_ioctl_add_key); static void fscrypt_get_test_dummy_secret(struct fscrypt_master_key_secret *secret) { static u8 test_key[FSCRYPT_MAX_KEY_SIZE]; get_random_once(test_key, FSCRYPT_MAX_KEY_SIZE); memset(secret, 0, sizeof(*secret)); secret->size = FSCRYPT_MAX_KEY_SIZE; memcpy(secret->raw, test_key, FSCRYPT_MAX_KEY_SIZE); } int fscrypt_get_test_dummy_key_identifier( u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) { struct fscrypt_master_key_secret secret; int err; fscrypt_get_test_dummy_secret(&secret); err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size); if (err) goto out; err = fscrypt_hkdf_expand(&secret.hkdf, HKDF_CONTEXT_KEY_IDENTIFIER, NULL, 0, key_identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); out: wipe_master_key_secret(&secret); return err; } /** * fscrypt_add_test_dummy_key() - add the test dummy encryption key * @sb: the filesystem instance to add the key to * @key_spec: the key specifier of the test dummy encryption key * * Add the key for the test_dummy_encryption mount option to the filesystem. To * prevent misuse of this mount option, a per-boot random key is used instead of * a hardcoded one. This makes it so that any encrypted files created using * this option won't be accessible after a reboot. * * Return: 0 on success, -errno on failure */ int fscrypt_add_test_dummy_key(struct super_block *sb, struct fscrypt_key_specifier *key_spec) { struct fscrypt_master_key_secret secret; int err; fscrypt_get_test_dummy_secret(&secret); err = add_master_key(sb, &secret, key_spec); wipe_master_key_secret(&secret); return err; } /* * Verify that the current user has added a master key with the given identifier * (returns -ENOKEY if not). This is needed to prevent a user from encrypting * their files using some other user's key which they don't actually know. * Cryptographically this isn't much of a problem, but the semantics of this * would be a bit weird, so it's best to just forbid it. * * The system administrator (CAP_FOWNER) can override this, which should be * enough for any use cases where encryption policies are being set using keys * that were chosen ahead of time but aren't available at the moment. * * Note that the key may have already removed by the time this returns, but * that's okay; we just care whether the key was there at some point. * * Return: 0 if the key is added, -ENOKEY if it isn't, or another -errno code */ int fscrypt_verify_key_added(struct super_block *sb, const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) { struct fscrypt_key_specifier mk_spec; struct fscrypt_master_key *mk; struct key *mk_user; int err; mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; memcpy(mk_spec.u.identifier, identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); mk = fscrypt_find_master_key(sb, &mk_spec); if (!mk) { err = -ENOKEY; goto out; } down_read(&mk->mk_sem); mk_user = find_master_key_user(mk); if (IS_ERR(mk_user)) { err = PTR_ERR(mk_user); } else { key_put(mk_user); err = 0; } up_read(&mk->mk_sem); fscrypt_put_master_key(mk); out: if (err == -ENOKEY && capable(CAP_FOWNER)) err = 0; return err; } /* * Try to evict the inode's dentries from the dentry cache. If the inode is a * directory, then it can have at most one dentry; however, that dentry may be * pinned by child dentries, so first try to evict the children too. */ static void shrink_dcache_inode(struct inode *inode) { struct dentry *dentry; if (S_ISDIR(inode->i_mode)) { dentry = d_find_any_alias(inode); if (dentry) { shrink_dcache_parent(dentry); dput(dentry); } } d_prune_aliases(inode); } static void evict_dentries_for_decrypted_inodes(struct fscrypt_master_key *mk) { struct fscrypt_inode_info *ci; struct inode *inode; struct inode *toput_inode = NULL; spin_lock(&mk->mk_decrypted_inodes_lock); list_for_each_entry(ci, &mk->mk_decrypted_inodes, ci_master_key_link) { inode = ci->ci_inode; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&mk->mk_decrypted_inodes_lock); shrink_dcache_inode(inode); iput(toput_inode); toput_inode = inode; spin_lock(&mk->mk_decrypted_inodes_lock); } spin_unlock(&mk->mk_decrypted_inodes_lock); iput(toput_inode); } static int check_for_busy_inodes(struct super_block *sb, struct fscrypt_master_key *mk) { struct list_head *pos; size_t busy_count = 0; unsigned long ino; char ino_str[50] = ""; spin_lock(&mk->mk_decrypted_inodes_lock); list_for_each(pos, &mk->mk_decrypted_inodes) busy_count++; if (busy_count == 0) { spin_unlock(&mk->mk_decrypted_inodes_lock); return 0; } { /* select an example file to show for debugging purposes */ struct inode *inode = list_first_entry(&mk->mk_decrypted_inodes, struct fscrypt_inode_info, ci_master_key_link)->ci_inode; ino = inode->i_ino; } spin_unlock(&mk->mk_decrypted_inodes_lock); /* If the inode is currently being created, ino may still be 0. */ if (ino) snprintf(ino_str, sizeof(ino_str), ", including ino %lu", ino); fscrypt_warn(NULL, "%s: %zu inode(s) still busy after removing key with %s %*phN%s", sb->s_id, busy_count, master_key_spec_type(&mk->mk_spec), master_key_spec_len(&mk->mk_spec), (u8 *)&mk->mk_spec.u, ino_str); return -EBUSY; } static int try_to_lock_encrypted_files(struct super_block *sb, struct fscrypt_master_key *mk) { int err1; int err2; /* * An inode can't be evicted while it is dirty or has dirty pages. * Thus, we first have to clean the inodes in ->mk_decrypted_inodes. * * Just do it the easy way: call sync_filesystem(). It's overkill, but * it works, and it's more important to minimize the amount of caches we * drop than the amount of data we sync. Also, unprivileged users can * already call sync_filesystem() via sys_syncfs() or sys_sync(). */ down_read(&sb->s_umount); err1 = sync_filesystem(sb); up_read(&sb->s_umount); /* If a sync error occurs, still try to evict as much as possible. */ /* * Inodes are pinned by their dentries, so we have to evict their * dentries. shrink_dcache_sb() would suffice, but would be overkill * and inappropriate for use by unprivileged users. So instead go * through the inodes' alias lists and try to evict each dentry. */ evict_dentries_for_decrypted_inodes(mk); /* * evict_dentries_for_decrypted_inodes() already iput() each inode in * the list; any inodes for which that dropped the last reference will * have been evicted due to fscrypt_drop_inode() detecting the key * removal and telling the VFS to evict the inode. So to finish, we * just need to check whether any inodes couldn't be evicted. */ err2 = check_for_busy_inodes(sb, mk); return err1 ?: err2; } /* * Try to remove an fscrypt master encryption key. * * FS_IOC_REMOVE_ENCRYPTION_KEY (all_users=false) removes the current user's * claim to the key, then removes the key itself if no other users have claims. * FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS (all_users=true) always removes the * key itself. * * To "remove the key itself", first we transition the key to the "incompletely * removed" state, so that no more inodes can be unlocked with it. Then we try * to evict all cached inodes that had been unlocked with the key. * * If all inodes were evicted, then we unlink the fscrypt_master_key from the * keyring. Otherwise it remains in the keyring in the "incompletely removed" * state where it tracks the list of remaining inodes. Userspace can execute * the ioctl again later to retry eviction, or alternatively can re-add the key. * * For more details, see the "Removing keys" section of * Documentation/filesystems/fscrypt.rst. */ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) { struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_remove_key_arg __user *uarg = _uarg; struct fscrypt_remove_key_arg arg; struct fscrypt_master_key *mk; u32 status_flags = 0; int err; bool inodes_remain; if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; if (!valid_key_spec(&arg.key_spec)) return -EINVAL; if (memchr_inv(arg.__reserved, 0, sizeof(arg.__reserved))) return -EINVAL; /* * Only root can add and remove keys that are identified by an arbitrary * descriptor rather than by a cryptographic hash. */ if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && !capable(CAP_SYS_ADMIN)) return -EACCES; /* Find the key being removed. */ mk = fscrypt_find_master_key(sb, &arg.key_spec); if (!mk) return -ENOKEY; down_write(&mk->mk_sem); /* If relevant, remove current user's (or all users) claim to the key */ if (mk->mk_users && mk->mk_users->keys.nr_leaves_on_tree != 0) { if (all_users) err = keyring_clear(mk->mk_users); else err = remove_master_key_user(mk); if (err) { up_write(&mk->mk_sem); goto out_put_key; } if (mk->mk_users->keys.nr_leaves_on_tree != 0) { /* * Other users have still added the key too. We removed * the current user's claim to the key, but we still * can't remove the key itself. */ status_flags |= FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS; err = 0; up_write(&mk->mk_sem); goto out_put_key; } } /* No user claims remaining. Initiate removal of the key. */ err = -ENOKEY; if (mk->mk_present) { fscrypt_initiate_key_removal(sb, mk); err = 0; } inodes_remain = refcount_read(&mk->mk_active_refs) > 0; up_write(&mk->mk_sem); if (inodes_remain) { /* Some inodes still reference this key; try to evict them. */ err = try_to_lock_encrypted_files(sb, mk); if (err == -EBUSY) { status_flags |= FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY; err = 0; } } /* * We return 0 if we successfully did something: removed a claim to the * key, initiated removal of the key, or tried locking the files again. * Users need to check the informational status flags if they care * whether the key has been fully removed including all files locked. */ out_put_key: fscrypt_put_master_key(mk); if (err == 0) err = put_user(status_flags, &uarg->removal_status_flags); return err; } int fscrypt_ioctl_remove_key(struct file *filp, void __user *uarg) { return do_remove_key(filp, uarg, false); } EXPORT_SYMBOL_GPL(fscrypt_ioctl_remove_key); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *uarg) { if (!capable(CAP_SYS_ADMIN)) return -EACCES; return do_remove_key(filp, uarg, true); } EXPORT_SYMBOL_GPL(fscrypt_ioctl_remove_key_all_users); /* * Retrieve the status of an fscrypt master encryption key. * * We set ->status to indicate whether the key is absent, present, or * incompletely removed. (For an explanation of what these statuses mean and * how they are represented internally, see struct fscrypt_master_key.) This * field allows applications to easily determine the status of an encrypted * directory without using a hack such as trying to open a regular file in it * (which can confuse the "incompletely removed" status with absent or present). * * In addition, for v2 policy keys we allow applications to determine, via * ->status_flags and ->user_count, whether the key has been added by the * current user, by other users, or by both. Most applications should not need * this, since ordinarily only one user should know a given key. However, if a * secret key is shared by multiple users, applications may wish to add an * already-present key to prevent other users from removing it. This ioctl can * be used to check whether that really is the case before the work is done to * add the key --- which might e.g. require prompting the user for a passphrase. * * For more details, see the "FS_IOC_GET_ENCRYPTION_KEY_STATUS" section of * Documentation/filesystems/fscrypt.rst. */ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) { struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_get_key_status_arg arg; struct fscrypt_master_key *mk; int err; if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; if (!valid_key_spec(&arg.key_spec)) return -EINVAL; if (memchr_inv(arg.__reserved, 0, sizeof(arg.__reserved))) return -EINVAL; arg.status_flags = 0; arg.user_count = 0; memset(arg.__out_reserved, 0, sizeof(arg.__out_reserved)); mk = fscrypt_find_master_key(sb, &arg.key_spec); if (!mk) { arg.status = FSCRYPT_KEY_STATUS_ABSENT; err = 0; goto out; } down_read(&mk->mk_sem); if (!mk->mk_present) { arg.status = refcount_read(&mk->mk_active_refs) > 0 ? FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED : FSCRYPT_KEY_STATUS_ABSENT /* raced with full removal */; err = 0; goto out_release_key; } arg.status = FSCRYPT_KEY_STATUS_PRESENT; if (mk->mk_users) { struct key *mk_user; arg.user_count = mk->mk_users->keys.nr_leaves_on_tree; mk_user = find_master_key_user(mk); if (!IS_ERR(mk_user)) { arg.status_flags |= FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF; key_put(mk_user); } else if (mk_user != ERR_PTR(-ENOKEY)) { err = PTR_ERR(mk_user); goto out_release_key; } } err = 0; out_release_key: up_read(&mk->mk_sem); fscrypt_put_master_key(mk); out: if (!err && copy_to_user(uarg, &arg, sizeof(arg))) err = -EFAULT; return err; } EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_key_status); int __init fscrypt_init_keyring(void) { int err; err = register_key_type(&key_type_fscrypt_user); if (err) return err; err = register_key_type(&key_type_fscrypt_provisioning); if (err) goto err_unregister_fscrypt_user; return 0; err_unregister_fscrypt_user: unregister_key_type(&key_type_fscrypt_user); return err; } |
| 964 825 257 352 726 117 956 988 972 40 978 979 978 979 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * sha256_base.h - core logic for SHA-256 implementations * * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> */ #ifndef _CRYPTO_SHA256_BASE_H #define _CRYPTO_SHA256_BASE_H #include <asm/byteorder.h> #include <asm/unaligned.h> #include <crypto/internal/hash.h> #include <crypto/sha2.h> #include <linux/string.h> #include <linux/types.h> typedef void (sha256_block_fn)(struct sha256_state *sst, u8 const *src, int blocks); static inline int sha224_base_init(struct shash_desc *desc) { struct sha256_state *sctx = shash_desc_ctx(desc); sha224_init(sctx); return 0; } static inline int sha256_base_init(struct shash_desc *desc) { struct sha256_state *sctx = shash_desc_ctx(desc); sha256_init(sctx); return 0; } static inline int lib_sha256_base_do_update(struct sha256_state *sctx, const u8 *data, unsigned int len, sha256_block_fn *block_fn) { unsigned int partial = sctx->count % SHA256_BLOCK_SIZE; sctx->count += len; if (unlikely((partial + len) >= SHA256_BLOCK_SIZE)) { int blocks; if (partial) { int p = SHA256_BLOCK_SIZE - partial; memcpy(sctx->buf + partial, data, p); data += p; len -= p; block_fn(sctx, sctx->buf, 1); } blocks = len / SHA256_BLOCK_SIZE; len %= SHA256_BLOCK_SIZE; if (blocks) { block_fn(sctx, data, blocks); data += blocks * SHA256_BLOCK_SIZE; } partial = 0; } if (len) memcpy(sctx->buf + partial, data, len); return 0; } static inline int sha256_base_do_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *block_fn) { struct sha256_state *sctx = shash_desc_ctx(desc); return lib_sha256_base_do_update(sctx, data, len, block_fn); } static inline int lib_sha256_base_do_finalize(struct sha256_state *sctx, sha256_block_fn *block_fn) { const int bit_offset = SHA256_BLOCK_SIZE - sizeof(__be64); __be64 *bits = (__be64 *)(sctx->buf + bit_offset); unsigned int partial = sctx->count % SHA256_BLOCK_SIZE; sctx->buf[partial++] = 0x80; if (partial > bit_offset) { memset(sctx->buf + partial, 0x0, SHA256_BLOCK_SIZE - partial); partial = 0; block_fn(sctx, sctx->buf, 1); } memset(sctx->buf + partial, 0x0, bit_offset - partial); *bits = cpu_to_be64(sctx->count << 3); block_fn(sctx, sctx->buf, 1); return 0; } static inline int sha256_base_do_finalize(struct shash_desc *desc, sha256_block_fn *block_fn) { struct sha256_state *sctx = shash_desc_ctx(desc); return lib_sha256_base_do_finalize(sctx, block_fn); } static inline int lib_sha256_base_finish(struct sha256_state *sctx, u8 *out, unsigned int digest_size) { __be32 *digest = (__be32 *)out; int i; for (i = 0; digest_size > 0; i++, digest_size -= sizeof(__be32)) put_unaligned_be32(sctx->state[i], digest++); memzero_explicit(sctx, sizeof(*sctx)); return 0; } static inline int sha256_base_finish(struct shash_desc *desc, u8 *out) { unsigned int digest_size = crypto_shash_digestsize(desc->tfm); struct sha256_state *sctx = shash_desc_ctx(desc); return lib_sha256_base_finish(sctx, out, digest_size); } #endif /* _CRYPTO_SHA256_BASE_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 | /* * linux/drivers/video/fbmem.c * * Copyright (C) 1994 Martin Schaller * * 2001 - Documented with DocBook * - Brad Douglas <brad@neruo.com> * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive * for more details. */ #include <linux/console.h> #include <linux/export.h> #include <linux/fb.h> #include <linux/fbcon.h> #include <video/nomodeset.h> #include "fb_internal.h" /* * Frame buffer device initialization and setup routines */ #define FBPIXMAPSIZE (1024 * 8) struct class *fb_class; DEFINE_MUTEX(registration_lock); struct fb_info *registered_fb[FB_MAX] __read_mostly; int num_registered_fb __read_mostly; #define for_each_registered_fb(i) \ for (i = 0; i < FB_MAX; i++) \ if (!registered_fb[i]) {} else struct fb_info *get_fb_info(unsigned int idx) { struct fb_info *fb_info; if (idx >= FB_MAX) return ERR_PTR(-ENODEV); mutex_lock(®istration_lock); fb_info = registered_fb[idx]; if (fb_info) refcount_inc(&fb_info->count); mutex_unlock(®istration_lock); return fb_info; } void put_fb_info(struct fb_info *fb_info) { if (!refcount_dec_and_test(&fb_info->count)) return; if (fb_info->fbops->fb_destroy) fb_info->fbops->fb_destroy(fb_info); } /* * Helpers */ int fb_get_color_depth(struct fb_var_screeninfo *var, struct fb_fix_screeninfo *fix) { int depth = 0; if (fix->visual == FB_VISUAL_MONO01 || fix->visual == FB_VISUAL_MONO10) depth = 1; else { if (var->green.length == var->blue.length && var->green.length == var->red.length && var->green.offset == var->blue.offset && var->green.offset == var->red.offset) depth = var->green.length; else depth = var->green.length + var->red.length + var->blue.length; } return depth; } EXPORT_SYMBOL(fb_get_color_depth); /* * Data padding functions. */ void fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch, u32 height) { __fb_pad_aligned_buffer(dst, d_pitch, src, s_pitch, height); } EXPORT_SYMBOL(fb_pad_aligned_buffer); void fb_pad_unaligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 idx, u32 height, u32 shift_high, u32 shift_low, u32 mod) { u8 mask = (u8) (0xfff << shift_high), tmp; int i, j; for (i = height; i--; ) { for (j = 0; j < idx; j++) { tmp = dst[j]; tmp &= mask; tmp |= *src >> shift_low; dst[j] = tmp; tmp = *src << shift_high; dst[j+1] = tmp; src++; } tmp = dst[idx]; tmp &= mask; tmp |= *src >> shift_low; dst[idx] = tmp; if (shift_high < mod) { tmp = *src << shift_high; dst[idx+1] = tmp; } src++; dst += d_pitch; } } EXPORT_SYMBOL(fb_pad_unaligned_buffer); /* * we need to lock this section since fb_cursor * may use fb_imageblit() */ char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size) { u32 align = buf->buf_align - 1, offset; char *addr = buf->addr; /* If IO mapped, we need to sync before access, no sharing of * the pixmap is done */ if (buf->flags & FB_PIXMAP_IO) { if (info->fbops->fb_sync && (buf->flags & FB_PIXMAP_SYNC)) info->fbops->fb_sync(info); return addr; } /* See if we fit in the remaining pixmap space */ offset = buf->offset + align; offset &= ~align; if (offset + size > buf->size) { /* We do not fit. In order to be able to re-use the buffer, * we must ensure no asynchronous DMA'ing or whatever operation * is in progress, we sync for that. */ if (info->fbops->fb_sync && (buf->flags & FB_PIXMAP_SYNC)) info->fbops->fb_sync(info); offset = 0; } buf->offset = offset + size; addr += offset; return addr; } EXPORT_SYMBOL(fb_get_buffer_offset); int fb_pan_display(struct fb_info *info, struct fb_var_screeninfo *var) { struct fb_fix_screeninfo *fix = &info->fix; unsigned int yres = info->var.yres; int err = 0; if (var->yoffset > 0) { if (var->vmode & FB_VMODE_YWRAP) { if (!fix->ywrapstep || (var->yoffset % fix->ywrapstep)) err = -EINVAL; else yres = 0; } else if (!fix->ypanstep || (var->yoffset % fix->ypanstep)) err = -EINVAL; } if (var->xoffset > 0 && (!fix->xpanstep || (var->xoffset % fix->xpanstep))) err = -EINVAL; if (err || !info->fbops->fb_pan_display || var->yoffset > info->var.yres_virtual - yres || var->xoffset > info->var.xres_virtual - info->var.xres) return -EINVAL; if ((err = info->fbops->fb_pan_display(var, info))) return err; info->var.xoffset = var->xoffset; info->var.yoffset = var->yoffset; if (var->vmode & FB_VMODE_YWRAP) info->var.vmode |= FB_VMODE_YWRAP; else info->var.vmode &= ~FB_VMODE_YWRAP; return 0; } EXPORT_SYMBOL(fb_pan_display); static int fb_check_caps(struct fb_info *info, struct fb_var_screeninfo *var, u32 activate) { struct fb_blit_caps caps, fbcaps; int err = 0; memset(&caps, 0, sizeof(caps)); memset(&fbcaps, 0, sizeof(fbcaps)); caps.flags = (activate & FB_ACTIVATE_ALL) ? 1 : 0; fbcon_get_requirement(info, &caps); info->fbops->fb_get_caps(info, &fbcaps, var); if (!bitmap_subset(caps.x, fbcaps.x, FB_MAX_BLIT_WIDTH) || !bitmap_subset(caps.y, fbcaps.y, FB_MAX_BLIT_HEIGHT) || (fbcaps.len < caps.len)) err = -EINVAL; return err; } int fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var) { int ret = 0; u32 activate; struct fb_var_screeninfo old_var; struct fb_videomode mode; struct fb_event event; u32 unused; if (var->activate & FB_ACTIVATE_INV_MODE) { struct fb_videomode mode1, mode2; fb_var_to_videomode(&mode1, var); fb_var_to_videomode(&mode2, &info->var); /* make sure we don't delete the videomode of current var */ ret = fb_mode_is_equal(&mode1, &mode2); if (!ret) { ret = fbcon_mode_deleted(info, &mode1); if (!ret) fb_delete_videomode(&mode1, &info->modelist); } return ret ? -EINVAL : 0; } if (!(var->activate & FB_ACTIVATE_FORCE) && !memcmp(&info->var, var, sizeof(struct fb_var_screeninfo))) return 0; activate = var->activate; /* When using FOURCC mode, make sure the red, green, blue and * transp fields are set to 0. */ if ((info->fix.capabilities & FB_CAP_FOURCC) && var->grayscale > 1) { if (var->red.offset || var->green.offset || var->blue.offset || var->transp.offset || var->red.length || var->green.length || var->blue.length || var->transp.length || var->red.msb_right || var->green.msb_right || var->blue.msb_right || var->transp.msb_right) return -EINVAL; } if (!info->fbops->fb_check_var) { *var = info->var; return 0; } /* bitfill_aligned() assumes that it's at least 8x8 */ if (var->xres < 8 || var->yres < 8) return -EINVAL; /* Too huge resolution causes multiplication overflow. */ if (check_mul_overflow(var->xres, var->yres, &unused) || check_mul_overflow(var->xres_virtual, var->yres_virtual, &unused)) return -EINVAL; ret = info->fbops->fb_check_var(var, info); if (ret) return ret; /* verify that virtual resolution >= physical resolution */ if (var->xres_virtual < var->xres || var->yres_virtual < var->yres) { pr_warn("WARNING: fbcon: Driver '%s' missed to adjust virtual screen size (%ux%u vs. %ux%u)\n", info->fix.id, var->xres_virtual, var->yres_virtual, var->xres, var->yres); return -EINVAL; } if ((var->activate & FB_ACTIVATE_MASK) != FB_ACTIVATE_NOW) return 0; if (info->fbops->fb_get_caps) { ret = fb_check_caps(info, var, activate); if (ret) return ret; } old_var = info->var; info->var = *var; if (info->fbops->fb_set_par) { ret = info->fbops->fb_set_par(info); if (ret) { info->var = old_var; printk(KERN_WARNING "detected " "fb_set_par error, " "error code: %d\n", ret); return ret; } } fb_pan_display(info, &info->var); fb_set_cmap(&info->cmap, info); fb_var_to_videomode(&mode, &info->var); if (info->modelist.prev && info->modelist.next && !list_empty(&info->modelist)) ret = fb_add_videomode(&mode, &info->modelist); if (ret) return ret; event.info = info; event.data = &mode; fb_notifier_call_chain(FB_EVENT_MODE_CHANGE, &event); return 0; } EXPORT_SYMBOL(fb_set_var); int fb_blank(struct fb_info *info, int blank) { struct fb_event event; int ret = -EINVAL; if (blank > FB_BLANK_POWERDOWN) blank = FB_BLANK_POWERDOWN; event.info = info; event.data = ␣ if (info->fbops->fb_blank) ret = info->fbops->fb_blank(blank, info); if (!ret) fb_notifier_call_chain(FB_EVENT_BLANK, &event); return ret; } EXPORT_SYMBOL(fb_blank); static int fb_check_foreignness(struct fb_info *fi) { const bool foreign_endian = fi->flags & FBINFO_FOREIGN_ENDIAN; fi->flags &= ~FBINFO_FOREIGN_ENDIAN; #ifdef __BIG_ENDIAN fi->flags |= foreign_endian ? 0 : FBINFO_BE_MATH; #else fi->flags |= foreign_endian ? FBINFO_BE_MATH : 0; #endif /* __BIG_ENDIAN */ if (fi->flags & FBINFO_BE_MATH && !fb_be_math(fi)) { pr_err("%s: enable CONFIG_FB_BIG_ENDIAN to " "support this framebuffer\n", fi->fix.id); return -ENOSYS; } else if (!(fi->flags & FBINFO_BE_MATH) && fb_be_math(fi)) { pr_err("%s: enable CONFIG_FB_LITTLE_ENDIAN to " "support this framebuffer\n", fi->fix.id); return -ENOSYS; } return 0; } static int do_register_framebuffer(struct fb_info *fb_info) { int i; struct fb_videomode mode; if (fb_check_foreignness(fb_info)) return -ENOSYS; if (num_registered_fb == FB_MAX) return -ENXIO; num_registered_fb++; for (i = 0 ; i < FB_MAX; i++) if (!registered_fb[i]) break; fb_info->node = i; refcount_set(&fb_info->count, 1); mutex_init(&fb_info->lock); mutex_init(&fb_info->mm_lock); fb_device_create(fb_info); if (fb_info->pixmap.addr == NULL) { fb_info->pixmap.addr = kmalloc(FBPIXMAPSIZE, GFP_KERNEL); if (fb_info->pixmap.addr) { fb_info->pixmap.size = FBPIXMAPSIZE; fb_info->pixmap.buf_align = 1; fb_info->pixmap.scan_align = 1; fb_info->pixmap.access_align = 32; fb_info->pixmap.flags = FB_PIXMAP_DEFAULT; } } fb_info->pixmap.offset = 0; if (bitmap_empty(fb_info->pixmap.blit_x, FB_MAX_BLIT_WIDTH)) bitmap_fill(fb_info->pixmap.blit_x, FB_MAX_BLIT_WIDTH); if (bitmap_empty(fb_info->pixmap.blit_y, FB_MAX_BLIT_HEIGHT)) bitmap_fill(fb_info->pixmap.blit_y, FB_MAX_BLIT_HEIGHT); if (!fb_info->modelist.prev || !fb_info->modelist.next) INIT_LIST_HEAD(&fb_info->modelist); if (fb_info->skip_vt_switch) pm_vt_switch_required(fb_info->device, false); else pm_vt_switch_required(fb_info->device, true); fb_var_to_videomode(&mode, &fb_info->var); fb_add_videomode(&mode, &fb_info->modelist); registered_fb[i] = fb_info; #ifdef CONFIG_GUMSTIX_AM200EPD { struct fb_event event; event.info = fb_info; fb_notifier_call_chain(FB_EVENT_FB_REGISTERED, &event); } #endif return fbcon_fb_registered(fb_info); } static void unbind_console(struct fb_info *fb_info) { int i = fb_info->node; if (WARN_ON(i < 0 || i >= FB_MAX || registered_fb[i] != fb_info)) return; fbcon_fb_unbind(fb_info); } static void unlink_framebuffer(struct fb_info *fb_info) { int i; i = fb_info->node; if (WARN_ON(i < 0 || i >= FB_MAX || registered_fb[i] != fb_info)) return; fb_device_destroy(fb_info); pm_vt_switch_unregister(fb_info->device); unbind_console(fb_info); } static void do_unregister_framebuffer(struct fb_info *fb_info) { unlink_framebuffer(fb_info); if (fb_info->pixmap.addr && (fb_info->pixmap.flags & FB_PIXMAP_DEFAULT)) { kfree(fb_info->pixmap.addr); fb_info->pixmap.addr = NULL; } fb_destroy_modelist(&fb_info->modelist); registered_fb[fb_info->node] = NULL; num_registered_fb--; #ifdef CONFIG_GUMSTIX_AM200EPD { struct fb_event event; event.info = fb_info; fb_notifier_call_chain(FB_EVENT_FB_UNREGISTERED, &event); } #endif fbcon_fb_unregistered(fb_info); /* this may free fb info */ put_fb_info(fb_info); } /** * register_framebuffer - registers a frame buffer device * @fb_info: frame buffer info structure * * Registers a frame buffer device @fb_info. * * Returns negative errno on error, or zero for success. * */ int register_framebuffer(struct fb_info *fb_info) { int ret; mutex_lock(®istration_lock); ret = do_register_framebuffer(fb_info); mutex_unlock(®istration_lock); return ret; } EXPORT_SYMBOL(register_framebuffer); /** * unregister_framebuffer - releases a frame buffer device * @fb_info: frame buffer info structure * * Unregisters a frame buffer device @fb_info. * * Returns negative errno on error, or zero for success. * * This function will also notify the framebuffer console * to release the driver. * * This is meant to be called within a driver's module_exit() * function. If this is called outside module_exit(), ensure * that the driver implements fb_open() and fb_release() to * check that no processes are using the device. */ void unregister_framebuffer(struct fb_info *fb_info) { mutex_lock(®istration_lock); do_unregister_framebuffer(fb_info); mutex_unlock(®istration_lock); } EXPORT_SYMBOL(unregister_framebuffer); /** * fb_set_suspend - low level driver signals suspend * @info: framebuffer affected * @state: 0 = resuming, !=0 = suspending * * This is meant to be used by low level drivers to * signal suspend/resume to the core & clients. * It must be called with the console semaphore held */ void fb_set_suspend(struct fb_info *info, int state) { WARN_CONSOLE_UNLOCKED(); if (state) { fbcon_suspended(info); info->state = FBINFO_STATE_SUSPENDED; } else { info->state = FBINFO_STATE_RUNNING; fbcon_resumed(info); } } EXPORT_SYMBOL(fb_set_suspend); static int __init fbmem_init(void) { int ret; fb_class = class_create("graphics"); if (IS_ERR(fb_class)) { ret = PTR_ERR(fb_class); pr_err("Unable to create fb class; errno = %d\n", ret); goto err_fb_class; } ret = fb_init_procfs(); if (ret) goto err_class_destroy; ret = fb_register_chrdev(); if (ret) goto err_fb_cleanup_procfs; fb_console_init(); return 0; err_fb_cleanup_procfs: fb_cleanup_procfs(); err_class_destroy: class_destroy(fb_class); err_fb_class: fb_class = NULL; return ret; } #ifdef MODULE static void __exit fbmem_exit(void) { fb_console_exit(); fb_unregister_chrdev(); fb_cleanup_procfs(); class_destroy(fb_class); } module_init(fbmem_init); module_exit(fbmem_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Framebuffer base"); #else subsys_initcall(fbmem_init); #endif int fb_new_modelist(struct fb_info *info) { struct fb_var_screeninfo var = info->var; struct list_head *pos, *n; struct fb_modelist *modelist; struct fb_videomode *m, mode; int err; list_for_each_safe(pos, n, &info->modelist) { modelist = list_entry(pos, struct fb_modelist, list); m = &modelist->mode; fb_videomode_to_var(&var, m); var.activate = FB_ACTIVATE_TEST; err = fb_set_var(info, &var); fb_var_to_videomode(&mode, &var); if (err || !fb_mode_is_equal(m, &mode)) { list_del(pos); kfree(pos); } } if (list_empty(&info->modelist)) return 1; fbcon_new_modelist(info); return 0; } bool fb_modesetting_disabled(const char *drvname) { bool fwonly = video_firmware_drivers_only(); if (fwonly) pr_warn("Driver %s not loading because of nomodeset parameter\n", drvname); return fwonly; } EXPORT_SYMBOL(fb_modesetting_disabled); MODULE_LICENSE("GPL"); |
| 5 12 11 7 7 12 2 2 7 14 14 6 7 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 | // SPDX-License-Identifier: GPL-2.0 /* * Ldisc rw semaphore * * The ldisc semaphore is semantically a rw_semaphore but which enforces * an alternate policy, namely: * 1) Supports lock wait timeouts * 2) Write waiter has priority * 3) Downgrading is not supported * * Implementation notes: * 1) Upper half of semaphore count is a wait count (differs from rwsem * in that rwsem normalizes the upper half to the wait bias) * 2) Lacks overflow checking * * The generic counting was copied and modified from include/asm-generic/rwsem.h * by Paul Mackerras <paulus@samba.org>. * * The scheduling policy was copied and modified from lib/rwsem.c * Written by David Howells (dhowells@redhat.com). * * This implementation incorporates the write lock stealing work of * Michel Lespinasse <walken@google.com>. * * Copyright (C) 2013 Peter Hurley <peter@hurleysoftware.com> */ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/tty.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/task.h> #if BITS_PER_LONG == 64 # define LDSEM_ACTIVE_MASK 0xffffffffL #else # define LDSEM_ACTIVE_MASK 0x0000ffffL #endif #define LDSEM_UNLOCKED 0L #define LDSEM_ACTIVE_BIAS 1L #define LDSEM_WAIT_BIAS (-LDSEM_ACTIVE_MASK-1) #define LDSEM_READ_BIAS LDSEM_ACTIVE_BIAS #define LDSEM_WRITE_BIAS (LDSEM_WAIT_BIAS + LDSEM_ACTIVE_BIAS) struct ldsem_waiter { struct list_head list; struct task_struct *task; }; /* * Initialize an ldsem: */ void __init_ldsem(struct ld_semaphore *sem, const char *name, struct lock_class_key *key) { #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Make sure we are not reinitializing a held semaphore: */ debug_check_no_locks_freed((void *)sem, sizeof(*sem)); lockdep_init_map(&sem->dep_map, name, key, 0); #endif atomic_long_set(&sem->count, LDSEM_UNLOCKED); sem->wait_readers = 0; raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->read_wait); INIT_LIST_HEAD(&sem->write_wait); } static void __ldsem_wake_readers(struct ld_semaphore *sem) { struct ldsem_waiter *waiter, *next; struct task_struct *tsk; long adjust, count; /* * Try to grant read locks to all readers on the read wait list. * Note the 'active part' of the count is incremented by * the number of readers before waking any processes up. */ adjust = sem->wait_readers * (LDSEM_ACTIVE_BIAS - LDSEM_WAIT_BIAS); count = atomic_long_add_return(adjust, &sem->count); do { if (count > 0) break; if (atomic_long_try_cmpxchg(&sem->count, &count, count - adjust)) return; } while (1); list_for_each_entry_safe(waiter, next, &sem->read_wait, list) { tsk = waiter->task; smp_store_release(&waiter->task, NULL); wake_up_process(tsk); put_task_struct(tsk); } INIT_LIST_HEAD(&sem->read_wait); sem->wait_readers = 0; } static inline int writer_trylock(struct ld_semaphore *sem) { /* * Only wake this writer if the active part of the count can be * transitioned from 0 -> 1 */ long count = atomic_long_add_return(LDSEM_ACTIVE_BIAS, &sem->count); do { if ((count & LDSEM_ACTIVE_MASK) == LDSEM_ACTIVE_BIAS) return 1; if (atomic_long_try_cmpxchg(&sem->count, &count, count - LDSEM_ACTIVE_BIAS)) return 0; } while (1); } static void __ldsem_wake_writer(struct ld_semaphore *sem) { struct ldsem_waiter *waiter; waiter = list_entry(sem->write_wait.next, struct ldsem_waiter, list); wake_up_process(waiter->task); } /* * handle the lock release when processes blocked on it that can now run * - if we come here from up_xxxx(), then: * - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed) * - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so) * - the spinlock must be held by the caller * - woken process blocks are discarded from the list after having task zeroed */ static void __ldsem_wake(struct ld_semaphore *sem) { if (!list_empty(&sem->write_wait)) __ldsem_wake_writer(sem); else if (!list_empty(&sem->read_wait)) __ldsem_wake_readers(sem); } static void ldsem_wake(struct ld_semaphore *sem) { unsigned long flags; raw_spin_lock_irqsave(&sem->wait_lock, flags); __ldsem_wake(sem); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); } /* * wait for the read lock to be granted */ static struct ld_semaphore __sched * down_read_failed(struct ld_semaphore *sem, long count, long timeout) { struct ldsem_waiter waiter; long adjust = -LDSEM_ACTIVE_BIAS + LDSEM_WAIT_BIAS; /* set up my own style of waitqueue */ raw_spin_lock_irq(&sem->wait_lock); /* * Try to reverse the lock attempt but if the count has changed * so that reversing fails, check if there are no waiters, * and early-out if not */ do { if (atomic_long_try_cmpxchg(&sem->count, &count, count + adjust)) { count += adjust; break; } if (count > 0) { raw_spin_unlock_irq(&sem->wait_lock); return sem; } } while (1); list_add_tail(&waiter.list, &sem->read_wait); sem->wait_readers++; waiter.task = current; get_task_struct(current); /* if there are no active locks, wake the new lock owner(s) */ if ((count & LDSEM_ACTIVE_MASK) == 0) __ldsem_wake(sem); raw_spin_unlock_irq(&sem->wait_lock); /* wait to be given the lock */ for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!smp_load_acquire(&waiter.task)) break; if (!timeout) break; timeout = schedule_timeout(timeout); } __set_current_state(TASK_RUNNING); if (!timeout) { /* * Lock timed out but check if this task was just * granted lock ownership - if so, pretend there * was no timeout; otherwise, cleanup lock wait. */ raw_spin_lock_irq(&sem->wait_lock); if (waiter.task) { atomic_long_add_return(-LDSEM_WAIT_BIAS, &sem->count); sem->wait_readers--; list_del(&waiter.list); raw_spin_unlock_irq(&sem->wait_lock); put_task_struct(waiter.task); return NULL; } raw_spin_unlock_irq(&sem->wait_lock); } return sem; } /* * wait for the write lock to be granted */ static struct ld_semaphore __sched * down_write_failed(struct ld_semaphore *sem, long count, long timeout) { struct ldsem_waiter waiter; long adjust = -LDSEM_ACTIVE_BIAS; int locked = 0; /* set up my own style of waitqueue */ raw_spin_lock_irq(&sem->wait_lock); /* * Try to reverse the lock attempt but if the count has changed * so that reversing fails, check if the lock is now owned, * and early-out if so. */ do { if (atomic_long_try_cmpxchg(&sem->count, &count, count + adjust)) break; if ((count & LDSEM_ACTIVE_MASK) == LDSEM_ACTIVE_BIAS) { raw_spin_unlock_irq(&sem->wait_lock); return sem; } } while (1); list_add_tail(&waiter.list, &sem->write_wait); waiter.task = current; set_current_state(TASK_UNINTERRUPTIBLE); for (;;) { if (!timeout) break; raw_spin_unlock_irq(&sem->wait_lock); timeout = schedule_timeout(timeout); raw_spin_lock_irq(&sem->wait_lock); set_current_state(TASK_UNINTERRUPTIBLE); locked = writer_trylock(sem); if (locked) break; } if (!locked) atomic_long_add_return(-LDSEM_WAIT_BIAS, &sem->count); list_del(&waiter.list); /* * In case of timeout, wake up every reader who gave the right of way * to writer. Prevent separation readers into two groups: * one that helds semaphore and another that sleeps. * (in case of no contention with a writer) */ if (!locked && list_empty(&sem->write_wait)) __ldsem_wake_readers(sem); raw_spin_unlock_irq(&sem->wait_lock); __set_current_state(TASK_RUNNING); /* lock wait may have timed out */ if (!locked) return NULL; return sem; } static int __ldsem_down_read_nested(struct ld_semaphore *sem, int subclass, long timeout) { long count; rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_); count = atomic_long_add_return(LDSEM_READ_BIAS, &sem->count); if (count <= 0) { lock_contended(&sem->dep_map, _RET_IP_); if (!down_read_failed(sem, count, timeout)) { rwsem_release(&sem->dep_map, _RET_IP_); return 0; } } lock_acquired(&sem->dep_map, _RET_IP_); return 1; } static int __ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, long timeout) { long count; rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_); count = atomic_long_add_return(LDSEM_WRITE_BIAS, &sem->count); if ((count & LDSEM_ACTIVE_MASK) != LDSEM_ACTIVE_BIAS) { lock_contended(&sem->dep_map, _RET_IP_); if (!down_write_failed(sem, count, timeout)) { rwsem_release(&sem->dep_map, _RET_IP_); return 0; } } lock_acquired(&sem->dep_map, _RET_IP_); return 1; } /* * lock for reading -- returns 1 if successful, 0 if timed out */ int __sched ldsem_down_read(struct ld_semaphore *sem, long timeout) { might_sleep(); return __ldsem_down_read_nested(sem, 0, timeout); } /* * trylock for reading -- returns 1 if successful, 0 if contention */ int ldsem_down_read_trylock(struct ld_semaphore *sem) { long count = atomic_long_read(&sem->count); while (count >= 0) { if (atomic_long_try_cmpxchg(&sem->count, &count, count + LDSEM_READ_BIAS)) { rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); lock_acquired(&sem->dep_map, _RET_IP_); return 1; } } return 0; } /* * lock for writing -- returns 1 if successful, 0 if timed out */ int __sched ldsem_down_write(struct ld_semaphore *sem, long timeout) { might_sleep(); return __ldsem_down_write_nested(sem, 0, timeout); } /* * trylock for writing -- returns 1 if successful, 0 if contention */ int ldsem_down_write_trylock(struct ld_semaphore *sem) { long count = atomic_long_read(&sem->count); while ((count & LDSEM_ACTIVE_MASK) == 0) { if (atomic_long_try_cmpxchg(&sem->count, &count, count + LDSEM_WRITE_BIAS)) { rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_); lock_acquired(&sem->dep_map, _RET_IP_); return 1; } } return 0; } /* * release a read lock */ void ldsem_up_read(struct ld_semaphore *sem) { long count; rwsem_release(&sem->dep_map, _RET_IP_); count = atomic_long_add_return(-LDSEM_READ_BIAS, &sem->count); if (count < 0 && (count & LDSEM_ACTIVE_MASK) == 0) ldsem_wake(sem); } /* * release a write lock */ void ldsem_up_write(struct ld_semaphore *sem) { long count; rwsem_release(&sem->dep_map, _RET_IP_); count = atomic_long_add_return(-LDSEM_WRITE_BIAS, &sem->count); if (count < 0) ldsem_wake(sem); } #ifdef CONFIG_DEBUG_LOCK_ALLOC int ldsem_down_read_nested(struct ld_semaphore *sem, int subclass, long timeout) { might_sleep(); return __ldsem_down_read_nested(sem, subclass, timeout); } int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, long timeout) { might_sleep(); return __ldsem_down_write_nested(sem, subclass, timeout); } #endif |
| 33 42 41 7 7 7 7 7 5 2 2 2 3 50 50 49 1 49 1 49 50 5 45 7 43 26 68 50 48 1 1 1 1 50 1 49 40 6 1 2 42 13 6 19 4 42 19 42 46 46 41 4 4 18 23 10 4 2 8 5 5 1 1 34 3 31 30 3 27 5 2 1 34 11 11 7 4 50 1 1 8 5 44 1 43 42 41 3 5 4 1 52 52 7 4 3 4 3 5 2 7 7 36 47 47 47 47 31 18 17 14 2 36 3 1 1 1 2 1 1 3 3 14 14 7 14 14 10 8 2 4 34 13 21 14 4 13 5 7 11 13 5 11 7 13 5 10 7 7 11 13 3 2 13 5 12 6 14 4 15 3 15 2 9 9 15 3 14 4 12 14 4 18 12 6 16 2 18 18 18 18 3 21 21 33 33 32 36 36 36 36 36 36 3 36 10 10 34 35 1 34 34 2 32 33 33 32 1 33 33 33 39 2 2 2 33 3 3 44 3 41 5 2 3 1 35 39 7 4 40 52 47 5 7 7 7 7 7 7 7 13 9 9 9 4 4 4 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 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 | /* FUSE: Filesystem in Userspace Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu> This program can be distributed under the terms of the GNU GPL. See the file COPYING. */ #include "fuse_i.h" #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/statfs.h> #include <linux/random.h> #include <linux/sched.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/pid_namespace.h> #include <uapi/linux/magic.h> MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); MODULE_DESCRIPTION("Filesystem in Userspace"); MODULE_LICENSE("GPL"); static struct kmem_cache *fuse_inode_cachep; struct list_head fuse_conn_list; DEFINE_MUTEX(fuse_mutex); static int set_global_limit(const char *val, const struct kernel_param *kp); unsigned max_user_bgreq; module_param_call(max_user_bgreq, set_global_limit, param_get_uint, &max_user_bgreq, 0644); __MODULE_PARM_TYPE(max_user_bgreq, "uint"); MODULE_PARM_DESC(max_user_bgreq, "Global limit for the maximum number of backgrounded requests an " "unprivileged user can set"); unsigned max_user_congthresh; module_param_call(max_user_congthresh, set_global_limit, param_get_uint, &max_user_congthresh, 0644); __MODULE_PARM_TYPE(max_user_congthresh, "uint"); MODULE_PARM_DESC(max_user_congthresh, "Global limit for the maximum congestion threshold an " "unprivileged user can set"); #define FUSE_DEFAULT_BLKSIZE 512 /** Maximum number of outstanding background requests */ #define FUSE_DEFAULT_MAX_BACKGROUND 12 /** Congestion starts at 75% of maximum */ #define FUSE_DEFAULT_CONGESTION_THRESHOLD (FUSE_DEFAULT_MAX_BACKGROUND * 3 / 4) #ifdef CONFIG_BLOCK static struct file_system_type fuseblk_fs_type; #endif struct fuse_forget_link *fuse_alloc_forget(void) { return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT); } static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void) { struct fuse_submount_lookup *sl; sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT); if (!sl) return NULL; sl->forget = fuse_alloc_forget(); if (!sl->forget) goto out_free; return sl; out_free: kfree(sl); return NULL; } static struct inode *fuse_alloc_inode(struct super_block *sb) { struct fuse_inode *fi; fi = alloc_inode_sb(sb, fuse_inode_cachep, GFP_KERNEL); if (!fi) return NULL; fi->i_time = 0; fi->inval_mask = ~0; fi->nodeid = 0; fi->nlookup = 0; fi->attr_version = 0; fi->orig_ino = 0; fi->state = 0; fi->submount_lookup = NULL; mutex_init(&fi->mutex); spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); if (!fi->forget) goto out_free; if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi)) goto out_free_forget; if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_inode_backing_set(fi, NULL); return &fi->inode; out_free_forget: kfree(fi->forget); out_free: kmem_cache_free(fuse_inode_cachep, fi); return NULL; } static void fuse_free_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); mutex_destroy(&fi->mutex); kfree(fi->forget); #ifdef CONFIG_FUSE_DAX kfree(fi->dax); #endif if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_backing_put(fuse_inode_backing(fi)); kmem_cache_free(fuse_inode_cachep, fi); } static void fuse_cleanup_submount_lookup(struct fuse_conn *fc, struct fuse_submount_lookup *sl) { if (!refcount_dec_and_test(&sl->count)) return; fuse_queue_forget(fc, sl->forget, sl->nodeid, 1); sl->forget = NULL; kfree(sl); } static void fuse_evict_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); /* Will write inode on close/munmap and in all other dirtiers */ WARN_ON(inode->i_state & I_DIRTY_INODE); truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_sb->s_flags & SB_ACTIVE) { struct fuse_conn *fc = get_fuse_conn(inode); if (FUSE_IS_DAX(inode)) fuse_dax_inode_cleanup(inode); if (fi->nlookup) { fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup); fi->forget = NULL; } if (fi->submount_lookup) { fuse_cleanup_submount_lookup(fc, fi->submount_lookup); fi->submount_lookup = NULL; } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { WARN_ON(fi->iocachectr != 0); WARN_ON(!list_empty(&fi->write_files)); WARN_ON(!list_empty(&fi->queued_writes)); } } static int fuse_reconfigure(struct fs_context *fsc) { struct super_block *sb = fsc->root->d_sb; sync_filesystem(sb); if (fsc->sb_flags & SB_MANDLOCK) return -EINVAL; return 0; } /* * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down * so that it will fit. */ static ino_t fuse_squash_ino(u64 ino64) { ino_t ino = (ino_t) ino64; if (sizeof(ino_t) < sizeof(u64)) ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8; return ino; } void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, struct fuse_statx *sx, u64 attr_valid, u32 cache_mask) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); lockdep_assert_held(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); fi->i_time = attr_valid; /* Clear basic stats from invalid mask */ set_mask_bits(&fi->inval_mask, STATX_BASIC_STATS, 0); inode->i_ino = fuse_squash_ino(attr->ino); inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); set_nlink(inode, attr->nlink); inode->i_uid = make_kuid(fc->user_ns, attr->uid); inode->i_gid = make_kgid(fc->user_ns, attr->gid); inode->i_blocks = attr->blocks; /* Sanitize nsecs */ attr->atimensec = min_t(u32, attr->atimensec, NSEC_PER_SEC - 1); attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1); attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1); inode_set_atime(inode, attr->atime, attr->atimensec); /* mtime from server may be stale due to local buffered write */ if (!(cache_mask & STATX_MTIME)) { inode_set_mtime(inode, attr->mtime, attr->mtimensec); } if (!(cache_mask & STATX_CTIME)) { inode_set_ctime(inode, attr->ctime, attr->ctimensec); } if (sx) { /* Sanitize nsecs */ sx->btime.tv_nsec = min_t(u32, sx->btime.tv_nsec, NSEC_PER_SEC - 1); /* * Btime has been queried, cache is valid (whether or not btime * is available or not) so clear STATX_BTIME from inval_mask. * * Availability of the btime attribute is indicated in * FUSE_I_BTIME */ set_mask_bits(&fi->inval_mask, STATX_BTIME, 0); if (sx->mask & STATX_BTIME) { set_bit(FUSE_I_BTIME, &fi->state); fi->i_btime.tv_sec = sx->btime.tv_sec; fi->i_btime.tv_nsec = sx->btime.tv_nsec; } } if (attr->blksize != 0) inode->i_blkbits = ilog2(attr->blksize); else inode->i_blkbits = inode->i_sb->s_blocksize_bits; /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the * check in may_delete(). */ fi->orig_i_mode = inode->i_mode; if (!fc->default_permissions) inode->i_mode &= ~S_ISVTX; fi->orig_ino = attr->ino; /* * We are refreshing inode data and it is possible that another * client set suid/sgid or security.capability xattr. So clear * S_NOSEC. Ideally, we could have cleared it only if suid/sgid * was set or if security.capability xattr was set. But we don't * know if security.capability has been set or not. So clear it * anyway. Its less efficient but should be safe. */ inode->i_flags &= ~S_NOSEC; } u32 fuse_get_cache_mask(struct inode *inode) { struct fuse_conn *fc = get_fuse_conn(inode); if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) return 0; return STATX_MTIME | STATX_CTIME | STATX_SIZE; } void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, struct fuse_statx *sx, u64 attr_valid, u64 attr_version) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); u32 cache_mask; loff_t oldsize; struct timespec64 old_mtime; spin_lock(&fi->lock); /* * In case of writeback_cache enabled, writes update mtime, ctime and * may update i_size. In these cases trust the cached value in the * inode. */ cache_mask = fuse_get_cache_mask(inode); if (cache_mask & STATX_SIZE) attr->size = i_size_read(inode); if (cache_mask & STATX_MTIME) { attr->mtime = inode_get_mtime_sec(inode); attr->mtimensec = inode_get_mtime_nsec(inode); } if (cache_mask & STATX_CTIME) { attr->ctime = inode_get_ctime_sec(inode); attr->ctimensec = inode_get_ctime_nsec(inode); } if ((attr_version != 0 && fi->attr_version > attr_version) || test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) { spin_unlock(&fi->lock); return; } old_mtime = inode_get_mtime(inode); fuse_change_attributes_common(inode, attr, sx, attr_valid, cache_mask); oldsize = inode->i_size; /* * In case of writeback_cache enabled, the cached writes beyond EOF * extend local i_size without keeping userspace server in sync. So, * attr->size coming from server can be stale. We cannot trust it. */ if (!(cache_mask & STATX_SIZE)) i_size_write(inode, attr->size); spin_unlock(&fi->lock); if (!cache_mask && S_ISREG(inode->i_mode)) { bool inval = false; if (oldsize != attr->size) { truncate_pagecache(inode, attr->size); if (!fc->explicit_inval_data) inval = true; } else if (fc->auto_inval_data) { struct timespec64 new_mtime = { .tv_sec = attr->mtime, .tv_nsec = attr->mtimensec, }; /* * Auto inval mode also checks and invalidates if mtime * has changed. */ if (!timespec64_equal(&old_mtime, &new_mtime)) inval = true; } if (inval) invalidate_inode_pages2(inode->i_mapping); } if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_dontcache(inode, attr->flags); } static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl, u64 nodeid) { sl->nodeid = nodeid; refcount_set(&sl->count, 1); } static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc) { inode->i_mode = attr->mode & S_IFMT; inode->i_size = attr->size; inode_set_mtime(inode, attr->mtime, attr->mtimensec); inode_set_ctime(inode, attr->ctime, attr->ctimensec); if (S_ISREG(inode->i_mode)) { fuse_init_common(inode); fuse_init_file_inode(inode, attr->flags); } else if (S_ISDIR(inode->i_mode)) fuse_init_dir(inode); else if (S_ISLNK(inode->i_mode)) fuse_init_symlink(inode); else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { fuse_init_common(inode); init_special_inode(inode, inode->i_mode, new_decode_dev(attr->rdev)); } else BUG(); /* * Ensure that we don't cache acls for daemons without FUSE_POSIX_ACL * so they see the exact same behavior as before. */ if (!fc->posix_acl) inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE; } static int fuse_inode_eq(struct inode *inode, void *_nodeidp) { u64 nodeid = *(u64 *) _nodeidp; if (get_node_id(inode) == nodeid) return 1; else return 0; } static int fuse_inode_set(struct inode *inode, void *_nodeidp) { u64 nodeid = *(u64 *) _nodeidp; get_fuse_inode(inode)->nodeid = nodeid; return 0; } struct inode *fuse_iget(struct super_block *sb, u64 nodeid, int generation, struct fuse_attr *attr, u64 attr_valid, u64 attr_version) { struct inode *inode; struct fuse_inode *fi; struct fuse_conn *fc = get_fuse_conn_super(sb); /* * Auto mount points get their node id from the submount root, which is * not a unique identifier within this filesystem. * * To avoid conflicts, do not place submount points into the inode hash * table. */ if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) && S_ISDIR(attr->mode)) { struct fuse_inode *fi; inode = new_inode(sb); if (!inode) return NULL; fuse_init_inode(inode, attr, fc); fi = get_fuse_inode(inode); fi->nodeid = nodeid; fi->submount_lookup = fuse_alloc_submount_lookup(); if (!fi->submount_lookup) { iput(inode); return NULL; } /* Sets nlookup = 1 on fi->submount_lookup->nlookup */ fuse_init_submount_lookup(fi->submount_lookup, nodeid); inode->i_flags |= S_AUTOMOUNT; goto done; } retry: inode = iget5_locked(sb, nodeid, fuse_inode_eq, fuse_inode_set, &nodeid); if (!inode) return NULL; if ((inode->i_state & I_NEW)) { inode->i_flags |= S_NOATIME; if (!fc->writeback_cache || !S_ISREG(attr->mode)) inode->i_flags |= S_NOCMTIME; inode->i_generation = generation; fuse_init_inode(inode, attr, fc); unlock_new_inode(inode); } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); if (inode != d_inode(sb->s_root)) { remove_inode_hash(inode); iput(inode); goto retry; } } fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup++; spin_unlock(&fi->lock); done: fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version); return inode; } struct inode *fuse_ilookup(struct fuse_conn *fc, u64 nodeid, struct fuse_mount **fm) { struct fuse_mount *fm_iter; struct inode *inode; WARN_ON(!rwsem_is_locked(&fc->killsb)); list_for_each_entry(fm_iter, &fc->mounts, fc_entry) { if (!fm_iter->sb) continue; inode = ilookup5(fm_iter->sb, nodeid, fuse_inode_eq, &nodeid); if (inode) { if (fm) *fm = fm_iter; return inode; } } return NULL; } int fuse_reverse_inval_inode(struct fuse_conn *fc, u64 nodeid, loff_t offset, loff_t len) { struct fuse_inode *fi; struct inode *inode; pgoff_t pg_start; pgoff_t pg_end; inode = fuse_ilookup(fc, nodeid, NULL); if (!inode) return -ENOENT; fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->attr_version = atomic64_inc_return(&fc->attr_version); spin_unlock(&fi->lock); fuse_invalidate_attr(inode); forget_all_cached_acls(inode); if (offset >= 0) { pg_start = offset >> PAGE_SHIFT; if (len <= 0) pg_end = -1; else pg_end = (offset + len - 1) >> PAGE_SHIFT; invalidate_inode_pages2_range(inode->i_mapping, pg_start, pg_end); } iput(inode); return 0; } bool fuse_lock_inode(struct inode *inode) { bool locked = false; if (!get_fuse_conn(inode)->parallel_dirops) { mutex_lock(&get_fuse_inode(inode)->mutex); locked = true; } return locked; } void fuse_unlock_inode(struct inode *inode, bool locked) { if (locked) mutex_unlock(&get_fuse_inode(inode)->mutex); } static void fuse_umount_begin(struct super_block *sb) { struct fuse_conn *fc = get_fuse_conn_super(sb); if (fc->no_force_umount) return; fuse_abort_conn(fc); // Only retire block-device-based superblocks. if (sb->s_bdev != NULL) retire_super(sb); } static void fuse_send_destroy(struct fuse_mount *fm) { if (fm->fc->conn_init) { FUSE_ARGS(args); args.opcode = FUSE_DESTROY; args.force = true; args.nocreds = true; fuse_simple_request(fm, &args); } } static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr) { stbuf->f_type = FUSE_SUPER_MAGIC; stbuf->f_bsize = attr->bsize; stbuf->f_frsize = attr->frsize; stbuf->f_blocks = attr->blocks; stbuf->f_bfree = attr->bfree; stbuf->f_bavail = attr->bavail; stbuf->f_files = attr->files; stbuf->f_ffree = attr->ffree; stbuf->f_namelen = attr->namelen; /* fsid is left zero */ } static int fuse_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct fuse_mount *fm = get_fuse_mount_super(sb); FUSE_ARGS(args); struct fuse_statfs_out outarg; int err; if (!fuse_allow_current_process(fm->fc)) { buf->f_type = FUSE_SUPER_MAGIC; return 0; } memset(&outarg, 0, sizeof(outarg)); args.in_numargs = 0; args.opcode = FUSE_STATFS; args.nodeid = get_node_id(d_inode(dentry)); args.out_numargs = 1; args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; err = fuse_simple_request(fm, &args); if (!err) convert_fuse_statfs(buf, &outarg.st); return err; } static struct fuse_sync_bucket *fuse_sync_bucket_alloc(void) { struct fuse_sync_bucket *bucket; bucket = kzalloc(sizeof(*bucket), GFP_KERNEL | __GFP_NOFAIL); if (bucket) { init_waitqueue_head(&bucket->waitq); /* Initial active count */ atomic_set(&bucket->count, 1); } return bucket; } static void fuse_sync_fs_writes(struct fuse_conn *fc) { struct fuse_sync_bucket *bucket, *new_bucket; int count; new_bucket = fuse_sync_bucket_alloc(); spin_lock(&fc->lock); bucket = rcu_dereference_protected(fc->curr_bucket, 1); count = atomic_read(&bucket->count); WARN_ON(count < 1); /* No outstanding writes? */ if (count == 1) { spin_unlock(&fc->lock); kfree(new_bucket); return; } /* * Completion of new bucket depends on completion of this bucket, so add * one more count. */ atomic_inc(&new_bucket->count); rcu_assign_pointer(fc->curr_bucket, new_bucket); spin_unlock(&fc->lock); /* * Drop initial active count. At this point if all writes in this and * ancestor buckets complete, the count will go to zero and this task * will be woken up. */ atomic_dec(&bucket->count); wait_event(bucket->waitq, atomic_read(&bucket->count) == 0); /* Drop temp count on descendant bucket */ fuse_sync_bucket_dec(new_bucket); kfree_rcu(bucket, rcu); } static int fuse_sync_fs(struct super_block *sb, int wait) { struct fuse_mount *fm = get_fuse_mount_super(sb); struct fuse_conn *fc = fm->fc; struct fuse_syncfs_in inarg; FUSE_ARGS(args); int err; /* * Userspace cannot handle the wait == 0 case. Avoid a * gratuitous roundtrip. */ if (!wait) return 0; /* The filesystem is being unmounted. Nothing to do. */ if (!sb->s_root) return 0; if (!fc->sync_fs) return 0; fuse_sync_fs_writes(fc); memset(&inarg, 0, sizeof(inarg)); args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.opcode = FUSE_SYNCFS; args.nodeid = get_node_id(sb->s_root->d_inode); args.out_numargs = 0; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fc->sync_fs = 0; err = 0; } return err; } enum { OPT_SOURCE, OPT_SUBTYPE, OPT_FD, OPT_ROOTMODE, OPT_USER_ID, OPT_GROUP_ID, OPT_DEFAULT_PERMISSIONS, OPT_ALLOW_OTHER, OPT_MAX_READ, OPT_BLKSIZE, OPT_ERR }; static const struct fs_parameter_spec fuse_fs_parameters[] = { fsparam_string ("source", OPT_SOURCE), fsparam_u32 ("fd", OPT_FD), fsparam_u32oct ("rootmode", OPT_ROOTMODE), fsparam_uid ("user_id", OPT_USER_ID), fsparam_gid ("group_id", OPT_GROUP_ID), fsparam_flag ("default_permissions", OPT_DEFAULT_PERMISSIONS), fsparam_flag ("allow_other", OPT_ALLOW_OTHER), fsparam_u32 ("max_read", OPT_MAX_READ), fsparam_u32 ("blksize", OPT_BLKSIZE), fsparam_string ("subtype", OPT_SUBTYPE), {} }; static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param) { struct fs_parse_result result; struct fuse_fs_context *ctx = fsc->fs_private; int opt; kuid_t kuid; kgid_t kgid; if (fsc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { /* * Ignore options coming from mount(MS_REMOUNT) for backward * compatibility. */ if (fsc->oldapi) return 0; return invalfc(fsc, "No changes allowed in reconfigure"); } opt = fs_parse(fsc, fuse_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case OPT_SOURCE: if (fsc->source) return invalfc(fsc, "Multiple sources specified"); fsc->source = param->string; param->string = NULL; break; case OPT_SUBTYPE: if (ctx->subtype) return invalfc(fsc, "Multiple subtypes specified"); ctx->subtype = param->string; param->string = NULL; return 0; case OPT_FD: ctx->fd = result.uint_32; ctx->fd_present = true; break; case OPT_ROOTMODE: if (!fuse_valid_type(result.uint_32)) return invalfc(fsc, "Invalid rootmode"); ctx->rootmode = result.uint_32; ctx->rootmode_present = true; break; case OPT_USER_ID: kuid = result.uid; /* * The requested uid must be representable in the * filesystem's idmapping. */ if (!kuid_has_mapping(fsc->user_ns, kuid)) return invalfc(fsc, "Invalid user_id"); ctx->user_id = kuid; ctx->user_id_present = true; break; case OPT_GROUP_ID: kgid = result.gid; /* * The requested gid must be representable in the * filesystem's idmapping. */ if (!kgid_has_mapping(fsc->user_ns, kgid)) return invalfc(fsc, "Invalid group_id"); ctx->group_id = kgid; ctx->group_id_present = true; break; case OPT_DEFAULT_PERMISSIONS: ctx->default_permissions = true; break; case OPT_ALLOW_OTHER: ctx->allow_other = true; break; case OPT_MAX_READ: ctx->max_read = result.uint_32; break; case OPT_BLKSIZE: if (!ctx->is_bdev) return invalfc(fsc, "blksize only supported for fuseblk"); ctx->blksize = result.uint_32; break; default: return -EINVAL; } return 0; } static void fuse_free_fsc(struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; if (ctx) { kfree(ctx->subtype); kfree(ctx); } } static int fuse_show_options(struct seq_file *m, struct dentry *root) { struct super_block *sb = root->d_sb; struct fuse_conn *fc = get_fuse_conn_super(sb); if (fc->legacy_opts_show) { seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id)); seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id)); if (fc->default_permissions) seq_puts(m, ",default_permissions"); if (fc->allow_other) seq_puts(m, ",allow_other"); if (fc->max_read != ~0) seq_printf(m, ",max_read=%u", fc->max_read); if (sb->s_bdev && sb->s_blocksize != FUSE_DEFAULT_BLKSIZE) seq_printf(m, ",blksize=%lu", sb->s_blocksize); } #ifdef CONFIG_FUSE_DAX if (fc->dax_mode == FUSE_DAX_ALWAYS) seq_puts(m, ",dax=always"); else if (fc->dax_mode == FUSE_DAX_NEVER) seq_puts(m, ",dax=never"); else if (fc->dax_mode == FUSE_DAX_INODE_USER) seq_puts(m, ",dax=inode"); #endif return 0; } static void fuse_iqueue_init(struct fuse_iqueue *fiq, const struct fuse_iqueue_ops *ops, void *priv) { memset(fiq, 0, sizeof(struct fuse_iqueue)); spin_lock_init(&fiq->lock); init_waitqueue_head(&fiq->waitq); INIT_LIST_HEAD(&fiq->pending); INIT_LIST_HEAD(&fiq->interrupts); fiq->forget_list_tail = &fiq->forget_list_head; fiq->connected = 1; fiq->ops = ops; fiq->priv = priv; } static void fuse_pqueue_init(struct fuse_pqueue *fpq) { unsigned int i; spin_lock_init(&fpq->lock); for (i = 0; i < FUSE_PQ_HASH_SIZE; i++) INIT_LIST_HEAD(&fpq->processing[i]); INIT_LIST_HEAD(&fpq->io); fpq->connected = 1; } void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm, struct user_namespace *user_ns, const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv) { memset(fc, 0, sizeof(*fc)); spin_lock_init(&fc->lock); spin_lock_init(&fc->bg_lock); init_rwsem(&fc->killsb); refcount_set(&fc->count, 1); atomic_set(&fc->dev_count, 1); init_waitqueue_head(&fc->blocked_waitq); fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv); INIT_LIST_HEAD(&fc->bg_queue); INIT_LIST_HEAD(&fc->entry); INIT_LIST_HEAD(&fc->devices); atomic_set(&fc->num_waiting, 0); fc->max_background = FUSE_DEFAULT_MAX_BACKGROUND; fc->congestion_threshold = FUSE_DEFAULT_CONGESTION_THRESHOLD; atomic64_set(&fc->khctr, 0); fc->polled_files = RB_ROOT; fc->blocked = 0; fc->initialized = 0; fc->connected = 1; atomic64_set(&fc->attr_version, 1); get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); fc->pid_ns = get_pid_ns(task_active_pid_ns(current)); fc->user_ns = get_user_ns(user_ns); fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; fc->max_pages_limit = FUSE_MAX_MAX_PAGES; if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_backing_files_init(fc); INIT_LIST_HEAD(&fc->mounts); list_add(&fm->fc_entry, &fc->mounts); fm->fc = fc; } EXPORT_SYMBOL_GPL(fuse_conn_init); static void delayed_release(struct rcu_head *p) { struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu); put_user_ns(fc->user_ns); fc->release(fc); } void fuse_conn_put(struct fuse_conn *fc) { if (refcount_dec_and_test(&fc->count)) { struct fuse_iqueue *fiq = &fc->iq; struct fuse_sync_bucket *bucket; if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_conn_free(fc); if (fiq->ops->release) fiq->ops->release(fiq); put_pid_ns(fc->pid_ns); bucket = rcu_dereference_protected(fc->curr_bucket, 1); if (bucket) { WARN_ON(atomic_read(&bucket->count) != 1); kfree(bucket); } if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) fuse_backing_files_free(fc); call_rcu(&fc->rcu, delayed_release); } } EXPORT_SYMBOL_GPL(fuse_conn_put); struct fuse_conn *fuse_conn_get(struct fuse_conn *fc) { refcount_inc(&fc->count); return fc; } EXPORT_SYMBOL_GPL(fuse_conn_get); static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode) { struct fuse_attr attr; memset(&attr, 0, sizeof(attr)); attr.mode = mode; attr.ino = FUSE_ROOT_ID; attr.nlink = 1; return fuse_iget(sb, FUSE_ROOT_ID, 0, &attr, 0, 0); } struct fuse_inode_handle { u64 nodeid; u32 generation; }; static struct dentry *fuse_get_dentry(struct super_block *sb, struct fuse_inode_handle *handle) { struct fuse_conn *fc = get_fuse_conn_super(sb); struct inode *inode; struct dentry *entry; int err = -ESTALE; if (handle->nodeid == 0) goto out_err; inode = ilookup5(sb, handle->nodeid, fuse_inode_eq, &handle->nodeid); if (!inode) { struct fuse_entry_out outarg; const struct qstr name = QSTR_INIT(".", 1); if (!fc->export_support) goto out_err; err = fuse_lookup_name(sb, handle->nodeid, &name, &outarg, &inode); if (err && err != -ENOENT) goto out_err; if (err || !inode) { err = -ESTALE; goto out_err; } err = -EIO; if (get_node_id(inode) != handle->nodeid) goto out_iput; } err = -ESTALE; if (inode->i_generation != handle->generation) goto out_iput; entry = d_obtain_alias(inode); if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID) fuse_invalidate_entry_cache(entry); return entry; out_iput: iput(inode); out_err: return ERR_PTR(err); } static int fuse_encode_fh(struct inode *inode, u32 *fh, int *max_len, struct inode *parent) { int len = parent ? 6 : 3; u64 nodeid; u32 generation; if (*max_len < len) { *max_len = len; return FILEID_INVALID; } nodeid = get_fuse_inode(inode)->nodeid; generation = inode->i_generation; fh[0] = (u32)(nodeid >> 32); fh[1] = (u32)(nodeid & 0xffffffff); fh[2] = generation; if (parent) { nodeid = get_fuse_inode(parent)->nodeid; generation = parent->i_generation; fh[3] = (u32)(nodeid >> 32); fh[4] = (u32)(nodeid & 0xffffffff); fh[5] = generation; } *max_len = len; return parent ? FILEID_INO64_GEN_PARENT : FILEID_INO64_GEN; } static struct dentry *fuse_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct fuse_inode_handle handle; if ((fh_type != FILEID_INO64_GEN && fh_type != FILEID_INO64_GEN_PARENT) || fh_len < 3) return NULL; handle.nodeid = (u64) fid->raw[0] << 32; handle.nodeid |= (u64) fid->raw[1]; handle.generation = fid->raw[2]; return fuse_get_dentry(sb, &handle); } static struct dentry *fuse_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct fuse_inode_handle parent; if (fh_type != FILEID_INO64_GEN_PARENT || fh_len < 6) return NULL; parent.nodeid = (u64) fid->raw[3] << 32; parent.nodeid |= (u64) fid->raw[4]; parent.generation = fid->raw[5]; return fuse_get_dentry(sb, &parent); } static struct dentry *fuse_get_parent(struct dentry *child) { struct inode *child_inode = d_inode(child); struct fuse_conn *fc = get_fuse_conn(child_inode); struct inode *inode; struct dentry *parent; struct fuse_entry_out outarg; int err; if (!fc->export_support) return ERR_PTR(-ESTALE); err = fuse_lookup_name(child_inode->i_sb, get_node_id(child_inode), &dotdot_name, &outarg, &inode); if (err) { if (err == -ENOENT) return ERR_PTR(-ESTALE); return ERR_PTR(err); } parent = d_obtain_alias(inode); if (!IS_ERR(parent) && get_node_id(inode) != FUSE_ROOT_ID) fuse_invalidate_entry_cache(parent); return parent; } /* only for fid encoding; no support for file handle */ static const struct export_operations fuse_export_fid_operations = { .encode_fh = fuse_encode_fh, }; static const struct export_operations fuse_export_operations = { .fh_to_dentry = fuse_fh_to_dentry, .fh_to_parent = fuse_fh_to_parent, .encode_fh = fuse_encode_fh, .get_parent = fuse_get_parent, }; static const struct super_operations fuse_super_operations = { .alloc_inode = fuse_alloc_inode, .free_inode = fuse_free_inode, .evict_inode = fuse_evict_inode, .write_inode = fuse_write_inode, .drop_inode = generic_delete_inode, .umount_begin = fuse_umount_begin, .statfs = fuse_statfs, .sync_fs = fuse_sync_fs, .show_options = fuse_show_options, }; static void sanitize_global_limit(unsigned *limit) { /* * The default maximum number of async requests is calculated to consume * 1/2^13 of the total memory, assuming 392 bytes per request. */ if (*limit == 0) *limit = ((totalram_pages() << PAGE_SHIFT) >> 13) / 392; if (*limit >= 1 << 16) *limit = (1 << 16) - 1; } static int set_global_limit(const char *val, const struct kernel_param *kp) { int rv; rv = param_set_uint(val, kp); if (rv) return rv; sanitize_global_limit((unsigned *)kp->arg); return 0; } static void process_init_limits(struct fuse_conn *fc, struct fuse_init_out *arg) { int cap_sys_admin = capable(CAP_SYS_ADMIN); if (arg->minor < 13) return; sanitize_global_limit(&max_user_bgreq); sanitize_global_limit(&max_user_congthresh); spin_lock(&fc->bg_lock); if (arg->max_background) { fc->max_background = arg->max_background; if (!cap_sys_admin && fc->max_background > max_user_bgreq) fc->max_background = max_user_bgreq; } if (arg->congestion_threshold) { fc->congestion_threshold = arg->congestion_threshold; if (!cap_sys_admin && fc->congestion_threshold > max_user_congthresh) fc->congestion_threshold = max_user_congthresh; } spin_unlock(&fc->bg_lock); } struct fuse_init_args { struct fuse_args args; struct fuse_init_in in; struct fuse_init_out out; }; static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, int error) { struct fuse_conn *fc = fm->fc; struct fuse_init_args *ia = container_of(args, typeof(*ia), args); struct fuse_init_out *arg = &ia->out; bool ok = true; if (error || arg->major != FUSE_KERNEL_VERSION) ok = false; else { unsigned long ra_pages; process_init_limits(fc, arg); if (arg->minor >= 6) { u64 flags = arg->flags; if (flags & FUSE_INIT_EXT) flags |= (u64) arg->flags2 << 32; ra_pages = arg->max_readahead / PAGE_SIZE; if (flags & FUSE_ASYNC_READ) fc->async_read = 1; if (!(flags & FUSE_POSIX_LOCKS)) fc->no_lock = 1; if (arg->minor >= 17) { if (!(flags & FUSE_FLOCK_LOCKS)) fc->no_flock = 1; } else { if (!(flags & FUSE_POSIX_LOCKS)) fc->no_flock = 1; } if (flags & FUSE_ATOMIC_O_TRUNC) fc->atomic_o_trunc = 1; if (arg->minor >= 9) { /* LOOKUP has dependency on proto version */ if (flags & FUSE_EXPORT_SUPPORT) fc->export_support = 1; } if (flags & FUSE_BIG_WRITES) fc->big_writes = 1; if (flags & FUSE_DONT_MASK) fc->dont_mask = 1; if (flags & FUSE_AUTO_INVAL_DATA) fc->auto_inval_data = 1; else if (flags & FUSE_EXPLICIT_INVAL_DATA) fc->explicit_inval_data = 1; if (flags & FUSE_DO_READDIRPLUS) { fc->do_readdirplus = 1; if (flags & FUSE_READDIRPLUS_AUTO) fc->readdirplus_auto = 1; } if (flags & FUSE_ASYNC_DIO) fc->async_dio = 1; if (flags & FUSE_WRITEBACK_CACHE) fc->writeback_cache = 1; if (flags & FUSE_PARALLEL_DIROPS) fc->parallel_dirops = 1; if (flags & FUSE_HANDLE_KILLPRIV) fc->handle_killpriv = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fm->sb->s_time_gran = arg->time_gran; if ((flags & FUSE_POSIX_ACL)) { fc->default_permissions = 1; fc->posix_acl = 1; } if (flags & FUSE_CACHE_SYMLINKS) fc->cache_symlinks = 1; if (flags & FUSE_ABORT_ERROR) fc->abort_err = 1; if (flags & FUSE_MAX_PAGES) { fc->max_pages = min_t(unsigned int, fc->max_pages_limit, max_t(unsigned int, arg->max_pages, 1)); } if (IS_ENABLED(CONFIG_FUSE_DAX)) { if (flags & FUSE_MAP_ALIGNMENT && !fuse_dax_check_alignment(fc, arg->map_alignment)) { ok = false; } if (flags & FUSE_HAS_INODE_DAX) fc->inode_dax = 1; } if (flags & FUSE_HANDLE_KILLPRIV_V2) { fc->handle_killpriv_v2 = 1; fm->sb->s_flags |= SB_NOSEC; } if (flags & FUSE_SETXATTR_EXT) fc->setxattr_ext = 1; if (flags & FUSE_SECURITY_CTX) fc->init_security = 1; if (flags & FUSE_CREATE_SUPP_GROUP) fc->create_supp_group = 1; if (flags & FUSE_DIRECT_IO_ALLOW_MMAP) fc->direct_io_allow_mmap = 1; /* * max_stack_depth is the max stack depth of FUSE fs, * so it has to be at least 1 to support passthrough * to backing files. * * with max_stack_depth > 1, the backing files can be * on a stacked fs (e.g. overlayfs) themselves and with * max_stack_depth == 1, FUSE fs can be stacked as the * underlying fs of a stacked fs (e.g. overlayfs). * * Also don't allow the combination of FUSE_PASSTHROUGH * and FUSE_WRITEBACK_CACHE, current design doesn't handle * them together. */ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) && (flags & FUSE_PASSTHROUGH) && arg->max_stack_depth > 0 && arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH && !(flags & FUSE_WRITEBACK_CACHE)) { fc->passthrough = 1; fc->max_stack_depth = arg->max_stack_depth; fm->sb->s_stack_depth = arg->max_stack_depth; } if (flags & FUSE_NO_EXPORT_SUPPORT) fm->sb->s_export_op = &fuse_export_fid_operations; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; fc->no_flock = 1; } fm->sb->s_bdi->ra_pages = min(fm->sb->s_bdi->ra_pages, ra_pages); fc->minor = arg->minor; fc->max_write = arg->minor < 5 ? 4096 : arg->max_write; fc->max_write = max_t(unsigned, 4096, fc->max_write); fc->conn_init = 1; } kfree(ia); if (!ok) { fc->conn_init = 0; fc->conn_error = 1; } fuse_set_initialized(fc); wake_up_all(&fc->blocked_waitq); } void fuse_send_init(struct fuse_mount *fm) { struct fuse_init_args *ia; u64 flags; ia = kzalloc(sizeof(*ia), GFP_KERNEL | __GFP_NOFAIL); ia->in.major = FUSE_KERNEL_VERSION; ia->in.minor = FUSE_KERNEL_MINOR_VERSION; ia->in.max_readahead = fm->sb->s_bdi->ra_pages * PAGE_SIZE; flags = FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT | FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP | FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; if (fuse_is_inode_dax_mode(fm->fc->dax_mode)) flags |= FUSE_HAS_INODE_DAX; #endif if (fm->fc->auto_submounts) flags |= FUSE_SUBMOUNTS; if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) flags |= FUSE_PASSTHROUGH; ia->in.flags = flags; ia->in.flags2 = flags >> 32; ia->args.opcode = FUSE_INIT; ia->args.in_numargs = 1; ia->args.in_args[0].size = sizeof(ia->in); ia->args.in_args[0].value = &ia->in; ia->args.out_numargs = 1; /* Variable length argument used for backward compatibility with interface version < 7.5. Rest of init_out is zeroed by do_get_request(), so a short reply is not a problem */ ia->args.out_argvar = true; ia->args.out_args[0].size = sizeof(ia->out); ia->args.out_args[0].value = &ia->out; ia->args.force = true; ia->args.nocreds = true; ia->args.end = process_init_reply; if (fuse_simple_background(fm, &ia->args, GFP_KERNEL) != 0) process_init_reply(fm, &ia->args, -ENOTCONN); } EXPORT_SYMBOL_GPL(fuse_send_init); void fuse_free_conn(struct fuse_conn *fc) { WARN_ON(!list_empty(&fc->devices)); kfree(fc); } EXPORT_SYMBOL_GPL(fuse_free_conn); static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) { int err; char *suffix = ""; if (sb->s_bdev) { suffix = "-fuseblk"; /* * sb->s_bdi points to blkdev's bdi however we want to redirect * it to our private bdi... */ bdi_put(sb->s_bdi); sb->s_bdi = &noop_backing_dev_info; } err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev), MINOR(fc->dev), suffix); if (err) return err; /* fuse does it's own writeback accounting */ sb->s_bdi->capabilities &= ~BDI_CAP_WRITEBACK_ACCT; sb->s_bdi->capabilities |= BDI_CAP_STRICTLIMIT; /* * For a single fuse filesystem use max 1% of dirty + * writeback threshold. * * This gives about 1M of write buffer for memory maps on a * machine with 1G and 10% dirty_ratio, which should be more * than enough. * * Privileged users can raise it by writing to * * /sys/class/bdi/<bdi>/max_ratio */ bdi_set_max_ratio(sb->s_bdi, 1); return 0; } struct fuse_dev *fuse_dev_alloc(void) { struct fuse_dev *fud; struct list_head *pq; fud = kzalloc(sizeof(struct fuse_dev), GFP_KERNEL); if (!fud) return NULL; pq = kcalloc(FUSE_PQ_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!pq) { kfree(fud); return NULL; } fud->pq.processing = pq; fuse_pqueue_init(&fud->pq); return fud; } EXPORT_SYMBOL_GPL(fuse_dev_alloc); void fuse_dev_install(struct fuse_dev *fud, struct fuse_conn *fc) { fud->fc = fuse_conn_get(fc); spin_lock(&fc->lock); list_add_tail(&fud->entry, &fc->devices); spin_unlock(&fc->lock); } EXPORT_SYMBOL_GPL(fuse_dev_install); struct fuse_dev *fuse_dev_alloc_install(struct fuse_conn *fc) { struct fuse_dev *fud; fud = fuse_dev_alloc(); if (!fud) return NULL; fuse_dev_install(fud, fc); return fud; } EXPORT_SYMBOL_GPL(fuse_dev_alloc_install); void fuse_dev_free(struct fuse_dev *fud) { struct fuse_conn *fc = fud->fc; if (fc) { spin_lock(&fc->lock); list_del(&fud->entry); spin_unlock(&fc->lock); fuse_conn_put(fc); } kfree(fud->pq.processing); kfree(fud); } EXPORT_SYMBOL_GPL(fuse_dev_free); static void fuse_fill_attr_from_inode(struct fuse_attr *attr, const struct fuse_inode *fi) { struct timespec64 atime = inode_get_atime(&fi->inode); struct timespec64 mtime = inode_get_mtime(&fi->inode); struct timespec64 ctime = inode_get_ctime(&fi->inode); *attr = (struct fuse_attr){ .ino = fi->inode.i_ino, .size = fi->inode.i_size, .blocks = fi->inode.i_blocks, .atime = atime.tv_sec, .mtime = mtime.tv_sec, .ctime = ctime.tv_sec, .atimensec = atime.tv_nsec, .mtimensec = mtime.tv_nsec, .ctimensec = ctime.tv_nsec, .mode = fi->inode.i_mode, .nlink = fi->inode.i_nlink, .uid = __kuid_val(fi->inode.i_uid), .gid = __kgid_val(fi->inode.i_gid), .rdev = fi->inode.i_rdev, .blksize = 1u << fi->inode.i_blkbits, }; } static void fuse_sb_defaults(struct super_block *sb) { sb->s_magic = FUSE_SUPER_MAGIC; sb->s_op = &fuse_super_operations; sb->s_xattr = fuse_xattr_handlers; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_time_gran = 1; sb->s_export_op = &fuse_export_operations; sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE; if (sb->s_user_ns != &init_user_ns) sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER; sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION); } static int fuse_fill_super_submount(struct super_block *sb, struct fuse_inode *parent_fi) { struct fuse_mount *fm = get_fuse_mount_super(sb); struct super_block *parent_sb = parent_fi->inode.i_sb; struct fuse_attr root_attr; struct inode *root; struct fuse_submount_lookup *sl; struct fuse_inode *fi; fuse_sb_defaults(sb); fm->sb = sb; WARN_ON(sb->s_bdi != &noop_backing_dev_info); sb->s_bdi = bdi_get(parent_sb->s_bdi); sb->s_xattr = parent_sb->s_xattr; sb->s_export_op = parent_sb->s_export_op; sb->s_time_gran = parent_sb->s_time_gran; sb->s_blocksize = parent_sb->s_blocksize; sb->s_blocksize_bits = parent_sb->s_blocksize_bits; sb->s_subtype = kstrdup(parent_sb->s_subtype, GFP_KERNEL); if (parent_sb->s_subtype && !sb->s_subtype) return -ENOMEM; fuse_fill_attr_from_inode(&root_attr, parent_fi); root = fuse_iget(sb, parent_fi->nodeid, 0, &root_attr, 0, 0); /* * This inode is just a duplicate, so it is not looked up and * its nlookup should not be incremented. fuse_iget() does * that, though, so undo it here. */ fi = get_fuse_inode(root); fi->nlookup--; sb->s_d_op = &fuse_dentry_operations; sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; /* * Grab the parent's submount_lookup pointer and take a * reference on the shared nlookup from the parent. This is to * prevent the last forget for this nodeid from getting * triggered until all users have finished with it. */ sl = parent_fi->submount_lookup; WARN_ON(!sl); if (sl) { refcount_inc(&sl->count); fi->submount_lookup = sl; } return 0; } /* Filesystem context private data holds the FUSE inode of the mount point */ static int fuse_get_tree_submount(struct fs_context *fsc) { struct fuse_mount *fm; struct fuse_inode *mp_fi = fsc->fs_private; struct fuse_conn *fc = get_fuse_conn(&mp_fi->inode); struct super_block *sb; int err; fm = kzalloc(sizeof(struct fuse_mount), GFP_KERNEL); if (!fm) return -ENOMEM; fm->fc = fuse_conn_get(fc); fsc->s_fs_info = fm; sb = sget_fc(fsc, NULL, set_anon_super_fc); if (fsc->s_fs_info) fuse_mount_destroy(fm); if (IS_ERR(sb)) return PTR_ERR(sb); /* Initialize superblock, making @mp_fi its root */ err = fuse_fill_super_submount(sb, mp_fi); if (err) { deactivate_locked_super(sb); return err; } down_write(&fc->killsb); list_add_tail(&fm->fc_entry, &fc->mounts); up_write(&fc->killsb); sb->s_flags |= SB_ACTIVE; fsc->root = dget(sb->s_root); return 0; } static const struct fs_context_operations fuse_context_submount_ops = { .get_tree = fuse_get_tree_submount, }; int fuse_init_fs_context_submount(struct fs_context *fsc) { fsc->ops = &fuse_context_submount_ops; return 0; } EXPORT_SYMBOL_GPL(fuse_init_fs_context_submount); int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx) { struct fuse_dev *fud = NULL; struct fuse_mount *fm = get_fuse_mount_super(sb); struct fuse_conn *fc = fm->fc; struct inode *root; struct dentry *root_dentry; int err; err = -EINVAL; if (sb->s_flags & SB_MANDLOCK) goto err; rcu_assign_pointer(fc->curr_bucket, fuse_sync_bucket_alloc()); fuse_sb_defaults(sb); if (ctx->is_bdev) { #ifdef CONFIG_BLOCK err = -EINVAL; if (!sb_set_blocksize(sb, ctx->blksize)) goto err; #endif } else { sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; } sb->s_subtype = ctx->subtype; ctx->subtype = NULL; if (IS_ENABLED(CONFIG_FUSE_DAX)) { err = fuse_dax_conn_alloc(fc, ctx->dax_mode, ctx->dax_dev); if (err) goto err; } if (ctx->fudptr) { err = -ENOMEM; fud = fuse_dev_alloc_install(fc); if (!fud) goto err_free_dax; } fc->dev = sb->s_dev; fm->sb = sb; err = fuse_bdi_init(fc, sb); if (err) goto err_dev_free; /* Handle umasking inside the fuse code */ if (sb->s_flags & SB_POSIXACL) fc->dont_mask = 1; sb->s_flags |= SB_POSIXACL; fc->default_permissions = ctx->default_permissions; fc->allow_other = ctx->allow_other; fc->user_id = ctx->user_id; fc->group_id = ctx->group_id; fc->legacy_opts_show = ctx->legacy_opts_show; fc->max_read = max_t(unsigned int, 4096, ctx->max_read); fc->destroy = ctx->destroy; fc->no_control = ctx->no_control; fc->no_force_umount = ctx->no_force_umount; err = -ENOMEM; root = fuse_get_root_inode(sb, ctx->rootmode); sb->s_d_op = &fuse_root_dentry_operations; root_dentry = d_make_root(root); if (!root_dentry) goto err_dev_free; /* Root dentry doesn't have .d_revalidate */ sb->s_d_op = &fuse_dentry_operations; mutex_lock(&fuse_mutex); err = -EINVAL; if (ctx->fudptr && *ctx->fudptr) goto err_unlock; err = fuse_ctl_add_conn(fc); if (err) goto err_unlock; list_add_tail(&fc->entry, &fuse_conn_list); sb->s_root = root_dentry; if (ctx->fudptr) *ctx->fudptr = fud; mutex_unlock(&fuse_mutex); return 0; err_unlock: mutex_unlock(&fuse_mutex); dput(root_dentry); err_dev_free: if (fud) fuse_dev_free(fud); err_free_dax: if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_conn_free(fc); err: return err; } EXPORT_SYMBOL_GPL(fuse_fill_super_common); static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; int err; if (!ctx->file || !ctx->rootmode_present || !ctx->user_id_present || !ctx->group_id_present) return -EINVAL; /* * Require mount to happen from the same user namespace which * opened /dev/fuse to prevent potential attacks. */ if ((ctx->file->f_op != &fuse_dev_operations) || (ctx->file->f_cred->user_ns != sb->s_user_ns)) return -EINVAL; ctx->fudptr = &ctx->file->private_data; err = fuse_fill_super_common(sb, ctx); if (err) return err; /* file->private_data shall be visible on all CPUs after this */ smp_mb(); fuse_send_init(get_fuse_mount_super(sb)); return 0; } /* * This is the path where user supplied an already initialized fuse dev. In * this case never create a new super if the old one is gone. */ static int fuse_set_no_super(struct super_block *sb, struct fs_context *fsc) { return -ENOTCONN; } static int fuse_test_super(struct super_block *sb, struct fs_context *fsc) { return fsc->sget_key == get_fuse_conn_super(sb); } static int fuse_get_tree(struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; struct fuse_dev *fud; struct fuse_conn *fc; struct fuse_mount *fm; struct super_block *sb; int err; fc = kmalloc(sizeof(*fc), GFP_KERNEL); if (!fc) return -ENOMEM; fm = kzalloc(sizeof(*fm), GFP_KERNEL); if (!fm) { kfree(fc); return -ENOMEM; } fuse_conn_init(fc, fm, fsc->user_ns, &fuse_dev_fiq_ops, NULL); fc->release = fuse_free_conn; fsc->s_fs_info = fm; if (ctx->fd_present) ctx->file = fget(ctx->fd); if (IS_ENABLED(CONFIG_BLOCK) && ctx->is_bdev) { err = get_tree_bdev(fsc, fuse_fill_super); goto out; } /* * While block dev mount can be initialized with a dummy device fd * (found by device name), normal fuse mounts can't */ err = -EINVAL; if (!ctx->file) goto out; /* * Allow creating a fuse mount with an already initialized fuse * connection */ fud = READ_ONCE(ctx->file->private_data); if (ctx->file->f_op == &fuse_dev_operations && fud) { fsc->sget_key = fud->fc; sb = sget_fc(fsc, fuse_test_super, fuse_set_no_super); err = PTR_ERR_OR_ZERO(sb); if (!IS_ERR(sb)) fsc->root = dget(sb->s_root); } else { err = get_tree_nodev(fsc, fuse_fill_super); } out: if (fsc->s_fs_info) fuse_mount_destroy(fm); if (ctx->file) fput(ctx->file); return err; } static const struct fs_context_operations fuse_context_ops = { .free = fuse_free_fsc, .parse_param = fuse_parse_param, .reconfigure = fuse_reconfigure, .get_tree = fuse_get_tree, }; /* * Set up the filesystem mount context. */ static int fuse_init_fs_context(struct fs_context *fsc) { struct fuse_fs_context *ctx; ctx = kzalloc(sizeof(struct fuse_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->max_read = ~0; ctx->blksize = FUSE_DEFAULT_BLKSIZE; ctx->legacy_opts_show = true; #ifdef CONFIG_BLOCK if (fsc->fs_type == &fuseblk_fs_type) { ctx->is_bdev = true; ctx->destroy = true; } #endif fsc->fs_private = ctx; fsc->ops = &fuse_context_ops; return 0; } bool fuse_mount_remove(struct fuse_mount *fm) { struct fuse_conn *fc = fm->fc; bool last = false; down_write(&fc->killsb); list_del_init(&fm->fc_entry); if (list_empty(&fc->mounts)) last = true; up_write(&fc->killsb); return last; } EXPORT_SYMBOL_GPL(fuse_mount_remove); void fuse_conn_destroy(struct fuse_mount *fm) { struct fuse_conn *fc = fm->fc; if (fc->destroy) fuse_send_destroy(fm); fuse_abort_conn(fc); fuse_wait_aborted(fc); if (!list_empty(&fc->entry)) { mutex_lock(&fuse_mutex); list_del(&fc->entry); fuse_ctl_remove_conn(fc); mutex_unlock(&fuse_mutex); } } EXPORT_SYMBOL_GPL(fuse_conn_destroy); static void fuse_sb_destroy(struct super_block *sb) { struct fuse_mount *fm = get_fuse_mount_super(sb); bool last; if (sb->s_root) { last = fuse_mount_remove(fm); if (last) fuse_conn_destroy(fm); } } void fuse_mount_destroy(struct fuse_mount *fm) { fuse_conn_put(fm->fc); kfree_rcu(fm, rcu); } EXPORT_SYMBOL(fuse_mount_destroy); static void fuse_kill_sb_anon(struct super_block *sb) { fuse_sb_destroy(sb); kill_anon_super(sb); fuse_mount_destroy(get_fuse_mount_super(sb)); } static struct file_system_type fuse_fs_type = { .owner = THIS_MODULE, .name = "fuse", .fs_flags = FS_HAS_SUBTYPE | FS_USERNS_MOUNT, .init_fs_context = fuse_init_fs_context, .parameters = fuse_fs_parameters, .kill_sb = fuse_kill_sb_anon, }; MODULE_ALIAS_FS("fuse"); #ifdef CONFIG_BLOCK static void fuse_kill_sb_blk(struct super_block *sb) { fuse_sb_destroy(sb); kill_block_super(sb); fuse_mount_destroy(get_fuse_mount_super(sb)); } static struct file_system_type fuseblk_fs_type = { .owner = THIS_MODULE, .name = "fuseblk", .init_fs_context = fuse_init_fs_context, .parameters = fuse_fs_parameters, .kill_sb = fuse_kill_sb_blk, .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE, }; MODULE_ALIAS_FS("fuseblk"); static inline int register_fuseblk(void) { return register_filesystem(&fuseblk_fs_type); } static inline void unregister_fuseblk(void) { unregister_filesystem(&fuseblk_fs_type); } #else static inline int register_fuseblk(void) { return 0; } static inline void unregister_fuseblk(void) { } #endif static void fuse_inode_init_once(void *foo) { struct inode *inode = foo; inode_init_once(inode); } static int __init fuse_fs_init(void) { int err; fuse_inode_cachep = kmem_cache_create("fuse_inode", sizeof(struct fuse_inode), 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT, fuse_inode_init_once); err = -ENOMEM; if (!fuse_inode_cachep) goto out; err = register_fuseblk(); if (err) goto out2; err = register_filesystem(&fuse_fs_type); if (err) goto out3; return 0; out3: unregister_fuseblk(); out2: kmem_cache_destroy(fuse_inode_cachep); out: return err; } static void fuse_fs_cleanup(void) { unregister_filesystem(&fuse_fs_type); unregister_fuseblk(); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(fuse_inode_cachep); } static struct kobject *fuse_kobj; static int fuse_sysfs_init(void) { int err; fuse_kobj = kobject_create_and_add("fuse", fs_kobj); if (!fuse_kobj) { err = -ENOMEM; goto out_err; } err = sysfs_create_mount_point(fuse_kobj, "connections"); if (err) goto out_fuse_unregister; return 0; out_fuse_unregister: kobject_put(fuse_kobj); out_err: return err; } static void fuse_sysfs_cleanup(void) { sysfs_remove_mount_point(fuse_kobj, "connections"); kobject_put(fuse_kobj); } static int __init fuse_init(void) { int res; pr_info("init (API version %i.%i)\n", FUSE_KERNEL_VERSION, FUSE_KERNEL_MINOR_VERSION); INIT_LIST_HEAD(&fuse_conn_list); res = fuse_fs_init(); if (res) goto err; res = fuse_dev_init(); if (res) goto err_fs_cleanup; res = fuse_sysfs_init(); if (res) goto err_dev_cleanup; res = fuse_ctl_init(); if (res) goto err_sysfs_cleanup; sanitize_global_limit(&max_user_bgreq); sanitize_global_limit(&max_user_congthresh); return 0; err_sysfs_cleanup: fuse_sysfs_cleanup(); err_dev_cleanup: fuse_dev_cleanup(); err_fs_cleanup: fuse_fs_cleanup(); err: return res; } static void __exit fuse_exit(void) { pr_debug("exit\n"); fuse_ctl_cleanup(); fuse_sysfs_cleanup(); fuse_fs_cleanup(); fuse_dev_cleanup(); } module_init(fuse_init); module_exit(fuse_exit); |
| 10 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 | /* * Copyright IBM Corporation, 2012 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. * */ #ifndef _LINUX_HUGETLB_CGROUP_H #define _LINUX_HUGETLB_CGROUP_H #include <linux/mmdebug.h> struct hugetlb_cgroup; struct resv_map; struct file_region; #ifdef CONFIG_CGROUP_HUGETLB enum hugetlb_memory_event { HUGETLB_MAX, HUGETLB_NR_MEMORY_EVENTS, }; struct hugetlb_cgroup_per_node { /* hugetlb usage in pages over all hstates. */ unsigned long usage[HUGE_MAX_HSTATE]; }; struct hugetlb_cgroup { struct cgroup_subsys_state css; /* * the counter to account for hugepages from hugetlb. */ struct page_counter hugepage[HUGE_MAX_HSTATE]; /* * the counter to account for hugepage reservations from hugetlb. */ struct page_counter rsvd_hugepage[HUGE_MAX_HSTATE]; atomic_long_t events[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; atomic_long_t events_local[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; /* Handle for "hugetlb.events" */ struct cgroup_file events_file[HUGE_MAX_HSTATE]; /* Handle for "hugetlb.events.local" */ struct cgroup_file events_local_file[HUGE_MAX_HSTATE]; struct hugetlb_cgroup_per_node *nodeinfo[]; }; static inline struct hugetlb_cgroup * __hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); if (rsvd) return folio->_hugetlb_cgroup_rsvd; else return folio->_hugetlb_cgroup; } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return __hugetlb_cgroup_from_folio(folio, false); } static inline struct hugetlb_cgroup * hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return __hugetlb_cgroup_from_folio(folio, true); } static inline void __set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); if (rsvd) folio->_hugetlb_cgroup_rsvd = h_cg; else folio->_hugetlb_cgroup = h_cg; } static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { __set_hugetlb_cgroup(folio, h_cg, false); } static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { __set_hugetlb_cgroup(folio, h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) { return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { css_put(&h_cg->css); } static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { if (resv_map->css) css_get(resv_map->css); } static inline void resv_map_put_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { if (resv_map->css) css_put(resv_map->css); } extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio); extern void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio); extern void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio); extern void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); extern void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); extern void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end); extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del); extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio); #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del) { } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct hugetlb_cgroup * hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return NULL; } static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { } static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { } static inline bool hugetlb_cgroup_disabled(void) { return true; } static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { } static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { } static inline void resv_map_put_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { } static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return 0; } static inline int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return 0; } static inline void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { } static inline void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { } static inline void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { } static inline void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end) { } static inline void hugetlb_cgroup_file_init(void) { } static inline void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio) { } #endif /* CONFIG_MEM_RES_CTLR_HUGETLB */ #endif |
| 2 2 2 2 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 | /* * Copyright (c) 2006-2009 Red Hat Inc. * Copyright (c) 2006-2008 Intel Corporation * Copyright (c) 2007 Dave Airlie <airlied@linux.ie> * * DRM framebuffer helper 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: * Dave Airlie <airlied@linux.ie> * Jesse Barnes <jesse.barnes@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/console.h> #include <linux/pci.h> #include <linux/sysrq.h> #include <linux/vga_switcheroo.h> #include <drm/drm_atomic.h> #include <drm/drm_drv.h> #include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_print.h> #include <drm/drm_vblank.h> #include "drm_internal.h" static bool drm_fbdev_emulation = true; module_param_named(fbdev_emulation, drm_fbdev_emulation, bool, 0600); MODULE_PARM_DESC(fbdev_emulation, "Enable legacy fbdev emulation [default=true]"); static int drm_fbdev_overalloc = CONFIG_DRM_FBDEV_OVERALLOC; module_param(drm_fbdev_overalloc, int, 0444); MODULE_PARM_DESC(drm_fbdev_overalloc, "Overallocation of the fbdev buffer (%) [default=" __MODULE_STRING(CONFIG_DRM_FBDEV_OVERALLOC) "]"); /* * In order to keep user-space compatibility, we want in certain use-cases * to keep leaking the fbdev physical address to the user-space program * handling the fbdev buffer. * * This is a bad habit, essentially kept to support closed-source OpenGL * drivers that should really be moved into open-source upstream projects * instead of using legacy physical addresses in user space to communicate * with other out-of-tree kernel modules. * * This module_param *should* be removed as soon as possible and be * considered as a broken and legacy behaviour from a modern fbdev device. */ static bool drm_leak_fbdev_smem; #if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) module_param_unsafe(drm_leak_fbdev_smem, bool, 0600); MODULE_PARM_DESC(drm_leak_fbdev_smem, "Allow unsafe leaking fbdev physical smem address [default=false]"); #endif static LIST_HEAD(kernel_fb_helper_list); static DEFINE_MUTEX(kernel_fb_helper_lock); /** * DOC: fbdev helpers * * The fb helper functions are useful to provide an fbdev on top of a drm kernel * mode setting driver. They can be used mostly independently from the crtc * helper functions used by many drivers to implement the kernel mode setting * interfaces. Drivers that use one of the shared memory managers, TTM, SHMEM, * DMA, should instead use the corresponding fbdev emulation. * * Existing fbdev implementations should restore the fbdev console by using * drm_fb_helper_lastclose() as their &drm_driver.lastclose callback. * They should also notify the fb helper code from updates to the output * configuration by using drm_fb_helper_output_poll_changed() as their * &drm_mode_config_funcs.output_poll_changed callback. New implementations * of fbdev should be build on top of struct &drm_client_funcs, which handles * this automatically. Setting the old callbacks should be avoided. * * For suspend/resume consider using drm_mode_config_helper_suspend() and * drm_mode_config_helper_resume() which takes care of fbdev as well. * * All other functions exported by the fb helper library can be used to * implement the fbdev driver interface by the driver. * * It is possible, though perhaps somewhat tricky, to implement race-free * hotplug detection using the fbdev helpers. The drm_fb_helper_prepare() * helper must be called first to initialize the minimum required to make * hotplug detection work. Drivers also need to make sure to properly set up * the &drm_mode_config.funcs member. After calling drm_kms_helper_poll_init() * it is safe to enable interrupts and start processing hotplug events. At the * same time, drivers should initialize all modeset objects such as CRTCs, * encoders and connectors. To finish up the fbdev helper initialization, the * drm_fb_helper_init() function is called. To probe for all attached displays * and set up an initial configuration using the detected hardware, drivers * should call drm_fb_helper_initial_config(). * * If &drm_framebuffer_funcs.dirty is set, the * drm_fb_helper_{cfb,sys}_{write,fillrect,copyarea,imageblit} functions will * accumulate changes and schedule &drm_fb_helper.dirty_work to run right * away. This worker then calls the dirty() function ensuring that it will * always run in process context since the fb_*() function could be running in * atomic context. If drm_fb_helper_deferred_io() is used as the deferred_io * callback it will also schedule dirty_work with the damage collected from the * mmap page writes. */ static void drm_fb_helper_restore_lut_atomic(struct drm_crtc *crtc) { uint16_t *r_base, *g_base, *b_base; if (crtc->funcs->gamma_set == NULL) return; r_base = crtc->gamma_store; g_base = r_base + crtc->gamma_size; b_base = g_base + crtc->gamma_size; crtc->funcs->gamma_set(crtc, r_base, g_base, b_base, crtc->gamma_size, NULL); } /** * drm_fb_helper_debug_enter - implementation for &fb_ops.fb_debug_enter * @info: fbdev registered by the helper */ int drm_fb_helper_debug_enter(struct fb_info *info) { struct drm_fb_helper *helper = info->par; const struct drm_crtc_helper_funcs *funcs; struct drm_mode_set *mode_set; list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) { mutex_lock(&helper->client.modeset_mutex); drm_client_for_each_modeset(mode_set, &helper->client) { if (!mode_set->crtc->enabled) continue; funcs = mode_set->crtc->helper_private; if (funcs->mode_set_base_atomic == NULL) continue; if (drm_drv_uses_atomic_modeset(mode_set->crtc->dev)) continue; funcs->mode_set_base_atomic(mode_set->crtc, mode_set->fb, mode_set->x, mode_set->y, ENTER_ATOMIC_MODE_SET); } mutex_unlock(&helper->client.modeset_mutex); } return 0; } EXPORT_SYMBOL(drm_fb_helper_debug_enter); /** * drm_fb_helper_debug_leave - implementation for &fb_ops.fb_debug_leave * @info: fbdev registered by the helper */ int drm_fb_helper_debug_leave(struct fb_info *info) { struct drm_fb_helper *helper = info->par; struct drm_client_dev *client = &helper->client; struct drm_device *dev = helper->dev; struct drm_crtc *crtc; const struct drm_crtc_helper_funcs *funcs; struct drm_mode_set *mode_set; struct drm_framebuffer *fb; mutex_lock(&client->modeset_mutex); drm_client_for_each_modeset(mode_set, client) { crtc = mode_set->crtc; if (drm_drv_uses_atomic_modeset(crtc->dev)) continue; funcs = crtc->helper_private; fb = crtc->primary->fb; if (!crtc->enabled) continue; if (!fb) { drm_err(dev, "no fb to restore?\n"); continue; } if (funcs->mode_set_base_atomic == NULL) continue; drm_fb_helper_restore_lut_atomic(mode_set->crtc); funcs->mode_set_base_atomic(mode_set->crtc, fb, crtc->x, crtc->y, LEAVE_ATOMIC_MODE_SET); } mutex_unlock(&client->modeset_mutex); return 0; } EXPORT_SYMBOL(drm_fb_helper_debug_leave); static int __drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, bool force) { bool do_delayed; int ret; if (!drm_fbdev_emulation || !fb_helper) return -ENODEV; if (READ_ONCE(fb_helper->deferred_setup)) return 0; mutex_lock(&fb_helper->lock); if (force) { /* * Yes this is the _locked version which expects the master lock * to be held. But for forced restores we're intentionally * racing here, see drm_fb_helper_set_par(). */ ret = drm_client_modeset_commit_locked(&fb_helper->client); } else { ret = drm_client_modeset_commit(&fb_helper->client); } do_delayed = fb_helper->delayed_hotplug; if (do_delayed) fb_helper->delayed_hotplug = false; mutex_unlock(&fb_helper->lock); if (do_delayed) drm_fb_helper_hotplug_event(fb_helper); return ret; } /** * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration * @fb_helper: driver-allocated fbdev helper, can be NULL * * This should be called from driver's drm &drm_driver.lastclose callback * when implementing an fbcon on top of kms using this helper. This ensures that * the user isn't greeted with a black screen when e.g. X dies. * * RETURNS: * Zero if everything went ok, negative error code otherwise. */ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) { return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false); } EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked); #ifdef CONFIG_MAGIC_SYSRQ /* emergency restore, don't bother with error reporting */ static void drm_fb_helper_restore_work_fn(struct work_struct *ignored) { struct drm_fb_helper *helper; mutex_lock(&kernel_fb_helper_lock); list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) { struct drm_device *dev = helper->dev; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) continue; mutex_lock(&helper->lock); drm_client_modeset_commit_locked(&helper->client); mutex_unlock(&helper->lock); } mutex_unlock(&kernel_fb_helper_lock); } static DECLARE_WORK(drm_fb_helper_restore_work, drm_fb_helper_restore_work_fn); static void drm_fb_helper_sysrq(u8 dummy1) { schedule_work(&drm_fb_helper_restore_work); } static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { .handler = drm_fb_helper_sysrq, .help_msg = "force-fb(v)", .action_msg = "Restore framebuffer console", }; #else static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { }; #endif static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode) { struct drm_fb_helper *fb_helper = info->par; mutex_lock(&fb_helper->lock); drm_client_modeset_dpms(&fb_helper->client, dpms_mode); mutex_unlock(&fb_helper->lock); } /** * drm_fb_helper_blank - implementation for &fb_ops.fb_blank * @blank: desired blanking state * @info: fbdev registered by the helper */ int drm_fb_helper_blank(int blank, struct fb_info *info) { if (oops_in_progress) return -EBUSY; switch (blank) { /* Display: On; HSync: On, VSync: On */ case FB_BLANK_UNBLANK: drm_fb_helper_dpms(info, DRM_MODE_DPMS_ON); break; /* Display: Off; HSync: On, VSync: On */ case FB_BLANK_NORMAL: drm_fb_helper_dpms(info, DRM_MODE_DPMS_STANDBY); break; /* Display: Off; HSync: Off, VSync: On */ case FB_BLANK_HSYNC_SUSPEND: drm_fb_helper_dpms(info, DRM_MODE_DPMS_STANDBY); break; /* Display: Off; HSync: On, VSync: Off */ case FB_BLANK_VSYNC_SUSPEND: drm_fb_helper_dpms(info, DRM_MODE_DPMS_SUSPEND); break; /* Display: Off; HSync: Off, VSync: Off */ case FB_BLANK_POWERDOWN: drm_fb_helper_dpms(info, DRM_MODE_DPMS_OFF); break; } return 0; } EXPORT_SYMBOL(drm_fb_helper_blank); static void drm_fb_helper_resume_worker(struct work_struct *work) { struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper, resume_work); console_lock(); fb_set_suspend(helper->info, 0); console_unlock(); } static void drm_fb_helper_fb_dirty(struct drm_fb_helper *helper) { struct drm_device *dev = helper->dev; struct drm_clip_rect *clip = &helper->damage_clip; struct drm_clip_rect clip_copy; unsigned long flags; int ret; if (drm_WARN_ON_ONCE(dev, !helper->funcs->fb_dirty)) return; spin_lock_irqsave(&helper->damage_lock, flags); clip_copy = *clip; clip->x1 = clip->y1 = ~0; clip->x2 = clip->y2 = 0; spin_unlock_irqrestore(&helper->damage_lock, flags); ret = helper->funcs->fb_dirty(helper, &clip_copy); if (ret) goto err; return; err: /* * Restore damage clip rectangle on errors. The next run * of the damage worker will perform the update. */ spin_lock_irqsave(&helper->damage_lock, flags); clip->x1 = min_t(u32, clip->x1, clip_copy.x1); clip->y1 = min_t(u32, clip->y1, clip_copy.y1); clip->x2 = max_t(u32, clip->x2, clip_copy.x2); clip->y2 = max_t(u32, clip->y2, clip_copy.y2); spin_unlock_irqrestore(&helper->damage_lock, flags); } static void drm_fb_helper_damage_work(struct work_struct *work) { struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper, damage_work); drm_fb_helper_fb_dirty(helper); } /** * drm_fb_helper_prepare - setup a drm_fb_helper structure * @dev: DRM device * @helper: driver-allocated fbdev helper structure to set up * @preferred_bpp: Preferred bits per pixel for the device. * @funcs: pointer to structure of functions associate with this helper * * Sets up the bare minimum to make the framebuffer helper usable. This is * useful to implement race-free initialization of the polling helpers. */ void drm_fb_helper_prepare(struct drm_device *dev, struct drm_fb_helper *helper, unsigned int preferred_bpp, const struct drm_fb_helper_funcs *funcs) { /* * Pick a preferred bpp of 32 if no value has been given. This * will select XRGB8888 for the framebuffer formats. All drivers * have to support XRGB8888 for backwards compatibility with legacy * userspace, so it's the safe choice here. * * TODO: Replace struct drm_mode_config.preferred_depth and this * bpp value with a preferred format that is given as struct * drm_format_info. Then derive all other values from the * format. */ if (!preferred_bpp) preferred_bpp = 32; INIT_LIST_HEAD(&helper->kernel_fb_list); spin_lock_init(&helper->damage_lock); INIT_WORK(&helper->resume_work, drm_fb_helper_resume_worker); INIT_WORK(&helper->damage_work, drm_fb_helper_damage_work); helper->damage_clip.x1 = helper->damage_clip.y1 = ~0; mutex_init(&helper->lock); helper->funcs = funcs; helper->dev = dev; helper->preferred_bpp = preferred_bpp; } EXPORT_SYMBOL(drm_fb_helper_prepare); /** * drm_fb_helper_unprepare - clean up a drm_fb_helper structure * @fb_helper: driver-allocated fbdev helper structure to set up * * Cleans up the framebuffer helper. Inverse of drm_fb_helper_prepare(). */ void drm_fb_helper_unprepare(struct drm_fb_helper *fb_helper) { mutex_destroy(&fb_helper->lock); } EXPORT_SYMBOL(drm_fb_helper_unprepare); /** * drm_fb_helper_init - initialize a &struct drm_fb_helper * @dev: drm device * @fb_helper: driver-allocated fbdev helper structure to initialize * * This allocates the structures for the fbdev helper with the given limits. * Note that this won't yet touch the hardware (through the driver interfaces) * nor register the fbdev. This is only done in drm_fb_helper_initial_config() * to allow driver writes more control over the exact init sequence. * * Drivers must call drm_fb_helper_prepare() before calling this function. * * RETURNS: * Zero if everything went ok, nonzero otherwise. */ int drm_fb_helper_init(struct drm_device *dev, struct drm_fb_helper *fb_helper) { int ret; /* * If this is not the generic fbdev client, initialize a drm_client * without callbacks so we can use the modesets. */ if (!fb_helper->client.funcs) { ret = drm_client_init(dev, &fb_helper->client, "drm_fb_helper", NULL); if (ret) return ret; } dev->fb_helper = fb_helper; return 0; } EXPORT_SYMBOL(drm_fb_helper_init); /** * drm_fb_helper_alloc_info - allocate fb_info and some of its members * @fb_helper: driver-allocated fbdev helper * * A helper to alloc fb_info and the member cmap. Called by the driver * within the fb_probe fb_helper callback function. Drivers do not * need to release the allocated fb_info structure themselves, this is * automatically done when calling drm_fb_helper_fini(). * * RETURNS: * fb_info pointer if things went okay, pointer containing error code * otherwise */ struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) { struct device *dev = fb_helper->dev->dev; struct fb_info *info; int ret; info = framebuffer_alloc(0, dev); if (!info) return ERR_PTR(-ENOMEM); if (!drm_leak_fbdev_smem) info->flags |= FBINFO_HIDE_SMEM_START; ret = fb_alloc_cmap(&info->cmap, 256, 0); if (ret) goto err_release; fb_helper->info = info; info->skip_vt_switch = true; return info; err_release: framebuffer_release(info); return ERR_PTR(ret); } EXPORT_SYMBOL(drm_fb_helper_alloc_info); /** * drm_fb_helper_release_info - release fb_info and its members * @fb_helper: driver-allocated fbdev helper * * A helper to release fb_info and the member cmap. Drivers do not * need to release the allocated fb_info structure themselves, this is * automatically done when calling drm_fb_helper_fini(). */ void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) { struct fb_info *info = fb_helper->info; if (!info) return; fb_helper->info = NULL; if (info->cmap.len) fb_dealloc_cmap(&info->cmap); framebuffer_release(info); } EXPORT_SYMBOL(drm_fb_helper_release_info); /** * drm_fb_helper_unregister_info - unregister fb_info framebuffer device * @fb_helper: driver-allocated fbdev helper, can be NULL * * A wrapper around unregister_framebuffer, to release the fb_info * framebuffer device. This must be called before releasing all resources for * @fb_helper by calling drm_fb_helper_fini(). */ void drm_fb_helper_unregister_info(struct drm_fb_helper *fb_helper) { if (fb_helper && fb_helper->info) unregister_framebuffer(fb_helper->info); } EXPORT_SYMBOL(drm_fb_helper_unregister_info); /** * drm_fb_helper_fini - finialize a &struct drm_fb_helper * @fb_helper: driver-allocated fbdev helper, can be NULL * * This cleans up all remaining resources associated with @fb_helper. */ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) { if (!fb_helper) return; fb_helper->dev->fb_helper = NULL; if (!drm_fbdev_emulation) return; cancel_work_sync(&fb_helper->resume_work); cancel_work_sync(&fb_helper->damage_work); drm_fb_helper_release_info(fb_helper); mutex_lock(&kernel_fb_helper_lock); if (!list_empty(&fb_helper->kernel_fb_list)) { list_del(&fb_helper->kernel_fb_list); if (list_empty(&kernel_fb_helper_list)) unregister_sysrq_key('v', &sysrq_drm_fb_helper_restore_op); } mutex_unlock(&kernel_fb_helper_lock); if (!fb_helper->client.funcs) drm_client_release(&fb_helper->client); } EXPORT_SYMBOL(drm_fb_helper_fini); static void drm_fb_helper_add_damage_clip(struct drm_fb_helper *helper, u32 x, u32 y, u32 width, u32 height) { struct drm_clip_rect *clip = &helper->damage_clip; unsigned long flags; spin_lock_irqsave(&helper->damage_lock, flags); clip->x1 = min_t(u32, clip->x1, x); clip->y1 = min_t(u32, clip->y1, y); clip->x2 = max_t(u32, clip->x2, x + width); clip->y2 = max_t(u32, clip->y2, y + height); spin_unlock_irqrestore(&helper->damage_lock, flags); } static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, u32 width, u32 height) { /* * This function may be invoked by panic() to flush the frame * buffer, where all CPUs except the panic CPU are stopped. * During the following schedule_work(), the panic CPU needs * the worker_pool lock, which might be held by a stopped CPU, * causing schedule_work() and panic() to block. Return early on * oops_in_progress to prevent this blocking. */ if (oops_in_progress) return; drm_fb_helper_add_damage_clip(helper, x, y, width, height); schedule_work(&helper->damage_work); } /* * Convert memory region into area of scanlines and pixels per * scanline. The parameters off and len must not reach beyond * the end of the framebuffer. */ static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, size_t len, struct drm_rect *clip) { u32 line_length = info->fix.line_length; u32 fb_height = info->var.yres; off_t end = off + len; u32 x1 = 0; u32 y1 = off / line_length; u32 x2 = info->var.xres; u32 y2 = DIV_ROUND_UP(end, line_length); /* Don't allow any of them beyond the bottom bound of display area */ if (y1 > fb_height) y1 = fb_height; if (y2 > fb_height) y2 = fb_height; if ((y2 - y1) == 1) { /* * We've only written to a single scanline. Try to reduce * the number of horizontal pixels that need an update. */ off_t bit_off = (off % line_length) * 8; off_t bit_end = (end % line_length) * 8; x1 = bit_off / info->var.bits_per_pixel; x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel); } drm_rect_init(clip, x1, y1, x2 - x1, y2 - y1); } /* Don't use in new code. */ void drm_fb_helper_damage_range(struct fb_info *info, off_t off, size_t len) { struct drm_fb_helper *fb_helper = info->par; struct drm_rect damage_area; drm_fb_helper_memory_range_to_clip(info, off, len, &damage_area); drm_fb_helper_damage(fb_helper, damage_area.x1, damage_area.y1, drm_rect_width(&damage_area), drm_rect_height(&damage_area)); } EXPORT_SYMBOL(drm_fb_helper_damage_range); /* Don't use in new code. */ void drm_fb_helper_damage_area(struct fb_info *info, u32 x, u32 y, u32 width, u32 height) { struct drm_fb_helper *fb_helper = info->par; drm_fb_helper_damage(fb_helper, x, y, width, height); } EXPORT_SYMBOL(drm_fb_helper_damage_area); /** * drm_fb_helper_deferred_io() - fbdev deferred_io callback function * @info: fb_info struct pointer * @pagereflist: list of mmap framebuffer pages that have to be flushed * * This function is used as the &fb_deferred_io.deferred_io * callback function for flushing the fbdev mmap writes. */ void drm_fb_helper_deferred_io(struct fb_info *info, struct list_head *pagereflist) { struct drm_fb_helper *helper = info->par; unsigned long start, end, min_off, max_off, total_size; struct fb_deferred_io_pageref *pageref; struct drm_rect damage_area; min_off = ULONG_MAX; max_off = 0; list_for_each_entry(pageref, pagereflist, list) { start = pageref->offset; end = start + PAGE_SIZE; min_off = min(min_off, start); max_off = max(max_off, end); } /* * As we can only track pages, we might reach beyond the end * of the screen and account for non-existing scanlines. Hence, * keep the covered memory area within the screen buffer. */ if (info->screen_size) total_size = info->screen_size; else total_size = info->fix.smem_len; max_off = min(max_off, total_size); if (min_off < max_off) { drm_fb_helper_memory_range_to_clip(info, min_off, max_off - min_off, &damage_area); drm_fb_helper_damage(helper, damage_area.x1, damage_area.y1, drm_rect_width(&damage_area), drm_rect_height(&damage_area)); } } EXPORT_SYMBOL(drm_fb_helper_deferred_io); /** * drm_fb_helper_set_suspend - wrapper around fb_set_suspend * @fb_helper: driver-allocated fbdev helper, can be NULL * @suspend: whether to suspend or resume * * A wrapper around fb_set_suspend implemented by fbdev core. * Use drm_fb_helper_set_suspend_unlocked() if you don't need to take * the lock yourself */ void drm_fb_helper_set_suspend(struct drm_fb_helper *fb_helper, bool suspend) { if (fb_helper && fb_helper->info) fb_set_suspend(fb_helper->info, suspend); } EXPORT_SYMBOL(drm_fb_helper_set_suspend); /** * drm_fb_helper_set_suspend_unlocked - wrapper around fb_set_suspend that also * takes the console lock * @fb_helper: driver-allocated fbdev helper, can be NULL * @suspend: whether to suspend or resume * * A wrapper around fb_set_suspend() that takes the console lock. If the lock * isn't available on resume, a worker is tasked with waiting for the lock * to become available. The console lock can be pretty contented on resume * due to all the printk activity. * * This function can be called multiple times with the same state since * &fb_info.state is checked to see if fbdev is running or not before locking. * * Use drm_fb_helper_set_suspend() if you need to take the lock yourself. */ void drm_fb_helper_set_suspend_unlocked(struct drm_fb_helper *fb_helper, bool suspend) { if (!fb_helper || !fb_helper->info) return; /* make sure there's no pending/ongoing resume */ flush_work(&fb_helper->resume_work); if (suspend) { if (fb_helper->info->state != FBINFO_STATE_RUNNING) return; console_lock(); } else { if (fb_helper->info->state == FBINFO_STATE_RUNNING) return; if (!console_trylock()) { schedule_work(&fb_helper->resume_work); return; } } fb_set_suspend(fb_helper->info, suspend); console_unlock(); } EXPORT_SYMBOL(drm_fb_helper_set_suspend_unlocked); static int setcmap_pseudo_palette(struct fb_cmap *cmap, struct fb_info *info) { u32 *palette = (u32 *)info->pseudo_palette; int i; if (cmap->start + cmap->len > 16) return -EINVAL; for (i = 0; i < cmap->len; ++i) { u16 red = cmap->red[i]; u16 green = cmap->green[i]; u16 blue = cmap->blue[i]; u32 value; red >>= 16 - info->var.red.length; green >>= 16 - info->var.green.length; blue >>= 16 - info->var.blue.length; value = (red << info->var.red.offset) | (green << info->var.green.offset) | (blue << info->var.blue.offset); if (info->var.transp.length > 0) { u32 mask = (1 << info->var.transp.length) - 1; mask <<= info->var.transp.offset; value |= mask; } palette[cmap->start + i] = value; } return 0; } static int setcmap_legacy(struct fb_cmap *cmap, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_mode_set *modeset; struct drm_crtc *crtc; u16 *r, *g, *b; int ret = 0; drm_modeset_lock_all(fb_helper->dev); drm_client_for_each_modeset(modeset, &fb_helper->client) { crtc = modeset->crtc; if (!crtc->funcs->gamma_set || !crtc->gamma_size) { ret = -EINVAL; goto out; } if (cmap->start + cmap->len > crtc->gamma_size) { ret = -EINVAL; goto out; } r = crtc->gamma_store; g = r + crtc->gamma_size; b = g + crtc->gamma_size; memcpy(r + cmap->start, cmap->red, cmap->len * sizeof(*r)); memcpy(g + cmap->start, cmap->green, cmap->len * sizeof(*g)); memcpy(b + cmap->start, cmap->blue, cmap->len * sizeof(*b)); ret = crtc->funcs->gamma_set(crtc, r, g, b, crtc->gamma_size, NULL); if (ret) goto out; } out: drm_modeset_unlock_all(fb_helper->dev); return ret; } static struct drm_property_blob *setcmap_new_gamma_lut(struct drm_crtc *crtc, struct fb_cmap *cmap) { struct drm_device *dev = crtc->dev; struct drm_property_blob *gamma_lut; struct drm_color_lut *lut; int size = crtc->gamma_size; int i; if (!size || cmap->start + cmap->len > size) return ERR_PTR(-EINVAL); gamma_lut = drm_property_create_blob(dev, sizeof(*lut) * size, NULL); if (IS_ERR(gamma_lut)) return gamma_lut; lut = gamma_lut->data; if (cmap->start || cmap->len != size) { u16 *r = crtc->gamma_store; u16 *g = r + crtc->gamma_size; u16 *b = g + crtc->gamma_size; for (i = 0; i < cmap->start; i++) { lut[i].red = r[i]; lut[i].green = g[i]; lut[i].blue = b[i]; } for (i = cmap->start + cmap->len; i < size; i++) { lut[i].red = r[i]; lut[i].green = g[i]; lut[i].blue = b[i]; } } for (i = 0; i < cmap->len; i++) { lut[cmap->start + i].red = cmap->red[i]; lut[cmap->start + i].green = cmap->green[i]; lut[cmap->start + i].blue = cmap->blue[i]; } return gamma_lut; } static int setcmap_atomic(struct fb_cmap *cmap, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; struct drm_property_blob *gamma_lut = NULL; struct drm_modeset_acquire_ctx ctx; struct drm_crtc_state *crtc_state; struct drm_atomic_state *state; struct drm_mode_set *modeset; struct drm_crtc *crtc; u16 *r, *g, *b; bool replaced; int ret = 0; drm_modeset_acquire_init(&ctx, 0); state = drm_atomic_state_alloc(dev); if (!state) { ret = -ENOMEM; goto out_ctx; } state->acquire_ctx = &ctx; retry: drm_client_for_each_modeset(modeset, &fb_helper->client) { crtc = modeset->crtc; if (!gamma_lut) gamma_lut = setcmap_new_gamma_lut(crtc, cmap); if (IS_ERR(gamma_lut)) { ret = PTR_ERR(gamma_lut); gamma_lut = NULL; goto out_state; } crtc_state = drm_atomic_get_crtc_state(state, crtc); if (IS_ERR(crtc_state)) { ret = PTR_ERR(crtc_state); goto out_state; } /* * FIXME: This always uses gamma_lut. Some HW have only * degamma_lut, in which case we should reset gamma_lut and set * degamma_lut. See drm_crtc_legacy_gamma_set(). */ replaced = drm_property_replace_blob(&crtc_state->degamma_lut, NULL); replaced |= drm_property_replace_blob(&crtc_state->ctm, NULL); replaced |= drm_property_replace_blob(&crtc_state->gamma_lut, gamma_lut); crtc_state->color_mgmt_changed |= replaced; } ret = drm_atomic_commit(state); if (ret) goto out_state; drm_client_for_each_modeset(modeset, &fb_helper->client) { crtc = modeset->crtc; r = crtc->gamma_store; g = r + crtc->gamma_size; b = g + crtc->gamma_size; memcpy(r + cmap->start, cmap->red, cmap->len * sizeof(*r)); memcpy(g + cmap->start, cmap->green, cmap->len * sizeof(*g)); memcpy(b + cmap->start, cmap->blue, cmap->len * sizeof(*b)); } out_state: if (ret == -EDEADLK) goto backoff; drm_property_blob_put(gamma_lut); drm_atomic_state_put(state); out_ctx: drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); return ret; backoff: drm_atomic_state_clear(state); drm_modeset_backoff(&ctx); goto retry; } /** * drm_fb_helper_setcmap - implementation for &fb_ops.fb_setcmap * @cmap: cmap to set * @info: fbdev registered by the helper */ int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; int ret; if (oops_in_progress) return -EBUSY; mutex_lock(&fb_helper->lock); if (!drm_master_internal_acquire(dev)) { ret = -EBUSY; goto unlock; } mutex_lock(&fb_helper->client.modeset_mutex); if (info->fix.visual == FB_VISUAL_TRUECOLOR) ret = setcmap_pseudo_palette(cmap, info); else if (drm_drv_uses_atomic_modeset(fb_helper->dev)) ret = setcmap_atomic(cmap, info); else ret = setcmap_legacy(cmap, info); mutex_unlock(&fb_helper->client.modeset_mutex); drm_master_internal_release(dev); unlock: mutex_unlock(&fb_helper->lock); return ret; } EXPORT_SYMBOL(drm_fb_helper_setcmap); /** * drm_fb_helper_ioctl - legacy ioctl implementation * @info: fbdev registered by the helper * @cmd: ioctl command * @arg: ioctl argument * * A helper to implement the standard fbdev ioctl. Only * FBIO_WAITFORVSYNC is implemented for now. */ int drm_fb_helper_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; struct drm_crtc *crtc; int ret = 0; mutex_lock(&fb_helper->lock); if (!drm_master_internal_acquire(dev)) { ret = -EBUSY; goto unlock; } switch (cmd) { case FBIO_WAITFORVSYNC: /* * Only consider the first CRTC. * * This ioctl is supposed to take the CRTC number as * an argument, but in fbdev times, what that number * was supposed to be was quite unclear, different * drivers were passing that argument differently * (some by reference, some by value), and most of the * userspace applications were just hardcoding 0 as an * argument. * * The first CRTC should be the integrated panel on * most drivers, so this is the best choice we can * make. If we're not smart enough here, one should * just consider switch the userspace to KMS. */ crtc = fb_helper->client.modesets[0].crtc; /* * Only wait for a vblank event if the CRTC is * enabled, otherwise just don't do anythintg, * not even report an error. */ ret = drm_crtc_vblank_get(crtc); if (!ret) { drm_crtc_wait_one_vblank(crtc); drm_crtc_vblank_put(crtc); } ret = 0; break; default: ret = -ENOTTY; } drm_master_internal_release(dev); unlock: mutex_unlock(&fb_helper->lock); return ret; } EXPORT_SYMBOL(drm_fb_helper_ioctl); static bool drm_fb_pixel_format_equal(const struct fb_var_screeninfo *var_1, const struct fb_var_screeninfo *var_2) { return var_1->bits_per_pixel == var_2->bits_per_pixel && var_1->grayscale == var_2->grayscale && var_1->red.offset == var_2->red.offset && var_1->red.length == var_2->red.length && var_1->red.msb_right == var_2->red.msb_right && var_1->green.offset == var_2->green.offset && var_1->green.length == var_2->green.length && var_1->green.msb_right == var_2->green.msb_right && var_1->blue.offset == var_2->blue.offset && var_1->blue.length == var_2->blue.length && var_1->blue.msb_right == var_2->blue.msb_right && var_1->transp.offset == var_2->transp.offset && var_1->transp.length == var_2->transp.length && var_1->transp.msb_right == var_2->transp.msb_right; } static void drm_fb_helper_fill_pixel_fmt(struct fb_var_screeninfo *var, const struct drm_format_info *format) { u8 depth = format->depth; if (format->is_color_indexed) { var->red.offset = 0; var->green.offset = 0; var->blue.offset = 0; var->red.length = depth; var->green.length = depth; var->blue.length = depth; var->transp.offset = 0; var->transp.length = 0; return; } switch (depth) { case 15: var->red.offset = 10; var->green.offset = 5; var->blue.offset = 0; var->red.length = 5; var->green.length = 5; var->blue.length = 5; var->transp.offset = 15; var->transp.length = 1; break; case 16: var->red.offset = 11; var->green.offset = 5; var->blue.offset = 0; var->red.length = 5; var->green.length = 6; var->blue.length = 5; var->transp.offset = 0; break; case 24: var->red.offset = 16; var->green.offset = 8; var->blue.offset = 0; var->red.length = 8; var->green.length = 8; var->blue.length = 8; var->transp.offset = 0; var->transp.length = 0; break; case 32: var->red.offset = 16; var->green.offset = 8; var->blue.offset = 0; var->red.length = 8; var->green.length = 8; var->blue.length = 8; var->transp.offset = 24; var->transp.length = 8; break; default: break; } } static void __fill_var(struct fb_var_screeninfo *var, struct fb_info *info, struct drm_framebuffer *fb) { int i; var->xres_virtual = fb->width; var->yres_virtual = fb->height; var->accel_flags = 0; var->bits_per_pixel = drm_format_info_bpp(fb->format, 0); var->height = info->var.height; var->width = info->var.width; var->left_margin = var->right_margin = 0; var->upper_margin = var->lower_margin = 0; var->hsync_len = var->vsync_len = 0; var->sync = var->vmode = 0; var->rotate = 0; var->colorspace = 0; for (i = 0; i < 4; i++) var->reserved[i] = 0; } /** * drm_fb_helper_check_var - implementation for &fb_ops.fb_check_var * @var: screeninfo to check * @info: fbdev registered by the helper */ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_framebuffer *fb = fb_helper->fb; const struct drm_format_info *format = fb->format; struct drm_device *dev = fb_helper->dev; unsigned int bpp; if (in_dbg_master()) return -EINVAL; if (var->pixclock != 0) { drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n"); var->pixclock = 0; } switch (format->format) { case DRM_FORMAT_C1: case DRM_FORMAT_C2: case DRM_FORMAT_C4: /* supported format with sub-byte pixels */ break; default: if ((drm_format_info_block_width(format, 0) > 1) || (drm_format_info_block_height(format, 0) > 1)) return -EINVAL; break; } /* * Changes struct fb_var_screeninfo are currently not pushed back * to KMS, hence fail if different settings are requested. */ bpp = drm_format_info_bpp(format, 0); if (var->bits_per_pixel > bpp || var->xres > fb->width || var->yres > fb->height || var->xres_virtual > fb->width || var->yres_virtual > fb->height) { drm_dbg_kms(dev, "fb requested width/height/bpp can't fit in current fb " "request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n", var->xres, var->yres, var->bits_per_pixel, var->xres_virtual, var->yres_virtual, fb->width, fb->height, bpp); return -EINVAL; } __fill_var(var, info, fb); /* * fb_pan_display() validates this, but fb_set_par() doesn't and just * falls over. Note that __fill_var above adjusts y/res_virtual. */ if (var->yoffset > var->yres_virtual - var->yres || var->xoffset > var->xres_virtual - var->xres) return -EINVAL; /* We neither support grayscale nor FOURCC (also stored in here). */ if (var->grayscale > 0) return -EINVAL; if (var->nonstd) return -EINVAL; /* * Workaround for SDL 1.2, which is known to be setting all pixel format * fields values to zero in some cases. We treat this situation as a * kind of "use some reasonable autodetected values". */ if (!var->red.offset && !var->green.offset && !var->blue.offset && !var->transp.offset && !var->red.length && !var->green.length && !var->blue.length && !var->transp.length && !var->red.msb_right && !var->green.msb_right && !var->blue.msb_right && !var->transp.msb_right) { drm_fb_helper_fill_pixel_fmt(var, format); } /* * drm fbdev emulation doesn't support changing the pixel format at all, * so reject all pixel format changing requests. */ if (!drm_fb_pixel_format_equal(var, &info->var)) { drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel format\n"); return -EINVAL; } return 0; } EXPORT_SYMBOL(drm_fb_helper_check_var); /** * drm_fb_helper_set_par - implementation for &fb_ops.fb_set_par * @info: fbdev registered by the helper * * This will let fbcon do the mode init and is called at initialization time by * the fbdev core when registering the driver, and later on through the hotplug * callback. */ int drm_fb_helper_set_par(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct fb_var_screeninfo *var = &info->var; bool force; if (oops_in_progress) return -EBUSY; /* * Normally we want to make sure that a kms master takes precedence over * fbdev, to avoid fbdev flickering and occasionally stealing the * display status. But Xorg first sets the vt back to text mode using * the KDSET IOCTL with KD_TEXT, and only after that drops the master * status when exiting. * * In the past this was caught by drm_fb_helper_lastclose(), but on * modern systems where logind always keeps a drm fd open to orchestrate * the vt switching, this doesn't work. * * To not break the userspace ABI we have this special case here, which * is only used for the above case. Everything else uses the normal * commit function, which ensures that we never steal the display from * an active drm master. */ force = var->activate & FB_ACTIVATE_KD_TEXT; __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force); return 0; } EXPORT_SYMBOL(drm_fb_helper_set_par); static void pan_set(struct drm_fb_helper *fb_helper, int x, int y) { struct drm_mode_set *mode_set; mutex_lock(&fb_helper->client.modeset_mutex); drm_client_for_each_modeset(mode_set, &fb_helper->client) { mode_set->x = x; mode_set->y = y; } mutex_unlock(&fb_helper->client.modeset_mutex); } static int pan_display_atomic(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; int ret; pan_set(fb_helper, var->xoffset, var->yoffset); ret = drm_client_modeset_commit_locked(&fb_helper->client); if (!ret) { info->var.xoffset = var->xoffset; info->var.yoffset = var->yoffset; } else pan_set(fb_helper, info->var.xoffset, info->var.yoffset); return ret; } static int pan_display_legacy(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_client_dev *client = &fb_helper->client; struct drm_mode_set *modeset; int ret = 0; mutex_lock(&client->modeset_mutex); drm_modeset_lock_all(fb_helper->dev); drm_client_for_each_modeset(modeset, client) { modeset->x = var->xoffset; modeset->y = var->yoffset; if (modeset->num_connectors) { ret = drm_mode_set_config_internal(modeset); if (!ret) { info->var.xoffset = var->xoffset; info->var.yoffset = var->yoffset; } } } drm_modeset_unlock_all(fb_helper->dev); mutex_unlock(&client->modeset_mutex); return ret; } /** * drm_fb_helper_pan_display - implementation for &fb_ops.fb_pan_display * @var: updated screen information * @info: fbdev registered by the helper */ int drm_fb_helper_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; int ret; if (oops_in_progress) return -EBUSY; mutex_lock(&fb_helper->lock); if (!drm_master_internal_acquire(dev)) { ret = -EBUSY; goto unlock; } if (drm_drv_uses_atomic_modeset(dev)) ret = pan_display_atomic(var, info); else ret = pan_display_legacy(var, info); drm_master_internal_release(dev); unlock: mutex_unlock(&fb_helper->lock); return ret; } EXPORT_SYMBOL(drm_fb_helper_pan_display); static uint32_t drm_fb_helper_find_format(struct drm_fb_helper *fb_helper, const uint32_t *formats, size_t format_count, uint32_t bpp, uint32_t depth) { struct drm_device *dev = fb_helper->dev; uint32_t format; size_t i; /* * Do not consider YUV or other complicated formats * for framebuffers. This means only legacy formats * are supported (fmt->depth is a legacy field), but * the framebuffer emulation can only deal with such * formats, specifically RGB/BGA formats. */ format = drm_mode_legacy_fb_format(bpp, depth); if (!format) goto err; for (i = 0; i < format_count; ++i) { if (formats[i] == format) return format; } err: /* We found nothing. */ drm_warn(dev, "bpp/depth value of %u/%u not supported\n", bpp, depth); return DRM_FORMAT_INVALID; } static uint32_t drm_fb_helper_find_color_mode_format(struct drm_fb_helper *fb_helper, const uint32_t *formats, size_t format_count, unsigned int color_mode) { struct drm_device *dev = fb_helper->dev; uint32_t bpp, depth; switch (color_mode) { case 1: case 2: case 4: case 8: case 16: case 24: bpp = depth = color_mode; break; case 15: bpp = 16; depth = 15; break; case 32: bpp = 32; depth = 24; break; default: drm_info(dev, "unsupported color mode of %d\n", color_mode); return DRM_FORMAT_INVALID; } return drm_fb_helper_find_format(fb_helper, formats, format_count, bpp, depth); } static int __drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; int crtc_count = 0; struct drm_connector_list_iter conn_iter; struct drm_connector *connector; struct drm_mode_set *mode_set; uint32_t surface_format = DRM_FORMAT_INVALID; const struct drm_format_info *info; memset(sizes, 0, sizeof(*sizes)); sizes->fb_width = (u32)-1; sizes->fb_height = (u32)-1; drm_client_for_each_modeset(mode_set, client) { struct drm_crtc *crtc = mode_set->crtc; struct drm_plane *plane = crtc->primary; drm_dbg_kms(dev, "test CRTC %u primary plane\n", drm_crtc_index(crtc)); drm_connector_list_iter_begin(fb_helper->dev, &conn_iter); drm_client_for_each_connector_iter(connector, &conn_iter) { struct drm_cmdline_mode *cmdline_mode = &connector->cmdline_mode; if (!cmdline_mode->bpp_specified) continue; surface_format = drm_fb_helper_find_color_mode_format(fb_helper, plane->format_types, plane->format_count, cmdline_mode->bpp); if (surface_format != DRM_FORMAT_INVALID) break; /* found supported format */ } drm_connector_list_iter_end(&conn_iter); if (surface_format != DRM_FORMAT_INVALID) break; /* found supported format */ /* try preferred color mode */ surface_format = drm_fb_helper_find_color_mode_format(fb_helper, plane->format_types, plane->format_count, fb_helper->preferred_bpp); if (surface_format != DRM_FORMAT_INVALID) break; /* found supported format */ } if (surface_format == DRM_FORMAT_INVALID) { /* * If none of the given color modes works, fall back * to XRGB8888. Drivers are expected to provide this * format for compatibility with legacy applications. */ drm_warn(dev, "No compatible format found\n"); surface_format = drm_driver_legacy_fb_format(dev, 32, 24); } info = drm_format_info(surface_format); sizes->surface_bpp = drm_format_info_bpp(info, 0); sizes->surface_depth = info->depth; /* first up get a count of crtcs now in use and new min/maxes width/heights */ crtc_count = 0; drm_client_for_each_modeset(mode_set, client) { struct drm_display_mode *desired_mode; int x, y, j; /* in case of tile group, are we the last tile vert or horiz? * If no tile group you are always the last one both vertically * and horizontally */ bool lastv = true, lasth = true; desired_mode = mode_set->mode; if (!desired_mode) continue; crtc_count++; x = mode_set->x; y = mode_set->y; sizes->surface_width = max_t(u32, desired_mode->hdisplay + x, sizes->surface_width); sizes->surface_height = max_t(u32, desired_mode->vdisplay + y, sizes->surface_height); for (j = 0; j < mode_set->num_connectors; j++) { struct drm_connector *connector = mode_set->connectors[j]; if (connector->has_tile && desired_mode->hdisplay == connector->tile_h_size && desired_mode->vdisplay == connector->tile_v_size) { lasth = (connector->tile_h_loc == (connector->num_h_tile - 1)); lastv = (connector->tile_v_loc == (connector->num_v_tile - 1)); /* cloning to multiple tiles is just crazy-talk, so: */ break; } } if (lasth) sizes->fb_width = min_t(u32, desired_mode->hdisplay + x, sizes->fb_width); if (lastv) sizes->fb_height = min_t(u32, desired_mode->vdisplay + y, sizes->fb_height); } if (crtc_count == 0 || sizes->fb_width == -1 || sizes->fb_height == -1) { drm_info(dev, "Cannot find any crtc or sizes\n"); return -EAGAIN; } return 0; } static int drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; struct drm_mode_config *config = &dev->mode_config; int ret; mutex_lock(&client->modeset_mutex); ret = __drm_fb_helper_find_sizes(fb_helper, sizes); mutex_unlock(&client->modeset_mutex); if (ret) return ret; /* Handle our overallocation */ sizes->surface_height *= drm_fbdev_overalloc; sizes->surface_height /= 100; if (sizes->surface_height > config->max_height) { drm_dbg_kms(dev, "Fbdev over-allocation too large; clamping height to %d\n", config->max_height); sizes->surface_height = config->max_height; } return 0; } /* * Allocates the backing storage and sets up the fbdev info structure through * the ->fb_probe callback. */ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; struct drm_fb_helper_surface_size sizes; int ret; ret = drm_fb_helper_find_sizes(fb_helper, &sizes); if (ret) { /* First time: disable all crtc's.. */ if (!fb_helper->deferred_setup) drm_client_modeset_commit(client); return ret; } /* push down into drivers */ ret = (*fb_helper->funcs->fb_probe)(fb_helper, &sizes); if (ret < 0) return ret; strcpy(fb_helper->fb->comm, "[fbcon]"); /* Set the fb info for vgaswitcheroo clients. Does nothing otherwise. */ if (dev_is_pci(dev->dev)) vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), fb_helper->info); return 0; } static void drm_fb_helper_fill_fix(struct fb_info *info, uint32_t pitch, bool is_color_indexed) { info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.visual = is_color_indexed ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; info->fix.mmio_start = 0; info->fix.mmio_len = 0; info->fix.type_aux = 0; info->fix.xpanstep = 1; /* doing it in hw */ info->fix.ypanstep = 1; /* doing it in hw */ info->fix.ywrapstep = 0; info->fix.accel = FB_ACCEL_NONE; info->fix.line_length = pitch; } static void drm_fb_helper_fill_var(struct fb_info *info, struct drm_fb_helper *fb_helper, uint32_t fb_width, uint32_t fb_height) { struct drm_framebuffer *fb = fb_helper->fb; const struct drm_format_info *format = fb->format; switch (format->format) { case DRM_FORMAT_C1: case DRM_FORMAT_C2: case DRM_FORMAT_C4: /* supported format with sub-byte pixels */ break; default: WARN_ON((drm_format_info_block_width(format, 0) > 1) || (drm_format_info_block_height(format, 0) > 1)); break; } info->pseudo_palette = fb_helper->pseudo_palette; info->var.xoffset = 0; info->var.yoffset = 0; __fill_var(&info->var, info, fb); info->var.activate = FB_ACTIVATE_NOW; drm_fb_helper_fill_pixel_fmt(&info->var, format); info->var.xres = fb_width; info->var.yres = fb_height; } /** * drm_fb_helper_fill_info - initializes fbdev information * @info: fbdev instance to set up * @fb_helper: fb helper instance to use as template * @sizes: describes fbdev size and scanout surface size * * Sets up the variable and fixed fbdev metainformation from the given fb helper * instance and the drm framebuffer allocated in &drm_fb_helper.fb. * * Drivers should call this (or their equivalent setup code) from their * &drm_fb_helper_funcs.fb_probe callback after having allocated the fbdev * backing storage framebuffer. */ void drm_fb_helper_fill_info(struct fb_info *info, struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_framebuffer *fb = fb_helper->fb; drm_fb_helper_fill_fix(info, fb->pitches[0], fb->format->is_color_indexed); drm_fb_helper_fill_var(info, fb_helper, sizes->fb_width, sizes->fb_height); info->par = fb_helper; /* * The DRM drivers fbdev emulation device name can be confusing if the * driver name also has a "drm" suffix on it. Leading to names such as * "simpledrmdrmfb" in /proc/fb. Unfortunately, it's an uAPI and can't * be changed due user-space tools (e.g: pm-utils) matching against it. */ snprintf(info->fix.id, sizeof(info->fix.id), "%sdrmfb", fb_helper->dev->driver->name); } EXPORT_SYMBOL(drm_fb_helper_fill_info); /* * This is a continuation of drm_setup_crtcs() that sets up anything related * to the framebuffer. During initialization, drm_setup_crtcs() is called before * the framebuffer has been allocated (fb_helper->fb and fb_helper->info). * So, any setup that touches those fields needs to be done here instead of in * drm_setup_crtcs(). */ static void drm_setup_crtcs_fb(struct drm_fb_helper *fb_helper) { struct drm_client_dev *client = &fb_helper->client; struct drm_connector_list_iter conn_iter; struct fb_info *info = fb_helper->info; unsigned int rotation, sw_rotations = 0; struct drm_connector *connector; struct drm_mode_set *modeset; mutex_lock(&client->modeset_mutex); drm_client_for_each_modeset(modeset, client) { if (!modeset->num_connectors) continue; modeset->fb = fb_helper->fb; if (drm_client_rotation(modeset, &rotation)) /* Rotating in hardware, fbcon should not rotate */ sw_rotations |= DRM_MODE_ROTATE_0; else sw_rotations |= rotation; } mutex_unlock(&client->modeset_mutex); drm_connector_list_iter_begin(fb_helper->dev, &conn_iter); drm_client_for_each_connector_iter(connector, &conn_iter) { /* use first connected connector for the physical dimensions */ if (connector->status == connector_status_connected) { info->var.width = connector->display_info.width_mm; info->var.height = connector->display_info.height_mm; break; } } drm_connector_list_iter_end(&conn_iter); switch (sw_rotations) { case DRM_MODE_ROTATE_0: info->fbcon_rotate_hint = FB_ROTATE_UR; break; case DRM_MODE_ROTATE_90: info->fbcon_rotate_hint = FB_ROTATE_CCW; break; case DRM_MODE_ROTATE_180: info->fbcon_rotate_hint = FB_ROTATE_UD; break; case DRM_MODE_ROTATE_270: info->fbcon_rotate_hint = FB_ROTATE_CW; break; default: /* * Multiple bits are set / multiple rotations requested * fbcon cannot handle separate rotation settings per * output, so fallback to unrotated. */ info->fbcon_rotate_hint = FB_ROTATE_UR; } } /* Note: Drops fb_helper->lock before returning. */ static int __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) { struct drm_device *dev = fb_helper->dev; struct fb_info *info; unsigned int width, height; int ret; width = dev->mode_config.max_width; height = dev->mode_config.max_height; drm_client_modeset_probe(&fb_helper->client, width, height); ret = drm_fb_helper_single_fb_probe(fb_helper); if (ret < 0) { if (ret == -EAGAIN) { fb_helper->deferred_setup = true; ret = 0; } mutex_unlock(&fb_helper->lock); return ret; } drm_setup_crtcs_fb(fb_helper); fb_helper->deferred_setup = false; info = fb_helper->info; info->var.pixclock = 0; /* Need to drop locks to avoid recursive deadlock in * register_framebuffer. This is ok because the only thing left to do is * register the fbdev emulation instance in kernel_fb_helper_list. */ mutex_unlock(&fb_helper->lock); ret = register_framebuffer(info); if (ret < 0) return ret; drm_info(dev, "fb%d: %s frame buffer device\n", info->node, info->fix.id); mutex_lock(&kernel_fb_helper_lock); if (list_empty(&kernel_fb_helper_list)) register_sysrq_key('v', &sysrq_drm_fb_helper_restore_op); list_add(&fb_helper->kernel_fb_list, &kernel_fb_helper_list); mutex_unlock(&kernel_fb_helper_lock); return 0; } /** * drm_fb_helper_initial_config - setup a sane initial connector configuration * @fb_helper: fb_helper device struct * * Scans the CRTCs and connectors and tries to put together an initial setup. * At the moment, this is a cloned configuration across all heads with * a new framebuffer object as the backing store. * * Note that this also registers the fbdev and so allows userspace to call into * the driver through the fbdev interfaces. * * This function will call down into the &drm_fb_helper_funcs.fb_probe callback * to let the driver allocate and initialize the fbdev info structure and the * drm framebuffer used to back the fbdev. drm_fb_helper_fill_info() is provided * as a helper to setup simple default values for the fbdev info structure. * * HANG DEBUGGING: * * When you have fbcon support built-in or already loaded, this function will do * a full modeset to setup the fbdev console. Due to locking misdesign in the * VT/fbdev subsystem that entire modeset sequence has to be done while holding * console_lock. Until console_unlock is called no dmesg lines will be sent out * to consoles, not even serial console. This means when your driver crashes, * you will see absolutely nothing else but a system stuck in this function, * with no further output. Any kind of printk() you place within your own driver * or in the drm core modeset code will also never show up. * * Standard debug practice is to run the fbcon setup without taking the * console_lock as a hack, to be able to see backtraces and crashes on the * serial line. This can be done by setting the fb.lockless_register_fb=1 kernel * cmdline option. * * The other option is to just disable fbdev emulation since very likely the * first modeset from userspace will crash in the same way, and is even easier * to debug. This can be done by setting the drm_kms_helper.fbdev_emulation=0 * kernel cmdline option. * * RETURNS: * Zero if everything went ok, nonzero otherwise. */ int drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper) { int ret; if (!drm_fbdev_emulation) return 0; mutex_lock(&fb_helper->lock); ret = __drm_fb_helper_initial_config_and_unlock(fb_helper); return ret; } EXPORT_SYMBOL(drm_fb_helper_initial_config); /** * drm_fb_helper_hotplug_event - respond to a hotplug notification by * probing all the outputs attached to the fb * @fb_helper: driver-allocated fbdev helper, can be NULL * * Scan the connectors attached to the fb_helper and try to put together a * setup after notification of a change in output configuration. * * Called at runtime, takes the mode config locks to be able to check/change the * modeset configuration. Must be run from process context (which usually means * either the output polling work or a work item launched from the driver's * hotplug interrupt). * * Note that drivers may call this even before calling * drm_fb_helper_initial_config but only after drm_fb_helper_init. This allows * for a race-free fbcon setup and will make sure that the fbdev emulation will * not miss any hotplug events. * * RETURNS: * 0 on success and a non-zero error code otherwise. */ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) { int err = 0; if (!drm_fbdev_emulation || !fb_helper) return 0; mutex_lock(&fb_helper->lock); if (fb_helper->deferred_setup) { err = __drm_fb_helper_initial_config_and_unlock(fb_helper); return err; } if (!fb_helper->fb || !drm_master_internal_acquire(fb_helper->dev)) { fb_helper->delayed_hotplug = true; mutex_unlock(&fb_helper->lock); return err; } drm_master_internal_release(fb_helper->dev); drm_dbg_kms(fb_helper->dev, "\n"); drm_client_modeset_probe(&fb_helper->client, fb_helper->fb->width, fb_helper->fb->height); drm_setup_crtcs_fb(fb_helper); mutex_unlock(&fb_helper->lock); drm_fb_helper_set_par(fb_helper->info); return 0; } EXPORT_SYMBOL(drm_fb_helper_hotplug_event); /** * drm_fb_helper_lastclose - DRM driver lastclose helper for fbdev emulation * @dev: DRM device * * This function can be used as the &drm_driver->lastclose callback for drivers * that only need to call drm_fb_helper_restore_fbdev_mode_unlocked(). */ void drm_fb_helper_lastclose(struct drm_device *dev) { drm_fb_helper_restore_fbdev_mode_unlocked(dev->fb_helper); } EXPORT_SYMBOL(drm_fb_helper_lastclose); /** * drm_fb_helper_output_poll_changed - DRM mode config \.output_poll_changed * helper for fbdev emulation * @dev: DRM device * * This function can be used as the * &drm_mode_config_funcs.output_poll_changed callback for drivers that only * need to call drm_fbdev.hotplug_event(). */ void drm_fb_helper_output_poll_changed(struct drm_device *dev) { drm_fb_helper_hotplug_event(dev->fb_helper); } EXPORT_SYMBOL(drm_fb_helper_output_poll_changed); |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 | // SPDX-License-Identifier: GPL-2.0-only /* * This file contains functions assisting in mapping VFS to 9P2000 * * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.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 "v9fs.h" #include "v9fs_vfs.h" #include "cache.h" static DEFINE_SPINLOCK(v9fs_sessionlist_lock); static LIST_HEAD(v9fs_sessionlist); struct kmem_cache *v9fs_inode_cache; /* * Option Parsing (code inspired by NFS code) * NOTE: each transport will parse its own options */ enum { /* Options that take integer arguments */ Opt_debug, Opt_dfltuid, Opt_dfltgid, Opt_afid, /* String options */ Opt_uname, Opt_remotename, Opt_cache, Opt_cachetag, /* Options that take no arguments */ Opt_nodevmap, Opt_noxattr, Opt_directio, Opt_ignoreqv, /* Access options */ Opt_access, Opt_posixacl, /* Lock timeout option */ Opt_locktimeout, /* Error token */ Opt_err }; static const match_table_t tokens = { {Opt_debug, "debug=%x"}, {Opt_dfltuid, "dfltuid=%u"}, {Opt_dfltgid, "dfltgid=%u"}, {Opt_afid, "afid=%u"}, {Opt_uname, "uname=%s"}, {Opt_remotename, "aname=%s"}, {Opt_nodevmap, "nodevmap"}, {Opt_noxattr, "noxattr"}, {Opt_directio, "directio"}, {Opt_ignoreqv, "ignoreqv"}, {Opt_cache, "cache=%s"}, {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, {Opt_posixacl, "posixacl"}, {Opt_locktimeout, "locktimeout=%u"}, {Opt_err, NULL} }; /* Interpret mount options for cache mode */ static int get_cache_mode(char *s) { int version = -EINVAL; if (!strcmp(s, "loose")) { version = CACHE_SC_LOOSE; p9_debug(P9_DEBUG_9P, "Cache mode: loose\n"); } else if (!strcmp(s, "fscache")) { version = CACHE_SC_FSCACHE; p9_debug(P9_DEBUG_9P, "Cache mode: fscache\n"); } else if (!strcmp(s, "mmap")) { version = CACHE_SC_MMAP; p9_debug(P9_DEBUG_9P, "Cache mode: mmap\n"); } else if (!strcmp(s, "readahead")) { version = CACHE_SC_READAHEAD; p9_debug(P9_DEBUG_9P, "Cache mode: readahead\n"); } else if (!strcmp(s, "none")) { version = CACHE_SC_NONE; p9_debug(P9_DEBUG_9P, "Cache mode: none\n"); } else if (kstrtoint(s, 0, &version) != 0) { version = -EINVAL; pr_info("Unknown Cache mode or invalid value %s\n", s); } return version; } /* * Display the mount options in /proc/mounts. */ int v9fs_show_options(struct seq_file *m, struct dentry *root) { struct v9fs_session_info *v9ses = root->d_sb->s_fs_info; if (v9ses->debug) seq_printf(m, ",debug=%x", v9ses->debug); if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID)) seq_printf(m, ",dfltuid=%u", from_kuid_munged(&init_user_ns, v9ses->dfltuid)); if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID)) seq_printf(m, ",dfltgid=%u", from_kgid_munged(&init_user_ns, v9ses->dfltgid)); if (v9ses->afid != ~0) seq_printf(m, ",afid=%u", v9ses->afid); if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0) seq_printf(m, ",uname=%s", v9ses->uname); if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0) seq_printf(m, ",aname=%s", v9ses->aname); if (v9ses->nodev) seq_puts(m, ",nodevmap"); if (v9ses->cache) seq_printf(m, ",cache=%x", v9ses->cache); #ifdef CONFIG_9P_FSCACHE if (v9ses->cachetag && (v9ses->cache & CACHE_FSCACHE)) seq_printf(m, ",cachetag=%s", v9ses->cachetag); #endif switch (v9ses->flags & V9FS_ACCESS_MASK) { case V9FS_ACCESS_USER: seq_puts(m, ",access=user"); break; case V9FS_ACCESS_ANY: seq_puts(m, ",access=any"); break; case V9FS_ACCESS_CLIENT: seq_puts(m, ",access=client"); break; case V9FS_ACCESS_SINGLE: seq_printf(m, ",access=%u", from_kuid_munged(&init_user_ns, v9ses->uid)); break; } if (v9ses->flags & V9FS_IGNORE_QV) seq_puts(m, ",ignoreqv"); if (v9ses->flags & V9FS_DIRECT_IO) seq_puts(m, ",directio"); if (v9ses->flags & V9FS_POSIX_ACL) seq_puts(m, ",posixacl"); if (v9ses->flags & V9FS_NO_XATTR) seq_puts(m, ",noxattr"); return p9_show_client_options(m, v9ses->clnt); } /** * v9fs_parse_options - parse mount options into session structure * @v9ses: existing v9fs session information * @opts: The mount option string * * Return 0 upon success, -ERRNO upon failure. */ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) { char *options, *tmp_options; substring_t args[MAX_OPT_ARGS]; char *p; int option = 0; char *s; int ret = 0; /* setup defaults */ v9ses->afid = ~0; v9ses->debug = 0; v9ses->cache = CACHE_NONE; #ifdef CONFIG_9P_FSCACHE v9ses->cachetag = NULL; #endif v9ses->session_lock_timeout = P9_LOCK_TIMEOUT; if (!opts) return 0; tmp_options = kstrdup(opts, GFP_KERNEL); if (!tmp_options) { ret = -ENOMEM; goto fail_option_alloc; } options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token, r; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case Opt_debug: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; } else { v9ses->debug = option; #ifdef CONFIG_NET_9P_DEBUG p9_debug_level = option; #endif } break; case Opt_dfltuid: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } v9ses->dfltuid = make_kuid(current_user_ns(), option); if (!uid_valid(v9ses->dfltuid)) { p9_debug(P9_DEBUG_ERROR, "uid field, but not a uid?\n"); ret = -EINVAL; } break; case Opt_dfltgid: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } v9ses->dfltgid = make_kgid(current_user_ns(), option); if (!gid_valid(v9ses->dfltgid)) { p9_debug(P9_DEBUG_ERROR, "gid field, but not a gid?\n"); ret = -EINVAL; } break; case Opt_afid: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; } else { v9ses->afid = option; } break; case Opt_uname: kfree(v9ses->uname); v9ses->uname = match_strdup(&args[0]); if (!v9ses->uname) { ret = -ENOMEM; goto free_and_return; } break; case Opt_remotename: kfree(v9ses->aname); v9ses->aname = match_strdup(&args[0]); if (!v9ses->aname) { ret = -ENOMEM; goto free_and_return; } break; case Opt_nodevmap: v9ses->nodev = 1; break; case Opt_noxattr: v9ses->flags |= V9FS_NO_XATTR; break; case Opt_directio: v9ses->flags |= V9FS_DIRECT_IO; break; case Opt_ignoreqv: v9ses->flags |= V9FS_IGNORE_QV; break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); v9ses->cachetag = match_strdup(&args[0]); if (!v9ses->cachetag) { ret = -ENOMEM; goto free_and_return; } #endif break; case Opt_cache: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of cache arg\n"); goto free_and_return; } r = get_cache_mode(s); if (r < 0) ret = r; else v9ses->cache = r; kfree(s); break; case Opt_access: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of access arg\n"); goto free_and_return; } v9ses->flags &= ~V9FS_ACCESS_MASK; if (strcmp(s, "user") == 0) v9ses->flags |= V9FS_ACCESS_USER; else if (strcmp(s, "any") == 0) v9ses->flags |= V9FS_ACCESS_ANY; else if (strcmp(s, "client") == 0) { v9ses->flags |= V9FS_ACCESS_CLIENT; } else { uid_t uid; v9ses->flags |= V9FS_ACCESS_SINGLE; r = kstrtouint(s, 10, &uid); if (r) { ret = r; pr_info("Unknown access argument %s: %d\n", s, r); kfree(s); continue; } v9ses->uid = make_kuid(current_user_ns(), uid); if (!uid_valid(v9ses->uid)) { ret = -EINVAL; pr_info("Unknown uid %s\n", s); } } kfree(s); break; case Opt_posixacl: #ifdef CONFIG_9P_FS_POSIX_ACL v9ses->flags |= V9FS_POSIX_ACL; #else p9_debug(P9_DEBUG_ERROR, "Not defined CONFIG_9P_FS_POSIX_ACL. Ignoring posixacl option\n"); #endif break; case Opt_locktimeout: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } if (option < 1) { p9_debug(P9_DEBUG_ERROR, "locktimeout must be a greater than zero integer.\n"); ret = -EINVAL; continue; } v9ses->session_lock_timeout = (long)option * HZ; break; default: continue; } } free_and_return: kfree(tmp_options); fail_option_alloc: return ret; } /** * v9fs_session_init - initialize session * @v9ses: session information structure * @dev_name: device being mounted * @data: options * */ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, const char *dev_name, char *data) { struct p9_fid *fid; int rc = -ENOMEM; v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL); if (!v9ses->uname) goto err_names; v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL); if (!v9ses->aname) goto err_names; init_rwsem(&v9ses->rename_sem); v9ses->uid = INVALID_UID; v9ses->dfltuid = V9FS_DEFUID; v9ses->dfltgid = V9FS_DEFGID; v9ses->clnt = p9_client_create(dev_name, data); if (IS_ERR(v9ses->clnt)) { rc = PTR_ERR(v9ses->clnt); p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n"); goto err_names; } v9ses->flags = V9FS_ACCESS_USER; if (p9_is_proto_dotl(v9ses->clnt)) { v9ses->flags = V9FS_ACCESS_CLIENT; v9ses->flags |= V9FS_PROTO_2000L; } else if (p9_is_proto_dotu(v9ses->clnt)) { v9ses->flags |= V9FS_PROTO_2000U; } rc = v9fs_parse_options(v9ses, data); if (rc < 0) goto err_clnt; v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ; if (!v9fs_proto_dotl(v9ses) && ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) { /* * We support ACCESS_CLIENT only for dotl. * Fall back to ACCESS_USER */ v9ses->flags &= ~V9FS_ACCESS_MASK; v9ses->flags |= V9FS_ACCESS_USER; } /*FIXME !! */ /* for legacy mode, fall back to V9FS_ACCESS_ANY */ if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) && ((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) { v9ses->flags &= ~V9FS_ACCESS_MASK; v9ses->flags |= V9FS_ACCESS_ANY; v9ses->uid = INVALID_UID; } if (!v9fs_proto_dotl(v9ses) || !((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) { /* * We support ACL checks on clinet only if the protocol is * 9P2000.L and access is V9FS_ACCESS_CLIENT. */ v9ses->flags &= ~V9FS_ACL_MASK; } fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID, v9ses->aname); if (IS_ERR(fid)) { rc = PTR_ERR(fid); p9_debug(P9_DEBUG_ERROR, "cannot attach\n"); goto err_clnt; } if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE) fid->uid = v9ses->uid; else fid->uid = INVALID_UID; #ifdef CONFIG_9P_FSCACHE /* register the session for caching */ if (v9ses->cache & CACHE_FSCACHE) { rc = v9fs_cache_session_get_cookie(v9ses, dev_name); if (rc < 0) goto err_clnt; } #endif spin_lock(&v9fs_sessionlist_lock); list_add(&v9ses->slist, &v9fs_sessionlist); spin_unlock(&v9fs_sessionlist_lock); return fid; err_clnt: #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); #endif p9_client_destroy(v9ses->clnt); err_names: kfree(v9ses->uname); kfree(v9ses->aname); return ERR_PTR(rc); } /** * v9fs_session_close - shutdown a session * @v9ses: session information structure * */ void v9fs_session_close(struct v9fs_session_info *v9ses) { if (v9ses->clnt) { p9_client_destroy(v9ses->clnt); v9ses->clnt = NULL; } #ifdef CONFIG_9P_FSCACHE fscache_relinquish_volume(v9fs_session_cache(v9ses), NULL, false); kfree(v9ses->cachetag); #endif kfree(v9ses->uname); kfree(v9ses->aname); spin_lock(&v9fs_sessionlist_lock); list_del(&v9ses->slist); spin_unlock(&v9fs_sessionlist_lock); } /** * v9fs_session_cancel - terminate a session * @v9ses: session to terminate * * mark transport as disconnected and cancel all pending requests. */ void v9fs_session_cancel(struct v9fs_session_info *v9ses) { p9_debug(P9_DEBUG_ERROR, "cancel session %p\n", v9ses); p9_client_disconnect(v9ses->clnt); } /** * v9fs_session_begin_cancel - Begin terminate of a session * @v9ses: session to terminate * * After this call we don't allow any request other than clunk. */ void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses) { p9_debug(P9_DEBUG_ERROR, "begin cancel session %p\n", v9ses); p9_client_begin_disconnect(v9ses->clnt); } static struct kobject *v9fs_kobj; #ifdef CONFIG_9P_FSCACHE /* * List caches associated with a session */ static ssize_t caches_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t n = 0, count = 0, limit = PAGE_SIZE; struct v9fs_session_info *v9ses; spin_lock(&v9fs_sessionlist_lock); list_for_each_entry(v9ses, &v9fs_sessionlist, slist) { if (v9ses->cachetag) { n = snprintf(buf, limit, "%s\n", v9ses->cachetag); if (n < 0) { count = n; break; } count += n; limit -= n; } } spin_unlock(&v9fs_sessionlist_lock); return count; } static struct kobj_attribute v9fs_attr_cache = __ATTR_RO(caches); #endif /* CONFIG_9P_FSCACHE */ static struct attribute *v9fs_attrs[] = { #ifdef CONFIG_9P_FSCACHE &v9fs_attr_cache.attr, #endif NULL, }; static const struct attribute_group v9fs_attr_group = { .attrs = v9fs_attrs, }; /** * v9fs_sysfs_init - Initialize the v9fs sysfs interface * */ static int __init v9fs_sysfs_init(void) { v9fs_kobj = kobject_create_and_add("9p", fs_kobj); if (!v9fs_kobj) return -ENOMEM; if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) { kobject_put(v9fs_kobj); return -ENOMEM; } return 0; } /** * v9fs_sysfs_cleanup - Unregister the v9fs sysfs interface * */ static void v9fs_sysfs_cleanup(void) { sysfs_remove_group(v9fs_kobj, &v9fs_attr_group); kobject_put(v9fs_kobj); } static void v9fs_inode_init_once(void *foo) { struct v9fs_inode *v9inode = (struct v9fs_inode *)foo; memset(&v9inode->qid, 0, sizeof(v9inode->qid)); inode_init_once(&v9inode->netfs.inode); } /** * v9fs_init_inode_cache - initialize a cache for 9P * Returns 0 on success. */ static int v9fs_init_inode_cache(void) { v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache", sizeof(struct v9fs_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), v9fs_inode_init_once); if (!v9fs_inode_cache) return -ENOMEM; return 0; } /** * v9fs_destroy_inode_cache - destroy the cache of 9P inode * */ static void v9fs_destroy_inode_cache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(v9fs_inode_cache); } static int v9fs_cache_register(void) { int ret; ret = v9fs_init_inode_cache(); if (ret < 0) return ret; return ret; } static void v9fs_cache_unregister(void) { v9fs_destroy_inode_cache(); } /** * init_v9fs - Initialize module * */ static int __init init_v9fs(void) { int err; pr_info("Installing v9fs 9p2000 file system support\n"); /* TODO: Setup list of registered trasnport modules */ err = v9fs_cache_register(); if (err < 0) { pr_err("Failed to register v9fs for caching\n"); return err; } err = v9fs_sysfs_init(); if (err < 0) { pr_err("Failed to register with sysfs\n"); goto out_cache; } err = register_filesystem(&v9fs_fs_type); if (err < 0) { pr_err("Failed to register filesystem\n"); goto out_sysfs_cleanup; } return 0; out_sysfs_cleanup: v9fs_sysfs_cleanup(); out_cache: v9fs_cache_unregister(); return err; } /** * exit_v9fs - shutdown module * */ static void __exit exit_v9fs(void) { v9fs_sysfs_cleanup(); v9fs_cache_unregister(); unregister_filesystem(&v9fs_fs_type); } module_init(init_v9fs) module_exit(exit_v9fs) MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>"); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>"); MODULE_DESCRIPTION("9P Client File System"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 1 1 1 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_generic.c Generic packet scheduler routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Jamal Hadi Salim, <hadi@cyberus.ca> 990601 * - Ingress support */ #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/if_vlan.h> #include <linux/skb_array.h> #include <linux/if_macvlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> #include <net/hotdata.h> #include <trace/events/qdisc.h> #include <trace/events/net.h> #include <net/xfrm.h> /* Qdisc to use by default */ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; EXPORT_SYMBOL(default_qdisc_ops); static void qdisc_maybe_clear_missed(struct Qdisc *q, const struct netdev_queue *txq) { clear_bit(__QDISC_STATE_MISSED, &q->state); /* Make sure the below netif_xmit_frozen_or_stopped() * checking happens after clearing STATE_MISSED. */ smp_mb__after_atomic(); /* Checking netif_xmit_frozen_or_stopped() again to * make sure STATE_MISSED is set if the STATE_MISSED * set by netif_tx_wake_queue()'s rescheduling of * net_tx_action() is cleared by the above clear_bit(). */ if (!netif_xmit_frozen_or_stopped(txq)) set_bit(__QDISC_STATE_MISSED, &q->state); else set_bit(__QDISC_STATE_DRAINING, &q->state); } /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with * qdisc_lock(qdisc) spinlock. * * The idea is the following: * - enqueue, dequeue are serialized via qdisc root lock * - ingress filtering is also serialized via qdisc root lock * - updates to tree and tree walking are only done under the rtnl mutex. */ #define SKB_XOFF_MAGIC ((struct sk_buff *)1UL) static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) { const struct netdev_queue *txq = q->dev_queue; spinlock_t *lock = NULL; struct sk_buff *skb; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } skb = skb_peek(&q->skb_bad_txq); if (skb) { /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { skb = __skb_dequeue(&q->skb_bad_txq); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; } } else { skb = SKB_XOFF_MAGIC; qdisc_maybe_clear_missed(q, txq); } } if (lock) spin_unlock(lock); return skb; } static inline struct sk_buff *qdisc_dequeue_skb_bad_txq(struct Qdisc *q) { struct sk_buff *skb = skb_peek(&q->skb_bad_txq); if (unlikely(skb)) skb = __skb_dequeue_bad_txq(q); return skb; } static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, struct sk_buff *skb) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } __skb_queue_tail(&q->skb_bad_txq, skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_inc(q, skb); qdisc_qstats_cpu_qlen_inc(q); } else { qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; } if (lock) spin_unlock(lock); } static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } while (skb) { struct sk_buff *next = skb->next; __skb_queue_tail(&q->gso_skb, skb); /* it's still part of the queue */ if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_requeues_inc(q); qdisc_qstats_cpu_backlog_inc(q, skb); qdisc_qstats_cpu_qlen_inc(q); } else { q->qstats.requeues++; qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; } skb = next; } if (lock) { spin_unlock(lock); set_bit(__QDISC_STATE_MISSED, &q->state); } else { __netif_schedule(q); } } static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, int *packets) { int bytelimit = qdisc_avail_bulklimit(txq) - skb->len; while (bytelimit > 0) { struct sk_buff *nskb = q->dequeue(q); if (!nskb) break; bytelimit -= nskb->len; /* covers GSO len */ skb->next = nskb; skb = nskb; (*packets)++; /* GSO counts as one pkt */ } skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure * all skbs in the chain are for the same txq */ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, struct sk_buff *skb, int *packets) { int mapping = skb_get_queue_mapping(skb); struct sk_buff *nskb; int cnt = 0; do { nskb = q->dequeue(q); if (!nskb) break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { qdisc_enqueue_skb_bad_txq(q, nskb); break; } skb->next = nskb; skb = nskb; } while (++cnt < 8); (*packets) += cnt; skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). * A requeued skb (via q->gso_skb) can also be a SKB list. */ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, int *packets) { const struct netdev_queue *txq = q->dev_queue; struct sk_buff *skb = NULL; *packets = 1; if (unlikely(!skb_queue_empty(&q->gso_skb))) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } skb = skb_peek(&q->gso_skb); /* skb may be null if another cpu pulls gso_skb off in between * empty check and lock. */ if (!skb) { if (lock) spin_unlock(lock); goto validate; } /* skb in gso_skb were already validated */ *validate = false; if (xfrm_offload(skb)) *validate = true; /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { skb = __skb_dequeue(&q->gso_skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; } } else { skb = NULL; qdisc_maybe_clear_missed(q, txq); } if (lock) spin_unlock(lock); goto trace; } validate: *validate = true; if ((q->flags & TCQ_F_ONETXQUEUE) && netif_xmit_frozen_or_stopped(txq)) { qdisc_maybe_clear_missed(q, txq); return skb; } skb = qdisc_dequeue_skb_bad_txq(q); if (unlikely(skb)) { if (skb == SKB_XOFF_MAGIC) return NULL; goto bulk; } skb = q->dequeue(q); if (skb) { bulk: if (qdisc_may_bulk(q)) try_bulk_dequeue_skb(q, skb, txq, packets); else try_bulk_dequeue_skb_slow(q, skb, packets); } trace: trace_qdisc_dequeue(q, txq, *packets, skb); return skb; } /* * Transmit possibly several skbs, and handle the return status as * required. Owning qdisc running bit guarantees that only one CPU * can execute this function. * * Returns to the caller: * false - hardware queue frozen backoff * true - feel free to send more pkts */ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate) { int ret = NETDEV_TX_BUSY; bool again = false; /* And release qdisc */ if (root_lock) spin_unlock(root_lock); /* Note that we validate skb (GSO, checksum, ...) outside of locks */ if (validate) skb = validate_xmit_skb_list(skb, dev, &again); #ifdef CONFIG_XFRM_OFFLOAD if (unlikely(again)) { if (root_lock) spin_lock(root_lock); dev_requeue_skb(skb, q); return false; } #endif if (likely(skb)) { HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); else qdisc_maybe_clear_missed(q, txq); HARD_TX_UNLOCK(dev, txq); } else { if (root_lock) spin_lock(root_lock); return true; } if (root_lock) spin_lock(root_lock); if (!dev_xmit_complete(ret)) { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely(ret != NETDEV_TX_BUSY)) net_warn_ratelimited("BUG %s code %d qlen %d\n", dev->name, ret, q->q.qlen); dev_requeue_skb(skb, q); return false; } return true; } /* * NOTE: Called under qdisc_lock(q) with locally disabled BH. * * running seqcount guarantees only one CPU can process * this qdisc at a time. qdisc_lock(q) serializes queue accesses for * this queue. * * netif_tx_lock serializes accesses to device driver. * * qdisc_lock(q) and netif_tx_lock are mutually exclusive, * if one is grabbed, another must be free. * * Note, that this procedure can be called by a watchdog timer * * Returns to the caller: * 0 - queue is empty or throttled. * >0 - queue is not empty. * */ static inline bool qdisc_restart(struct Qdisc *q, int *packets) { spinlock_t *root_lock = NULL; struct netdev_queue *txq; struct net_device *dev; struct sk_buff *skb; bool validate; /* Dequeue packet */ skb = dequeue_skb(q, &validate, packets); if (unlikely(!skb)) return false; if (!(q->flags & TCQ_F_NOLOCK)) root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = skb_get_tx_queue(dev, skb); return sch_direct_xmit(skb, q, dev, txq, root_lock, validate); } void __qdisc_run(struct Qdisc *q) { int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { quota -= packets; if (quota <= 0) { if (q->flags & TCQ_F_NOLOCK) set_bit(__QDISC_STATE_MISSED, &q->state); else __netif_schedule(q); break; } } } unsigned long dev_trans_start(struct net_device *dev) { unsigned long res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start); unsigned long val; unsigned int i; for (i = 1; i < dev->num_tx_queues; i++) { val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start); if (val && time_after(val, res)) res = val; } return res; } EXPORT_SYMBOL(dev_trans_start); static void netif_freeze_queues(struct net_device *dev) { unsigned int i; int cpu; cpu = smp_processor_id(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* We are the only thread of execution doing a * freeze, but we have to grab the _xmit_lock in * order to synchronize with threads which are in * the ->hard_start_xmit() handler and already * checked the frozen bit. */ __netif_tx_lock(txq, cpu); set_bit(__QUEUE_STATE_FROZEN, &txq->state); __netif_tx_unlock(txq); } } void netif_tx_lock(struct net_device *dev) { spin_lock(&dev->tx_global_lock); netif_freeze_queues(dev); } EXPORT_SYMBOL(netif_tx_lock); static void netif_unfreeze_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* No need to grab the _xmit_lock here. If the * queue is not stopped for another reason, we * force a schedule. */ clear_bit(__QUEUE_STATE_FROZEN, &txq->state); netif_schedule_queue(txq); } } void netif_tx_unlock(struct net_device *dev) { netif_unfreeze_queues(dev); spin_unlock(&dev->tx_global_lock); } EXPORT_SYMBOL(netif_tx_unlock); static void dev_watchdog(struct timer_list *t) { struct net_device *dev = from_timer(dev, t, watchdog_timer); bool release = true; spin_lock(&dev->tx_global_lock); if (!qdisc_tx_is_noop(dev)) { if (netif_device_present(dev) && netif_running(dev) && netif_carrier_ok(dev)) { unsigned int timedout_ms = 0; unsigned int i; unsigned long trans_start; unsigned long oldest_start = jiffies; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); trans_start = READ_ONCE(txq->trans_start); if (!netif_xmit_stopped(txq)) continue; if (time_after(jiffies, trans_start + dev->watchdog_timeo)) { timedout_ms = jiffies_to_msecs(jiffies - trans_start); atomic_long_inc(&txq->trans_timeout); break; } if (time_after(oldest_start, trans_start)) oldest_start = trans_start; } if (unlikely(timedout_ms)) { trace_net_dev_xmit_timeout(dev, i); netdev_crit(dev, "NETDEV WATCHDOG: CPU: %d: transmit queue %u timed out %u ms\n", raw_smp_processor_id(), i, timedout_ms); netif_freeze_queues(dev); dev->netdev_ops->ndo_tx_timeout(dev, i); netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(oldest_start + dev->watchdog_timeo))) release = false; } } spin_unlock(&dev->tx_global_lock); if (release) netdev_put(dev, &dev->watchdog_dev_tracker); } void __netdev_watchdog_up(struct net_device *dev) { if (dev->netdev_ops->ndo_tx_timeout) { if (dev->watchdog_timeo <= 0) dev->watchdog_timeo = 5*HZ; if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) netdev_hold(dev, &dev->watchdog_dev_tracker, GFP_ATOMIC); } } EXPORT_SYMBOL_GPL(__netdev_watchdog_up); static void dev_watchdog_up(struct net_device *dev) { __netdev_watchdog_up(dev); } static void dev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); if (del_timer(&dev->watchdog_timer)) netdev_put(dev, &dev->watchdog_dev_tracker); netif_tx_unlock_bh(dev); } /** * netif_carrier_on - set carrier * @dev: network device * * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_up_count); linkwatch_fire_event(dev); if (netif_running(dev)) __netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_carrier_on); /** * netif_carrier_off - clear carrier * @dev: network device * * Device has detected loss of carrier. */ void netif_carrier_off(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } } EXPORT_SYMBOL(netif_carrier_off); /** * netif_carrier_event - report carrier state event * @dev: network device * * Device has detected a carrier event but the carrier state wasn't changed. * Use in drivers when querying carrier state asynchronously, to avoid missing * events (link flaps) if link recovers before it's queried. */ void netif_carrier_event(struct net_device *dev) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_up_count); atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } EXPORT_SYMBOL_GPL(netif_carrier_event); /* "NOOP" scheduler: the best scheduler, recommended for all interfaces under all circumstances. It is difficult to invent anything faster or cheaper. */ static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { dev_core_stats_tx_dropped_inc(skb->dev); __qdisc_drop(skb, to_free); return NET_XMIT_CN; } static struct sk_buff *noop_dequeue(struct Qdisc *qdisc) { return NULL; } struct Qdisc_ops noop_qdisc_ops __read_mostly = { .id = "noop", .priv_size = 0, .enqueue = noop_enqueue, .dequeue = noop_dequeue, .peek = noop_dequeue, .owner = THIS_MODULE, }; static struct netdev_queue noop_netdev_queue = { RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), RCU_POINTER_INITIALIZER(qdisc_sleeping, &noop_qdisc), }; struct Qdisc noop_qdisc = { .enqueue = noop_enqueue, .dequeue = noop_dequeue, .flags = TCQ_F_BUILTIN, .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, .prev = (struct sk_buff *)&noop_qdisc.gso_skb, .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock), }, .skb_bad_txq = { .next = (struct sk_buff *)&noop_qdisc.skb_bad_txq, .prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq, .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), }, .owner = -1, }; EXPORT_SYMBOL(noop_qdisc); static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt, struct netlink_ext_ack *extack) { /* register_qdisc() assigns a default of noop_enqueue if unset, * but __dev_queue_xmit() treats noqueue only as such * if this is NULL - so clear it here. */ qdisc->enqueue = NULL; return 0; } struct Qdisc_ops noqueue_qdisc_ops __read_mostly = { .id = "noqueue", .priv_size = 0, .init = noqueue_init, .enqueue = noop_enqueue, .dequeue = noop_dequeue, .peek = noop_dequeue, .owner = THIS_MODULE, }; const u8 sch_default_prio2band[TC_PRIO_MAX + 1] = { 1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1 }; EXPORT_SYMBOL(sch_default_prio2band); /* 3-band FIFO queue: old style, but should be a bit faster than generic prio+fifo combination. */ #define PFIFO_FAST_BANDS 3 /* * Private data for a pfifo_fast scheduler containing: * - rings for priority bands */ struct pfifo_fast_priv { struct skb_array q[PFIFO_FAST_BANDS]; }; static inline struct skb_array *band2list(struct pfifo_fast_priv *priv, int band) { return &priv->q[band]; } static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { int band = sch_default_prio2band[skb->priority & TC_PRIO_MAX]; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct skb_array *q = band2list(priv, band); unsigned int pkt_len = qdisc_pkt_len(skb); int err; err = skb_array_produce(q, skb); if (unlikely(err)) { if (qdisc_is_percpu_stats(qdisc)) return qdisc_drop_cpu(skb, qdisc, to_free); else return qdisc_drop(skb, qdisc, to_free); } qdisc_update_stats_at_enqueue(qdisc, pkt_len); return NET_XMIT_SUCCESS; } static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; bool need_retry = true; int band; retry: for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); if (__skb_array_empty(q)) continue; skb = __skb_array_consume(q); } if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else if (need_retry && READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) { /* Delay clearing the STATE_MISSED here to reduce * the overhead of the second spin_trylock() in * qdisc_run_begin() and __netif_schedule() calling * in qdisc_run_end(). */ clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); /* Make sure dequeuing happens after clearing * STATE_MISSED. */ smp_mb__after_atomic(); need_retry = false; goto retry; } return skb; } static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; int band; for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); skb = __skb_array_peek(q); } return skb; } static void pfifo_fast_reset(struct Qdisc *qdisc) { int i, band; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); for (band = 0; band < PFIFO_FAST_BANDS; band++) { struct skb_array *q = band2list(priv, band); struct sk_buff *skb; /* NULL ring is possible if destroy path is due to a failed * skb_array_init() in pfifo_fast_init() case. */ if (!q->ring.queue) continue; while ((skb = __skb_array_consume(q)) != NULL) kfree_skb(skb); } if (qdisc_is_percpu_stats(qdisc)) { for_each_possible_cpu(i) { struct gnet_stats_queue *q; q = per_cpu_ptr(qdisc->cpu_qstats, i); q->backlog = 0; q->qlen = 0; } } } static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; memcpy(&opt.priomap, sch_default_prio2band, TC_PRIO_MAX + 1); if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt, struct netlink_ext_ack *extack) { unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int prio; /* guard against zero length rings */ if (!qlen) return -EINVAL; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); int err; err = skb_array_init(q, qlen, GFP_KERNEL); if (err) return -ENOMEM; } /* Can by-pass the queue discipline */ qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } static void pfifo_fast_destroy(struct Qdisc *sch) { struct pfifo_fast_priv *priv = qdisc_priv(sch); int prio; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); /* NULL ring is possible if destroy path is due to a failed * skb_array_init() in pfifo_fast_init() case. */ if (!q->ring.queue) continue; /* Destroy ring but no need to kfree_skb because a call to * pfifo_fast_reset() has already done that work. */ ptr_ring_cleanup(&q->ring, NULL); } } static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch, unsigned int new_len) { struct pfifo_fast_priv *priv = qdisc_priv(sch); struct skb_array *bands[PFIFO_FAST_BANDS]; int prio; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); bands[prio] = q; } return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len, GFP_KERNEL); } struct Qdisc_ops pfifo_fast_ops __read_mostly = { .id = "pfifo_fast", .priv_size = sizeof(struct pfifo_fast_priv), .enqueue = pfifo_fast_enqueue, .dequeue = pfifo_fast_dequeue, .peek = pfifo_fast_peek, .init = pfifo_fast_init, .destroy = pfifo_fast_destroy, .reset = pfifo_fast_reset, .dump = pfifo_fast_dump, .change_tx_queue_len = pfifo_fast_change_tx_queue_len, .owner = THIS_MODULE, .static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS, }; EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) { struct Qdisc *sch; unsigned int size = sizeof(*sch) + ops->priv_size; int err = -ENOBUFS; struct net_device *dev; if (!dev_queue) { NL_SET_ERR_MSG(extack, "No device queue given"); err = -EINVAL; goto errout; } dev = dev_queue->dev; sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); if (!sch) goto errout; __skb_queue_head_init(&sch->gso_skb); __skb_queue_head_init(&sch->skb_bad_txq); gnet_stats_basic_sync_init(&sch->bstats); lockdep_register_key(&sch->root_lock_key); spin_lock_init(&sch->q.lock); lockdep_set_class(&sch->q.lock, &sch->root_lock_key); if (ops->static_flags & TCQ_F_CPUSTATS) { sch->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!sch->cpu_bstats) goto errout1; sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!sch->cpu_qstats) { free_percpu(sch->cpu_bstats); goto errout1; } } spin_lock_init(&sch->busylock); lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); sch->ops = ops; sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; sch->owner = -1; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); return sch; errout1: lockdep_unregister_key(&sch->root_lock_key); kfree(sch); errout: return ERR_PTR(err); } struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, unsigned int parentid, struct netlink_ext_ack *extack) { struct Qdisc *sch; if (!try_module_get(ops->owner)) { NL_SET_ERR_MSG(extack, "Failed to increase module reference counter"); return NULL; } sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { module_put(ops->owner); return NULL; } sch->parent = parentid; if (!ops->init || ops->init(sch, NULL, extack) == 0) { trace_qdisc_create(ops, dev_queue->dev, parentid); return sch; } qdisc_put(sch); return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); /* Under qdisc_lock(qdisc) and BH! */ void qdisc_reset(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; trace_qdisc_reset(qdisc); if (ops->reset) ops->reset(qdisc); __skb_queue_purge(&qdisc->gso_skb); __skb_queue_purge(&qdisc->skb_bad_txq); qdisc->q.qlen = 0; qdisc->qstats.backlog = 0; } EXPORT_SYMBOL(qdisc_reset); void qdisc_free(struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); free_percpu(qdisc->cpu_qstats); } kfree(qdisc); } static void qdisc_free_cb(struct rcu_head *head) { struct Qdisc *q = container_of(head, struct Qdisc, rcu); qdisc_free(q); } static void __qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; struct net_device *dev = qdisc_dev(qdisc); #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); qdisc_put_stab(rtnl_dereference(qdisc->stab)); #endif gen_kill_estimator(&qdisc->rate_est); qdisc_reset(qdisc); if (ops->destroy) ops->destroy(qdisc); lockdep_unregister_key(&qdisc->root_lock_key); module_put(ops->owner); netdev_put(dev, &qdisc->dev_tracker); trace_qdisc_destroy(qdisc); call_rcu(&qdisc->rcu, qdisc_free_cb); } void qdisc_destroy(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; __qdisc_destroy(qdisc); } void qdisc_put(struct Qdisc *qdisc) { if (!qdisc) return; if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_test(&qdisc->refcnt)) return; __qdisc_destroy(qdisc); } EXPORT_SYMBOL(qdisc_put); /* Version of qdisc_put() that is called with rtnl mutex unlocked. * Intended to be used as optimization, this function only takes rtnl lock if * qdisc reference counter reached zero. */ void qdisc_put_unlocked(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) return; __qdisc_destroy(qdisc); rtnl_unlock(); } EXPORT_SYMBOL(qdisc_put_unlocked); /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { struct Qdisc *oqdisc = rtnl_dereference(dev_queue->qdisc_sleeping); spinlock_t *root_lock; root_lock = qdisc_lock(oqdisc); spin_lock_bh(root_lock); /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); spin_unlock_bh(root_lock); return oqdisc; } EXPORT_SYMBOL(dev_graft_qdisc); static void shutdown_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { rcu_assign_pointer(dev_queue->qdisc, qdisc_default); rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc_default); qdisc_put(qdisc); } } static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { struct Qdisc *qdisc; const struct Qdisc_ops *ops = default_qdisc_ops; if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; else if(dev->type == ARPHRD_CAN) ops = &pfifo_fast_ops; qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); if (!qdisc) return; if (!netif_is_multiqueue(dev)) qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } static void attach_default_qdiscs(struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; txq = netdev_get_tx_queue(dev, 0); if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); if (qdisc) { rcu_assign_pointer(dev->qdisc, qdisc); qdisc->ops->attach(qdisc); } } qdisc = rtnl_dereference(dev->qdisc); /* Detect default qdisc setup/init failed and fallback to "noqueue" */ if (qdisc == &noop_qdisc) { netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n", default_qdisc_ops->id, noqueue_qdisc_ops.id); netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; } #ifdef CONFIG_NET_SCHED if (qdisc != &noop_qdisc) qdisc_hash_add(qdisc, false); #endif } static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) { struct Qdisc *new_qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); int *need_watchdog_p = _need_watchdog; if (!(new_qdisc->flags & TCQ_F_BUILTIN)) clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p) { WRITE_ONCE(dev_queue->trans_start, 0); *need_watchdog_p = 1; } } void dev_activate(struct net_device *dev) { int need_watchdog; /* No queueing discipline is attached to device; * create default one for devices, which need queueing * and noqueue_qdisc for virtual interfaces */ if (rtnl_dereference(dev->qdisc) == &noop_qdisc) attach_default_qdiscs(dev); if (!netif_carrier_ok(dev)) /* Delay activation until next carrier-on event */ return; need_watchdog = 0; netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog); if (dev_ingress_queue(dev)) transition_one_qdisc(dev, dev_ingress_queue(dev), NULL); if (need_watchdog) { netif_trans_update(dev); dev_watchdog_up(dev); } } EXPORT_SYMBOL(dev_activate); static void qdisc_deactivate(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); } static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { struct Qdisc *qdisc_default = _qdisc_default; struct Qdisc *qdisc; qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { qdisc_deactivate(qdisc); rcu_assign_pointer(dev_queue->qdisc, qdisc_default); } } static void dev_reset_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { struct Qdisc *qdisc; bool nolock; qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); if (!qdisc) return; nolock = qdisc->flags & TCQ_F_NOLOCK; if (nolock) spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; spinlock_t *root_lock; struct Qdisc *q; int val; dev_queue = netdev_get_tx_queue(dev, i); q = rtnl_dereference(dev_queue->qdisc_sleeping); root_lock = qdisc_lock(q); spin_lock_bh(root_lock); val = (qdisc_is_running(q) || test_bit(__QDISC_STATE_SCHED, &q->state)); spin_unlock_bh(root_lock); if (val) return true; } return false; } /** * dev_deactivate_many - deactivate transmissions on several devices * @head: list of devices to deactivate * * This function returns only when all outstanding transmissions * have completed, unless all devices are in dismantle phase. */ void dev_deactivate_many(struct list_head *head) { struct net_device *dev; list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_deactivate_queue(dev, dev_ingress_queue(dev), &noop_qdisc); dev_watchdog_down(dev); } /* Wait for outstanding qdisc-less dev_queue_xmit calls or * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net(); list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); if (dev_ingress_queue(dev)) dev_reset_queue(dev, dev_ingress_queue(dev), NULL); } /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) { /* wait_event() would avoid this sleep-loop but would * require expensive checks in the fast paths of packet * processing which isn't worth it. */ schedule_timeout_uninterruptible(1); } } } void dev_deactivate(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); dev_deactivate_many(&single); list_del(&single); } EXPORT_SYMBOL(dev_deactivate); static int qdisc_change_tx_queue_len(struct net_device *dev, struct netdev_queue *dev_queue) { struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); const struct Qdisc_ops *ops = qdisc->ops; if (ops->change_tx_queue_len) return ops->change_tx_queue_len(qdisc, dev->tx_queue_len); return 0; } void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx) { struct Qdisc *qdisc = rtnl_dereference(dev->qdisc); if (qdisc->ops->change_real_num_tx) qdisc->ops->change_real_num_tx(qdisc, new_real_tx); } void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) { #ifdef CONFIG_NET_SCHED struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int i; for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); /* Only update the default qdiscs we created, * qdiscs with handles are always hashed. */ if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_del(qdisc); } for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_add(qdisc, false); } #endif } EXPORT_SYMBOL(mq_change_real_num_tx); int dev_qdisc_change_tx_queue_len(struct net_device *dev) { bool up = dev->flags & IFF_UP; unsigned int i; int ret = 0; if (up) dev_deactivate(dev); for (i = 0; i < dev->num_tx_queues; i++) { ret = qdisc_change_tx_queue_len(dev, &dev->_tx[i]); /* TODO: revert changes on a partial failure */ if (ret) break; } if (up) dev_activate(dev); return ret; } static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc) { struct Qdisc *qdisc = _qdisc; rcu_assign_pointer(dev_queue->qdisc, qdisc); rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } void dev_init_scheduler(struct net_device *dev) { rcu_assign_pointer(dev->qdisc, &noop_qdisc); netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); qdisc_put(rtnl_dereference(dev->qdisc)); rcu_assign_pointer(dev->qdisc, &noop_qdisc); WARN_ON(timer_pending(&dev->watchdog_timer)); } /** * psched_ratecfg_precompute__() - Pre-compute values for reciprocal division * @rate: Rate to compute reciprocal division values of * @mult: Multiplier for reciprocal division * @shift: Shift for reciprocal division * * The multiplier and shift for reciprocal division by rate are stored * in mult and shift. * * The deal here is to replace a divide by a reciprocal one * in fast path (a reciprocal divide is a multiply and a shift) * * Normal formula would be : * time_in_ns = (NSEC_PER_SEC * len) / rate_bps * * We compute mult/shift to use instead : * time_in_ns = (len * mult) >> shift; * * We try to get the highest possible mult value for accuracy, * but have to make sure no overflows will ever happen. * * reciprocal_value() is not used here it doesn't handle 64-bit values. */ static void psched_ratecfg_precompute__(u64 rate, u32 *mult, u8 *shift) { u64 factor = NSEC_PER_SEC; *mult = 1; *shift = 0; if (rate <= 0) return; for (;;) { *mult = div64_u64(factor, rate); if (*mult & (1U << 31) || factor & (1ULL << 63)) break; factor <<= 1; (*shift)++; } } void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64) { memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; r->mpu = conf->mpu; r->rate_bytes_ps = max_t(u64, conf->rate, rate64); r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift); } EXPORT_SYMBOL(psched_ratecfg_precompute); void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64) { r->rate_pkts_ps = pktrate64; psched_ratecfg_precompute__(r->rate_pkts_ps, &r->mult, &r->shift); } EXPORT_SYMBOL(psched_ppscfg_precompute); void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head) { /* Protected with chain0->filter_chain_lock. * Can't access chain directly because tp_head can be NULL. */ struct mini_Qdisc *miniq_old = rcu_dereference_protected(*miniqp->p_miniq, 1); struct mini_Qdisc *miniq; if (!tp_head) { RCU_INIT_POINTER(*miniqp->p_miniq, NULL); } else { miniq = miniq_old != &miniqp->miniq1 ? &miniqp->miniq1 : &miniqp->miniq2; /* We need to make sure that readers won't see the miniq * we are about to modify. So ensure that at least one RCU * grace period has elapsed since the miniq was made * inactive. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) cond_synchronize_rcu(miniq->rcu_state); else if (!poll_state_synchronize_rcu(miniq->rcu_state)) synchronize_rcu_expedited(); miniq->filter_list = tp_head; rcu_assign_pointer(*miniqp->p_miniq, miniq); } if (miniq_old) /* This is counterpart of the rcu sync above. We need to * block potential new user of miniq_old until all readers * are not seeing it. */ miniq_old->rcu_state = start_poll_synchronize_rcu(); } EXPORT_SYMBOL(mini_qdisc_pair_swap); void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block) { miniqp->miniq1.block = block; miniqp->miniq2.block = block; } EXPORT_SYMBOL(mini_qdisc_pair_block_init); void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq) { miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats; miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats; miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats; miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats; miniqp->miniq1.rcu_state = get_state_synchronize_rcu(); miniqp->miniq2.rcu_state = miniqp->miniq1.rcu_state; miniqp->p_miniq = p_miniq; } EXPORT_SYMBOL(mini_qdisc_pair_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <net/net_namespace.h> #include <linux/if_arp.h> #include <net/rtnetlink.h> static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev) { dev_lstats_add(dev, skb->len); dev_kfree_skb(skb); return NETDEV_TX_OK; } struct nlmon { struct netlink_tap nt; }; static int nlmon_open(struct net_device *dev) { struct nlmon *nlmon = netdev_priv(dev); nlmon->nt.dev = dev; nlmon->nt.module = THIS_MODULE; return netlink_add_tap(&nlmon->nt); } static int nlmon_close(struct net_device *dev) { struct nlmon *nlmon = netdev_priv(dev); return netlink_remove_tap(&nlmon->nt); } static void nlmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { dev_lstats_read(dev, &stats->rx_packets, &stats->rx_bytes); } static u32 always_on(struct net_device *dev) { return 1; } static const struct ethtool_ops nlmon_ethtool_ops = { .get_link = always_on, }; static const struct net_device_ops nlmon_ops = { .ndo_open = nlmon_open, .ndo_stop = nlmon_close, .ndo_start_xmit = nlmon_xmit, .ndo_get_stats64 = nlmon_get_stats64, }; static void nlmon_setup(struct net_device *dev) { dev->type = ARPHRD_NETLINK; dev->priv_flags |= IFF_NO_QUEUE; dev->netdev_ops = &nlmon_ops; dev->ethtool_ops = &nlmon_ethtool_ops; dev->needs_free_netdev = true; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_LLTX; dev->flags = IFF_NOARP; dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS; /* That's rather a softlimit here, which, of course, * can be altered. Not a real MTU, but what is to be * expected in most cases. */ dev->mtu = NLMSG_GOODSIZE; dev->min_mtu = sizeof(struct nlmsghdr); } static int nlmon_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) return -EINVAL; return 0; } static struct rtnl_link_ops nlmon_link_ops __read_mostly = { .kind = "nlmon", .priv_size = sizeof(struct nlmon), .setup = nlmon_setup, .validate = nlmon_validate, }; static __init int nlmon_register(void) { return rtnl_link_register(&nlmon_link_ops); } static __exit void nlmon_unregister(void) { rtnl_link_unregister(&nlmon_link_ops); } module_init(nlmon_register); module_exit(nlmon_unregister); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_AUTHOR("Mathieu Geli <geli@enseirb.fr>"); MODULE_DESCRIPTION("Netlink monitoring device"); MODULE_ALIAS_RTNL_LINK("nlmon"); |
| 818 813 3 3 907 905 927 45 914 913 930 876 286 45 912 907 3 909 905 3 239 239 855 4 862 3 859 862 85 85 85 240 238 2 859 860 859 859 3 853 270 108 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 | // SPDX-License-Identifier: GPL-2.0 /* * Interface between ext4 and JBD */ #include "ext4_jbd2.h" #include <trace/events/ext4.h> int ext4_inode_journal_mode(struct inode *inode) { if (EXT4_JOURNAL(inode) == NULL) return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ /* We do not support data journalling with delayed allocation */ if (!S_ISREG(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) || test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) && !test_opt(inode->i_sb, DELALLOC))) { /* We do not support data journalling for encrypted data */ if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */ } if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ BUG(); } /* Just increment the non-pointer handle value */ static handle_t *ext4_get_nojournal(void) { handle_t *handle = current->journal_info; unsigned long ref_cnt = (unsigned long)handle; BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT); ref_cnt++; handle = (handle_t *)ref_cnt; current->journal_info = handle; return handle; } /* Decrement the non-pointer handle value */ static void ext4_put_nojournal(handle_t *handle) { unsigned long ref_cnt = (unsigned long)handle; BUG_ON(ref_cnt == 0); ref_cnt--; handle = (handle_t *)ref_cnt; current->journal_info = handle; } /* * Wrappers for jbd2_journal_start/end. */ static int ext4_journal_check_start(struct super_block *sb) { journal_t *journal; might_sleep(); if (unlikely(ext4_forced_shutdown(sb))) return -EIO; if (WARN_ON_ONCE(sb_rdonly(sb))) return -EROFS; WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; /* * Special case here: if the journal has aborted behind our * backs (eg. EIO in the commit thread), then we still need to * take the FS itself readonly cleanly. */ if (journal && is_journal_aborted(journal)) { ext4_abort(sb, -journal->j_errno, "Detected aborted journal"); return -EROFS; } return 0; } handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { journal_t *journal; int err; if (inode) trace_ext4_journal_start_inode(inode, blocks, rsv_blocks, revoke_creds, type, _RET_IP_); else trace_ext4_journal_start_sb(sb, blocks, rsv_blocks, revoke_creds, type, _RET_IP_); err = ext4_journal_check_start(sb); if (err < 0) return ERR_PTR(err); journal = EXT4_SB(sb)->s_journal; if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return ext4_get_nojournal(); return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds, GFP_NOFS, type, line); } int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) { struct super_block *sb; int err; int rc; if (!ext4_handle_valid(handle)) { ext4_put_nojournal(handle); return 0; } err = handle->h_err; if (!handle->h_transaction) { rc = jbd2_journal_stop(handle); return err ? err : rc; } sb = handle->h_transaction->t_journal->j_private; rc = jbd2_journal_stop(handle); if (!err) err = rc; if (err) __ext4_std_error(sb, where, line, err); return err; } handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type) { struct super_block *sb; int err; if (!ext4_handle_valid(handle)) return ext4_get_nojournal(); sb = handle->h_journal->j_private; trace_ext4_journal_start_reserved(sb, jbd2_handle_buffer_credits(handle), _RET_IP_); err = ext4_journal_check_start(sb); if (err < 0) { jbd2_journal_free_reserved(handle); return ERR_PTR(err); } err = jbd2_journal_start_reserved(handle, type, line); if (err < 0) return ERR_PTR(err); return handle; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred) { if (!ext4_handle_valid(handle)) return 0; if (is_handle_aborted(handle)) return -EROFS; if (jbd2_handle_buffer_credits(handle) >= check_cred && handle->h_revoke_credits >= revoke_cred) return 0; extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle)); revoke_cred = max(0, revoke_cred - handle->h_revoke_credits); return ext4_journal_extend(handle, extend_cred, revoke_cred); } static void ext4_journal_abort_handle(const char *caller, unsigned int line, const char *err_fn, struct buffer_head *bh, handle_t *handle, int err) { char nbuf[16]; const char *errstr = ext4_decode_error(NULL, err, nbuf); BUG_ON(!ext4_handle_valid(handle)); if (bh) BUFFER_TRACE(bh, "abort"); if (!handle->h_err) handle->h_err = err; if (is_handle_aborted(handle)) return; printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n", caller, line, errstr, err_fn); jbd2_journal_abort_handle(handle); } static void ext4_check_bdev_write_error(struct super_block *sb) { struct address_space *mapping = sb->s_bdev->bd_mapping; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; /* * If the block device has write error flag, it may have failed to * async write out metadata buffers in the background. In this case, * we could read old data from disk and write it out again, which * may lead to on-disk filesystem inconsistency. */ if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) { spin_lock(&sbi->s_bdev_wb_lock); err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err); spin_unlock(&sbi->s_bdev_wb_lock); if (err) ext4_error_err(sb, -err, "Error while async write back metadata"); } } int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type) { int err; might_sleep(); if (ext4_handle_valid(handle)) { err = jbd2_journal_get_write_access(handle, bh); if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); return err; } } else ext4_check_bdev_write_error(sb); if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb)) return 0; BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT); jbd2_journal_set_triggers(bh, &EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers); return 0; } /* * The ext4 forget function must perform a revoke if we are freeing data * which has been journaled. Metadata (eg. indirect blocks) must be * revoked in all cases. * * "bh" may be NULL: a metadata block may have been freed from memory * but there may still be a record of it in the journal, and that record * still needs to be revoked. */ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr) { int err; might_sleep(); trace_ext4_forget(inode, is_metadata, blocknr); BUFFER_TRACE(bh, "enter"); ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n", bh, is_metadata, inode->i_mode, test_opt(inode->i_sb, DATA_FLAGS)); /* In the no journal case, we can just do a bforget and return */ if (!ext4_handle_valid(handle)) { bforget(bh); return 0; } /* Never use the revoke function if we are doing full data * journaling: there is no need to, and a V1 superblock won't * support it. Otherwise, only skip the revoke on un-journaled * data blocks. */ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || (!is_metadata && !ext4_should_journal_data(inode))) { if (bh) { BUFFER_TRACE(bh, "call jbd2_journal_forget"); err = jbd2_journal_forget(handle, bh); if (err) ext4_journal_abort_handle(where, line, __func__, bh, handle, err); return err; } return 0; } /* * data!=journal && (is_metadata || should_journal_data(inode)) */ BUFFER_TRACE(bh, "call jbd2_journal_revoke"); err = jbd2_journal_revoke(handle, blocknr, bh); if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); __ext4_error(inode->i_sb, where, line, true, -err, 0, "error %d when attempting revoke", err); } BUFFER_TRACE(bh, "exit"); return err; } int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type) { int err; if (!ext4_handle_valid(handle)) return 0; err = jbd2_journal_get_create_access(handle, bh); if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); return err; } if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb)) return 0; BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT); jbd2_journal_set_triggers(bh, &EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers); return 0; } int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh) { int err = 0; might_sleep(); set_buffer_meta(bh); set_buffer_prio(bh); set_buffer_uptodate(bh); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); /* Errors can only happen due to aborted journal or a nasty bug */ if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); if (inode == NULL) { pr_err("EXT4: jbd2_journal_dirty_metadata " "failed: handle type %u started at " "line %u, credits %u/%u, errcode %d", handle->h_type, handle->h_line_no, handle->h_requested_credits, jbd2_handle_buffer_credits(handle), err); return err; } ext4_error_inode(inode, where, line, bh->b_blocknr, "journal_dirty_metadata failed: " "handle type %u started at line %u, " "credits %u/%u, errcode %d", handle->h_type, handle->h_line_no, handle->h_requested_credits, jbd2_handle_buffer_credits(handle), err); } } else { if (inode) mark_buffer_dirty_inode(bh, inode); else mark_buffer_dirty(bh); if (inode && inode_needs_sync(inode)) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) { ext4_error_inode_err(inode, where, line, bh->b_blocknr, EIO, "IO error syncing itable block"); err = -EIO; } } } return err; } |
| 61 60 1 3 2 1 19 19 13 13 13 4 3 7 1 7 7 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Common helpers for stackable filesystems and backing files. * * Forked from fs/overlayfs/file.c. * * Copyright (C) 2017 Red Hat, Inc. * Copyright (C) 2023 CTERA Networks. */ #include <linux/fs.h> #include <linux/backing-file.h> #include <linux/splice.h> #include <linux/mm.h> #include "internal.h" /** * backing_file_open - open a backing file for kernel internal use * @user_path: path that the user reuqested to open * @flags: open flags * @real_path: path of the backing file * @cred: credentials for open * * Open a backing file for a stackable filesystem (e.g., overlayfs). * @user_path may be on the stackable filesystem and @real_path on the * underlying filesystem. In this case, we want to be able to return the * @user_path of the stackable filesystem. This is done by embedding the * returned file into a container structure that also stores the stacked * file's path, which can be retrieved using backing_file_user_path(). */ struct file *backing_file_open(const struct path *user_path, int flags, const struct path *real_path, const struct cred *cred) { struct file *f; int error; f = alloc_empty_backing_file(flags, cred); if (IS_ERR(f)) return f; path_get(user_path); *backing_file_user_path(f) = *user_path; error = vfs_open(real_path, f); if (error) { fput(f); f = ERR_PTR(error); } return f; } EXPORT_SYMBOL_GPL(backing_file_open); struct file *backing_tmpfile_open(const struct path *user_path, int flags, const struct path *real_parentpath, umode_t mode, const struct cred *cred) { struct mnt_idmap *real_idmap = mnt_idmap(real_parentpath->mnt); struct file *f; int error; f = alloc_empty_backing_file(flags, cred); if (IS_ERR(f)) return f; path_get(user_path); *backing_file_user_path(f) = *user_path; error = vfs_tmpfile(real_idmap, real_parentpath, f, mode); if (error) { fput(f); f = ERR_PTR(error); } return f; } EXPORT_SYMBOL(backing_tmpfile_open); struct backing_aio { struct kiocb iocb; refcount_t ref; struct kiocb *orig_iocb; /* used for aio completion */ void (*end_write)(struct file *); struct work_struct work; long res; }; static struct kmem_cache *backing_aio_cachep; #define BACKING_IOCB_MASK \ (IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND) static rwf_t iocb_to_rw_flags(int flags) { return (__force rwf_t)(flags & BACKING_IOCB_MASK); } static void backing_aio_put(struct backing_aio *aio) { if (refcount_dec_and_test(&aio->ref)) { fput(aio->iocb.ki_filp); kmem_cache_free(backing_aio_cachep, aio); } } static void backing_aio_cleanup(struct backing_aio *aio, long res) { struct kiocb *iocb = &aio->iocb; struct kiocb *orig_iocb = aio->orig_iocb; if (aio->end_write) aio->end_write(orig_iocb->ki_filp); orig_iocb->ki_pos = iocb->ki_pos; backing_aio_put(aio); } static void backing_aio_rw_complete(struct kiocb *iocb, long res) { struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb); struct kiocb *orig_iocb = aio->orig_iocb; if (iocb->ki_flags & IOCB_WRITE) kiocb_end_write(iocb); backing_aio_cleanup(aio, res); orig_iocb->ki_complete(orig_iocb, res); } static void backing_aio_complete_work(struct work_struct *work) { struct backing_aio *aio = container_of(work, struct backing_aio, work); backing_aio_rw_complete(&aio->iocb, aio->res); } static void backing_aio_queue_completion(struct kiocb *iocb, long res) { struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb); /* * Punt to a work queue to serialize updates of mtime/size. */ aio->res = res; INIT_WORK(&aio->work, backing_aio_complete_work); queue_work(file_inode(aio->orig_iocb->ki_filp)->i_sb->s_dio_done_wq, &aio->work); } static int backing_aio_init_wq(struct kiocb *iocb) { struct super_block *sb = file_inode(iocb->ki_filp)->i_sb; if (sb->s_dio_done_wq) return 0; return sb_init_dio_done_wq(sb); } ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, struct kiocb *iocb, int flags, struct backing_file_ctx *ctx) { struct backing_aio *aio = NULL; const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING))) return -EIO; if (!iov_iter_count(iter)) return 0; if (iocb->ki_flags & IOCB_DIRECT && !(file->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; old_cred = override_creds(ctx->cred); if (is_sync_kiocb(iocb)) { rwf_t rwf = iocb_to_rw_flags(flags); ret = vfs_iter_read(file, iter, &iocb->ki_pos, rwf); } else { ret = -ENOMEM; aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); if (!aio) goto out; aio->orig_iocb = iocb; kiocb_clone(&aio->iocb, iocb, get_file(file)); aio->iocb.ki_complete = backing_aio_rw_complete; refcount_set(&aio->ref, 2); ret = vfs_iocb_iter_read(file, &aio->iocb, iter); backing_aio_put(aio); if (ret != -EIOCBQUEUED) backing_aio_cleanup(aio, ret); } out: revert_creds(old_cred); if (ctx->accessed) ctx->accessed(ctx->user_file); return ret; } EXPORT_SYMBOL_GPL(backing_file_read_iter); ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, struct kiocb *iocb, int flags, struct backing_file_ctx *ctx) { const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING))) return -EIO; if (!iov_iter_count(iter)) return 0; ret = file_remove_privs(ctx->user_file); if (ret) return ret; if (iocb->ki_flags & IOCB_DIRECT && !(file->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; /* * Stacked filesystems don't support deferred completions, don't copy * this property in case it is set by the issuer. */ flags &= ~IOCB_DIO_CALLER_COMP; old_cred = override_creds(ctx->cred); if (is_sync_kiocb(iocb)) { rwf_t rwf = iocb_to_rw_flags(flags); ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf); if (ctx->end_write) ctx->end_write(ctx->user_file); } else { struct backing_aio *aio; ret = backing_aio_init_wq(iocb); if (ret) goto out; ret = -ENOMEM; aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL); if (!aio) goto out; aio->orig_iocb = iocb; aio->end_write = ctx->end_write; kiocb_clone(&aio->iocb, iocb, get_file(file)); aio->iocb.ki_flags = flags; aio->iocb.ki_complete = backing_aio_queue_completion; refcount_set(&aio->ref, 2); ret = vfs_iocb_iter_write(file, &aio->iocb, iter); backing_aio_put(aio); if (ret != -EIOCBQUEUED) backing_aio_cleanup(aio, ret); } out: revert_creds(old_cred); return ret; } EXPORT_SYMBOL_GPL(backing_file_write_iter); ssize_t backing_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags, struct backing_file_ctx *ctx) { const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING))) return -EIO; old_cred = override_creds(ctx->cred); ret = vfs_splice_read(in, ppos, pipe, len, flags); revert_creds(old_cred); if (ctx->accessed) ctx->accessed(ctx->user_file); return ret; } EXPORT_SYMBOL_GPL(backing_file_splice_read); ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags, struct backing_file_ctx *ctx) { const struct cred *old_cred; ssize_t ret; if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING))) return -EIO; if (!out->f_op->splice_write) return -EINVAL; ret = file_remove_privs(ctx->user_file); if (ret) return ret; old_cred = override_creds(ctx->cred); file_start_write(out); ret = out->f_op->splice_write(pipe, out, ppos, len, flags); file_end_write(out); revert_creds(old_cred); if (ctx->end_write) ctx->end_write(ctx->user_file); return ret; } EXPORT_SYMBOL_GPL(backing_file_splice_write); int backing_file_mmap(struct file *file, struct vm_area_struct *vma, struct backing_file_ctx *ctx) { const struct cred *old_cred; int ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)) || WARN_ON_ONCE(ctx->user_file != vma->vm_file)) return -EIO; if (!file->f_op->mmap) return -ENODEV; vma_set_file(vma, file); old_cred = override_creds(ctx->cred); ret = call_mmap(vma->vm_file, vma); revert_creds(old_cred); if (ctx->accessed) ctx->accessed(ctx->user_file); return ret; } EXPORT_SYMBOL_GPL(backing_file_mmap); static int __init backing_aio_init(void) { backing_aio_cachep = KMEM_CACHE(backing_aio, SLAB_HWCACHE_ALIGN); if (!backing_aio_cachep) return -ENOMEM; return 0; } fs_initcall(backing_aio_init); |
| 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-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 |
| 3 3 7 7 22 3 1 15 2 1 2 5 5 10 3 12 3 10 15 1 6 8 4 4 9 1 3 5 4 2 2 5 1 1 3 48 48 1 45 3 2 3 48 1 1 47 1 48 47 1 28 28 2 2 24 2 24 24 23 2 10 6 2 29 9 9 32 3 3 23 5 28 9 1 23 43 43 12 11 23 40 40 2 38 31 4 9 17 7 2 8 14 3 16 1 1 1 1 1 28 28 23 1 9 8 3 2 1 1 3 1 1 4 1 2 1 1 1 1 1 1 1 1 2 141 141 17 14 1 2 2 1 15 9 1 1 2 5 1 1 1 28 2 3 2 1 1 2 3 1 4 1 6 2 1 1 11 1 1 3 1 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 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_rtalloc.h" #include "xfs_iwalk.h" #include "xfs_itable.h" #include "xfs_error.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_fsops.h" #include "xfs_discard.h" #include "xfs_quota.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_trans.h" #include "xfs_btree.h" #include <linux/fsmap.h> #include "xfs_fsmap.h" #include "scrub/xfs_scrub.h" #include "xfs_sb.h" #include "xfs_ag.h" #include "xfs_health.h" #include "xfs_reflink.h" #include "xfs_ioctl.h" #include "xfs_xattr.h" #include "xfs_rtbitmap.h" #include "xfs_file.h" #include "xfs_exchrange.h" #include "xfs_handle.h" #include <linux/mount.h> #include <linux/fileattr.h> /* Return 0 on success or positive error */ int xfs_fsbulkstat_one_fmt( struct xfs_ibulk *breq, const struct xfs_bulkstat *bstat) { struct xfs_bstat bs1; xfs_bulkstat_to_bstat(breq->mp, &bs1, bstat); if (copy_to_user(breq->ubuffer, &bs1, sizeof(bs1))) return -EFAULT; return xfs_ibulk_advance(breq, sizeof(struct xfs_bstat)); } int xfs_fsinumbers_fmt( struct xfs_ibulk *breq, const struct xfs_inumbers *igrp) { struct xfs_inogrp ig1; xfs_inumbers_to_inogrp(&ig1, igrp); if (copy_to_user(breq->ubuffer, &ig1, sizeof(struct xfs_inogrp))) return -EFAULT; return xfs_ibulk_advance(breq, sizeof(struct xfs_inogrp)); } STATIC int xfs_ioc_fsbulkstat( struct file *file, unsigned int cmd, void __user *arg) { struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount; struct xfs_fsop_bulkreq bulkreq; struct xfs_ibulk breq = { .mp = mp, .idmap = file_mnt_idmap(file), .ocount = 0, }; xfs_ino_t lastino; int error; /* done = 1 if there are more stats to get and if bulkstat */ /* should be called again (unused here, but used in dmapi) */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (xfs_is_shutdown(mp)) return -EIO; if (copy_from_user(&bulkreq, arg, sizeof(struct xfs_fsop_bulkreq))) return -EFAULT; if (copy_from_user(&lastino, bulkreq.lastip, sizeof(__s64))) return -EFAULT; if (bulkreq.icount <= 0) return -EINVAL; if (bulkreq.ubuffer == NULL) return -EINVAL; breq.ubuffer = bulkreq.ubuffer; breq.icount = bulkreq.icount; /* * FSBULKSTAT_SINGLE expects that *lastip contains the inode number * that we want to stat. However, FSINUMBERS and FSBULKSTAT expect * that *lastip contains either zero or the number of the last inode to * be examined by the previous call and return results starting with * the next inode after that. The new bulk request back end functions * take the inode to start with, so we have to compute the startino * parameter from lastino to maintain correct function. lastino == 0 * is a special case because it has traditionally meant "first inode * in filesystem". */ if (cmd == XFS_IOC_FSINUMBERS) { breq.startino = lastino ? lastino + 1 : 0; error = xfs_inumbers(&breq, xfs_fsinumbers_fmt); lastino = breq.startino - 1; } else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE) { breq.startino = lastino; breq.icount = 1; error = xfs_bulkstat_one(&breq, xfs_fsbulkstat_one_fmt); } else { /* XFS_IOC_FSBULKSTAT */ breq.startino = lastino ? lastino + 1 : 0; error = xfs_bulkstat(&breq, xfs_fsbulkstat_one_fmt); lastino = breq.startino - 1; } if (error) return error; if (bulkreq.lastip != NULL && copy_to_user(bulkreq.lastip, &lastino, sizeof(xfs_ino_t))) return -EFAULT; if (bulkreq.ocount != NULL && copy_to_user(bulkreq.ocount, &breq.ocount, sizeof(__s32))) return -EFAULT; return 0; } /* Return 0 on success or positive error */ static int xfs_bulkstat_fmt( struct xfs_ibulk *breq, const struct xfs_bulkstat *bstat) { if (copy_to_user(breq->ubuffer, bstat, sizeof(struct xfs_bulkstat))) return -EFAULT; return xfs_ibulk_advance(breq, sizeof(struct xfs_bulkstat)); } /* * Check the incoming bulk request @hdr from userspace and initialize the * internal @breq bulk request appropriately. Returns 0 if the bulk request * should proceed; -ECANCELED if there's nothing to do; or the usual * negative error code. */ static int xfs_bulk_ireq_setup( struct xfs_mount *mp, const struct xfs_bulk_ireq *hdr, struct xfs_ibulk *breq, void __user *ubuffer) { if (hdr->icount == 0 || (hdr->flags & ~XFS_BULK_IREQ_FLAGS_ALL) || memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) return -EINVAL; breq->startino = hdr->ino; breq->ubuffer = ubuffer; breq->icount = hdr->icount; breq->ocount = 0; breq->flags = 0; /* * The @ino parameter is a special value, so we must look it up here. * We're not allowed to have IREQ_AGNO, and we only return one inode * worth of data. */ if (hdr->flags & XFS_BULK_IREQ_SPECIAL) { if (hdr->flags & XFS_BULK_IREQ_AGNO) return -EINVAL; switch (hdr->ino) { case XFS_BULK_IREQ_SPECIAL_ROOT: breq->startino = mp->m_sb.sb_rootino; break; default: return -EINVAL; } breq->icount = 1; } /* * The IREQ_AGNO flag means that we only want results from a given AG. * If @hdr->ino is zero, we start iterating in that AG. If @hdr->ino is * beyond the specified AG then we return no results. */ if (hdr->flags & XFS_BULK_IREQ_AGNO) { if (hdr->agno >= mp->m_sb.sb_agcount) return -EINVAL; if (breq->startino == 0) breq->startino = XFS_AGINO_TO_INO(mp, hdr->agno, 0); else if (XFS_INO_TO_AGNO(mp, breq->startino) < hdr->agno) return -EINVAL; breq->flags |= XFS_IBULK_SAME_AG; /* Asking for an inode past the end of the AG? We're done! */ if (XFS_INO_TO_AGNO(mp, breq->startino) > hdr->agno) return -ECANCELED; } else if (hdr->agno) return -EINVAL; /* Asking for an inode past the end of the FS? We're done! */ if (XFS_INO_TO_AGNO(mp, breq->startino) >= mp->m_sb.sb_agcount) return -ECANCELED; if (hdr->flags & XFS_BULK_IREQ_NREXT64) breq->flags |= XFS_IBULK_NREXT64; return 0; } /* * Update the userspace bulk request @hdr to reflect the end state of the * internal bulk request @breq. */ static void xfs_bulk_ireq_teardown( struct xfs_bulk_ireq *hdr, struct xfs_ibulk *breq) { hdr->ino = breq->startino; hdr->ocount = breq->ocount; } /* Handle the v5 bulkstat ioctl. */ STATIC int xfs_ioc_bulkstat( struct file *file, unsigned int cmd, struct xfs_bulkstat_req __user *arg) { struct xfs_mount *mp = XFS_I(file_inode(file))->i_mount; struct xfs_bulk_ireq hdr; struct xfs_ibulk breq = { .mp = mp, .idmap = file_mnt_idmap(file), }; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (xfs_is_shutdown(mp)) return -EIO; if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr))) return -EFAULT; error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->bulkstat); if (error == -ECANCELED) goto out_teardown; if (error < 0) return error; error = xfs_bulkstat(&breq, xfs_bulkstat_fmt); if (error) return error; out_teardown: xfs_bulk_ireq_teardown(&hdr, &breq); if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr))) return -EFAULT; return 0; } STATIC int xfs_inumbers_fmt( struct xfs_ibulk *breq, const struct xfs_inumbers *igrp) { if (copy_to_user(breq->ubuffer, igrp, sizeof(struct xfs_inumbers))) return -EFAULT; return xfs_ibulk_advance(breq, sizeof(struct xfs_inumbers)); } /* Handle the v5 inumbers ioctl. */ STATIC int xfs_ioc_inumbers( struct xfs_mount *mp, unsigned int cmd, struct xfs_inumbers_req __user *arg) { struct xfs_bulk_ireq hdr; struct xfs_ibulk breq = { .mp = mp, }; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (xfs_is_shutdown(mp)) return -EIO; if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr))) return -EFAULT; error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->inumbers); if (error == -ECANCELED) goto out_teardown; if (error < 0) return error; error = xfs_inumbers(&breq, xfs_inumbers_fmt); if (error) return error; out_teardown: xfs_bulk_ireq_teardown(&hdr, &breq); if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr))) return -EFAULT; return 0; } STATIC int xfs_ioc_fsgeometry( struct xfs_mount *mp, void __user *arg, int struct_version) { struct xfs_fsop_geom fsgeo; size_t len; xfs_fs_geometry(mp, &fsgeo, struct_version); if (struct_version <= 3) len = sizeof(struct xfs_fsop_geom_v1); else if (struct_version == 4) len = sizeof(struct xfs_fsop_geom_v4); else { xfs_fsop_geom_health(mp, &fsgeo); len = sizeof(fsgeo); } if (copy_to_user(arg, &fsgeo, len)) return -EFAULT; return 0; } STATIC int xfs_ioc_ag_geometry( struct xfs_mount *mp, void __user *arg) { struct xfs_perag *pag; struct xfs_ag_geometry ageo; int error; if (copy_from_user(&ageo, arg, sizeof(ageo))) return -EFAULT; if (ageo.ag_flags) return -EINVAL; if (memchr_inv(&ageo.ag_reserved, 0, sizeof(ageo.ag_reserved))) return -EINVAL; pag = xfs_perag_get(mp, ageo.ag_number); if (!pag) return -EINVAL; error = xfs_ag_get_geometry(pag, &ageo); xfs_perag_put(pag); if (error) return error; if (copy_to_user(arg, &ageo, sizeof(ageo))) return -EFAULT; return 0; } /* * Linux extended inode flags interface. */ static void xfs_fill_fsxattr( struct xfs_inode *ip, int whichfork, struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); fileattr_fill_xflags(fa, xfs_ip2xflags(ip)); if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) { fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); } else if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) { /* * Don't let a misaligned extent size hint on a directory * escape to userspace if it won't pass the setattr checks * later. */ if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && xfs_extlen_to_rtxmod(mp, ip->i_extsize) > 0) { fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); fa->fsx_extsize = 0; } else { fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize); } } if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); fa->fsx_projid = ip->i_projid; if (ifp && !xfs_need_iread_extents(ifp)) fa->fsx_nextents = xfs_iext_count(ifp); else fa->fsx_nextents = xfs_ifork_nextents(ifp); } STATIC int xfs_ioc_fsgetxattra( xfs_inode_t *ip, void __user *arg) { struct fileattr fa; xfs_ilock(ip, XFS_ILOCK_SHARED); xfs_fill_fsxattr(ip, XFS_ATTR_FORK, &fa); xfs_iunlock(ip, XFS_ILOCK_SHARED); return copy_fsxattr_to_user(&fa, arg); } int xfs_fileattr_get( struct dentry *dentry, struct fileattr *fa) { struct xfs_inode *ip = XFS_I(d_inode(dentry)); if (d_is_special(dentry)) return -ENOTTY; xfs_ilock(ip, XFS_ILOCK_SHARED); xfs_fill_fsxattr(ip, XFS_DATA_FORK, fa); xfs_iunlock(ip, XFS_ILOCK_SHARED); return 0; } static int xfs_ioctl_setattr_xflags( struct xfs_trans *tp, struct xfs_inode *ip, struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; bool rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME); uint64_t i_flags2; if (rtflag != XFS_IS_REALTIME_INODE(ip)) { /* Can't change realtime flag if any extents are allocated. */ if (ip->i_df.if_nextents || ip->i_delayed_blks) return -EINVAL; /* * If S_DAX is enabled on this file, we can only switch the * device if both support fsdax. We can't update S_DAX because * there might be other threads walking down the access paths. */ if (IS_DAX(VFS_I(ip)) && (mp->m_ddev_targp->bt_daxdev == NULL || (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == NULL))) return -EINVAL; } if (rtflag) { /* If realtime flag is set then must have realtime device */ if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || xfs_extlen_to_rtxmod(mp, ip->i_extsize)) return -EINVAL; /* Clear reflink if we are actually able to set the rt flag. */ if (xfs_is_reflink_inode(ip)) ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* diflags2 only valid for v3 inodes. */ i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); if (i_flags2 && !xfs_has_v3inodes(mp)) return -EINVAL; ip->i_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); ip->i_diflags2 = i_flags2; xfs_diflags_to_iflags(ip, false); /* * Make the stable writes flag match that of the device the inode * resides on when flipping the RT flag. */ if (rtflag != XFS_IS_REALTIME_INODE(ip) && S_ISREG(VFS_I(ip)->i_mode)) xfs_update_stable_writes(ip); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(mp, xs_ig_attrchg); return 0; } static void xfs_ioctl_setattr_prepare_dax( struct xfs_inode *ip, struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); if (S_ISDIR(inode->i_mode)) return; if (xfs_has_dax_always(mp) || xfs_has_dax_never(mp)) return; if (((fa->fsx_xflags & FS_XFLAG_DAX) && !(ip->i_diflags2 & XFS_DIFLAG2_DAX)) || (!(fa->fsx_xflags & FS_XFLAG_DAX) && (ip->i_diflags2 & XFS_DIFLAG2_DAX))) d_mark_dontcache(inode); } /* * Set up the transaction structure for the setattr operation, checking that we * have permission to do so. On success, return a clean transaction and the * inode locked exclusively ready for further operation specific checks. On * failure, return an error without modifying or locking the inode. */ static struct xfs_trans * xfs_ioctl_setattr_get_trans( struct xfs_inode *ip, struct xfs_dquot *pdqp) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error = -EROFS; if (xfs_is_readonly(mp)) goto out_error; error = -EIO; if (xfs_is_shutdown(mp)) goto out_error; error = xfs_trans_alloc_ichange(ip, NULL, NULL, pdqp, has_capability_noaudit(current, CAP_FOWNER), &tp); if (error) goto out_error; if (xfs_has_wsync(mp)) xfs_trans_set_sync(tp); return tp; out_error: return ERR_PTR(error); } /* * Validate a proposed extent size hint. For regular files, the hint can only * be changed if no extents are allocated. */ static int xfs_ioctl_setattr_check_extsize( struct xfs_inode *ip, struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; xfs_failaddr_t failaddr; uint16_t new_diflags; if (!fa->fsx_valid) return 0; if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents && XFS_FSB_TO_B(mp, ip->i_extsize) != fa->fsx_extsize) return -EINVAL; if (fa->fsx_extsize & mp->m_blockmask) return -EINVAL; new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); /* * Inode verifiers do not check that the extent size hint is an integer * multiple of the rt extent size on a directory with both rtinherit * and extszinherit flags set. Don't let sysadmins misconfigure * directories. */ if ((new_diflags & XFS_DIFLAG_RTINHERIT) && (new_diflags & XFS_DIFLAG_EXTSZINHERIT)) { unsigned int rtextsize_bytes; rtextsize_bytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize); if (fa->fsx_extsize % rtextsize_bytes) return -EINVAL; } failaddr = xfs_inode_validate_extsize(ip->i_mount, XFS_B_TO_FSB(mp, fa->fsx_extsize), VFS_I(ip)->i_mode, new_diflags); return failaddr != NULL ? -EINVAL : 0; } static int xfs_ioctl_setattr_check_cowextsize( struct xfs_inode *ip, struct fileattr *fa) { struct xfs_mount *mp = ip->i_mount; xfs_failaddr_t failaddr; uint64_t new_diflags2; uint16_t new_diflags; if (!fa->fsx_valid) return 0; if (fa->fsx_cowextsize & mp->m_blockmask) return -EINVAL; new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); new_diflags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); failaddr = xfs_inode_validate_cowextsize(ip->i_mount, XFS_B_TO_FSB(mp, fa->fsx_cowextsize), VFS_I(ip)->i_mode, new_diflags, new_diflags2); return failaddr != NULL ? -EINVAL : 0; } static int xfs_ioctl_setattr_check_projid( struct xfs_inode *ip, struct fileattr *fa) { if (!fa->fsx_valid) return 0; /* Disallow 32bit project ids if 32bit IDs are not enabled. */ if (fa->fsx_projid > (uint16_t)-1 && !xfs_has_projid32(ip->i_mount)) return -EINVAL; return 0; } int xfs_fileattr_set( struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct xfs_inode *ip = XFS_I(d_inode(dentry)); struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; struct xfs_dquot *pdqp = NULL; struct xfs_dquot *olddquot = NULL; int error; trace_xfs_ioctl_setattr(ip); if (d_is_special(dentry)) return -ENOTTY; if (!fa->fsx_valid) { if (fa->flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NOATIME_FL | FS_NODUMP_FL | FS_SYNC_FL | FS_DAX_FL | FS_PROJINHERIT_FL)) return -EOPNOTSUPP; } error = xfs_ioctl_setattr_check_projid(ip, fa); if (error) return error; /* * If disk quotas is on, we make sure that the dquots do exist on disk, * before we start any other transactions. Trying to do this later * is messy. We don't care to take a readlock to look at the ids * in inode here, because we can't hold it across the trans_reserve. * If the IDs do change before we take the ilock, we're covered * because the i_*dquot fields will get updated anyway. */ if (fa->fsx_valid && XFS_IS_QUOTA_ON(mp)) { error = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid, VFS_I(ip)->i_gid, fa->fsx_projid, XFS_QMOPT_PQUOTA, NULL, NULL, &pdqp); if (error) return error; } xfs_ioctl_setattr_prepare_dax(ip, fa); tp = xfs_ioctl_setattr_get_trans(ip, pdqp); if (IS_ERR(tp)) { error = PTR_ERR(tp); goto error_free_dquots; } error = xfs_ioctl_setattr_check_extsize(ip, fa); if (error) goto error_trans_cancel; error = xfs_ioctl_setattr_check_cowextsize(ip, fa); if (error) goto error_trans_cancel; error = xfs_ioctl_setattr_xflags(tp, ip, fa); if (error) goto error_trans_cancel; if (!fa->fsx_valid) goto skip_xattr; /* * Change file ownership. Must be the owner or privileged. CAP_FSETID * overrides the following restrictions: * * The set-user-ID and set-group-ID bits of a file will be cleared upon * successful return from chown() */ if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) && !capable_wrt_inode_uidgid(idmap, VFS_I(ip), CAP_FSETID)) VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID); /* Change the ownerships and register project quota modifications */ if (ip->i_projid != fa->fsx_projid) { if (XFS_IS_PQUOTA_ON(mp)) { olddquot = xfs_qm_vop_chown(tp, ip, &ip->i_pdquot, pdqp); } ip->i_projid = fa->fsx_projid; } /* * Only set the extent size hint if we've already determined that the * extent size hint should be set on the inode. If no extent size flags * are set on the inode then unconditionally clear the extent size hint. */ if (ip->i_diflags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT)) ip->i_extsize = XFS_B_TO_FSB(mp, fa->fsx_extsize); else ip->i_extsize = 0; if (xfs_has_v3inodes(mp)) { if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) ip->i_cowextsize = XFS_B_TO_FSB(mp, fa->fsx_cowextsize); else ip->i_cowextsize = 0; } skip_xattr: error = xfs_trans_commit(tp); /* * Release any dquot(s) the inode had kept before chown. */ xfs_qm_dqrele(olddquot); xfs_qm_dqrele(pdqp); return error; error_trans_cancel: xfs_trans_cancel(tp); error_free_dquots: xfs_qm_dqrele(pdqp); return error; } static bool xfs_getbmap_format( struct kgetbmap *p, struct getbmapx __user *u, size_t recsize) { if (put_user(p->bmv_offset, &u->bmv_offset) || put_user(p->bmv_block, &u->bmv_block) || put_user(p->bmv_length, &u->bmv_length) || put_user(0, &u->bmv_count) || put_user(0, &u->bmv_entries)) return false; if (recsize < sizeof(struct getbmapx)) return true; if (put_user(0, &u->bmv_iflags) || put_user(p->bmv_oflags, &u->bmv_oflags) || put_user(0, &u->bmv_unused1) || put_user(0, &u->bmv_unused2)) return false; return true; } STATIC int xfs_ioc_getbmap( struct file *file, unsigned int cmd, void __user *arg) { struct getbmapx bmx = { 0 }; struct kgetbmap *buf; size_t recsize; int error, i; switch (cmd) { case XFS_IOC_GETBMAPA: bmx.bmv_iflags = BMV_IF_ATTRFORK; fallthrough; case XFS_IOC_GETBMAP: /* struct getbmap is a strict subset of struct getbmapx. */ recsize = sizeof(struct getbmap); break; case XFS_IOC_GETBMAPX: recsize = sizeof(struct getbmapx); break; default: return -EINVAL; } if (copy_from_user(&bmx, arg, recsize)) return -EFAULT; if (bmx.bmv_count < 2) return -EINVAL; if (bmx.bmv_count >= INT_MAX / recsize) return -ENOMEM; buf = kvcalloc(bmx.bmv_count, sizeof(*buf), GFP_KERNEL); if (!buf) return -ENOMEM; error = xfs_getbmap(XFS_I(file_inode(file)), &bmx, buf); if (error) goto out_free_buf; error = -EFAULT; if (copy_to_user(arg, &bmx, recsize)) goto out_free_buf; arg += recsize; for (i = 0; i < bmx.bmv_entries; i++) { if (!xfs_getbmap_format(buf + i, arg, recsize)) goto out_free_buf; arg += recsize; } error = 0; out_free_buf: kvfree(buf); return error; } STATIC int xfs_ioc_getfsmap( struct xfs_inode *ip, struct fsmap_head __user *arg) { struct xfs_fsmap_head xhead = {0}; struct fsmap_head head; struct fsmap *recs; unsigned int count; __u32 last_flags = 0; bool done = false; int error; if (copy_from_user(&head, arg, sizeof(struct fsmap_head))) return -EFAULT; if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) || memchr_inv(head.fmh_keys[0].fmr_reserved, 0, sizeof(head.fmh_keys[0].fmr_reserved)) || memchr_inv(head.fmh_keys[1].fmr_reserved, 0, sizeof(head.fmh_keys[1].fmr_reserved))) return -EINVAL; /* * Use an internal memory buffer so that we don't have to copy fsmap * data to userspace while holding locks. Start by trying to allocate * up to 128k for the buffer, but fall back to a single page if needed. */ count = min_t(unsigned int, head.fmh_count, 131072 / sizeof(struct fsmap)); recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL); if (!recs) { count = min_t(unsigned int, head.fmh_count, PAGE_SIZE / sizeof(struct fsmap)); recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL); if (!recs) return -ENOMEM; } xhead.fmh_iflags = head.fmh_iflags; xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]); xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]); trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]); head.fmh_entries = 0; do { struct fsmap __user *user_recs; struct fsmap *last_rec; user_recs = &arg->fmh_recs[head.fmh_entries]; xhead.fmh_entries = 0; xhead.fmh_count = min_t(unsigned int, count, head.fmh_count - head.fmh_entries); /* Run query, record how many entries we got. */ error = xfs_getfsmap(ip->i_mount, &xhead, recs); switch (error) { case 0: /* * There are no more records in the result set. Copy * whatever we got to userspace and break out. */ done = true; break; case -ECANCELED: /* * The internal memory buffer is full. Copy whatever * records we got to userspace and go again if we have * not yet filled the userspace buffer. */ error = 0; break; default: goto out_free; } head.fmh_entries += xhead.fmh_entries; head.fmh_oflags = xhead.fmh_oflags; /* * If the caller wanted a record count or there aren't any * new records to return, we're done. */ if (head.fmh_count == 0 || xhead.fmh_entries == 0) break; /* Copy all the records we got out to userspace. */ if (copy_to_user(user_recs, recs, xhead.fmh_entries * sizeof(struct fsmap))) { error = -EFAULT; goto out_free; } /* Remember the last record flags we copied to userspace. */ last_rec = &recs[xhead.fmh_entries - 1]; last_flags = last_rec->fmr_flags; /* Set up the low key for the next iteration. */ xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec); trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); } while (!done && head.fmh_entries < head.fmh_count); /* * If there are no more records in the query result set and we're not * in counting mode, mark the last record returned with the LAST flag. */ if (done && head.fmh_count > 0 && head.fmh_entries > 0) { struct fsmap __user *user_rec; last_flags |= FMR_OF_LAST; user_rec = &arg->fmh_recs[head.fmh_entries - 1]; if (copy_to_user(&user_rec->fmr_flags, &last_flags, sizeof(last_flags))) { error = -EFAULT; goto out_free; } } /* copy back header */ if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) { error = -EFAULT; goto out_free; } out_free: kvfree(recs); return error; } int xfs_ioc_swapext( xfs_swapext_t *sxp) { xfs_inode_t *ip, *tip; struct fd f, tmp; int error = 0; /* Pull information for the target fd */ f = fdget((int)sxp->sx_fdtarget); if (!f.file) { error = -EINVAL; goto out; } if (!(f.file->f_mode & FMODE_WRITE) || !(f.file->f_mode & FMODE_READ) || (f.file->f_flags & O_APPEND)) { error = -EBADF; goto out_put_file; } tmp = fdget((int)sxp->sx_fdtmp); if (!tmp.file) { error = -EINVAL; goto out_put_file; } if (!(tmp.file->f_mode & FMODE_WRITE) || !(tmp.file->f_mode & FMODE_READ) || (tmp.file->f_flags & O_APPEND)) { error = -EBADF; goto out_put_tmp_file; } if (IS_SWAPFILE(file_inode(f.file)) || IS_SWAPFILE(file_inode(tmp.file))) { error = -EINVAL; goto out_put_tmp_file; } /* * We need to ensure that the fds passed in point to XFS inodes * before we cast and access them as XFS structures as we have no * control over what the user passes us here. */ if (f.file->f_op != &xfs_file_operations || tmp.file->f_op != &xfs_file_operations) { error = -EINVAL; goto out_put_tmp_file; } ip = XFS_I(file_inode(f.file)); tip = XFS_I(file_inode(tmp.file)); if (ip->i_mount != tip->i_mount) { error = -EINVAL; goto out_put_tmp_file; } if (ip->i_ino == tip->i_ino) { error = -EINVAL; goto out_put_tmp_file; } if (xfs_is_shutdown(ip->i_mount)) { error = -EIO; goto out_put_tmp_file; } error = xfs_swap_extents(ip, tip, sxp); out_put_tmp_file: fdput(tmp); out_put_file: fdput(f); out: return error; } static int xfs_ioc_getlabel( struct xfs_mount *mp, char __user *user_label) { struct xfs_sb *sbp = &mp->m_sb; char label[XFSLABEL_MAX + 1]; /* Paranoia */ BUILD_BUG_ON(sizeof(sbp->sb_fname) > FSLABEL_MAX); /* 1 larger than sb_fname, so this ensures a trailing NUL char */ memset(label, 0, sizeof(label)); spin_lock(&mp->m_sb_lock); strncpy(label, sbp->sb_fname, XFSLABEL_MAX); spin_unlock(&mp->m_sb_lock); if (copy_to_user(user_label, label, sizeof(label))) return -EFAULT; return 0; } static int xfs_ioc_setlabel( struct file *filp, struct xfs_mount *mp, char __user *newlabel) { struct xfs_sb *sbp = &mp->m_sb; char label[XFSLABEL_MAX + 1]; size_t len; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * The generic ioctl allows up to FSLABEL_MAX chars, but XFS is much * smaller, at 12 bytes. We copy one more to be sure we find the * (required) NULL character to test the incoming label length. * NB: The on disk label doesn't need to be null terminated. */ if (copy_from_user(label, newlabel, XFSLABEL_MAX + 1)) return -EFAULT; len = strnlen(label, XFSLABEL_MAX + 1); if (len > sizeof(sbp->sb_fname)) return -EINVAL; error = mnt_want_write_file(filp); if (error) return error; spin_lock(&mp->m_sb_lock); memset(sbp->sb_fname, 0, sizeof(sbp->sb_fname)); memcpy(sbp->sb_fname, label, len); spin_unlock(&mp->m_sb_lock); /* * Now we do several things to satisfy userspace. * In addition to normal logging of the primary superblock, we also * immediately write these changes to sector zero for the primary, then * update all backup supers (as xfs_db does for a label change), then * invalidate the block device page cache. This is so that any prior * buffered reads from userspace (i.e. from blkid) are invalidated, * and userspace will see the newly-written label. */ error = xfs_sync_sb_buf(mp); if (error) goto out; /* * growfs also updates backup supers so lock against that. */ mutex_lock(&mp->m_growlock); error = xfs_update_secondary_sbs(mp); mutex_unlock(&mp->m_growlock); invalidate_bdev(mp->m_ddev_targp->bt_bdev); out: mnt_drop_write_file(filp); return error; } static inline int xfs_fs_eofblocks_from_user( struct xfs_fs_eofblocks *src, struct xfs_icwalk *dst) { if (src->eof_version != XFS_EOFBLOCKS_VERSION) return -EINVAL; if (src->eof_flags & ~XFS_EOF_FLAGS_VALID) return -EINVAL; if (memchr_inv(&src->pad32, 0, sizeof(src->pad32)) || memchr_inv(src->pad64, 0, sizeof(src->pad64))) return -EINVAL; dst->icw_flags = 0; if (src->eof_flags & XFS_EOF_FLAGS_SYNC) dst->icw_flags |= XFS_ICWALK_FLAG_SYNC; if (src->eof_flags & XFS_EOF_FLAGS_UID) dst->icw_flags |= XFS_ICWALK_FLAG_UID; if (src->eof_flags & XFS_EOF_FLAGS_GID) dst->icw_flags |= XFS_ICWALK_FLAG_GID; if (src->eof_flags & XFS_EOF_FLAGS_PRID) dst->icw_flags |= XFS_ICWALK_FLAG_PRID; if (src->eof_flags & XFS_EOF_FLAGS_MINFILESIZE) dst->icw_flags |= XFS_ICWALK_FLAG_MINFILESIZE; dst->icw_prid = src->eof_prid; dst->icw_min_file_size = src->eof_min_file_size; dst->icw_uid = INVALID_UID; if (src->eof_flags & XFS_EOF_FLAGS_UID) { dst->icw_uid = make_kuid(current_user_ns(), src->eof_uid); if (!uid_valid(dst->icw_uid)) return -EINVAL; } dst->icw_gid = INVALID_GID; if (src->eof_flags & XFS_EOF_FLAGS_GID) { dst->icw_gid = make_kgid(current_user_ns(), src->eof_gid); if (!gid_valid(dst->icw_gid)) return -EINVAL; } return 0; } static int xfs_ioctl_getset_resblocks( struct file *filp, unsigned int cmd, void __user *arg) { struct xfs_mount *mp = XFS_I(file_inode(filp))->i_mount; struct xfs_fsop_resblks fsop = { }; int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (cmd == XFS_IOC_SET_RESBLKS) { if (xfs_is_readonly(mp)) return -EROFS; if (copy_from_user(&fsop, arg, sizeof(fsop))) return -EFAULT; error = mnt_want_write_file(filp); if (error) return error; error = xfs_reserve_blocks(mp, fsop.resblks); mnt_drop_write_file(filp); if (error) return error; } spin_lock(&mp->m_sb_lock); fsop.resblks = mp->m_resblks; fsop.resblks_avail = mp->m_resblks_avail; spin_unlock(&mp->m_sb_lock); if (copy_to_user(arg, &fsop, sizeof(fsop))) return -EFAULT; return 0; } static int xfs_ioctl_fs_counts( struct xfs_mount *mp, struct xfs_fsop_counts __user *uarg) { struct xfs_fsop_counts out = { .allocino = percpu_counter_read_positive(&mp->m_icount), .freeino = percpu_counter_read_positive(&mp->m_ifree), .freedata = percpu_counter_read_positive(&mp->m_fdblocks) - xfs_fdblocks_unavailable(mp), .freertx = percpu_counter_read_positive(&mp->m_frextents), }; if (copy_to_user(uarg, &out, sizeof(out))) return -EFAULT; return 0; } /* * These long-unused ioctls were removed from the official ioctl API in 5.17, * but retain these definitions so that we can log warnings about them. */ #define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64) #define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64) #define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64) #define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64) /* * Note: some of the ioctl's return positive numbers as a * byte count indicating success, such as readlink_by_handle. * So we don't "sign flip" like most other routines. This means * true errors need to be returned as a negative value. */ long xfs_file_ioctl( struct file *filp, unsigned int cmd, unsigned long p) { struct inode *inode = file_inode(filp); struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; void __user *arg = (void __user *)p; int error; trace_xfs_file_ioctl(ip); switch (cmd) { case FITRIM: return xfs_ioc_trim(mp, arg); case FS_IOC_GETFSLABEL: return xfs_ioc_getlabel(mp, arg); case FS_IOC_SETFSLABEL: return xfs_ioc_setlabel(filp, mp, arg); case XFS_IOC_ALLOCSP: case XFS_IOC_FREESP: case XFS_IOC_ALLOCSP64: case XFS_IOC_FREESP64: xfs_warn_once(mp, "%s should use fallocate; XFS_IOC_{ALLOC,FREE}SP ioctl unsupported", current->comm); return -ENOTTY; case XFS_IOC_DIOINFO: { struct xfs_buftarg *target = xfs_inode_buftarg(ip); struct dioattr da; da.d_mem = da.d_miniosz = target->bt_logical_sectorsize; da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1); if (copy_to_user(arg, &da, sizeof(da))) return -EFAULT; return 0; } case XFS_IOC_FSBULKSTAT_SINGLE: case XFS_IOC_FSBULKSTAT: case XFS_IOC_FSINUMBERS: return xfs_ioc_fsbulkstat(filp, cmd, arg); case XFS_IOC_BULKSTAT: return xfs_ioc_bulkstat(filp, cmd, arg); case XFS_IOC_INUMBERS: return xfs_ioc_inumbers(mp, cmd, arg); case XFS_IOC_FSGEOMETRY_V1: return xfs_ioc_fsgeometry(mp, arg, 3); case XFS_IOC_FSGEOMETRY_V4: return xfs_ioc_fsgeometry(mp, arg, 4); case XFS_IOC_FSGEOMETRY: return xfs_ioc_fsgeometry(mp, arg, 5); case XFS_IOC_AG_GEOMETRY: return xfs_ioc_ag_geometry(mp, arg); case XFS_IOC_GETVERSION: return put_user(inode->i_generation, (int __user *)arg); case XFS_IOC_FSGETXATTRA: return xfs_ioc_fsgetxattra(ip, arg); case XFS_IOC_GETPARENTS: return xfs_ioc_getparents(filp, arg); case XFS_IOC_GETPARENTS_BY_HANDLE: return xfs_ioc_getparents_by_handle(filp, arg); case XFS_IOC_GETBMAP: case XFS_IOC_GETBMAPA: case XFS_IOC_GETBMAPX: return xfs_ioc_getbmap(filp, cmd, arg); case FS_IOC_GETFSMAP: return xfs_ioc_getfsmap(ip, arg); case XFS_IOC_SCRUBV_METADATA: return xfs_ioc_scrubv_metadata(filp, arg); case XFS_IOC_SCRUB_METADATA: return xfs_ioc_scrub_metadata(filp, arg); case XFS_IOC_FD_TO_HANDLE: case XFS_IOC_PATH_TO_HANDLE: case XFS_IOC_PATH_TO_FSHANDLE: { xfs_fsop_handlereq_t hreq; if (copy_from_user(&hreq, arg, sizeof(hreq))) return -EFAULT; return xfs_find_handle(cmd, &hreq); } case XFS_IOC_OPEN_BY_HANDLE: { xfs_fsop_handlereq_t hreq; if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t))) return -EFAULT; return xfs_open_by_handle(filp, &hreq); } case XFS_IOC_READLINK_BY_HANDLE: { xfs_fsop_handlereq_t hreq; if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t))) return -EFAULT; return xfs_readlink_by_handle(filp, &hreq); } case XFS_IOC_ATTRLIST_BY_HANDLE: return xfs_attrlist_by_handle(filp, arg); case XFS_IOC_ATTRMULTI_BY_HANDLE: return xfs_attrmulti_by_handle(filp, arg); case XFS_IOC_SWAPEXT: { struct xfs_swapext sxp; if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t))) return -EFAULT; error = mnt_want_write_file(filp); if (error) return error; error = xfs_ioc_swapext(&sxp); mnt_drop_write_file(filp); return error; } case XFS_IOC_FSCOUNTS: return xfs_ioctl_fs_counts(mp, arg); case XFS_IOC_SET_RESBLKS: case XFS_IOC_GET_RESBLKS: return xfs_ioctl_getset_resblocks(filp, cmd, arg); case XFS_IOC_FSGROWFSDATA: { struct xfs_growfs_data in; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; error = mnt_want_write_file(filp); if (error) return error; error = xfs_growfs_data(mp, &in); mnt_drop_write_file(filp); return error; } case XFS_IOC_FSGROWFSLOG: { struct xfs_growfs_log in; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; error = mnt_want_write_file(filp); if (error) return error; error = xfs_growfs_log(mp, &in); mnt_drop_write_file(filp); return error; } case XFS_IOC_FSGROWFSRT: { xfs_growfs_rt_t in; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; error = mnt_want_write_file(filp); if (error) return error; error = xfs_growfs_rt(mp, &in); mnt_drop_write_file(filp); return error; } case XFS_IOC_GOINGDOWN: { uint32_t in; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(in, (uint32_t __user *)arg)) return -EFAULT; return xfs_fs_goingdown(mp, in); } case XFS_IOC_ERROR_INJECTION: { xfs_error_injection_t in; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; return xfs_errortag_add(mp, in.errtag); } case XFS_IOC_ERROR_CLEARALL: if (!capable(CAP_SYS_ADMIN)) return -EPERM; return xfs_errortag_clearall(mp); case XFS_IOC_FREE_EOFBLOCKS: { struct xfs_fs_eofblocks eofb; struct xfs_icwalk icw; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (xfs_is_readonly(mp)) return -EROFS; if (copy_from_user(&eofb, arg, sizeof(eofb))) return -EFAULT; error = xfs_fs_eofblocks_from_user(&eofb, &icw); if (error) return error; trace_xfs_ioc_free_eofblocks(mp, &icw, _RET_IP_); sb_start_write(mp->m_super); error = xfs_blockgc_free_space(mp, &icw); sb_end_write(mp->m_super); return error; } case XFS_IOC_EXCHANGE_RANGE: return xfs_ioc_exchange_range(filp, arg); default: return -ENOTTY; } } |
| 3 3 748 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <crypto/hash.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ __be32 s_head; /* blocknr of head of log, only uptodate * while the filesystem is clean */ /* 0x005C */ __u32 s_padding[40]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_jdata: Flag to force data journaling. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_jdata: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. * (Locking Documentation improved by LockDoc) */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock, no locks needed fo * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of metadata buffers being * shadowed by log IO. The IO buffers on the iobuf list and * the shadow buffers on this list match each other one for * one at all times. [j_list_lock, no locks needed for jbd2 * thread] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested [j_state_lock] */ unsigned long t_requested; /* * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; /* * For use by the filesystem to store fs-specific data * structures associated with the transaction */ struct list_head t_private_list; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock, * no lock for quick racy checks] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock, * no lock for quick racy checks] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock, no lock for quick racy checks] [caller holding * open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_shrinker: * * Journal head shrinker, reclaim buffer's journal head which * has been written back. */ struct shrinker *j_shrinker; /** * @j_checkpoint_jh_count: * * Number of journal buffers on the checkpoint list. [j_list_lock] */ struct percpu_counter j_checkpoint_jh_count; /** * @j_shrink_transaction: * * Record next transaction will shrink on the checkpoint list. * [j_list_lock] */ transaction_t *j_shrink_transaction; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_fs_dev_wb_err: * * Records the errseq of the client fs's backing block device. */ errseq_t j_fs_dev_wb_err; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_transaction_overhead: * * Number of blocks each transaction needs for its own bookkeeping */ int j_transaction_overhead_buffers; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_chksum_driver: * * Reference to checksum algorithm driver via cryptoapi. */ struct crypto_shash *j_chksum_driver; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); /** * @j_bmap: * * Bmap function that should be used instead of the generic * VFS bmap function. */ int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* * We can support any known requested features iff the * superblock is not in version 1. Otherwise we fail to support any * extended sb features. */ static inline bool jbd2_format_support_feature(journal_t *j) { return j->j_superblock->s_header.h_blocktype != cpu_to_be32(JBD2_SUPERBLOCK_V1); } /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return (jbd2_format_support_feature(j) && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* Journal high priority write IO operation flags */ #define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ #define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on * clean and empty filesystem * logging area */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ #define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 #define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 #define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); void jbd2_journal_wait_updates(journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_handle(_gfp_flags) \ ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define jbd2_alloc_inode(_gfp_flags) \ ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which * could be used to detect the client fs's metadata async write error. */ errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); } static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) { return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j); } static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && journal->j_chksum_driver == NULL); return journal->j_chksum_driver != NULL; } static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[JBD_MAX_CHECKSUM_SIZE]; } desc; int err; BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > JBD_MAX_CHECKSUM_SIZE); desc.shash.tfm = journal->j_chksum_driver; *(u32 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, address, length); BUG_ON(err); return *(u32 *)desc.ctx; } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_H */ |
| 28 44 85 9 26 26 32 6 18 18 25 20 2 20 29 28 13 107 52 1 106 27 97 24 106 27 34 29 29 10 27 27 27 21 2 12 27 5 44 34 40 31 28 14 17 16 22 56 12 1 29 27 18 10 2 26 14 54 15 45 49 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 | // SPDX-License-Identifier: GPL-2.0 /* Generic part */ typedef struct { block_t *p; block_t key; struct buffer_head *bh; } Indirect; static DEFINE_RWLOCK(pointers_lock); static inline void add_chain(Indirect *p, struct buffer_head *bh, block_t *v) { p->key = *(p->p = v); p->bh = bh; } static inline int verify_chain(Indirect *from, Indirect *to) { while (from <= to && from->key == *from->p) from++; return (from > to); } static inline block_t *block_end(struct buffer_head *bh) { return (block_t *)((char*)bh->b_data + bh->b_size); } static inline Indirect *get_branch(struct inode *inode, int depth, int *offsets, Indirect chain[DEPTH], int *err) { struct super_block *sb = inode->i_sb; Indirect *p = chain; struct buffer_head *bh; *err = 0; /* i_data is not going away, no lock needed */ add_chain (chain, NULL, i_data(inode) + *offsets); if (!p->key) goto no_block; while (--depth) { bh = sb_bread(sb, block_to_cpu(p->key)); if (!bh) goto failure; read_lock(&pointers_lock); if (!verify_chain(chain, p)) goto changed; add_chain(++p, bh, (block_t *)bh->b_data + *++offsets); read_unlock(&pointers_lock); if (!p->key) goto no_block; } return NULL; changed: read_unlock(&pointers_lock); brelse(bh); *err = -EAGAIN; goto no_block; failure: *err = -EIO; no_block: return p; } static int alloc_branch(struct inode *inode, int num, int *offsets, Indirect *branch) { int n = 0; int i; int parent = minix_new_block(inode); int err = -ENOSPC; branch[0].key = cpu_to_block(parent); if (parent) for (n = 1; n < num; n++) { struct buffer_head *bh; /* Allocate the next block */ int nr = minix_new_block(inode); if (!nr) break; branch[n].key = cpu_to_block(nr); bh = sb_getblk(inode->i_sb, parent); if (!bh) { minix_free_block(inode, nr); err = -ENOMEM; break; } lock_buffer(bh); memset(bh->b_data, 0, bh->b_size); branch[n].bh = bh; branch[n].p = (block_t*) bh->b_data + offsets[n]; *branch[n].p = branch[n].key; set_buffer_uptodate(bh); unlock_buffer(bh); mark_buffer_dirty_inode(bh, inode); parent = nr; } if (n == num) return 0; /* Allocation failed, free what we already allocated */ for (i = 1; i < n; i++) bforget(branch[i].bh); for (i = 0; i < n; i++) minix_free_block(inode, block_to_cpu(branch[i].key)); return err; } static inline int splice_branch(struct inode *inode, Indirect chain[DEPTH], Indirect *where, int num) { int i; write_lock(&pointers_lock); /* Verify that place we are splicing to is still there and vacant */ if (!verify_chain(chain, where-1) || *where->p) goto changed; *where->p = where->key; write_unlock(&pointers_lock); /* We are done with atomic stuff, now do the rest of housekeeping */ inode_set_ctime_current(inode); /* had we spliced it onto indirect block? */ if (where->bh) mark_buffer_dirty_inode(where->bh, inode); mark_inode_dirty(inode); return 0; changed: write_unlock(&pointers_lock); for (i = 1; i < num; i++) bforget(where[i].bh); for (i = 0; i < num; i++) minix_free_block(inode, block_to_cpu(where[i].key)); return -EAGAIN; } static int get_block(struct inode * inode, sector_t block, struct buffer_head *bh, int create) { int err = -EIO; int offsets[DEPTH]; Indirect chain[DEPTH]; Indirect *partial; int left; int depth = block_to_path(inode, block, offsets); if (depth == 0) goto out; reread: partial = get_branch(inode, depth, offsets, chain, &err); /* Simplest case - block found, no allocation needed */ if (!partial) { got_it: map_bh(bh, inode->i_sb, block_to_cpu(chain[depth-1].key)); /* Clean up and exit */ partial = chain+depth-1; /* the whole chain */ goto cleanup; } /* Next simple case - plain lookup or failed read of indirect block */ if (!create || err == -EIO) { cleanup: while (partial > chain) { brelse(partial->bh); partial--; } out: return err; } /* * Indirect block might be removed by truncate while we were * reading it. Handling of that case (forget what we've got and * reread) is taken out of the main path. */ if (err == -EAGAIN) goto changed; left = (chain + depth) - partial; err = alloc_branch(inode, left, offsets+(partial-chain), partial); if (err) goto cleanup; if (splice_branch(inode, chain, partial, left) < 0) goto changed; set_buffer_new(bh); goto got_it; changed: while (partial > chain) { brelse(partial->bh); partial--; } goto reread; } static inline int all_zeroes(block_t *p, block_t *q) { while (p < q) if (*p++) return 0; return 1; } static Indirect *find_shared(struct inode *inode, int depth, int offsets[DEPTH], Indirect chain[DEPTH], block_t *top) { Indirect *partial, *p; int k, err; *top = 0; for (k = depth; k > 1 && !offsets[k-1]; k--) ; partial = get_branch(inode, k, offsets, chain, &err); write_lock(&pointers_lock); if (!partial) partial = chain + k-1; if (!partial->key && *partial->p) { write_unlock(&pointers_lock); goto no_top; } for (p=partial;p>chain && all_zeroes((block_t*)p->bh->b_data,p->p);p--) ; if (p == chain + k - 1 && p > chain) { p->p--; } else { *top = *p->p; *p->p = 0; } write_unlock(&pointers_lock); while(partial > p) { brelse(partial->bh); partial--; } no_top: return partial; } static inline void free_data(struct inode *inode, block_t *p, block_t *q) { unsigned long nr; for ( ; p < q ; p++) { nr = block_to_cpu(*p); if (nr) { *p = 0; minix_free_block(inode, nr); } } } static void free_branches(struct inode *inode, block_t *p, block_t *q, int depth) { struct buffer_head * bh; unsigned long nr; if (depth--) { for ( ; p < q ; p++) { nr = block_to_cpu(*p); if (!nr) continue; *p = 0; bh = sb_bread(inode->i_sb, nr); if (!bh) continue; free_branches(inode, (block_t*)bh->b_data, block_end(bh), depth); bforget(bh); minix_free_block(inode, nr); mark_inode_dirty(inode); } } else free_data(inode, p, q); } static inline void truncate (struct inode * inode) { struct super_block *sb = inode->i_sb; block_t *idata = i_data(inode); int offsets[DEPTH]; Indirect chain[DEPTH]; Indirect *partial; block_t nr = 0; int n; int first_whole; long iblock; iblock = (inode->i_size + sb->s_blocksize -1) >> sb->s_blocksize_bits; block_truncate_page(inode->i_mapping, inode->i_size, get_block); n = block_to_path(inode, iblock, offsets); if (!n) return; if (n == 1) { free_data(inode, idata+offsets[0], idata + DIRECT); first_whole = 0; goto do_indirects; } first_whole = offsets[0] + 1 - DIRECT; partial = find_shared(inode, n, offsets, chain, &nr); if (nr) { if (partial == chain) mark_inode_dirty(inode); else mark_buffer_dirty_inode(partial->bh, inode); free_branches(inode, &nr, &nr+1, (chain+n-1) - partial); } /* Clear the ends of indirect blocks on the shared branch */ while (partial > chain) { free_branches(inode, partial->p + 1, block_end(partial->bh), (chain+n-1) - partial); mark_buffer_dirty_inode(partial->bh, inode); brelse (partial->bh); partial--; } do_indirects: /* Kill the remaining (whole) subtrees */ while (first_whole < DEPTH-1) { nr = idata[DIRECT+first_whole]; if (nr) { idata[DIRECT+first_whole] = 0; mark_inode_dirty(inode); free_branches(inode, &nr, &nr+1, first_whole+1); } first_whole++; } inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); } static inline unsigned nblocks(loff_t size, struct super_block *sb) { int k = sb->s_blocksize_bits - 10; unsigned blocks, res, direct = DIRECT, i = DEPTH; blocks = (size + sb->s_blocksize - 1) >> (BLOCK_SIZE_BITS + k); res = blocks; while (--i && blocks > direct) { blocks -= direct; blocks += sb->s_blocksize/sizeof(block_t) - 1; blocks /= sb->s_blocksize/sizeof(block_t); res += blocks; direct = 1; } return res; } |
| 2 2 2 2 1 1 2 2 2 2 2 2 35 36 2 5 2 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/nospec.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "tctx.h" #include "poll.h" #include "timeout.h" #include "waitid.h" #include "futex.h" #include "cancel.h" struct io_cancel { struct file *file; u64 addr; u32 flags; s32 fd; u8 opcode; }; #define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ IORING_ASYNC_CANCEL_ANY | IORING_ASYNC_CANCEL_FD_FIXED | \ IORING_ASYNC_CANCEL_USERDATA | IORING_ASYNC_CANCEL_OP) /* * Returns true if the request matches the criteria outlined by 'cd'. */ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd) { bool match_user_data = cd->flags & IORING_ASYNC_CANCEL_USERDATA; if (req->ctx != cd->ctx) return false; if (!(cd->flags & (IORING_ASYNC_CANCEL_FD | IORING_ASYNC_CANCEL_OP))) match_user_data = true; if (cd->flags & IORING_ASYNC_CANCEL_ANY) goto check_seq; if (cd->flags & IORING_ASYNC_CANCEL_FD) { if (req->file != cd->file) return false; } if (cd->flags & IORING_ASYNC_CANCEL_OP) { if (req->opcode != cd->opcode) return false; } if (match_user_data && req->cqe.user_data != cd->data) return false; if (cd->flags & IORING_ASYNC_CANCEL_ALL) { check_seq: if (io_cancel_match_sequence(req, cd->seq)) return false; } return true; } static bool io_cancel_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_cancel_data *cd = data; return io_cancel_req_match(req, cd); } static int io_async_cancel_one(struct io_uring_task *tctx, struct io_cancel_data *cd) { enum io_wq_cancel cancel_ret; int ret = 0; bool all; if (!tctx || !tctx->io_wq) return -ENOENT; all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; break; case IO_WQ_CANCEL_RUNNING: ret = -EALREADY; break; case IO_WQ_CANCEL_NOTFOUND: ret = -ENOENT; break; } return ret; } int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, unsigned issue_flags) { struct io_ring_ctx *ctx = cd->ctx; int ret; WARN_ON_ONCE(!io_wq_current_is_worker() && tctx != current->io_uring); ret = io_async_cancel_one(tctx, cd); /* * Fall-through even for -EALREADY, as we may have poll armed * that need unarming. */ if (!ret) return 0; ret = io_poll_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; ret = io_waitid_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; ret = io_futex_cancel(ctx, cd, issue_flags); if (ret != -ENOENT) return ret; spin_lock(&ctx->completion_lock); if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) ret = io_timeout_cancel(ctx, cd); spin_unlock(&ctx->completion_lock); return ret; } int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_cancel *cancel = io_kiocb_to_cmd(req, struct io_cancel); if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; if (sqe->off || sqe->splice_fd_in) return -EINVAL; cancel->addr = READ_ONCE(sqe->addr); cancel->flags = READ_ONCE(sqe->cancel_flags); if (cancel->flags & ~CANCEL_FLAGS) return -EINVAL; if (cancel->flags & IORING_ASYNC_CANCEL_FD) { if (cancel->flags & IORING_ASYNC_CANCEL_ANY) return -EINVAL; cancel->fd = READ_ONCE(sqe->fd); } if (cancel->flags & IORING_ASYNC_CANCEL_OP) { if (cancel->flags & IORING_ASYNC_CANCEL_ANY) return -EINVAL; cancel->opcode = READ_ONCE(sqe->len); } return 0; } static int __io_async_cancel(struct io_cancel_data *cd, struct io_uring_task *tctx, unsigned int issue_flags) { bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); struct io_ring_ctx *ctx = cd->ctx; struct io_tctx_node *node; int ret, nr = 0; do { ret = io_try_cancel(tctx, cd, issue_flags); if (ret == -ENOENT) break; if (!all) return ret; nr++; } while (1); /* slow path, try all io-wq's */ io_ring_submit_lock(ctx, issue_flags); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { ret = io_async_cancel_one(node->task->io_uring, cd); if (ret != -ENOENT) { if (!all) break; nr++; } } io_ring_submit_unlock(ctx, issue_flags); return all ? nr : ret; } int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_cancel *cancel = io_kiocb_to_cmd(req, struct io_cancel); struct io_cancel_data cd = { .ctx = req->ctx, .data = cancel->addr, .flags = cancel->flags, .opcode = cancel->opcode, .seq = atomic_inc_return(&req->ctx->cancel_seq), }; struct io_uring_task *tctx = req->task->io_uring; int ret; if (cd.flags & IORING_ASYNC_CANCEL_FD) { if (req->flags & REQ_F_FIXED_FILE || cd.flags & IORING_ASYNC_CANCEL_FD_FIXED) { req->flags |= REQ_F_FIXED_FILE; req->file = io_file_get_fixed(req, cancel->fd, issue_flags); } else { req->file = io_file_get_normal(req, cancel->fd); } if (!req->file) { ret = -EBADF; goto done; } cd.file = req->file; } ret = __io_async_cancel(&cd, tctx, issue_flags); done: if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); return IOU_OK; } void init_hash_table(struct io_hash_table *table, unsigned size) { unsigned int i; for (i = 0; i < size; i++) { spin_lock_init(&table->hbs[i].lock); INIT_HLIST_HEAD(&table->hbs[i].list); } } static int __io_sync_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, int fd) { struct io_ring_ctx *ctx = cd->ctx; /* fixed must be grabbed every time since we drop the uring_lock */ if ((cd->flags & IORING_ASYNC_CANCEL_FD) && (cd->flags & IORING_ASYNC_CANCEL_FD_FIXED)) { if (unlikely(fd >= ctx->nr_user_files)) return -EBADF; fd = array_index_nospec(fd, ctx->nr_user_files); cd->file = io_file_from_index(&ctx->file_table, fd); if (!cd->file) return -EBADF; } return __io_async_cancel(cd, tctx, 0); } int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg) __must_hold(&ctx->uring_lock) { struct io_cancel_data cd = { .ctx = ctx, .seq = atomic_inc_return(&ctx->cancel_seq), }; ktime_t timeout = KTIME_MAX; struct io_uring_sync_cancel_reg sc; struct file *file = NULL; DEFINE_WAIT(wait); int ret, i; if (copy_from_user(&sc, arg, sizeof(sc))) return -EFAULT; if (sc.flags & ~CANCEL_FLAGS) return -EINVAL; for (i = 0; i < ARRAY_SIZE(sc.pad); i++) if (sc.pad[i]) return -EINVAL; for (i = 0; i < ARRAY_SIZE(sc.pad2); i++) if (sc.pad2[i]) return -EINVAL; cd.data = sc.addr; cd.flags = sc.flags; cd.opcode = sc.opcode; /* we can grab a normal file descriptor upfront */ if ((cd.flags & IORING_ASYNC_CANCEL_FD) && !(cd.flags & IORING_ASYNC_CANCEL_FD_FIXED)) { file = fget(sc.fd); if (!file) return -EBADF; cd.file = file; } ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); /* found something, done! */ if (ret != -EALREADY) goto out; if (sc.timeout.tv_sec != -1UL || sc.timeout.tv_nsec != -1UL) { struct timespec64 ts = { .tv_sec = sc.timeout.tv_sec, .tv_nsec = sc.timeout.tv_nsec }; timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } /* * Keep looking until we get -ENOENT. we'll get woken everytime * every time a request completes and will retry the cancelation. */ do { cd.seq = atomic_inc_return(&ctx->cancel_seq); prepare_to_wait(&ctx->cq_wait, &wait, TASK_INTERRUPTIBLE); ret = __io_sync_cancel(current->io_uring, &cd, sc.fd); mutex_unlock(&ctx->uring_lock); if (ret != -EALREADY) break; ret = io_run_task_work_sig(ctx); if (ret < 0) break; ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS); if (!ret) { ret = -ETIME; break; } mutex_lock(&ctx->uring_lock); } while (1); finish_wait(&ctx->cq_wait, &wait); mutex_lock(&ctx->uring_lock); if (ret == -ENOENT || ret > 0) ret = 0; out: if (file) fput(file); return ret; } |
| 223 3 223 223 222 277 119 10 227 1 6 3 223 222 223 1 2 2 2 2 259 27 145 176 16 22 210 2 2 115 243 110 108 2 1 102 83 10 7 1 77 102 108 82 90 16 6 82 6 77 13 72 108 2 1 1 1 1 1 30 30 14 6 8 3 3 195 195 2 2 109 27 1 81 145 3 36 1 113 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * */ #include <linux/fs.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" // clang-format off #define SYSTEM_DOS_ATTRIB "system.dos_attrib" #define SYSTEM_NTFS_ATTRIB "system.ntfs_attrib" #define SYSTEM_NTFS_ATTRIB_BE "system.ntfs_attrib_be" #define SYSTEM_NTFS_SECURITY "system.ntfs_security" // clang-format on static inline size_t unpacked_ea_size(const struct EA_FULL *ea) { return ea->size ? le32_to_cpu(ea->size) : ALIGN(struct_size(ea, name, 1 + ea->name_len + le16_to_cpu(ea->elength)), 4); } static inline size_t packed_ea_size(const struct EA_FULL *ea) { return struct_size(ea, name, 1 + ea->name_len + le16_to_cpu(ea->elength)) - offsetof(struct EA_FULL, flags); } /* * find_ea * * Assume there is at least one xattr in the list. */ static inline bool find_ea(const struct EA_FULL *ea_all, u32 bytes, const char *name, u8 name_len, u32 *off, u32 *ea_sz) { u32 ea_size; *off = 0; if (!ea_all) return false; for (; *off < bytes; *off += ea_size) { const struct EA_FULL *ea = Add2Ptr(ea_all, *off); ea_size = unpacked_ea_size(ea); if (ea->name_len == name_len && !memcmp(ea->name, name, name_len)) { if (ea_sz) *ea_sz = ea_size; return true; } } return false; } /* * ntfs_read_ea - Read all extended attributes. * @ea: New allocated memory. * @info: Pointer into resident data. */ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea, size_t add_bytes, const struct EA_INFO **info) { int err = -EINVAL; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTR_LIST_ENTRY *le = NULL; struct ATTRIB *attr_info, *attr_ea; void *ea_p; u32 size, off, ea_size; static_assert(le32_to_cpu(ATTR_EA_INFO) < le32_to_cpu(ATTR_EA)); *ea = NULL; *info = NULL; attr_info = ni_find_attr(ni, NULL, &le, ATTR_EA_INFO, NULL, 0, NULL, NULL); attr_ea = ni_find_attr(ni, attr_info, &le, ATTR_EA, NULL, 0, NULL, NULL); if (!attr_ea || !attr_info) return 0; *info = resident_data_ex(attr_info, sizeof(struct EA_INFO)); if (!*info) goto out; /* Check Ea limit. */ size = le32_to_cpu((*info)->size); if (size > sbi->ea_max_size) { err = -EFBIG; goto out; } if (attr_size(attr_ea) > sbi->ea_max_size) { err = -EFBIG; goto out; } if (!size) { /* EA info persists, but xattr is empty. Looks like EA problem. */ goto out; } /* Allocate memory for packed Ea. */ ea_p = kmalloc(size_add(size, add_bytes), GFP_NOFS); if (!ea_p) return -ENOMEM; if (attr_ea->non_res) { struct runs_tree run; run_init(&run); err = attr_load_runs_range(ni, ATTR_EA, NULL, 0, &run, 0, size); if (!err) err = ntfs_read_run_nb(sbi, &run, 0, ea_p, size, NULL); run_close(&run); if (err) goto out1; } else { void *p = resident_data_ex(attr_ea, size); if (!p) goto out1; memcpy(ea_p, p, size); } memset(Add2Ptr(ea_p, size), 0, add_bytes); err = -EINVAL; /* Check all attributes for consistency. */ for (off = 0; off < size; off += ea_size) { const struct EA_FULL *ef = Add2Ptr(ea_p, off); u32 bytes = size - off; /* Check if we can use field ea->size. */ if (bytes < sizeof(ef->size)) goto out1; if (ef->size) { ea_size = le32_to_cpu(ef->size); if (ea_size > bytes) goto out1; continue; } /* Check if we can use fields ef->name_len and ef->elength. */ if (bytes < offsetof(struct EA_FULL, name)) goto out1; ea_size = ALIGN(struct_size(ef, name, 1 + ef->name_len + le16_to_cpu(ef->elength)), 4); if (ea_size > bytes) goto out1; } *ea = ea_p; return 0; out1: kfree(ea_p); out: ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); return err; } /* * ntfs_list_ea * * Copy a list of xattrs names into the buffer * provided, or compute the buffer size required. * * Return: * * Number of bytes used / required on * * -ERRNO - on failure */ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, size_t bytes_per_buffer) { const struct EA_INFO *info; struct EA_FULL *ea_all = NULL; u32 off, size; int err; size_t ret; err = ntfs_read_ea(ni, &ea_all, 0, &info); if (err) return err; if (!info || !ea_all) return 0; size = le32_to_cpu(info->size); /* Enumerate all xattrs. */ ret = 0; off = 0; while (off + sizeof(struct EA_FULL) < size) { const struct EA_FULL *ea = Add2Ptr(ea_all, off); int ea_size = unpacked_ea_size(ea); u8 name_len = ea->name_len; if (!name_len) break; if (name_len > ea_size) { ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); err = -EINVAL; /* corrupted fs. */ break; } if (buffer) { /* Check if we can use field ea->name */ if (off + ea_size > size) break; if (ret + name_len + 1 > bytes_per_buffer) { err = -ERANGE; goto out; } memcpy(buffer + ret, ea->name, name_len); buffer[ret + name_len] = 0; } ret += name_len + 1; off += ea_size; } out: kfree(ea_all); return err ? err : ret; } static int ntfs_get_ea(struct inode *inode, const char *name, size_t name_len, void *buffer, size_t size, size_t *required) { struct ntfs_inode *ni = ntfs_i(inode); const struct EA_INFO *info; struct EA_FULL *ea_all = NULL; const struct EA_FULL *ea; u32 off, len; int err; if (!(ni->ni_flags & NI_FLAG_EA)) return -ENODATA; if (!required) ni_lock(ni); len = 0; if (name_len > 255) { err = -ENAMETOOLONG; goto out; } err = ntfs_read_ea(ni, &ea_all, 0, &info); if (err) goto out; if (!info) goto out; /* Enumerate all xattrs. */ if (!find_ea(ea_all, le32_to_cpu(info->size), name, name_len, &off, NULL)) { err = -ENODATA; goto out; } ea = Add2Ptr(ea_all, off); len = le16_to_cpu(ea->elength); if (!buffer) { err = 0; goto out; } if (len > size) { err = -ERANGE; if (required) *required = len; goto out; } memcpy(buffer, ea->name + ea->name_len + 1, len); err = 0; out: kfree(ea_all); if (!required) ni_unlock(ni); return err ? err : len; } static noinline int ntfs_set_ea(struct inode *inode, const char *name, size_t name_len, const void *value, size_t val_size, int flags, bool locked, __le16 *ea_size) { struct ntfs_inode *ni = ntfs_i(inode); struct ntfs_sb_info *sbi = ni->mi.sbi; int err; struct EA_INFO ea_info; const struct EA_INFO *info; struct E |