| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2010 Red Hat, Inc. All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_extent_busy.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_trace.h" #include "xfs_discard.h" /* * Allocate a new ticket. Failing to get a new ticket makes it really hard to * recover, so we don't allow failure here. Also, we allocate in a context that * we don't want to be issuing transactions from, so we need to tell the * allocation code this as well. * * We don't reserve any space for the ticket - we are going to steal whatever * space we require from transactions as they commit. To ensure we reserve all * the space required, we need to set the current reservation of the ticket to * zero so that we know to steal the initial transaction overhead from the * first transaction commit. */ static struct xlog_ticket * xlog_cil_ticket_alloc( struct xlog *log) { struct xlog_ticket *tic; tic = xlog_ticket_alloc(log, 0, 1, 0); /* * set the current reservation to zero so we know to steal the basic * transaction overhead reservation from the first transaction commit. */ tic->t_curr_res = 0; tic->t_iclog_hdrs = 0; return tic; } static inline void xlog_cil_set_iclog_hdr_count(struct xfs_cil *cil) { struct xlog *log = cil->xc_log; atomic_set(&cil->xc_iclog_hdrs, (XLOG_CIL_BLOCKING_SPACE_LIMIT(log) / (log->l_iclog_size - log->l_iclog_hsize))); } /* * Check if the current log item was first committed in this sequence. * We can't rely on just the log item being in the CIL, we have to check * the recorded commit sequence number. * * Note: for this to be used in a non-racy manner, it has to be called with * CIL flushing locked out. As a result, it should only be used during the * transaction commit process when deciding what to format into the item. */ static bool xlog_item_in_current_chkpt( struct xfs_cil *cil, struct xfs_log_item *lip) { if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) return false; /* * li_seq is written on the first commit of a log item to record the * first checkpoint it is written to. Hence if it is different to the * current sequence, we're in a new checkpoint. */ return lip->li_seq == READ_ONCE(cil->xc_current_sequence); } bool xfs_log_item_in_current_chkpt( struct xfs_log_item *lip) { return xlog_item_in_current_chkpt(lip->li_log->l_cilp, lip); } /* * Unavoidable forward declaration - xlog_cil_push_work() calls * xlog_cil_ctx_alloc() itself. */ static void xlog_cil_push_work(struct work_struct *work); static struct xfs_cil_ctx * xlog_cil_ctx_alloc(void) { struct xfs_cil_ctx *ctx; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&ctx->committing); INIT_LIST_HEAD(&ctx->busy_extents.extent_list); INIT_LIST_HEAD(&ctx->log_items); INIT_LIST_HEAD(&ctx->lv_chain); INIT_WORK(&ctx->push_work, xlog_cil_push_work); return ctx; } /* * Aggregate the CIL per cpu structures into global counts, lists, etc and * clear the percpu state ready for the next context to use. This is called * from the push code with the context lock held exclusively, hence nothing else * will be accessing or modifying the per-cpu counters. */ static void xlog_cil_push_pcp_aggregate( struct xfs_cil *cil, struct xfs_cil_ctx *ctx) { struct xlog_cil_pcp *cilpcp; int cpu; for_each_cpu(cpu, &ctx->cil_pcpmask) { cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); ctx->ticket->t_curr_res += cilpcp->space_reserved; cilpcp->space_reserved = 0; if (!list_empty(&cilpcp->busy_extents)) { list_splice_init(&cilpcp->busy_extents, &ctx->busy_extents.extent_list); } if (!list_empty(&cilpcp->log_items)) list_splice_init(&cilpcp->log_items, &ctx->log_items); /* * We're in the middle of switching cil contexts. Reset the * counter we use to detect when the current context is nearing * full. */ cilpcp->space_used = 0; } } /* * Aggregate the CIL per-cpu space used counters into the global atomic value. * This is called when the per-cpu counter aggregation will first pass the soft * limit threshold so we can switch to atomic counter aggregation for accurate * detection of hard limit traversal. */ static void xlog_cil_insert_pcp_aggregate( struct xfs_cil *cil, struct xfs_cil_ctx *ctx) { int cpu; int count = 0; /* Trigger atomic updates then aggregate only for the first caller */ if (!test_and_clear_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) return; /* * We can race with other cpus setting cil_pcpmask. However, we've * atomically cleared PCP_SPACE which forces other threads to add to * the global space used count. cil_pcpmask is a superset of cilpcp * structures that could have a nonzero space_used. */ for_each_cpu(cpu, &ctx->cil_pcpmask) { struct xlog_cil_pcp *cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); count += xchg(&cilpcp->space_used, 0); } atomic_add(count, &ctx->space_used); } static void xlog_cil_ctx_switch( struct xfs_cil *cil, struct xfs_cil_ctx *ctx) { xlog_cil_set_iclog_hdr_count(cil); set_bit(XLOG_CIL_EMPTY, &cil->xc_flags); set_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags); ctx->sequence = ++cil->xc_current_sequence; ctx->cil = cil; cil->xc_ctx = ctx; } /* * After the first stage of log recovery is done, we know where the head and * tail of the log are. We need this log initialisation done before we can * initialise the first CIL checkpoint context. * * Here we allocate a log ticket to track space usage during a CIL push. This * ticket is passed to xlog_write() directly so that we don't slowly leak log * space by failing to account for space used by log headers and additional * region headers for split regions. */ void xlog_cil_init_post_recovery( struct xlog *log) { log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log); log->l_cilp->xc_ctx->sequence = 1; xlog_cil_set_iclog_hdr_count(log->l_cilp); } static inline int xlog_cil_iovec_space( uint niovecs) { return round_up((sizeof(struct xfs_log_vec) + niovecs * sizeof(struct xfs_log_iovec)), sizeof(uint64_t)); } /* * Allocate or pin log vector buffers for CIL insertion. * * The CIL currently uses disposable buffers for copying a snapshot of the * modified items into the log during a push. The biggest problem with this is * the requirement to allocate the disposable buffer during the commit if: * a) does not exist; or * b) it is too small * * If we do this allocation within xlog_cil_insert_format_items(), it is done * under the xc_ctx_lock, which means that a CIL push cannot occur during * the memory allocation. This means that we have a potential deadlock situation * under low memory conditions when we have lots of dirty metadata pinned in * the CIL and we need a CIL commit to occur to free memory. * * To avoid this, we need to move the memory allocation outside the * xc_ctx_lock, but because the log vector buffers are disposable, that opens * up a TOCTOU race condition w.r.t. the CIL committing and removing the log * vector buffers between the check and the formatting of the item into the * log vector buffer within the xc_ctx_lock. * * Because the log vector buffer needs to be unchanged during the CIL push * process, we cannot share the buffer between the transaction commit (which * modifies the buffer) and the CIL push context that is writing the changes * into the log. This means skipping preallocation of buffer space is * unreliable, but we most definitely do not want to be allocating and freeing * buffers unnecessarily during commits when overwrites can be done safely. * * The simplest solution to this problem is to allocate a shadow buffer when a * log item is committed for the second time, and then to only use this buffer * if necessary. The buffer can remain attached to the log item until such time * it is needed, and this is the buffer that is reallocated to match the size of * the incoming modification. Then during the formatting of the item we can swap * the active buffer with the new one if we can't reuse the existing buffer. We * don't free the old buffer as it may be reused on the next modification if * it's size is right, otherwise we'll free and reallocate it at that point. * * This function builds a vector for the changes in each log item in the * transaction. It then works out the length of the buffer needed for each log * item, allocates them and attaches the vector to the log item in preparation * for the formatting step which occurs under the xc_ctx_lock. * * While this means the memory footprint goes up, it avoids the repeated * alloc/free pattern that repeated modifications of an item would otherwise * cause, and hence minimises the CPU overhead of such behaviour. */ static void xlog_cil_alloc_shadow_bufs( struct xlog *log, struct xfs_trans *tp) { struct xfs_log_item *lip; list_for_each_entry(lip, &tp->t_items, li_trans) { struct xfs_log_vec *lv; int niovecs = 0; int nbytes = 0; int buf_size; bool ordered = false; /* Skip items which aren't dirty in this transaction. */ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; /* get number of vecs and size of data to be stored */ lip->li_ops->iop_size(lip, &niovecs, &nbytes); /* * Ordered items need to be tracked but we do not wish to write * them. We need a logvec to track the object, but we do not * need an iovec or buffer to be allocated for copying data. */ if (niovecs == XFS_LOG_VEC_ORDERED) { ordered = true; niovecs = 0; nbytes = 0; } /* * We 64-bit align the length of each iovec so that the start of * the next one is naturally aligned. We'll need to account for * that slack space here. * * We also add the xlog_op_header to each region when * formatting, but that's not accounted to the size of the item * at this point. Hence we'll need an addition number of bytes * for each vector to hold an opheader. * * Then round nbytes up to 64-bit alignment so that the initial * buffer alignment is easy to calculate and verify. */ nbytes += niovecs * (sizeof(uint64_t) + sizeof(struct xlog_op_header)); nbytes = round_up(nbytes, sizeof(uint64_t)); /* * The data buffer needs to start 64-bit aligned, so round up * that space to ensure we can align it appropriately and not * overrun the buffer. */ buf_size = nbytes + xlog_cil_iovec_space(niovecs); /* * if we have no shadow buffer, or it is too small, we need to * reallocate it. */ if (!lip->li_lv_shadow || buf_size > lip->li_lv_shadow->lv_size) { /* * We free and allocate here as a realloc would copy * unnecessary data. We don't use kvzalloc() for the * same reason - we don't need to zero the data area in * the buffer, only the log vector header and the iovec * storage. */ kvfree(lip->li_lv_shadow); lv = xlog_kvmalloc(buf_size); memset(lv, 0, xlog_cil_iovec_space(niovecs)); INIT_LIST_HEAD(&lv->lv_list); lv->lv_item = lip; lv->lv_size = buf_size; if (ordered) lv->lv_buf_len = XFS_LOG_VEC_ORDERED; else lv->lv_iovecp = (struct xfs_log_iovec *)&lv[1]; lip->li_lv_shadow = lv; } else { /* same or smaller, optimise common overwrite case */ lv = lip->li_lv_shadow; if (ordered) lv->lv_buf_len = XFS_LOG_VEC_ORDERED; else lv->lv_buf_len = 0; lv->lv_bytes = 0; } /* Ensure the lv is set up according to ->iop_size */ lv->lv_niovecs = niovecs; /* The allocated data region lies beyond the iovec region */ lv->lv_buf = (char *)lv + xlog_cil_iovec_space(niovecs); } } /* * Prepare the log item for insertion into the CIL. Calculate the difference in * log space it will consume, and if it is a new item pin it as well. */ STATIC void xfs_cil_prepare_item( struct xlog *log, struct xfs_log_vec *lv, struct xfs_log_vec *old_lv, int *diff_len) { /* Account for the new LV being passed in */ if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) *diff_len += lv->lv_bytes; /* * If there is no old LV, this is the first time we've seen the item in * this CIL context and so we need to pin it. If we are replacing the * old_lv, then remove the space it accounts for and make it the shadow * buffer for later freeing. In both cases we are now switching to the * shadow buffer, so update the pointer to it appropriately. */ if (!old_lv) { if (lv->lv_item->li_ops->iop_pin) lv->lv_item->li_ops->iop_pin(lv->lv_item); lv->lv_item->li_lv_shadow = NULL; } else if (old_lv != lv) { ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED); *diff_len -= old_lv->lv_bytes; lv->lv_item->li_lv_shadow = old_lv; } /* attach new log vector to log item */ lv->lv_item->li_lv = lv; /* * If this is the first time the item is being committed to the * CIL, store the sequence number on the log item so we can * tell in future commits whether this is the first checkpoint * the item is being committed into. */ if (!lv->lv_item->li_seq) lv->lv_item->li_seq = log->l_cilp->xc_ctx->sequence; } /* * Format log item into a flat buffers * * For delayed logging, we need to hold a formatted buffer containing all the * changes on the log item. This enables us to relog the item in memory and * write it out asynchronously without needing to relock the object that was * modified at the time it gets written into the iclog. * * This function takes the prepared log vectors attached to each log item, and * formats the changes into the log vector buffer. The buffer it uses is * dependent on the current state of the vector in the CIL - the shadow lv is * guaranteed to be large enough for the current modification, but we will only * use that if we can't reuse the existing lv. If we can't reuse the existing * lv, then simple swap it out for the shadow lv. We don't free it - that is * done lazily either by th enext modification or the freeing of the log item. * * We don't set up region headers during this process; we simply copy the * regions into the flat buffer. We can do this because we still have to do a * formatting step to write the regions into the iclog buffer. Writing the * ophdrs during the iclog write means that we can support splitting large * regions across iclog boundares without needing a change in the format of the * item/region encapsulation. * * Hence what we need to do now is change the rewrite the vector array to point * to the copied region inside the buffer we just allocated. This allows us to * format the regions into the iclog as though they are being formatted * directly out of the objects themselves. */ static void xlog_cil_insert_format_items( struct xlog *log, struct xfs_trans *tp, int *diff_len) { struct xfs_log_item *lip; /* Bail out if we didn't find a log item. */ if (list_empty(&tp->t_items)) { ASSERT(0); return; } list_for_each_entry(lip, &tp->t_items, li_trans) { struct xfs_log_vec *lv; struct xfs_log_vec *old_lv = NULL; struct xfs_log_vec *shadow; bool ordered = false; /* Skip items which aren't dirty in this transaction. */ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; /* * The formatting size information is already attached to * the shadow lv on the log item. */ shadow = lip->li_lv_shadow; if (shadow->lv_buf_len == XFS_LOG_VEC_ORDERED) ordered = true; /* Skip items that do not have any vectors for writing */ if (!shadow->lv_niovecs && !ordered) continue; /* compare to existing item size */ old_lv = lip->li_lv; if (lip->li_lv && shadow->lv_size <= lip->li_lv->lv_size) { /* same or smaller, optimise common overwrite case */ lv = lip->li_lv; if (ordered) goto insert; /* * set the item up as though it is a new insertion so * that the space reservation accounting is correct. */ *diff_len -= lv->lv_bytes; /* Ensure the lv is set up according to ->iop_size */ lv->lv_niovecs = shadow->lv_niovecs; /* reset the lv buffer information for new formatting */ lv->lv_buf_len = 0; lv->lv_bytes = 0; lv->lv_buf = (char *)lv + xlog_cil_iovec_space(lv->lv_niovecs); } else { /* switch to shadow buffer! */ lv = shadow; lv->lv_item = lip; if (ordered) { /* track as an ordered logvec */ ASSERT(lip->li_lv == NULL); goto insert; } } ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t))); lip->li_ops->iop_format(lip, lv); insert: xfs_cil_prepare_item(log, lv, old_lv, diff_len); } } /* * The use of lockless waitqueue_active() requires that the caller has * serialised itself against the wakeup call in xlog_cil_push_work(). That * can be done by either holding the push lock or the context lock. */ static inline bool xlog_cil_over_hard_limit( struct xlog *log, int32_t space_used) { if (waitqueue_active(&log->l_cilp->xc_push_wait)) return true; if (space_used >= XLOG_CIL_BLOCKING_SPACE_LIMIT(log)) return true; return false; } /* * Insert the log items into the CIL and calculate the difference in space * consumed by the item. Add the space to the checkpoint ticket and calculate * if the change requires additional log metadata. If it does, take that space * as well. Remove the amount of space we added to the checkpoint ticket from * the current transaction ticket so that the accounting works out correctly. */ static void xlog_cil_insert_items( struct xlog *log, struct xfs_trans *tp, uint32_t released_space) { struct xfs_cil *cil = log->l_cilp; struct xfs_cil_ctx *ctx = cil->xc_ctx; struct xfs_log_item *lip; int len = 0; int iovhdr_res = 0, split_res = 0, ctx_res = 0; int space_used; int order; unsigned int cpu_nr; struct xlog_cil_pcp *cilpcp; ASSERT(tp); /* * We can do this safely because the context can't checkpoint until we * are done so it doesn't matter exactly how we update the CIL. */ xlog_cil_insert_format_items(log, tp, &len); /* * Subtract the space released by intent cancelation from the space we * consumed so that we remove it from the CIL space and add it back to * the current transaction reservation context. */ len -= released_space; /* * Grab the per-cpu pointer for the CIL before we start any accounting. * That ensures that we are running with pre-emption disabled and so we * can't be scheduled away between split sample/update operations that * are done without outside locking to serialise them. */ cpu_nr = get_cpu(); cilpcp = this_cpu_ptr(cil->xc_pcp); /* Tell the future push that there was work added by this CPU. */ if (!cpumask_test_cpu(cpu_nr, &ctx->cil_pcpmask)) cpumask_test_and_set_cpu(cpu_nr, &ctx->cil_pcpmask); /* * We need to take the CIL checkpoint unit reservation on the first * commit into the CIL. Test the XLOG_CIL_EMPTY bit first so we don't * unnecessarily do an atomic op in the fast path here. We can clear the * XLOG_CIL_EMPTY bit as we are under the xc_ctx_lock here and that * needs to be held exclusively to reset the XLOG_CIL_EMPTY bit. */ if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags) && test_and_clear_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) ctx_res = ctx->ticket->t_unit_res; /* * Check if we need to steal iclog headers. atomic_read() is not a * locked atomic operation, so we can check the value before we do any * real atomic ops in the fast path. If we've already taken the CIL unit * reservation from this commit, we've already got one iclog header * space reserved so we have to account for that otherwise we risk * overrunning the reservation on this ticket. * * If the CIL is already at the hard limit, we might need more header * space that originally reserved. So steal more header space from every * commit that occurs once we are over the hard limit to ensure the CIL * push won't run out of reservation space. * * This can steal more than we need, but that's OK. * * The cil->xc_ctx_lock provides the serialisation necessary for safely * calling xlog_cil_over_hard_limit() in this context. */ space_used = atomic_read(&ctx->space_used) + cilpcp->space_used + len; if (atomic_read(&cil->xc_iclog_hdrs) > 0 || xlog_cil_over_hard_limit(log, space_used)) { split_res = log->l_iclog_hsize + sizeof(struct xlog_op_header); if (ctx_res) ctx_res += split_res * (tp->t_ticket->t_iclog_hdrs - 1); else ctx_res = split_res * tp->t_ticket->t_iclog_hdrs; atomic_sub(tp->t_ticket->t_iclog_hdrs, &cil->xc_iclog_hdrs); } cilpcp->space_reserved += ctx_res; /* * Accurately account when over the soft limit, otherwise fold the * percpu count into the global count if over the per-cpu threshold. */ if (!test_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) { atomic_add(len, &ctx->space_used); } else if (cilpcp->space_used + len > (XLOG_CIL_SPACE_LIMIT(log) / num_online_cpus())) { space_used = atomic_add_return(cilpcp->space_used + len, &ctx->space_used); cilpcp->space_used = 0; /* * If we just transitioned over the soft limit, we need to * transition to the global atomic counter. */ if (space_used >= XLOG_CIL_SPACE_LIMIT(log)) xlog_cil_insert_pcp_aggregate(cil, ctx); } else { cilpcp->space_used += len; } /* attach the transaction to the CIL if it has any busy extents */ if (!list_empty(&tp->t_busy)) list_splice_init(&tp->t_busy, &cilpcp->busy_extents); /* * Now update the order of everything modified in the transaction * and insert items into the CIL if they aren't already there. * We do this here so we only need to take the CIL lock once during * the transaction commit. */ order = atomic_inc_return(&ctx->order_id); list_for_each_entry(lip, &tp->t_items, li_trans) { /* Skip items which aren't dirty in this transaction. */ if (!test_bit(XFS_LI_DIRTY, &lip->li_flags)) continue; lip->li_order_id = order; if (!list_empty(&lip->li_cil)) continue; list_add_tail(&lip->li_cil, &cilpcp->log_items); } put_cpu(); /* * If we've overrun the reservation, dump the tx details before we move * the log items. Shutdown is imminent... */ tp->t_ticket->t_curr_res -= ctx_res + len; if (WARN_ON(tp->t_ticket->t_curr_res < 0)) { xfs_warn(log->l_mp, "Transaction log reservation overrun:"); xfs_warn(log->l_mp, " log items: %d bytes (iov hdrs: %d bytes)", len, iovhdr_res); xfs_warn(log->l_mp, " split region headers: %d bytes", split_res); xfs_warn(log->l_mp, " ctx ticket: %d bytes", ctx_res); xlog_print_trans(tp); xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } } static inline void xlog_cil_ail_insert_batch( struct xfs_ail *ailp, struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t commit_lsn) { int i; spin_lock(&ailp->ail_lock); /* xfs_trans_ail_update_bulk drops ailp->ail_lock */ xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn); for (i = 0; i < nr_items; i++) { struct xfs_log_item *lip = log_items[i]; if (lip->li_ops->iop_unpin) lip->li_ops->iop_unpin(lip, 0); } } /* * Take the checkpoint's log vector chain of items and insert the attached log * items into the AIL. This uses bulk insertion techniques to minimise AIL lock * traffic. * * The AIL tracks log items via the start record LSN of the checkpoint, * not the commit record LSN. This is because we can pipeline multiple * checkpoints, and so the start record of checkpoint N+1 can be * written before the commit record of checkpoint N. i.e: * * start N commit N * +-------------+------------+----------------+ * start N+1 commit N+1 * * The tail of the log cannot be moved to the LSN of commit N when all * the items of that checkpoint are written back, because then the * start record for N+1 is no longer in the active portion of the log * and recovery will fail/corrupt the filesystem. * * Hence when all the log items in checkpoint N are written back, the * tail of the log most now only move as far forwards as the start LSN * of checkpoint N+1. * * If we are called with the aborted flag set, it is because a log write during * a CIL checkpoint commit has failed. In this case, all the items in the * checkpoint have already gone through iop_committed and iop_committing, which * means that checkpoint commit abort handling is treated exactly the same as an * iclog write error even though we haven't started any IO yet. Hence in this * case all we need to do is iop_committed processing, followed by an * iop_unpin(aborted) call. * * The AIL cursor is used to optimise the insert process. If commit_lsn is not * at the end of the AIL, the insert cursor avoids the need to walk the AIL to * find the insertion point on every xfs_log_item_batch_insert() call. This * saves a lot of needless list walking and is a net win, even though it * slightly increases that amount of AIL lock traffic to set it up and tear it * down. */ static void xlog_cil_ail_insert( struct xfs_cil_ctx *ctx, bool aborted) { #define LOG_ITEM_BATCH_SIZE 32 struct xfs_ail *ailp = ctx->cil->xc_log->l_ailp; struct xfs_log_item *log_items[LOG_ITEM_BATCH_SIZE]; struct xfs_log_vec *lv; struct xfs_ail_cursor cur; xfs_lsn_t old_head; int i = 0; /* * Update the AIL head LSN with the commit record LSN of this * checkpoint. As iclogs are always completed in order, this should * always be the same (as iclogs can contain multiple commit records) or * higher LSN than the current head. We do this before insertion of the * items so that log space checks during insertion will reflect the * space that this checkpoint has already consumed. We call * xfs_ail_update_finish() so that tail space and space-based wakeups * will be recalculated appropriately. */ ASSERT(XFS_LSN_CMP(ctx->commit_lsn, ailp->ail_head_lsn) >= 0 || aborted); spin_lock(&ailp->ail_lock); xfs_trans_ail_cursor_last(ailp, &cur, ctx->start_lsn); old_head = ailp->ail_head_lsn; ailp->ail_head_lsn = ctx->commit_lsn; /* xfs_ail_update_finish() drops the ail_lock */ xfs_ail_update_finish(ailp, NULLCOMMITLSN); /* * We move the AIL head forwards to account for the space used in the * log before we remove that space from the grant heads. This prevents a * transient condition where reservation space appears to become * available on return, only for it to disappear again immediately as * the AIL head update accounts in the log tail space. */ smp_wmb(); /* paired with smp_rmb in xlog_grant_space_left */ xlog_grant_return_space(ailp->ail_log, old_head, ailp->ail_head_lsn); /* unpin all the log items */ list_for_each_entry(lv, &ctx->lv_chain, lv_list) { struct xfs_log_item *lip = lv->lv_item; xfs_lsn_t item_lsn; if (aborted) set_bit(XFS_LI_ABORTED, &lip->li_flags); if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) { lip->li_ops->iop_release(lip); continue; } if (lip->li_ops->iop_committed) item_lsn = lip->li_ops->iop_committed(lip, ctx->start_lsn); else item_lsn = ctx->start_lsn; /* item_lsn of -1 means the item needs no further processing */ if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0) continue; /* * if we are aborting the operation, no point in inserting the * object into the AIL as we are in a shutdown situation. */ if (aborted) { ASSERT(xlog_is_shutdown(ailp->ail_log)); if (lip->li_ops->iop_unpin) lip->li_ops->iop_unpin(lip, 1); continue; } if (item_lsn != ctx->start_lsn) { /* * Not a bulk update option due to unusual item_lsn. * Push into AIL immediately, rechecking the lsn once * we have the ail lock. Then unpin the item. This does * not affect the AIL cursor the bulk insert path is * using. */ spin_lock(&ailp->ail_lock); if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0) xfs_trans_ail_update(ailp, lip, item_lsn); else spin_unlock(&ailp->ail_lock); if (lip->li_ops->iop_unpin) lip->li_ops->iop_unpin(lip, 0); continue; } /* Item is a candidate for bulk AIL insert. */ log_items[i++] = lv->lv_item; if (i >= LOG_ITEM_BATCH_SIZE) { xlog_cil_ail_insert_batch(ailp, &cur, log_items, LOG_ITEM_BATCH_SIZE, ctx->start_lsn); i = 0; } } /* make sure we insert the remainder! */ if (i) xlog_cil_ail_insert_batch(ailp, &cur, log_items, i, ctx->start_lsn); spin_lock(&ailp->ail_lock); xfs_trans_ail_cursor_done(&cur); spin_unlock(&ailp->ail_lock); } static void xlog_cil_free_logvec( struct list_head *lv_chain) { struct xfs_log_vec *lv; while (!list_empty(lv_chain)) { lv = list_first_entry(lv_chain, struct xfs_log_vec, lv_list); list_del_init(&lv->lv_list); kvfree(lv); } } /* * Mark all items committed and clear busy extents. We free the log vector * chains in a separate pass so that we unpin the log items as quickly as * possible. */ static void xlog_cil_committed( struct xfs_cil_ctx *ctx) { struct xfs_mount *mp = ctx->cil->xc_log->l_mp; bool abort = xlog_is_shutdown(ctx->cil->xc_log); /* * If the I/O failed, we're aborting the commit and already shutdown. * Wake any commit waiters before aborting the log items so we don't * block async log pushers on callbacks. Async log pushers explicitly do * not wait on log force completion because they may be holding locks * required to unpin items. */ if (abort) { spin_lock(&ctx->cil->xc_push_lock); wake_up_all(&ctx->cil->xc_start_wait); wake_up_all(&ctx->cil->xc_commit_wait); spin_unlock(&ctx->cil->xc_push_lock); } xlog_cil_ail_insert(ctx, abort); xfs_extent_busy_sort(&ctx->busy_extents.extent_list); xfs_extent_busy_clear(&ctx->busy_extents.extent_list, xfs_has_discard(mp) && !abort); spin_lock(&ctx->cil->xc_push_lock); list_del(&ctx->committing); spin_unlock(&ctx->cil->xc_push_lock); xlog_cil_free_logvec(&ctx->lv_chain); if (!list_empty(&ctx->busy_extents.extent_list)) { ctx->busy_extents.owner = ctx; xfs_discard_extents(mp, &ctx->busy_extents); return; } kfree(ctx); } void xlog_cil_process_committed( struct list_head *list) { struct xfs_cil_ctx *ctx; while ((ctx = list_first_entry_or_null(list, struct xfs_cil_ctx, iclog_entry))) { list_del(&ctx->iclog_entry); xlog_cil_committed(ctx); } } /* * Record the LSN of the iclog we were just granted space to start writing into. * If the context doesn't have a start_lsn recorded, then this iclog will * contain the start record for the checkpoint. Otherwise this write contains * the commit record for the checkpoint. */ void xlog_cil_set_ctx_write_state( struct xfs_cil_ctx *ctx, struct xlog_in_core *iclog) { struct xfs_cil *cil = ctx->cil; xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header.h_lsn); ASSERT(!ctx->commit_lsn); if (!ctx->start_lsn) { spin_lock(&cil->xc_push_lock); /* * The LSN we need to pass to the log items on transaction * commit is the LSN reported by the first log vector write, not * the commit lsn. If we use the commit record lsn then we can * move the grant write head beyond the tail LSN and overwrite * it. */ ctx->start_lsn = lsn; wake_up_all(&cil->xc_start_wait); spin_unlock(&cil->xc_push_lock); /* * Make sure the metadata we are about to overwrite in the log * has been flushed to stable storage before this iclog is * issued. */ spin_lock(&cil->xc_log->l_icloglock); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; spin_unlock(&cil->xc_log->l_icloglock); return; } /* * Take a reference to the iclog for the context so that we still hold * it when xlog_write is done and has released it. This means the * context controls when the iclog is released for IO. */ atomic_inc(&iclog->ic_refcnt); /* * xlog_state_get_iclog_space() guarantees there is enough space in the * iclog for an entire commit record, so we can attach the context * callbacks now. This needs to be done before we make the commit_lsn * visible to waiters so that checkpoints with commit records in the * same iclog order their IO completion callbacks in the same order that * the commit records appear in the iclog. */ spin_lock(&cil->xc_log->l_icloglock); list_add_tail(&ctx->iclog_entry, &iclog->ic_callbacks); spin_unlock(&cil->xc_log->l_icloglock); /* * Now we can record the commit LSN and wake anyone waiting for this * sequence to have the ordered commit record assigned to a physical * location in the log. */ spin_lock(&cil->xc_push_lock); ctx->commit_iclog = iclog; ctx->commit_lsn = lsn; wake_up_all(&cil->xc_commit_wait); spin_unlock(&cil->xc_push_lock); } /* * Ensure that the order of log writes follows checkpoint sequence order. This * relies on the context LSN being zero until the log write has guaranteed the * LSN that the log write will start at via xlog_state_get_iclog_space(). */ enum _record_type { _START_RECORD, _COMMIT_RECORD, }; static int xlog_cil_order_write( struct xfs_cil *cil, xfs_csn_t sequence, enum _record_type record) { struct xfs_cil_ctx *ctx; restart: spin_lock(&cil->xc_push_lock); list_for_each_entry(ctx, &cil->xc_committing, committing) { /* * Avoid getting stuck in this loop because we were woken by the * shutdown, but then went back to sleep once already in the * shutdown state. */ if (xlog_is_shutdown(cil->xc_log)) { spin_unlock(&cil->xc_push_lock); return -EIO; } /* * Higher sequences will wait for this one so skip them. * Don't wait for our own sequence, either. */ if (ctx->sequence >= sequence) continue; /* Wait until the LSN for the record has been recorded. */ switch (record) { case _START_RECORD: if (!ctx->start_lsn) { xlog_wait(&cil->xc_start_wait, &cil->xc_push_lock); goto restart; } break; case _COMMIT_RECORD: if (!ctx->commit_lsn) { xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock); goto restart; } break; } } spin_unlock(&cil->xc_push_lock); return 0; } /* * Write out the log vector change now attached to the CIL context. This will * write a start record that needs to be strictly ordered in ascending CIL * sequence order so that log recovery will always use in-order start LSNs when * replaying checkpoints. */ static int xlog_cil_write_chain( struct xfs_cil_ctx *ctx, uint32_t chain_len) { struct xlog *log = ctx->cil->xc_log; int error; error = xlog_cil_order_write(ctx->cil, ctx->sequence, _START_RECORD); if (error) return error; return xlog_write(log, ctx, &ctx->lv_chain, ctx->ticket, chain_len); } /* * Write out the commit record of a checkpoint transaction to close off a * running log write. These commit records are strictly ordered in ascending CIL * sequence order so that log recovery will always replay the checkpoints in the * correct order. */ static int xlog_cil_write_commit_record( struct xfs_cil_ctx *ctx) { struct xlog *log = ctx->cil->xc_log; struct xlog_op_header ophdr = { .oh_clientid = XFS_TRANSACTION, .oh_tid = cpu_to_be32(ctx->ticket->t_tid), .oh_flags = XLOG_COMMIT_TRANS, }; struct xfs_log_iovec reg = { .i_addr = &ophdr, .i_len = sizeof(struct xlog_op_header), .i_type = XLOG_REG_TYPE_COMMIT, }; struct xfs_log_vec vec = { .lv_niovecs = 1, .lv_iovecp = ®, }; int error; LIST_HEAD(lv_chain); list_add(&vec.lv_list, &lv_chain); if (xlog_is_shutdown(log)) return -EIO; error = xlog_cil_order_write(ctx->cil, ctx->sequence, _COMMIT_RECORD); if (error) return error; /* account for space used by record data */ ctx->ticket->t_curr_res -= reg.i_len; error = xlog_write(log, ctx, &lv_chain, ctx->ticket, reg.i_len); if (error) xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); return error; } struct xlog_cil_trans_hdr { struct xlog_op_header oph[2]; struct xfs_trans_header thdr; struct xfs_log_iovec lhdr[2]; }; /* * Build a checkpoint transaction header to begin the journal transaction. We * need to account for the space used by the transaction header here as it is * not accounted for in xlog_write(). * * This is the only place we write a transaction header, so we also build the * log opheaders that indicate the start of a log transaction and wrap the * transaction header. We keep the start record in it's own log vector rather * than compacting them into a single region as this ends up making the logic * in xlog_write() for handling empty opheaders for start, commit and unmount * records much simpler. */ static void xlog_cil_build_trans_hdr( struct xfs_cil_ctx *ctx, struct xlog_cil_trans_hdr *hdr, struct xfs_log_vec *lvhdr, int num_iovecs) { struct xlog_ticket *tic = ctx->ticket; __be32 tid = cpu_to_be32(tic->t_tid); memset(hdr, 0, sizeof(*hdr)); /* Log start record */ hdr->oph[0].oh_tid = tid; hdr->oph[0].oh_clientid = XFS_TRANSACTION; hdr->oph[0].oh_flags = XLOG_START_TRANS; /* log iovec region pointer */ hdr->lhdr[0].i_addr = &hdr->oph[0]; hdr->lhdr[0].i_len = sizeof(struct xlog_op_header); hdr->lhdr[0].i_type = XLOG_REG_TYPE_LRHEADER; /* log opheader */ hdr->oph[1].oh_tid = tid; hdr->oph[1].oh_clientid = XFS_TRANSACTION; hdr->oph[1].oh_len = cpu_to_be32(sizeof(struct xfs_trans_header)); /* transaction header in host byte order format */ hdr->thdr.th_magic = XFS_TRANS_HEADER_MAGIC; hdr->thdr.th_type = XFS_TRANS_CHECKPOINT; hdr->thdr.th_tid = tic->t_tid; hdr->thdr.th_num_items = num_iovecs; /* log iovec region pointer */ hdr->lhdr[1].i_addr = &hdr->oph[1]; hdr->lhdr[1].i_len = sizeof(struct xlog_op_header) + sizeof(struct xfs_trans_header); hdr->lhdr[1].i_type = XLOG_REG_TYPE_TRANSHDR; lvhdr->lv_niovecs = 2; lvhdr->lv_iovecp = &hdr->lhdr[0]; lvhdr->lv_bytes = hdr->lhdr[0].i_len + hdr->lhdr[1].i_len; tic->t_curr_res -= lvhdr->lv_bytes; } /* * CIL item reordering compare function. We want to order in ascending ID order, * but we want to leave items with the same ID in the order they were added to * the list. This is important for operations like reflink where we log 4 order * dependent intents in a single transaction when we overwrite an existing * shared extent with a new shared extent. i.e. BUI(unmap), CUI(drop), * CUI (inc), BUI(remap)... */ static int xlog_cil_order_cmp( void *priv, const struct list_head *a, const struct list_head *b) { struct xfs_log_vec *l1 = container_of(a, struct xfs_log_vec, lv_list); struct xfs_log_vec *l2 = container_of(b, struct xfs_log_vec, lv_list); return l1->lv_order_id > l2->lv_order_id; } /* * Pull all the log vectors off the items in the CIL, and remove the items from * the CIL. We don't need the CIL lock here because it's only needed on the * transaction commit side which is currently locked out by the flush lock. * * If a log item is marked with a whiteout, we do not need to write it to the * journal and so we just move them to the whiteout list for the caller to * dispose of appropriately. */ static void xlog_cil_build_lv_chain( struct xfs_cil_ctx *ctx, struct list_head *whiteouts, uint32_t *num_iovecs, uint32_t *num_bytes) { while (!list_empty(&ctx->log_items)) { struct xfs_log_item *item; struct xfs_log_vec *lv; item = list_first_entry(&ctx->log_items, struct xfs_log_item, li_cil); if (test_bit(XFS_LI_WHITEOUT, &item->li_flags)) { list_move(&item->li_cil, whiteouts); trace_xfs_cil_whiteout_skip(item); continue; } lv = item->li_lv; lv->lv_order_id = item->li_order_id; /* we don't write ordered log vectors */ if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) *num_bytes += lv->lv_bytes; *num_iovecs += lv->lv_niovecs; list_add_tail(&lv->lv_list, &ctx->lv_chain); list_del_init(&item->li_cil); item->li_order_id = 0; item->li_lv = NULL; } } static void xlog_cil_cleanup_whiteouts( struct list_head *whiteouts) { while (!list_empty(whiteouts)) { struct xfs_log_item *item = list_first_entry(whiteouts, struct xfs_log_item, li_cil); list_del_init(&item->li_cil); trace_xfs_cil_whiteout_unpin(item); item->li_ops->iop_unpin(item, 1); } } /* * Push the Committed Item List to the log. * * If the current sequence is the same as xc_push_seq we need to do a flush. If * xc_push_seq is less than the current sequence, then it has already been * flushed and we don't need to do anything - the caller will wait for it to * complete if necessary. * * xc_push_seq is checked unlocked against the sequence number for a match. * Hence we can allow log forces to run racily and not issue pushes for the * same sequence twice. If we get a race between multiple pushes for the same * sequence they will block on the first one and then abort, hence avoiding * needless pushes. * * This runs from a workqueue so it does not inherent any specific memory * allocation context. However, we do not want to block on memory reclaim * recursing back into the filesystem because this push may have been triggered * by memory reclaim itself. Hence we really need to run under full GFP_NOFS * contraints here. */ static void xlog_cil_push_work( struct work_struct *work) { unsigned int nofs_flags = memalloc_nofs_save(); struct xfs_cil_ctx *ctx = container_of(work, struct xfs_cil_ctx, push_work); struct xfs_cil *cil = ctx->cil; struct xlog *log = cil->xc_log; struct xfs_cil_ctx *new_ctx; int num_iovecs = 0; int num_bytes = 0; int error = 0; struct xlog_cil_trans_hdr thdr; struct xfs_log_vec lvhdr = {}; xfs_csn_t push_seq; bool push_commit_stable; LIST_HEAD (whiteouts); struct xlog_ticket *ticket; new_ctx = xlog_cil_ctx_alloc(); new_ctx->ticket = xlog_cil_ticket_alloc(log); down_write(&cil->xc_ctx_lock); spin_lock(&cil->xc_push_lock); push_seq = cil->xc_push_seq; ASSERT(push_seq <= ctx->sequence); push_commit_stable = cil->xc_push_commit_stable; cil->xc_push_commit_stable = false; /* * As we are about to switch to a new, empty CIL context, we no longer * need to throttle tasks on CIL space overruns. Wake any waiters that * the hard push throttle may have caught so they can start committing * to the new context. The ctx->xc_push_lock provides the serialisation * necessary for safely using the lockless waitqueue_active() check in * this context. */ if (waitqueue_active(&cil->xc_push_wait)) wake_up_all(&cil->xc_push_wait); xlog_cil_push_pcp_aggregate(cil, ctx); /* * Check if we've anything to push. If there is nothing, then we don't * move on to a new sequence number and so we have to be able to push * this sequence again later. */ if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) { cil->xc_push_seq = 0; spin_unlock(&cil->xc_push_lock); goto out_skip; } /* check for a previously pushed sequence */ if (push_seq < ctx->sequence) { spin_unlock(&cil->xc_push_lock); goto out_skip; } /* * We are now going to push this context, so add it to the committing * list before we do anything else. This ensures that anyone waiting on * this push can easily detect the difference between a "push in * progress" and "CIL is empty, nothing to do". * * IOWs, a wait loop can now check for: * the current sequence not being found on the committing list; * an empty CIL; and * an unchanged sequence number * to detect a push that had nothing to do and therefore does not need * waiting on. If the CIL is not empty, we get put on the committing * list before emptying the CIL and bumping the sequence number. Hence * an empty CIL and an unchanged sequence number means we jumped out * above after doing nothing. * * Hence the waiter will either find the commit sequence on the * committing list or the sequence number will be unchanged and the CIL * still dirty. In that latter case, the push has not yet started, and * so the waiter will have to continue trying to check the CIL * committing list until it is found. In extreme cases of delay, the * sequence may fully commit between the attempts the wait makes to wait * on the commit sequence. */ list_add(&ctx->committing, &cil->xc_committing); spin_unlock(&cil->xc_push_lock); xlog_cil_build_lv_chain(ctx, &whiteouts, &num_iovecs, &num_bytes); /* * Switch the contexts so we can drop the context lock and move out * of a shared context. We can't just go straight to the commit record, * though - we need to synchronise with previous and future commits so * that the commit records are correctly ordered in the log to ensure * that we process items during log IO completion in the correct order. * * For example, if we get an EFI in one checkpoint and the EFD in the * next (e.g. due to log forces), we do not want the checkpoint with * the EFD to be committed before the checkpoint with the EFI. Hence * we must strictly order the commit records of the checkpoints so * that: a) the checkpoint callbacks are attached to the iclogs in the * correct order; and b) the checkpoints are replayed in correct order * in log recovery. * * Hence we need to add this context to the committing context list so * that higher sequences will wait for us to write out a commit record * before they do. * * xfs_log_force_seq requires us to mirror the new sequence into the cil * structure atomically with the addition of this sequence to the * committing list. This also ensures that we can do unlocked checks * against the current sequence in log forces without risking * deferencing a freed context pointer. */ spin_lock(&cil->xc_push_lock); xlog_cil_ctx_switch(cil, new_ctx); spin_unlock(&cil->xc_push_lock); up_write(&cil->xc_ctx_lock); /* * Sort the log vector chain before we add the transaction headers. * This ensures we always have the transaction headers at the start * of the chain. */ list_sort(NULL, &ctx->lv_chain, xlog_cil_order_cmp); /* * Build a checkpoint transaction header and write it to the log to * begin the transaction. We need to account for the space used by the * transaction header here as it is not accounted for in xlog_write(). * Add the lvhdr to the head of the lv chain we pass to xlog_write() so * it gets written into the iclog first. */ xlog_cil_build_trans_hdr(ctx, &thdr, &lvhdr, num_iovecs); num_bytes += lvhdr.lv_bytes; list_add(&lvhdr.lv_list, &ctx->lv_chain); /* * Take the lvhdr back off the lv_chain immediately after calling * xlog_cil_write_chain() as it should not be passed to log IO * completion. */ error = xlog_cil_write_chain(ctx, num_bytes); list_del(&lvhdr.lv_list); if (error) goto out_abort_free_ticket; error = xlog_cil_write_commit_record(ctx); if (error) goto out_abort_free_ticket; /* * Grab the ticket from the ctx so we can ungrant it after releasing the * commit_iclog. The ctx may be freed by the time we return from * releasing the commit_iclog (i.e. checkpoint has been completed and * callback run) so we can't reference the ctx after the call to * xlog_state_release_iclog(). */ ticket = ctx->ticket; /* * If the checkpoint spans multiple iclogs, wait for all previous iclogs * to complete before we submit the commit_iclog. We can't use state * checks for this - ACTIVE can be either a past completed iclog or a * future iclog being filled, while WANT_SYNC through SYNC_DONE can be a * past or future iclog awaiting IO or ordered IO completion to be run. * In the latter case, if it's a future iclog and we wait on it, the we * will hang because it won't get processed through to ic_force_wait * wakeup until this commit_iclog is written to disk. Hence we use the * iclog header lsn and compare it to the commit lsn to determine if we * need to wait on iclogs or not. */ spin_lock(&log->l_icloglock); if (ctx->start_lsn != ctx->commit_lsn) { xfs_lsn_t plsn; plsn = be64_to_cpu(ctx->commit_iclog->ic_prev->ic_header.h_lsn); if (plsn && XFS_LSN_CMP(plsn, ctx->commit_lsn) < 0) { /* * Waiting on ic_force_wait orders the completion of * iclogs older than ic_prev. Hence we only need to wait * on the most recent older iclog here. */ xlog_wait_on_iclog(ctx->commit_iclog->ic_prev); spin_lock(&log->l_icloglock); } /* * We need to issue a pre-flush so that the ordering for this * checkpoint is correctly preserved down to stable storage. */ ctx->commit_iclog->ic_flags |= XLOG_ICL_NEED_FLUSH; } /* * The commit iclog must be written to stable storage to guarantee * journal IO vs metadata writeback IO is correctly ordered on stable * storage. * * If the push caller needs the commit to be immediately stable and the * commit_iclog is not yet marked as XLOG_STATE_WANT_SYNC to indicate it * will be written when released, switch it's state to WANT_SYNC right * now. */ ctx->commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA; if (push_commit_stable && ctx->commit_iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(log, ctx->commit_iclog, 0); ticket = ctx->ticket; xlog_state_release_iclog(log, ctx->commit_iclog, ticket); /* Not safe to reference ctx now! */ spin_unlock(&log->l_icloglock); xlog_cil_cleanup_whiteouts(&whiteouts); xfs_log_ticket_ungrant(log, ticket); memalloc_nofs_restore(nofs_flags); return; out_skip: up_write(&cil->xc_ctx_lock); xfs_log_ticket_put(new_ctx->ticket); kfree(new_ctx); memalloc_nofs_restore(nofs_flags); return; out_abort_free_ticket: ASSERT(xlog_is_shutdown(log)); xlog_cil_cleanup_whiteouts(&whiteouts); if (!ctx->commit_iclog) { xfs_log_ticket_ungrant(log, ctx->ticket); xlog_cil_committed(ctx); memalloc_nofs_restore(nofs_flags); return; } spin_lock(&log->l_icloglock); ticket = ctx->ticket; xlog_state_release_iclog(log, ctx->commit_iclog, ticket); /* Not safe to reference ctx now! */ spin_unlock(&log->l_icloglock); xfs_log_ticket_ungrant(log, ticket); memalloc_nofs_restore(nofs_flags); } /* * We need to push CIL every so often so we don't cache more than we can fit in * the log. The limit really is that a checkpoint can't be more than half the * log (the current checkpoint is not allowed to overwrite the previous * checkpoint), but commit latency and memory usage limit this to a smaller * size. */ static void xlog_cil_push_background( struct xlog *log) { struct xfs_cil *cil = log->l_cilp; int space_used = atomic_read(&cil->xc_ctx->space_used); /* * The cil won't be empty because we are called while holding the * context lock so whatever we added to the CIL will still be there. */ ASSERT(!test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)); /* * We are done if: * - we haven't used up all the space available yet; or * - we've already queued up a push; and * - we're not over the hard limit; and * - nothing has been over the hard limit. * * If so, we don't need to take the push lock as there's nothing to do. */ if (space_used < XLOG_CIL_SPACE_LIMIT(log) || (cil->xc_push_seq == cil->xc_current_sequence && space_used < XLOG_CIL_BLOCKING_SPACE_LIMIT(log) && !waitqueue_active(&cil->xc_push_wait))) { up_read(&cil->xc_ctx_lock); return; } spin_lock(&cil->xc_push_lock); if (cil->xc_push_seq < cil->xc_current_sequence) { cil->xc_push_seq = cil->xc_current_sequence; queue_work(cil->xc_push_wq, &cil->xc_ctx->push_work); } /* * Drop the context lock now, we can't hold that if we need to sleep * because we are over the blocking threshold. The push_lock is still * held, so blocking threshold sleep/wakeup is still correctly * serialised here. */ up_read(&cil->xc_ctx_lock); /* * If we are well over the space limit, throttle the work that is being * done until the push work on this context has begun. Enforce the hard * throttle on all transaction commits once it has been activated, even * if the committing transactions have resulted in the space usage * dipping back down under the hard limit. * * The ctx->xc_push_lock provides the serialisation necessary for safely * calling xlog_cil_over_hard_limit() in this context. */ if (xlog_cil_over_hard_limit(log, space_used)) { trace_xfs_log_cil_wait(log, cil->xc_ctx->ticket); ASSERT(space_used < log->l_logsize); xlog_wait(&cil->xc_push_wait, &cil->xc_push_lock); return; } spin_unlock(&cil->xc_push_lock); } /* * xlog_cil_push_now() is used to trigger an immediate CIL push to the sequence * number that is passed. When it returns, the work will be queued for * @push_seq, but it won't be completed. * * If the caller is performing a synchronous force, we will flush the workqueue * to get previously queued work moving to minimise the wait time they will * undergo waiting for all outstanding pushes to complete. The caller is * expected to do the required waiting for push_seq to complete. * * If the caller is performing an async push, we need to ensure that the * checkpoint is fully flushed out of the iclogs when we finish the push. If we * don't do this, then the commit record may remain sitting in memory in an * ACTIVE iclog. This then requires another full log force to push to disk, * which defeats the purpose of having an async, non-blocking CIL force * mechanism. Hence in this case we need to pass a flag to the push work to * indicate it needs to flush the commit record itself. */ static void xlog_cil_push_now( struct xlog *log, xfs_lsn_t push_seq, bool async) { struct xfs_cil *cil = log->l_cilp; if (!cil) return; ASSERT(push_seq && push_seq <= cil->xc_current_sequence); /* start on any pending background push to minimise wait time on it */ if (!async) flush_workqueue(cil->xc_push_wq); spin_lock(&cil->xc_push_lock); /* * If this is an async flush request, we always need to set the * xc_push_commit_stable flag even if something else has already queued * a push. The flush caller is asking for the CIL to be on stable * storage when the next push completes, so regardless of who has queued * the push, the flush requires stable semantics from it. */ cil->xc_push_commit_stable = async; /* * If the CIL is empty or we've already pushed the sequence then * there's no more work that we need to do. */ if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags) || push_seq <= cil->xc_push_seq) { spin_unlock(&cil->xc_push_lock); return; } cil->xc_push_seq = push_seq; queue_work(cil->xc_push_wq, &cil->xc_ctx->push_work); spin_unlock(&cil->xc_push_lock); } bool xlog_cil_empty( struct xlog *log) { struct xfs_cil *cil = log->l_cilp; bool empty = false; spin_lock(&cil->xc_push_lock); if (test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) empty = true; spin_unlock(&cil->xc_push_lock); return empty; } /* * If there are intent done items in this transaction and the related intent was * committed in the current (same) CIL checkpoint, we don't need to write either * the intent or intent done item to the journal as the change will be * journalled atomically within this checkpoint. As we cannot remove items from * the CIL here, mark the related intent with a whiteout so that the CIL push * can remove it rather than writing it to the journal. Then remove the intent * done item from the current transaction and release it so it doesn't get put * into the CIL at all. */ static uint32_t xlog_cil_process_intents( struct xfs_cil *cil, struct xfs_trans *tp) { struct xfs_log_item *lip, *ilip, *next; uint32_t len = 0; list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { if (!(lip->li_ops->flags & XFS_ITEM_INTENT_DONE)) continue; ilip = lip->li_ops->iop_intent(lip); if (!ilip || !xlog_item_in_current_chkpt(cil, ilip)) continue; set_bit(XFS_LI_WHITEOUT, &ilip->li_flags); trace_xfs_cil_whiteout_mark(ilip); len += ilip->li_lv->lv_bytes; kvfree(ilip->li_lv); ilip->li_lv = NULL; xfs_trans_del_item(lip); lip->li_ops->iop_release(lip); } return len; } /* * Commit a transaction with the given vector to the Committed Item List. * * To do this, we need to format the item, pin it in memory if required and * account for the space used by the transaction. Once we have done that we * need to release the unused reservation for the transaction, attach the * transaction to the checkpoint context so we carry the busy extents through * to checkpoint completion, and then unlock all the items in the transaction. * * Called with the context lock already held in read mode to lock out * background commit, returns without it held once background commits are * allowed again. */ void xlog_cil_commit( struct xlog *log, struct xfs_trans *tp, xfs_csn_t *commit_seq, bool regrant) { struct xfs_cil *cil = log->l_cilp; struct xfs_log_item *lip, *next; uint32_t released_space = 0; /* * Do all necessary memory allocation before we lock the CIL. * This ensures the allocation does not deadlock with a CIL * push in memory reclaim (e.g. from kswapd). */ xlog_cil_alloc_shadow_bufs(log, tp); /* lock out background commit */ down_read(&cil->xc_ctx_lock); if (tp->t_flags & XFS_TRANS_HAS_INTENT_DONE) released_space = xlog_cil_process_intents(cil, tp); xlog_cil_insert_items(log, tp, released_space); if (regrant && !xlog_is_shutdown(log)) xfs_log_ticket_regrant(log, tp->t_ticket); else xfs_log_ticket_ungrant(log, tp->t_ticket); tp->t_ticket = NULL; xfs_trans_unreserve_and_mod_sb(tp); /* * Once all the items of the transaction have been copied to the CIL, * the items can be unlocked and possibly freed. * * This needs to be done before we drop the CIL context lock because we * have to update state in the log items and unlock them before they go * to disk. If we don't, then the CIL checkpoint can race with us and * we can run checkpoint completion before we've updated and unlocked * the log items. This affects (at least) processing of stale buffers, * inodes and EFIs. */ trace_xfs_trans_commit_items(tp, _RET_IP_); list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { xfs_trans_del_item(lip); if (lip->li_ops->iop_committing) lip->li_ops->iop_committing(lip, cil->xc_ctx->sequence); } if (commit_seq) *commit_seq = cil->xc_ctx->sequence; /* xlog_cil_push_background() releases cil->xc_ctx_lock */ xlog_cil_push_background(log); } /* * Flush the CIL to stable storage but don't wait for it to complete. This * requires the CIL push to ensure the commit record for the push hits the disk, * but otherwise is no different to a push done from a log force. */ void xlog_cil_flush( struct xlog *log) { xfs_csn_t seq = log->l_cilp->xc_current_sequence; trace_xfs_log_force(log->l_mp, seq, _RET_IP_); xlog_cil_push_now(log, seq, true); /* * If the CIL is empty, make sure that any previous checkpoint that may * still be in an active iclog is pushed to stable storage. */ if (test_bit(XLOG_CIL_EMPTY, &log->l_cilp->xc_flags)) xfs_log_force(log->l_mp, 0); } /* * Conditionally push the CIL based on the sequence passed in. * * We only need to push if we haven't already pushed the sequence number given. * Hence the only time we will trigger a push here is if the push sequence is * the same as the current context. * * We return the current commit lsn to allow the callers to determine if a * iclog flush is necessary following this call. */ xfs_lsn_t xlog_cil_force_seq( struct xlog *log, xfs_csn_t sequence) { struct xfs_cil *cil = log->l_cilp; struct xfs_cil_ctx *ctx; xfs_lsn_t commit_lsn = NULLCOMMITLSN; ASSERT(sequence <= cil->xc_current_sequence); if (!sequence) sequence = cil->xc_current_sequence; trace_xfs_log_force(log->l_mp, sequence, _RET_IP_); /* * check to see if we need to force out the current context. * xlog_cil_push() handles racing pushes for the same sequence, * so no need to deal with it here. */ restart: xlog_cil_push_now(log, sequence, false); /* * See if we can find a previous sequence still committing. * We need to wait for all previous sequence commits to complete * before allowing the force of push_seq to go ahead. Hence block * on commits for those as well. */ spin_lock(&cil->xc_push_lock); list_for_each_entry(ctx, &cil->xc_committing, committing) { /* * Avoid getting stuck in this loop because we were woken by the * shutdown, but then went back to sleep once already in the * shutdown state. */ if (xlog_is_shutdown(log)) goto out_shutdown; if (ctx->sequence > sequence) continue; if (!ctx->commit_lsn) { /* * It is still being pushed! Wait for the push to * complete, then start again from the beginning. */ XFS_STATS_INC(log->l_mp, xs_log_force_sleep); xlog_wait(&cil->xc_commit_wait, &cil->xc_push_lock); goto restart; } if (ctx->sequence != sequence) continue; /* found it! */ commit_lsn = ctx->commit_lsn; } /* * The call to xlog_cil_push_now() executes the push in the background. * Hence by the time we have got here it our sequence may not have been * pushed yet. This is true if the current sequence still matches the * push sequence after the above wait loop and the CIL still contains * dirty objects. This is guaranteed by the push code first adding the * context to the committing list before emptying the CIL. * * Hence if we don't find the context in the committing list and the * current sequence number is unchanged then the CIL contents are * significant. If the CIL is empty, if means there was nothing to push * and that means there is nothing to wait for. If the CIL is not empty, * it means we haven't yet started the push, because if it had started * we would have found the context on the committing list. */ if (sequence == cil->xc_current_sequence && !test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)) { spin_unlock(&cil->xc_push_lock); goto restart; } spin_unlock(&cil->xc_push_lock); return commit_lsn; /* * We detected a shutdown in progress. We need to trigger the log force * to pass through it's iclog state machine error handling, even though * we are already in a shutdown state. Hence we can't return * NULLCOMMITLSN here as that has special meaning to log forces (i.e. * LSN is already stable), so we return a zero LSN instead. */ out_shutdown: spin_unlock(&cil->xc_push_lock); return 0; } /* * Perform initial CIL structure initialisation. */ int xlog_cil_init( struct xlog *log) { struct xfs_cil *cil; struct xfs_cil_ctx *ctx; struct xlog_cil_pcp *cilpcp; int cpu; cil = kzalloc(sizeof(*cil), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!cil) return -ENOMEM; /* * Limit the CIL pipeline depth to 4 concurrent works to bound the * concurrency the log spinlocks will be exposed to. */ cil->xc_push_wq = alloc_workqueue("xfs-cil/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_UNBOUND), 4, log->l_mp->m_super->s_id); if (!cil->xc_push_wq) goto out_destroy_cil; cil->xc_log = log; cil->xc_pcp = alloc_percpu(struct xlog_cil_pcp); if (!cil->xc_pcp) goto out_destroy_wq; for_each_possible_cpu(cpu) { cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); INIT_LIST_HEAD(&cilpcp->busy_extents); INIT_LIST_HEAD(&cilpcp->log_items); } INIT_LIST_HEAD(&cil->xc_committing); spin_lock_init(&cil->xc_push_lock); init_waitqueue_head(&cil->xc_push_wait); init_rwsem(&cil->xc_ctx_lock); init_waitqueue_head(&cil->xc_start_wait); init_waitqueue_head(&cil->xc_commit_wait); log->l_cilp = cil; ctx = xlog_cil_ctx_alloc(); xlog_cil_ctx_switch(cil, ctx); return 0; out_destroy_wq: destroy_workqueue(cil->xc_push_wq); out_destroy_cil: kfree(cil); return -ENOMEM; } void xlog_cil_destroy( struct xlog *log) { struct xfs_cil *cil = log->l_cilp; if (cil->xc_ctx) { if (cil->xc_ctx->ticket) xfs_log_ticket_put(cil->xc_ctx->ticket); kfree(cil->xc_ctx); } ASSERT(test_bit(XLOG_CIL_EMPTY, &cil->xc_flags)); free_percpu(cil->xc_pcp); destroy_workqueue(cil->xc_push_wq); kfree(cil); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015 Facebook. All rights reserved. */ #include <linux/kernel.h> #include <linux/sched/mm.h> #include "messages.h" #include "ctree.h" #include "disk-io.h" #include "locking.h" #include "free-space-tree.h" #include "transaction.h" #include "block-group.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "root-tree.h" static int __add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path); static struct btrfs_root *btrfs_free_space_root( struct btrfs_block_group *block_group) { struct btrfs_key key = { .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; if (btrfs_fs_incompat(block_group->fs_info, EXTENT_TREE_V2)) key.offset = block_group->global_root_id; return btrfs_global_root(block_group->fs_info, &key); } void set_free_space_tree_thresholds(struct btrfs_block_group *cache) { u32 bitmap_range; size_t bitmap_size; u64 num_bitmaps, total_bitmap_size; if (WARN_ON(cache->length == 0)) btrfs_warn(cache->fs_info, "block group %llu length is zero", cache->start); /* * We convert to bitmaps when the disk space required for using extents * exceeds that required for using bitmaps. */ bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS; num_bitmaps = div_u64(cache->length + bitmap_range - 1, bitmap_range); bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE; total_bitmap_size = num_bitmaps * bitmap_size; cache->bitmap_high_thresh = div_u64(total_bitmap_size, sizeof(struct btrfs_item)); /* * We allow for a small buffer between the high threshold and low * threshold to avoid thrashing back and forth between the two formats. */ if (cache->bitmap_high_thresh > 100) cache->bitmap_low_thresh = cache->bitmap_high_thresh - 100; else cache->bitmap_low_thresh = 0; } static int add_new_free_space_info(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_free_space_info *info; struct btrfs_key key; struct extent_buffer *leaf; int ret; key.objectid = block_group->start; key.type = BTRFS_FREE_SPACE_INFO_KEY; key.offset = block_group->length; ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info)); if (ret) goto out; leaf = path->nodes[0]; info = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_free_space_info); btrfs_set_free_space_extent_count(leaf, info, 0); btrfs_set_free_space_flags(leaf, info, 0); ret = 0; out: btrfs_release_path(path); return ret; } EXPORT_FOR_TESTS struct btrfs_free_space_info *search_free_space_info( struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, int cow) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key; int ret; key.objectid = block_group->start; key.type = BTRFS_FREE_SPACE_INFO_KEY; key.offset = block_group->length; ret = btrfs_search_slot(trans, root, &key, path, 0, cow); if (ret < 0) return ERR_PTR(ret); if (ret != 0) { btrfs_warn(fs_info, "missing free space info for %llu", block_group->start); ASSERT(0); return ERR_PTR(-ENOENT); } return btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_free_space_info); } /* * btrfs_search_slot() but we're looking for the greatest key less than the * passed key. */ static int btrfs_search_prev_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow) { int ret; ret = btrfs_search_slot(trans, root, key, p, ins_len, cow); if (ret < 0) return ret; if (ret == 0) { ASSERT(0); return -EIO; } if (p->slots[0] == 0) { ASSERT(0); return -EIO; } p->slots[0]--; return 0; } static inline u32 free_space_bitmap_size(const struct btrfs_fs_info *fs_info, u64 size) { return DIV_ROUND_UP(size >> fs_info->sectorsize_bits, BITS_PER_BYTE); } static unsigned long *alloc_bitmap(u32 bitmap_size) { unsigned long *ret; unsigned int nofs_flag; u32 bitmap_rounded_size = round_up(bitmap_size, sizeof(unsigned long)); /* * GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse * into the filesystem as the free space bitmap can be modified in the * critical section of a transaction commit. * * TODO: push the memalloc_nofs_{save,restore}() to the caller where we * know that recursion is unsafe. */ nofs_flag = memalloc_nofs_save(); ret = kvzalloc(bitmap_rounded_size, GFP_KERNEL); memalloc_nofs_restore(nofs_flag); return ret; } static void le_bitmap_set(unsigned long *map, unsigned int start, int len) { u8 *p = ((u8 *)map) + BIT_BYTE(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE); u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_BYTE; mask_to_set = ~0; p++; } if (len) { mask_to_set &= BITMAP_LAST_BYTE_MASK(size); *p |= mask_to_set; } } EXPORT_FOR_TESTS int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_free_space_info *info; struct btrfs_key key, found_key; struct extent_buffer *leaf; unsigned long *bitmap; char *bitmap_cursor; u64 start, end; u64 bitmap_range, i; u32 bitmap_size, flags, expected_extent_count; u32 extent_count = 0; int done = 0, nr; int ret; bitmap_size = free_space_bitmap_size(fs_info, block_group->length); bitmap = alloc_bitmap(bitmap_size); if (!bitmap) { ret = -ENOMEM; goto out; } start = block_group->start; end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; key.offset = (u64)-1; while (!done) { ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) goto out; leaf = path->nodes[0]; nr = 0; path->slots[0]++; while (path->slots[0] > 0) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { ASSERT(found_key.objectid == block_group->start); ASSERT(found_key.offset == block_group->length); done = 1; break; } else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) { u64 first, last; ASSERT(found_key.objectid >= start); ASSERT(found_key.objectid < end); ASSERT(found_key.objectid + found_key.offset <= end); first = div_u64(found_key.objectid - start, fs_info->sectorsize); last = div_u64(found_key.objectid + found_key.offset - start, fs_info->sectorsize); le_bitmap_set(bitmap, first, last - first); extent_count++; nr++; path->slots[0]--; } else { ASSERT(0); } } ret = btrfs_del_items(trans, root, path, path->slots[0], nr); if (ret) goto out; btrfs_release_path(path); } info = search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; } leaf = path->nodes[0]; flags = btrfs_free_space_flags(leaf, info); flags |= BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); btrfs_release_path(path); if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; goto out; } bitmap_cursor = (char *)bitmap; bitmap_range = fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS; i = start; while (i < end) { unsigned long ptr; u64 extent_size; u32 data_size; extent_size = min(end - i, bitmap_range); data_size = free_space_bitmap_size(fs_info, extent_size); key.objectid = i; key.type = BTRFS_FREE_SPACE_BITMAP_KEY; key.offset = extent_size; ret = btrfs_insert_empty_item(trans, root, path, &key, data_size); if (ret) goto out; leaf = path->nodes[0]; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, bitmap_cursor, ptr, data_size); btrfs_release_path(path); i += extent_size; bitmap_cursor += data_size; } ret = 0; out: kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, ret); return ret; } EXPORT_FOR_TESTS int convert_free_space_to_extents(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_free_space_info *info; struct btrfs_key key, found_key; struct extent_buffer *leaf; unsigned long *bitmap; u64 start, end; u32 bitmap_size, flags, expected_extent_count; unsigned long nrbits, start_bit, end_bit; u32 extent_count = 0; int done = 0, nr; int ret; bitmap_size = free_space_bitmap_size(fs_info, block_group->length); bitmap = alloc_bitmap(bitmap_size); if (!bitmap) { ret = -ENOMEM; goto out; } start = block_group->start; end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; key.offset = (u64)-1; while (!done) { ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) goto out; leaf = path->nodes[0]; nr = 0; path->slots[0]++; while (path->slots[0] > 0) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { ASSERT(found_key.objectid == block_group->start); ASSERT(found_key.offset == block_group->length); done = 1; break; } else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) { unsigned long ptr; char *bitmap_cursor; u32 bitmap_pos, data_size; ASSERT(found_key.objectid >= start); ASSERT(found_key.objectid < end); ASSERT(found_key.objectid + found_key.offset <= end); bitmap_pos = div_u64(found_key.objectid - start, fs_info->sectorsize * BITS_PER_BYTE); bitmap_cursor = ((char *)bitmap) + bitmap_pos; data_size = free_space_bitmap_size(fs_info, found_key.offset); ptr = btrfs_item_ptr_offset(leaf, path->slots[0] - 1); read_extent_buffer(leaf, bitmap_cursor, ptr, data_size); nr++; path->slots[0]--; } else { ASSERT(0); } } ret = btrfs_del_items(trans, root, path, path->slots[0], nr); if (ret) goto out; btrfs_release_path(path); } info = search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; } leaf = path->nodes[0]; flags = btrfs_free_space_flags(leaf, info); flags &= ~BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); btrfs_release_path(path); nrbits = block_group->length >> block_group->fs_info->sectorsize_bits; start_bit = find_next_bit_le(bitmap, nrbits, 0); while (start_bit < nrbits) { end_bit = find_next_zero_bit_le(bitmap, nrbits, start_bit); ASSERT(start_bit < end_bit); key.objectid = start + start_bit * block_group->fs_info->sectorsize; key.type = BTRFS_FREE_SPACE_EXTENT_KEY; key.offset = (end_bit - start_bit) * block_group->fs_info->sectorsize; ret = btrfs_insert_empty_item(trans, root, path, &key, 0); if (ret) goto out; btrfs_release_path(path); extent_count++; start_bit = find_next_bit_le(bitmap, nrbits, end_bit); } if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; goto out; } ret = 0; out: kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, ret); return ret; } static int update_free_space_extent_count(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, int new_extents) { struct btrfs_free_space_info *info; u32 flags; u32 extent_count; int ret = 0; if (new_extents == 0) return 0; info = search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; } flags = btrfs_free_space_flags(path->nodes[0], info); extent_count = btrfs_free_space_extent_count(path->nodes[0], info); extent_count += new_extents; btrfs_set_free_space_extent_count(path->nodes[0], info, extent_count); btrfs_release_path(path); if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) && extent_count > block_group->bitmap_high_thresh) { ret = convert_free_space_to_bitmaps(trans, block_group, path); } else if ((flags & BTRFS_FREE_SPACE_USING_BITMAPS) && extent_count < block_group->bitmap_low_thresh) { ret = convert_free_space_to_extents(trans, block_group, path); } out: return ret; } EXPORT_FOR_TESTS int free_space_test_bit(struct btrfs_block_group *block_group, struct btrfs_path *path, u64 offset) { struct extent_buffer *leaf; struct btrfs_key key; u64 found_start, found_end; unsigned long ptr, i; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY); found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(offset >= found_start && offset < found_end); ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); i = div_u64(offset - found_start, block_group->fs_info->sectorsize); return !!extent_buffer_test_bit(leaf, ptr, i); } static void free_space_set_bits(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 *start, u64 *size, int bit) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct extent_buffer *leaf; struct btrfs_key key; u64 end = *start + *size; u64 found_start, found_end; unsigned long ptr, first, last; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY); found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(*start >= found_start && *start < found_end); ASSERT(end > found_start); if (end > found_end) end = found_end; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); first = (*start - found_start) >> fs_info->sectorsize_bits; last = (end - found_start) >> fs_info->sectorsize_bits; if (bit) extent_buffer_bitmap_set(leaf, ptr, first, last - first); else extent_buffer_bitmap_clear(leaf, ptr, first, last - first); btrfs_mark_buffer_dirty(trans, leaf); *size -= end - *start; *start = end; } /* * We can't use btrfs_next_item() in modify_free_space_bitmap() because * btrfs_next_leaf() doesn't get the path for writing. We can forgo the fancy * tree walking in btrfs_next_leaf() anyways because we know exactly what we're * looking for. */ static int free_space_next_bitmap(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *p) { struct btrfs_key key; if (p->slots[0] + 1 < btrfs_header_nritems(p->nodes[0])) { p->slots[0]++; return 0; } btrfs_item_key_to_cpu(p->nodes[0], &key, p->slots[0]); btrfs_release_path(p); key.objectid += key.offset; key.type = (u8)-1; key.offset = (u64)-1; return btrfs_search_prev_slot(trans, root, &key, p, 0, 1); } /* * If remove is 1, then we are removing free space, thus clearing bits in the * bitmap. If remove is 0, then we are adding free space, thus setting bits in * the bitmap. */ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size, int remove) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key; u64 end = start + size; u64 cur_start, cur_size; int prev_bit, next_bit; int new_extents; int ret; /* * Read the bit for the block immediately before the extent of space if * that block is within the block group. */ if (start > block_group->start) { u64 prev_block = start - block_group->fs_info->sectorsize; key.objectid = prev_block; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1); if (ret) goto out; prev_bit = free_space_test_bit(block_group, path, prev_block); /* The previous block may have been in the previous bitmap. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (start >= key.objectid + key.offset) { ret = free_space_next_bitmap(trans, root, path); if (ret) goto out; } } else { key.objectid = start; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1); if (ret) goto out; prev_bit = -1; } /* * Iterate over all of the bitmaps overlapped by the extent of space, * clearing/setting bits as required. */ cur_start = start; cur_size = size; while (1) { free_space_set_bits(trans, block_group, path, &cur_start, &cur_size, !remove); if (cur_size == 0) break; ret = free_space_next_bitmap(trans, root, path); if (ret) goto out; } /* * Read the bit for the block immediately after the extent of space if * that block is within the block group. */ if (end < block_group->start + block_group->length) { /* The next block may be in the next bitmap. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (end >= key.objectid + key.offset) { ret = free_space_next_bitmap(trans, root, path); if (ret) goto out; } next_bit = free_space_test_bit(block_group, path, end); } else { next_bit = -1; } if (remove) { new_extents = -1; if (prev_bit == 1) { /* Leftover on the left. */ new_extents++; } if (next_bit == 1) { /* Leftover on the right. */ new_extents++; } } else { new_extents = 1; if (prev_bit == 1) { /* Merging with neighbor on the left. */ new_extents--; } if (next_bit == 1) { /* Merging with neighbor on the right. */ new_extents--; } } btrfs_release_path(path); ret = update_free_space_extent_count(trans, block_group, path, new_extents); out: return ret; } static int remove_free_space_extent(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key; u64 found_start, found_end; u64 end = start + size; int new_extents = -1; int ret; key.objectid = start; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) goto out; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY); found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(start >= found_start && end <= found_end); /* * Okay, now that we've found the free space extent which contains the * free space that we are removing, there are four cases: * * 1. We're using the whole extent: delete the key we found and * decrement the free space extent count. * 2. We are using part of the extent starting at the beginning: delete * the key we found and insert a new key representing the leftover at * the end. There is no net change in the number of extents. * 3. We are using part of the extent ending at the end: delete the key * we found and insert a new key representing the leftover at the * beginning. There is no net change in the number of extents. * 4. We are using part of the extent in the middle: delete the key we * found and insert two new keys representing the leftovers on each * side. Where we used to have one extent, we now have two, so increment * the extent count. We may need to convert the block group to bitmaps * as a result. */ /* Delete the existing key (cases 1-4). */ ret = btrfs_del_item(trans, root, path); if (ret) goto out; /* Add a key for leftovers at the beginning (cases 3 and 4). */ if (start > found_start) { key.objectid = found_start; key.type = BTRFS_FREE_SPACE_EXTENT_KEY; key.offset = start - found_start; btrfs_release_path(path); ret = btrfs_insert_empty_item(trans, root, path, &key, 0); if (ret) goto out; new_extents++; } /* Add a key for leftovers at the end (cases 2 and 4). */ if (end < found_end) { key.objectid = end; key.type = BTRFS_FREE_SPACE_EXTENT_KEY; key.offset = found_end - end; btrfs_release_path(path); ret = btrfs_insert_empty_item(trans, root, path, &key, 0); if (ret) goto out; new_extents++; } btrfs_release_path(path); ret = update_free_space_extent_count(trans, block_group, path, new_extents); out: return ret; } EXPORT_FOR_TESTS int __remove_from_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_free_space_info *info; u32 flags; int ret; if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; } info = search_free_space_info(NULL, block_group, path, 0); if (IS_ERR(info)) return PTR_ERR(info); flags = btrfs_free_space_flags(path->nodes[0], info); btrfs_release_path(path); if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) { return modify_free_space_bitmap(trans, block_group, path, start, size, 1); } else { return remove_free_space_extent(trans, block_group, path, start, size); } } int remove_from_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { struct btrfs_block_group *block_group; struct btrfs_path *path; int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } block_group = btrfs_lookup_block_group(trans->fs_info, start); if (!block_group) { ASSERT(0); ret = -ENOENT; goto out; } mutex_lock(&block_group->free_space_lock); ret = __remove_from_free_space_tree(trans, block_group, path, start, size); mutex_unlock(&block_group->free_space_lock); btrfs_put_block_group(block_group); out: btrfs_free_path(path); if (ret) btrfs_abort_transaction(trans, ret); return ret; } static int add_free_space_extent(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key, new_key; u64 found_start, found_end; u64 end = start + size; int new_extents = 1; int ret; /* * We are adding a new extent of free space, but we need to merge * extents. There are four cases here: * * 1. The new extent does not have any immediate neighbors to merge * with: add the new key and increment the free space extent count. We * may need to convert the block group to bitmaps as a result. * 2. The new extent has an immediate neighbor before it: remove the * previous key and insert a new key combining both of them. There is no * net change in the number of extents. * 3. The new extent has an immediate neighbor after it: remove the next * key and insert a new key combining both of them. There is no net * change in the number of extents. * 4. The new extent has immediate neighbors on both sides: remove both * of the keys and insert a new key combining all of them. Where we used * to have two extents, we now have one, so decrement the extent count. */ new_key.objectid = start; new_key.type = BTRFS_FREE_SPACE_EXTENT_KEY; new_key.offset = size; /* Search for a neighbor on the left. */ if (start == block_group->start) goto right; key.objectid = start - 1; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) goto out; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) { ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY); btrfs_release_path(path); goto right; } found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(found_start >= block_group->start && found_end > block_group->start); ASSERT(found_start < start && found_end <= start); /* * Delete the neighbor on the left and absorb it into the new key (cases * 2 and 4). */ if (found_end == start) { ret = btrfs_del_item(trans, root, path); if (ret) goto out; new_key.objectid = found_start; new_key.offset += key.offset; new_extents--; } btrfs_release_path(path); right: /* Search for a neighbor on the right. */ if (end == block_group->start + block_group->length) goto insert; key.objectid = end; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) goto out; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) { ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY); btrfs_release_path(path); goto insert; } found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(found_start >= block_group->start && found_end > block_group->start); ASSERT((found_start < start && found_end <= start) || (found_start >= end && found_end > end)); /* * Delete the neighbor on the right and absorb it into the new key * (cases 3 and 4). */ if (found_start == end) { ret = btrfs_del_item(trans, root, path); if (ret) goto out; new_key.offset += key.offset; new_extents--; } btrfs_release_path(path); insert: /* Insert the new key (cases 1-4). */ ret = btrfs_insert_empty_item(trans, root, path, &new_key, 0); if (ret) goto out; btrfs_release_path(path); ret = update_free_space_extent_count(trans, block_group, path, new_extents); out: return ret; } EXPORT_FOR_TESTS int __add_to_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_free_space_info *info; u32 flags; int ret; if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; } info = search_free_space_info(NULL, block_group, path, 0); if (IS_ERR(info)) return PTR_ERR(info); flags = btrfs_free_space_flags(path->nodes[0], info); btrfs_release_path(path); if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) { return modify_free_space_bitmap(trans, block_group, path, start, size, 0); } else { return add_free_space_extent(trans, block_group, path, start, size); } } int add_to_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { struct btrfs_block_group *block_group; struct btrfs_path *path; int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } block_group = btrfs_lookup_block_group(trans->fs_info, start); if (!block_group) { ASSERT(0); ret = -ENOENT; goto out; } mutex_lock(&block_group->free_space_lock); ret = __add_to_free_space_tree(trans, block_group, path, start, size); mutex_unlock(&block_group->free_space_lock); btrfs_put_block_group(block_group); out: btrfs_free_path(path); if (ret) btrfs_abort_transaction(trans, ret); return ret; } /* * Populate the free space tree by walking the extent tree. Operations on the * extent tree that happen as a result of writes to the free space tree will go * through the normal add/remove hooks. */ static int populate_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { struct btrfs_root *extent_root; struct btrfs_path *path, *path2; struct btrfs_key key; u64 start, end; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; path->reada = READA_FORWARD; path2 = btrfs_alloc_path(); if (!path2) { btrfs_free_path(path); return -ENOMEM; } ret = add_new_free_space_info(trans, block_group, path2); if (ret) goto out; mutex_lock(&block_group->free_space_lock); /* * Iterate through all of the extent and metadata items in this block * group, adding the free space between them and the free space at the * end. Note that EXTENT_ITEM and METADATA_ITEM are less than * BLOCK_GROUP_ITEM, so an extent may precede the block group that it's * contained in. */ key.objectid = block_group->start; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = 0; extent_root = btrfs_extent_root(trans->fs_info, key.objectid); ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0); if (ret < 0) goto out_locked; ASSERT(ret == 0); start = block_group->start; end = block_group->start + block_group->length; while (1) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY) { if (key.objectid >= end) break; if (start < key.objectid) { ret = __add_to_free_space_tree(trans, block_group, path2, start, key.objectid - start); if (ret) goto out_locked; } start = key.objectid; if (key.type == BTRFS_METADATA_ITEM_KEY) start += trans->fs_info->nodesize; else start += key.offset; } else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) { if (key.objectid != block_group->start) break; } ret = btrfs_next_item(extent_root, path); if (ret < 0) goto out_locked; if (ret) break; } if (start < end) { ret = __add_to_free_space_tree(trans, block_group, path2, start, end - start); if (ret) goto out_locked; } ret = 0; out_locked: mutex_unlock(&block_group->free_space_lock); out: btrfs_free_path(path2); btrfs_free_path(path); return ret; } int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *free_space_root; struct btrfs_block_group *block_group; struct rb_node *node; int ret; trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { ret = PTR_ERR(free_space_root); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out_clear; } ret = btrfs_global_root_insert(free_space_root); if (ret) { btrfs_put_root(free_space_root); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out_clear; } node = rb_first_cached(&fs_info->block_group_cache_tree); while (node) { block_group = rb_entry(node, struct btrfs_block_group, cache_node); ret = populate_free_space_tree(trans, block_group); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out_clear; } node = rb_next(node); } btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); ret = btrfs_commit_transaction(trans); /* * Now that we've committed the transaction any reading of our commit * root will be safe, so we can cache from the free space tree now. */ clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); return ret; out_clear: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); return ret; } static int clear_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct btrfs_path *path; struct btrfs_key key; int nr; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = 0; key.type = 0; key.offset = 0; while (1) { ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) goto out; nr = btrfs_header_nritems(path->nodes[0]); if (!nr) break; path->slots[0] = 0; ret = btrfs_del_items(trans, root, path, 0, nr); if (ret) goto out; btrfs_release_path(path); } ret = 0; out: btrfs_free_path(path); return ret; } int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_key key = { .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; struct btrfs_root *free_space_root = btrfs_global_root(fs_info, &key); int ret; trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); ret = clear_free_space_tree(trans, free_space_root); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } ret = btrfs_del_root(trans, &free_space_root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } btrfs_global_root_delete(free_space_root); spin_lock(&fs_info->trans_lock); list_del(&free_space_root->dirty_list); spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(free_space_root->node); btrfs_clear_buffer_dirty(trans, free_space_root->node); btrfs_tree_unlock(free_space_root->node); ret = btrfs_free_tree_block(trans, btrfs_root_id(free_space_root), free_space_root->node, 0, 1); btrfs_put_root(free_space_root); if (ret < 0) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } return btrfs_commit_transaction(trans); } int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_key key = { .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; struct btrfs_root *free_space_root = btrfs_global_root(fs_info, &key); struct rb_node *node; int ret; trans = btrfs_start_transaction(free_space_root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); ret = clear_free_space_tree(trans, free_space_root); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } node = rb_first_cached(&fs_info->block_group_cache_tree); while (node) { struct btrfs_block_group *block_group; block_group = rb_entry(node, struct btrfs_block_group, cache_node); ret = populate_free_space_tree(trans, block_group); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } if (btrfs_should_end_transaction(trans)) { btrfs_end_transaction(trans); trans = btrfs_start_transaction(free_space_root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); } node = rb_next(node); } btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); ret = btrfs_commit_transaction(trans); clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); return ret; } static int __add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { int ret; clear_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags); ret = add_new_free_space_info(trans, block_group, path); if (ret) return ret; return __add_to_free_space_tree(trans, block_group, path, block_group->start, block_group->length); } int add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path = NULL; int ret = 0; if (!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) return 0; mutex_lock(&block_group->free_space_lock); if (!test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) goto out; path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } ret = __add_block_group_free_space(trans, block_group, path); out: btrfs_free_path(path); mutex_unlock(&block_group->free_space_lock); if (ret) btrfs_abort_transaction(trans, ret); return ret; } int remove_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_path *path; struct btrfs_key key, found_key; struct extent_buffer *leaf; u64 start, end; int done = 0, nr; int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { /* We never added this block group to the free space tree. */ return 0; } path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } start = block_group->start; end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; key.offset = (u64)-1; while (!done) { ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) goto out; leaf = path->nodes[0]; nr = 0; path->slots[0]++; while (path->slots[0] > 0) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { ASSERT(found_key.objectid == block_group->start); ASSERT(found_key.offset == block_group->length); done = 1; nr++; path->slots[0]--; break; } else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY || found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) { ASSERT(found_key.objectid >= start); ASSERT(found_key.objectid < end); ASSERT(found_key.objectid + found_key.offset <= end); nr++; path->slots[0]--; } else { ASSERT(0); } } ret = btrfs_del_items(trans, root, path, path->slots[0], nr); if (ret) goto out; btrfs_release_path(path); } ret = 0; out: btrfs_free_path(path); if (ret) btrfs_abort_transaction(trans, ret); return ret; } static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, struct btrfs_path *path, u32 expected_extent_count) { struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_root *root; struct btrfs_key key; int prev_bit = 0, bit; /* Initialize to silence GCC. */ u64 extent_start = 0; u64 end, offset; u64 total_found = 0; u32 extent_count = 0; int ret; block_group = caching_ctl->block_group; fs_info = block_group->fs_info; root = btrfs_free_space_root(block_group); end = block_group->start + block_group->length; while (1) { ret = btrfs_next_item(root, path); if (ret < 0) goto out; if (ret) break; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_FREE_SPACE_INFO_KEY) break; ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY); ASSERT(key.objectid < end && key.objectid + key.offset <= end); offset = key.objectid; while (offset < key.objectid + key.offset) { bit = free_space_test_bit(block_group, path, offset); if (prev_bit == 0 && bit == 1) { extent_start = offset; } else if (prev_bit == 1 && bit == 0) { u64 space_added; ret = btrfs_add_new_free_space(block_group, extent_start, offset, &space_added); if (ret) goto out; total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); } extent_count++; } prev_bit = bit; offset += fs_info->sectorsize; } } if (prev_bit == 1) { ret = btrfs_add_new_free_space(block_group, extent_start, end, NULL); if (ret) goto out; extent_count++; } if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; goto out; } ret = 0; out: return ret; } static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, struct btrfs_path *path, u32 expected_extent_count) { struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_root *root; struct btrfs_key key; u64 end; u64 total_found = 0; u32 extent_count = 0; int ret; block_group = caching_ctl->block_group; fs_info = block_group->fs_info; root = btrfs_free_space_root(block_group); end = block_group->start + block_group->length; while (1) { u64 space_added; ret = btrfs_next_item(root, path); if (ret < 0) goto out; if (ret) break; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_FREE_SPACE_INFO_KEY) break; ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY); ASSERT(key.objectid < end && key.objectid + key.offset <= end); ret = btrfs_add_new_free_space(block_group, key.objectid, key.objectid + key.offset, &space_added); if (ret) goto out; total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); } extent_count++; } if (extent_count != expected_extent_count) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); ASSERT(0); ret = -EIO; goto out; } ret = 0; out: return ret; } int load_free_space_tree(struct btrfs_caching_control *caching_ctl) { struct btrfs_block_group *block_group; struct btrfs_free_space_info *info; struct btrfs_path *path; u32 extent_count, flags; int ret; block_group = caching_ctl->block_group; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* * Just like caching_thread() doesn't want to deadlock on the extent * tree, we don't want to deadlock on the free space tree. */ path->skip_locking = 1; path->search_commit_root = 1; path->reada = READA_FORWARD; info = search_free_space_info(NULL, block_group, path, 0); if (IS_ERR(info)) { ret = PTR_ERR(info); goto out; } extent_count = btrfs_free_space_extent_count(path->nodes[0], info); flags = btrfs_free_space_flags(path->nodes[0], info); /* * We left path pointing to the free space info item, so now * load_free_space_foo can just iterate through the free space tree from * there. */ if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) ret = load_free_space_bitmaps(caching_ctl, path, extent_count); else ret = load_free_space_extents(caching_ctl, path, extent_count); out: btrfs_free_path(path); return ret; } |
| 3 2 2 3 24 21 36 36 33 30 21 18 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * Null algorithms, aka Much Ado About Nothing. * * These are needed for IPsec, and may be useful in general for * testing & debugging. * * The null cipher is compliant with RFC2410. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> */ #include <crypto/null.h> #include <crypto/internal/hash.h> #include <crypto/internal/skcipher.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/string.h> static DEFINE_MUTEX(crypto_default_null_skcipher_lock); static struct crypto_sync_skcipher *crypto_default_null_skcipher; static int crypto_default_null_skcipher_refcnt; static int null_compress(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen) { if (slen > *dlen) return -EINVAL; memcpy(dst, src, slen); *dlen = slen; return 0; } static int null_init(struct shash_desc *desc) { return 0; } static int null_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return 0; } static int null_final(struct shash_desc *desc, u8 *out) { return 0; } static int null_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return 0; } static int null_hash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { return 0; } static int null_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { return 0; } static int null_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen) { return 0; } static void null_crypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { memcpy(dst, src, NULL_BLOCK_SIZE); } static int null_skcipher_crypt(struct skcipher_request *req) { struct skcipher_walk walk; int err; err = skcipher_walk_virt(&walk, req, false); while (walk.nbytes) { if (walk.src.virt.addr != walk.dst.virt.addr) memcpy(walk.dst.virt.addr, walk.src.virt.addr, walk.nbytes); err = skcipher_walk_done(&walk, 0); } return err; } static struct shash_alg digest_null = { .digestsize = NULL_DIGEST_SIZE, .setkey = null_hash_setkey, .init = null_init, .update = null_update, .finup = null_digest, .digest = null_digest, .final = null_final, .base = { .cra_name = "digest_null", .cra_driver_name = "digest_null-generic", .cra_blocksize = NULL_BLOCK_SIZE, .cra_module = THIS_MODULE, } }; static struct skcipher_alg skcipher_null = { .base.cra_name = "ecb(cipher_null)", .base.cra_driver_name = "ecb-cipher_null", .base.cra_priority = 100, .base.cra_blocksize = NULL_BLOCK_SIZE, .base.cra_ctxsize = 0, .base.cra_module = THIS_MODULE, .min_keysize = NULL_KEY_SIZE, .max_keysize = NULL_KEY_SIZE, .ivsize = NULL_IV_SIZE, .setkey = null_skcipher_setkey, .encrypt = null_skcipher_crypt, .decrypt = null_skcipher_crypt, }; static struct crypto_alg null_algs[] = { { .cra_name = "cipher_null", .cra_driver_name = "cipher_null-generic", .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = NULL_BLOCK_SIZE, .cra_ctxsize = 0, .cra_module = THIS_MODULE, .cra_u = { .cipher = { .cia_min_keysize = NULL_KEY_SIZE, .cia_max_keysize = NULL_KEY_SIZE, .cia_setkey = null_setkey, .cia_encrypt = null_crypt, .cia_decrypt = null_crypt } } }, { .cra_name = "compress_null", .cra_driver_name = "compress_null-generic", .cra_flags = CRYPTO_ALG_TYPE_COMPRESS, .cra_blocksize = NULL_BLOCK_SIZE, .cra_ctxsize = 0, .cra_module = THIS_MODULE, .cra_u = { .compress = { .coa_compress = null_compress, .coa_decompress = null_compress } } } }; MODULE_ALIAS_CRYPTO("compress_null"); MODULE_ALIAS_CRYPTO("digest_null"); MODULE_ALIAS_CRYPTO("cipher_null"); struct crypto_sync_skcipher *crypto_get_default_null_skcipher(void) { struct crypto_sync_skcipher *tfm; mutex_lock(&crypto_default_null_skcipher_lock); tfm = crypto_default_null_skcipher; if (!tfm) { tfm = crypto_alloc_sync_skcipher("ecb(cipher_null)", 0, 0); if (IS_ERR(tfm)) goto unlock; crypto_default_null_skcipher = tfm; } crypto_default_null_skcipher_refcnt++; unlock: mutex_unlock(&crypto_default_null_skcipher_lock); return tfm; } EXPORT_SYMBOL_GPL(crypto_get_default_null_skcipher); void crypto_put_default_null_skcipher(void) { mutex_lock(&crypto_default_null_skcipher_lock); if (!--crypto_default_null_skcipher_refcnt) { crypto_free_sync_skcipher(crypto_default_null_skcipher); crypto_default_null_skcipher = NULL; } mutex_unlock(&crypto_default_null_skcipher_lock); } EXPORT_SYMBOL_GPL(crypto_put_default_null_skcipher); static int __init crypto_null_mod_init(void) { int ret = 0; ret = crypto_register_algs(null_algs, ARRAY_SIZE(null_algs)); if (ret < 0) goto out; ret = crypto_register_shash(&digest_null); if (ret < 0) goto out_unregister_algs; ret = crypto_register_skcipher(&skcipher_null); if (ret < 0) goto out_unregister_shash; return 0; out_unregister_shash: crypto_unregister_shash(&digest_null); out_unregister_algs: crypto_unregister_algs(null_algs, ARRAY_SIZE(null_algs)); out: return ret; } static void __exit crypto_null_mod_fini(void) { crypto_unregister_algs(null_algs, ARRAY_SIZE(null_algs)); crypto_unregister_shash(&digest_null); crypto_unregister_skcipher(&skcipher_null); } subsys_initcall(crypto_null_mod_init); module_exit(crypto_null_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Null Cryptographic Algorithms"); |
| 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask_types.h> #include <linux/rcupdate.h> #include <linux/workqueue_types.h> /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum work_bits { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_INACTIVE_BIT, /* work item is inactive */ WORK_STRUCT_PWQ_BIT, /* data points to pwq */ WORK_STRUCT_LINKED_BIT, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT, /* static initializer (debugobjects) */ #endif WORK_STRUCT_FLAG_BITS, /* color for workqueue flushing */ WORK_STRUCT_COLOR_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_STRUCT_COLOR_BITS = 4, /* * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/ * debugobjects turned off. This makes pwqs aligned to 256 bytes (512 * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors. * * MSB * [ pwq pointer ] [ flush color ] [ STRUCT flags ] * 4 bits 4 or 5 bits */ WORK_STRUCT_PWQ_SHIFT = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* * data contains off-queue information when !WORK_STRUCT_PWQ. * * MSB * [ pool ID ] [ disable depth ] [ OFFQ flags ] [ STRUCT flags ] * 16 bits 1 bit 4 or 5 bits */ WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_OFFQ_BH_BIT = WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_FLAG_END, WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_DISABLE_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_DISABLE_BITS = 16, /* * When a work item is off queue, the high bits encode off-queue flags * and the last pool it was on. Cap pool ID to 31 bits and use the * highest number to indicate that no pool is associated. */ WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_DISABLE_SHIFT + WORK_OFFQ_DISABLE_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, }; enum work_flags { WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif }; enum wq_misc_consts { WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS), /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 32, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ #define WORK_OFFQ_BH (1ul << WORK_OFFQ_BH_BIT) #define WORK_OFFQ_FLAG_MASK (((1ul << WORK_OFFQ_FLAG_BITS) - 1) << WORK_OFFQ_FLAG_SHIFT) #define WORK_OFFQ_DISABLE_MASK (((1ul << WORK_OFFQ_DISABLE_BITS) - 1) << WORK_OFFQ_DISABLE_SHIFT) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1)) #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; struct rcu_work { struct work_struct work; struct rcu_head rcu; /* target workqueue ->rcu uses to queue ->work */ struct workqueue_struct *wq; }; enum wq_affn_scope { WQ_AFFN_DFL, /* use system default */ WQ_AFFN_CPU, /* one pod per CPU */ WQ_AFFN_SMT, /* one pod poer SMT */ WQ_AFFN_CACHE, /* one pod per LLC */ WQ_AFFN_NUMA, /* one pod per NUMA node */ WQ_AFFN_SYSTEM, /* one pod across the whole system */ WQ_AFFN_NR_TYPES, }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs * * Work items in this workqueue are affine to these CPUs and not allowed * to execute on other CPUs. A pool serving a workqueue must have the * same @cpumask. */ cpumask_var_t cpumask; /** * @__pod_cpumask: internal attribute used to create per-pod pools * * Internal use only. * * Per-pod unbound worker pools are used to improve locality. Always a * subset of ->cpumask. A workqueue can be associated with multiple * worker pools with disjoint @__pod_cpumask's. Whether the enforcement * of a pool's @__pod_cpumask is strict depends on @affn_strict. */ cpumask_var_t __pod_cpumask; /** * @affn_strict: affinity scope is strict * * If clear, workqueue will make a best-effort attempt at starting the * worker inside @__pod_cpumask but the scheduler is free to migrate it * outside. * * If set, workers are only allowed to run inside @__pod_cpumask. */ bool affn_strict; /* * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't * participate in pool hash calculations or equality comparisons. * * If @affn_strict is set, @cpumask isn't a property of a worker_pool * either. */ /** * @affn_scope: unbound CPU affinity scope * * CPU pods are used to improve execution locality of unbound work * items. There are multiple pod types, one for each wq_affn_scope, and * every CPU in the system belongs to one pod in every pod type. CPUs * that belong to the same pod share the worker pool. For example, * selecting %WQ_AFFN_NUMA makes the workqueue use a separate worker * pool for each NUMA node. */ enum wq_affn_scope affn_scope; /** * @ordered: work items must be executed one by one in queueing order */ bool ordered; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } static inline struct rcu_work *to_rcu_work(struct work_struct *work) { return container_of(work, struct rcu_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, (_key), 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define __INIT_WORK(_work, _func, _onstack) \ do { \ static __maybe_unused struct lock_class_key __key; \ \ __INIT_WORK_KEY(_work, _func, _onstack, &__key); \ } while (0) #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define INIT_WORK_ONSTACK_KEY(_work, _func, _key) \ __INIT_WORK_KEY((_work), (_func), 1, _key) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __init_timer(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __init_timer_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) #define INIT_RCU_WORK(_work, _func) \ INIT_WORK(&(_work)->work, (_func)) #define INIT_RCU_WORK_ONSTACK(_work, _func) \ INIT_WORK_ONSTACK(&(_work)->work, (_func)) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum wq_flags { WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * execute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, __WQ_DESTROYING = 1 << 15, /* internal: workqueue is destroying */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ /* BH wq only allows the following flags */ __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI, }; enum wq_consts { WQ_MAX_ACTIVE = 2048, /* I like 2048, better ideas? */ WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, /* * Per-node default cap on min_active. Unless explicitly set, min_active * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see * workqueue_struct->min_active definition. */ WQ_DFL_MIN_ACTIVE = 8, }; /* * System-wide workqueues which are always present. * * system_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_wq but may host long running * works. Queue flushing might take relatively long. * * system_unbound_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. * * system_bh[_highpri]_wq are convenience interface to softirq. BH work items * are executed in the queueing CPU's BH context in the queueing order. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; extern struct workqueue_struct *system_bh_wq; extern struct workqueue_struct *system_bh_highpri_wq; void workqueue_softirq_action(bool highpri); void workqueue_softirq_dead(unsigned int cpu); /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @...: args for @fmt * * For a per-cpu workqueue, @max_active limits the number of in-flight work * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be * executing at most one work item for the workqueue. * * For unbound workqueues, @max_active limits the number of in-flight work items * for the whole system. e.g. @max_active of 16 indicates that that there can be * at most 16 work items executing for the workqueue in the whole system. * * As sharing the same active counter for an unbound workqueue across multiple * NUMA nodes can be expensive, @max_active is distributed to each NUMA node * according to the proportion of the number of online CPUs and enforced * independently. * * Depending on online CPU distribution, a node may end up with per-node * max_active which is significantly lower than @max_active, which can lead to * deadlocks if the per-node concurrency limit is lower than the maximum number * of interdependent work items for the workqueue. * * To guarantee forward progress regardless of online CPU distribution, the * concurrency limit on every node is guaranteed to be equal to or greater than * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means * that the sum of per-node max_active's may be larger than @max_active. * * For detailed information on %WQ_* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(1, 4) struct workqueue_struct * alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); #ifdef CONFIG_LOCKDEP /** * alloc_workqueue_lockdep_map - allocate a workqueue with user-defined lockdep_map * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @lockdep_map: user-defined lockdep_map * @...: args for @fmt * * Same as alloc_workqueue but with the a user-define lockdep_map. Useful for * workqueues created with the same purpose and to avoid leaking a lockdep_map * on each workqueue creation. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(1, 5) struct workqueue_struct * alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, struct lockdep_map *lockdep_map, ...); /** * alloc_ordered_workqueue_lockdep_map - allocate an ordered workqueue with * user-defined lockdep_map * * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @lockdep_map: user-defined lockdep_map * @args: args for @fmt * * Same as alloc_ordered_workqueue but with the a user-define lockdep_map. * Useful for workqueues created with the same purpose and to avoid leaking a * lockdep_map on each workqueue creation. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...) \ alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), \ 1, lockdep_map, ##args) #endif /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) #define from_work(var, callback_work, work_fieldname) \ container_of(callback_work, typeof(*var), work_fieldname) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(void); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern bool disable_work(struct work_struct *work); extern bool disable_work_sync(struct work_struct *work); extern bool enable_work(struct work_struct *work); extern bool disable_delayed_work(struct delayed_work *dwork); extern bool disable_delayed_work_sync(struct delayed_work *dwork); extern bool enable_delayed_work(struct delayed_work *dwork); extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern void workqueue_set_min_active(struct workqueue_struct *wq, int min_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. * * Memory-ordering properties: If it returns %true, guarantees that all stores * preceding the call to queue_work() in the program order will be visible from * the CPU which will execute @work by the time such work executes, e.g., * * { x is initially 0 } * * CPU0 CPU1 * * WRITE_ONCE(x, 1); [ @work is being executed ] * r0 = queue_work(wq, work); r1 = READ_ONCE(x); * * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_wq, work); } /** * schedule_work - put work task in global workqueue * @work: job to be done * * Returns %false if @work was already on the kernel-global workqueue and * %true otherwise. * * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. * * Shares the same memory-ordering properties of queue_work(), cf. the * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_wq, work); } /** * enable_and_queue_work - Enable and queue a work item on a specific workqueue * @wq: The target workqueue * @work: The work item to be enabled and queued * * This function combines the operations of enable_work() and queue_work(), * providing a convenient way to enable and queue a work item in a single call. * It invokes enable_work() on @work and then queues it if the disable depth * reached 0. Returns %true if the disable depth reached 0 and @work is queued, * and %false otherwise. * * Note that @work is always queued when disable depth reaches zero. If the * desired behavior is queueing only if certain events took place while @work is * disabled, the user should implement the necessary state tracking and perform * explicit conditional queueing after enable_work(). */ static inline bool enable_and_queue_work(struct workqueue_struct *wq, struct work_struct *work) { if (enable_work(work)) { queue_work(wq, work); return true; } return false; } /* * Detect attempt to flush system-wide workqueues at compile time when possible. * Warn attempt to flush system-wide workqueues at runtime. * * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp * for reasons and steps for converting system-wide workqueues into local workqueues. */ extern void __warn_flushing_systemwide_wq(void) __compiletime_warning("Please avoid flushing system-wide workqueues."); /* Please stop using this function, for this function will be removed in near future. */ #define flush_scheduled_work() \ ({ \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(system_wq); \ }) #define flush_workqueue(wq) \ ({ \ struct workqueue_struct *_wq = (wq); \ \ if ((__builtin_constant_p(_wq == system_wq) && \ _wq == system_wq) || \ (__builtin_constant_p(_wq == system_highpri_wq) && \ _wq == system_highpri_wq) || \ (__builtin_constant_p(_wq == system_long_wq) && \ _wq == system_long_wq) || \ (__builtin_constant_p(_wq == system_unbound_wq) && \ _wq == system_unbound_wq) || \ (__builtin_constant_p(_wq == system_freezable_wq) && \ _wq == system_freezable_wq) || \ (__builtin_constant_p(_wq == system_power_efficient_wq) && \ _wq == system_power_efficient_wq) || \ (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ _wq == system_freezable_power_efficient_wq)) \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(_wq); \ }) /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_wq, dwork, delay); } /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the kernel-global * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key); /* * A new key is defined for each caller to make sure the work * associated with the function doesn't share its locking class. */ #define work_on_cpu(_cpu, _fn, _arg) \ ({ \ static struct lock_class_key __key; \ \ work_on_cpu_key(_cpu, _fn, _arg, &__key); \ }) long work_on_cpu_safe_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key); /* * A new key is defined for each caller to make sure the work * associated with the function doesn't share its locking class. */ #define work_on_cpu_safe(_cpu, _fn, _arg) \ ({ \ static struct lock_class_key __key; \ \ work_on_cpu_safe_key(_cpu, _fn, _arg, &__key); \ }) #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif void __init workqueue_init_early(void); void __init workqueue_init(void); void __init workqueue_init_topology(void); #endif |
| 11917 11915 11995 1284 1205 111 1166 12 1198 111 1169 1200 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM net #if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NET_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/tracepoint.h> TRACE_EVENT(net_dev_start_xmit, TP_PROTO(const struct sk_buff *skb, const struct net_device *dev), TP_ARGS(skb, dev), TP_STRUCT__entry( __string( name, dev->name ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( int, network_offset ) __field( bool, transport_offset_valid) __field( int, transport_offset) __field( u8, tx_flags ) __field( u16, gso_size ) __field( u16, gso_segs ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name); __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->network_offset = skb_network_offset(skb); __entry->transport_offset_valid = skb_transport_header_was_set(skb); __entry->transport_offset = skb_transport_header_was_set(skb) ? skb_transport_offset(skb) : 0; __entry->tx_flags = skb_shinfo(skb)->tx_flags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_segs = skb_shinfo(skb)->gso_segs; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", __get_str(name), __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->len, __entry->data_len, __entry->network_offset, __entry->transport_offset_valid, __entry->transport_offset, __entry->tx_flags, __entry->gso_size, __entry->gso_segs, __entry->gso_type) ); TRACE_EVENT(net_dev_xmit, TP_PROTO(struct sk_buff *skb, int rc, struct net_device *dev, unsigned int skb_len), TP_ARGS(skb, rc, dev, skb_len), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __field( int, rc ) __string( name, dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb_len; __entry->rc = rc; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u rc=%d", __get_str(name), __entry->skbaddr, __entry->len, __entry->rc) ); TRACE_EVENT(net_dev_xmit_timeout, TP_PROTO(struct net_device *dev, int queue_index), TP_ARGS(dev, queue_index), TP_STRUCT__entry( __string( name, dev->name ) __string( driver, netdev_drivername(dev)) __field( int, queue_index ) ), TP_fast_assign( __assign_str(name); __assign_str(driver); __entry->queue_index = queue_index; ), TP_printk("dev=%s driver=%s queue=%d", __get_str(name), __get_str(driver), __entry->queue_index) ); DECLARE_EVENT_CLASS(net_dev_template, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __string( name, skb->dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb->len; __assign_str(name); ), TP_printk("dev=%s skbaddr=%p len=%u", __get_str(name), __entry->skbaddr, __entry->len) ) DEFINE_EVENT(net_dev_template, net_dev_queue, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_receive_skb, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_rx, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __string( name, skb->dev->name ) __field( unsigned int, napi_id ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( u32, hash ) __field( bool, l4_hash ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( unsigned int, truesize ) __field( bool, mac_header_valid) __field( int, mac_header ) __field( unsigned char, nr_frags ) __field( u16, gso_size ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name); #ifdef CONFIG_NET_RX_BUSY_POLL __entry->napi_id = skb->napi_id; #else __entry->napi_id = 0; #endif __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->hash = skb->hash; __entry->l4_hash = skb->l4_hash; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->truesize = skb->truesize; __entry->mac_header_valid = skb_mac_header_was_set(skb); __entry->mac_header = skb_mac_header(skb) - skb->data; __entry->nr_frags = skb_shinfo(skb)->nr_frags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", __get_str(name), __entry->napi_id, __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->hash, __entry->l4_hash, __entry->len, __entry->data_len, __entry->truesize, __entry->mac_header_valid, __entry->mac_header, __entry->nr_frags, __entry->gso_size, __entry->gso_type) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_frags_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_receive_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_exit_template, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field(int, ret) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, TP_PROTO(int ret), TP_ARGS(ret) ); #endif /* _TRACE_NET_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * corsair-cpro.c - Linux driver for Corsair Commander Pro * Copyright (C) 2020 Marius Zachmann <mail@mariuszachmann.de> * * This driver uses hid reports to communicate with the device to allow hidraw userspace drivers * still being used. The device does not use report ids. When using hidraw and this driver * simultaniously, reports could be switched. */ #include <linux/bitops.h> #include <linux/completion.h> #include <linux/debugfs.h> #include <linux/hid.h> #include <linux/hwmon.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/types.h> #define USB_VENDOR_ID_CORSAIR 0x1b1c #define USB_PRODUCT_ID_CORSAIR_COMMANDERPRO 0x0c10 #define USB_PRODUCT_ID_CORSAIR_1000D 0x1d00 #define OUT_BUFFER_SIZE 63 #define IN_BUFFER_SIZE 16 #define LABEL_LENGTH 11 #define REQ_TIMEOUT 300 #define CTL_GET_FW_VER 0x02 /* returns the firmware version in bytes 1-3 */ #define CTL_GET_BL_VER 0x06 /* returns the bootloader version in bytes 1-2 */ #define CTL_GET_TMP_CNCT 0x10 /* * returns in bytes 1-4 for each temp sensor: * 0 not connected * 1 connected */ #define CTL_GET_TMP 0x11 /* * send: byte 1 is channel, rest zero * rcv: returns temp for channel in centi-degree celsius * in bytes 1 and 2 * returns 0x11 in byte 0 if no sensor is connected */ #define CTL_GET_VOLT 0x12 /* * send: byte 1 is rail number: 0 = 12v, 1 = 5v, 2 = 3.3v * rcv: returns millivolt in bytes 1,2 * returns error 0x10 if request is invalid */ #define CTL_GET_FAN_CNCT 0x20 /* * returns in bytes 1-6 for each fan: * 0 not connected * 1 3pin * 2 4pin */ #define CTL_GET_FAN_RPM 0x21 /* * send: byte 1 is channel, rest zero * rcv: returns rpm in bytes 1,2 */ #define CTL_GET_FAN_PWM 0x22 /* * send: byte 1 is channel, rest zero * rcv: returns pwm in byte 1 if it was set * returns error 0x12 if fan is controlled via * fan_target or fan curve */ #define CTL_SET_FAN_FPWM 0x23 /* * set fixed pwm * send: byte 1 is fan number * send: byte 2 is percentage from 0 - 100 */ #define CTL_SET_FAN_TARGET 0x24 /* * set target rpm * send: byte 1 is fan number * send: byte 2-3 is target * device accepts all values from 0x00 - 0xFFFF */ #define NUM_FANS 6 #define NUM_TEMP_SENSORS 4 struct ccp_device { struct hid_device *hdev; struct device *hwmon_dev; struct dentry *debugfs; /* For reinitializing the completion below */ spinlock_t wait_input_report_lock; struct completion wait_input_report; struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */ u8 *cmd_buffer; u8 *buffer; int target[6]; DECLARE_BITMAP(temp_cnct, NUM_TEMP_SENSORS); DECLARE_BITMAP(fan_cnct, NUM_FANS); char fan_label[6][LABEL_LENGTH]; u8 firmware_ver[3]; u8 bootloader_ver[2]; }; /* converts response error in buffer to errno */ static int ccp_get_errno(struct ccp_device *ccp) { switch (ccp->buffer[0]) { case 0x00: /* success */ return 0; case 0x01: /* called invalid command */ return -EOPNOTSUPP; case 0x10: /* called GET_VOLT / GET_TMP with invalid arguments */ return -EINVAL; case 0x11: /* requested temps of disconnected sensors */ case 0x12: /* requested pwm of not pwm controlled channels */ return -ENODATA; default: hid_dbg(ccp->hdev, "unknown device response error: %d", ccp->buffer[0]); return -EIO; } } /* send command, check for error in response, response in ccp->buffer */ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2, u8 byte3) { unsigned long t; int ret; memset(ccp->cmd_buffer, 0x00, OUT_BUFFER_SIZE); ccp->cmd_buffer[0] = command; ccp->cmd_buffer[1] = byte1; ccp->cmd_buffer[2] = byte2; ccp->cmd_buffer[3] = byte3; /* * Disable raw event parsing for a moment to safely reinitialize the * completion. Reinit is done because hidraw could have triggered * the raw event parsing and marked the ccp->wait_input_report * completion as done. */ spin_lock_bh(&ccp->wait_input_report_lock); reinit_completion(&ccp->wait_input_report); spin_unlock_bh(&ccp->wait_input_report_lock); ret = hid_hw_output_report(ccp->hdev, ccp->cmd_buffer, OUT_BUFFER_SIZE); if (ret < 0) return ret; t = wait_for_completion_timeout(&ccp->wait_input_report, msecs_to_jiffies(REQ_TIMEOUT)); if (!t) return -ETIMEDOUT; return ccp_get_errno(ccp); } static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct ccp_device *ccp = hid_get_drvdata(hdev); /* only copy buffer when requested */ spin_lock(&ccp->wait_input_report_lock); if (!completion_done(&ccp->wait_input_report)) { memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size)); complete_all(&ccp->wait_input_report); } spin_unlock(&ccp->wait_input_report_lock); return 0; } /* requests and returns single data values depending on channel */ static int get_data(struct ccp_device *ccp, int command, int channel, bool two_byte_data) { int ret; mutex_lock(&ccp->mutex); ret = send_usb_cmd(ccp, command, channel, 0, 0); if (ret) goto out_unlock; ret = ccp->buffer[1]; if (two_byte_data) ret = (ret << 8) + ccp->buffer[2]; out_unlock: mutex_unlock(&ccp->mutex); return ret; } static int set_pwm(struct ccp_device *ccp, int channel, long val) { int ret; if (val < 0 || val > 255) return -EINVAL; /* The Corsair Commander Pro uses values from 0-100 */ val = DIV_ROUND_CLOSEST(val * 100, 255); mutex_lock(&ccp->mutex); ret = send_usb_cmd(ccp, CTL_SET_FAN_FPWM, channel, val, 0); if (!ret) ccp->target[channel] = -ENODATA; mutex_unlock(&ccp->mutex); return ret; } static int set_target(struct ccp_device *ccp, int channel, long val) { int ret; val = clamp_val(val, 0, 0xFFFF); ccp->target[channel] = val; mutex_lock(&ccp->mutex); ret = send_usb_cmd(ccp, CTL_SET_FAN_TARGET, channel, val >> 8, val); mutex_unlock(&ccp->mutex); return ret; } static int ccp_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, const char **str) { struct ccp_device *ccp = dev_get_drvdata(dev); switch (type) { case hwmon_fan: switch (attr) { case hwmon_fan_label: *str = ccp->fan_label[channel]; return 0; default: break; } break; default: break; } return -EOPNOTSUPP; } static int ccp_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { struct ccp_device *ccp = dev_get_drvdata(dev); int ret; switch (type) { case hwmon_temp: switch (attr) { case hwmon_temp_input: ret = get_data(ccp, CTL_GET_TMP, channel, true); if (ret < 0) return ret; *val = ret * 10; return 0; default: break; } break; case hwmon_fan: switch (attr) { case hwmon_fan_input: ret = get_data(ccp, CTL_GET_FAN_RPM, channel, true); if (ret < 0) return ret; *val = ret; return 0; case hwmon_fan_target: /* how to read target values from the device is unknown */ /* driver returns last set value or 0 */ if (ccp->target[channel] < 0) return -ENODATA; *val = ccp->target[channel]; return 0; default: break; } break; case hwmon_pwm: switch (attr) { case hwmon_pwm_input: ret = get_data(ccp, CTL_GET_FAN_PWM, channel, false); if (ret < 0) return ret; *val = DIV_ROUND_CLOSEST(ret * 255, 100); return 0; default: break; } break; case hwmon_in: switch (attr) { case hwmon_in_input: ret = get_data(ccp, CTL_GET_VOLT, channel, true); if (ret < 0) return ret; *val = ret; return 0; default: break; } break; default: break; } return -EOPNOTSUPP; }; static int ccp_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long val) { struct ccp_device *ccp = dev_get_drvdata(dev); switch (type) { case hwmon_pwm: switch (attr) { case hwmon_pwm_input: return set_pwm(ccp, channel, val); default: break; } break; case hwmon_fan: switch (attr) { case hwmon_fan_target: return set_target(ccp, channel, val); default: break; } break; default: break; } return -EOPNOTSUPP; }; static umode_t ccp_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) { const struct ccp_device *ccp = data; switch (type) { case hwmon_temp: if (!test_bit(channel, ccp->temp_cnct)) break; switch (attr) { case hwmon_temp_input: return 0444; case hwmon_temp_label: return 0444; default: break; } break; case hwmon_fan: if (!test_bit(channel, ccp->fan_cnct)) break; switch (attr) { case hwmon_fan_input: return 0444; case hwmon_fan_label: return 0444; case hwmon_fan_target: return 0644; default: break; } break; case hwmon_pwm: if (!test_bit(channel, ccp->fan_cnct)) break; switch (attr) { case hwmon_pwm_input: return 0644; default: break; } break; case hwmon_in: switch (attr) { case hwmon_in_input: return 0444; default: break; } break; default: break; } return 0; }; static const struct hwmon_ops ccp_hwmon_ops = { .is_visible = ccp_is_visible, .read = ccp_read, .read_string = ccp_read_string, .write = ccp_write, }; static const struct hwmon_channel_info * const ccp_info[] = { HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ), HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT, HWMON_T_INPUT, HWMON_T_INPUT, HWMON_T_INPUT ), HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_TARGET, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_TARGET, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_TARGET, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_TARGET, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_TARGET, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_TARGET ), HWMON_CHANNEL_INFO(pwm, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT ), HWMON_CHANNEL_INFO(in, HWMON_I_INPUT, HWMON_I_INPUT, HWMON_I_INPUT ), NULL }; static const struct hwmon_chip_info ccp_chip_info = { .ops = &ccp_hwmon_ops, .info = ccp_info, }; /* read fan connection status and set labels */ static int get_fan_cnct(struct ccp_device *ccp) { int channel; int mode; int ret; ret = send_usb_cmd(ccp, CTL_GET_FAN_CNCT, 0, 0, 0); if (ret) return ret; for (channel = 0; channel < NUM_FANS; channel++) { mode = ccp->buffer[channel + 1]; if (mode == 0) continue; set_bit(channel, ccp->fan_cnct); ccp->target[channel] = -ENODATA; switch (mode) { case 1: scnprintf(ccp->fan_label[channel], LABEL_LENGTH, "fan%d 3pin", channel + 1); break; case 2: scnprintf(ccp->fan_label[channel], LABEL_LENGTH, "fan%d 4pin", channel + 1); break; default: scnprintf(ccp->fan_label[channel], LABEL_LENGTH, "fan%d other", channel + 1); break; } } return 0; } /* read temp sensor connection status */ static int get_temp_cnct(struct ccp_device *ccp) { int channel; int mode; int ret; ret = send_usb_cmd(ccp, CTL_GET_TMP_CNCT, 0, 0, 0); if (ret) return ret; for (channel = 0; channel < NUM_TEMP_SENSORS; channel++) { mode = ccp->buffer[channel + 1]; if (mode == 0) continue; set_bit(channel, ccp->temp_cnct); } return 0; } /* read firmware version */ static int get_fw_version(struct ccp_device *ccp) { int ret; ret = send_usb_cmd(ccp, CTL_GET_FW_VER, 0, 0, 0); if (ret) { hid_notice(ccp->hdev, "Failed to read firmware version.\n"); return ret; } ccp->firmware_ver[0] = ccp->buffer[1]; ccp->firmware_ver[1] = ccp->buffer[2]; ccp->firmware_ver[2] = ccp->buffer[3]; return 0; } /* read bootloader version */ static int get_bl_version(struct ccp_device *ccp) { int ret; ret = send_usb_cmd(ccp, CTL_GET_BL_VER, 0, 0, 0); if (ret) { hid_notice(ccp->hdev, "Failed to read bootloader version.\n"); return ret; } ccp->bootloader_ver[0] = ccp->buffer[1]; ccp->bootloader_ver[1] = ccp->buffer[2]; return 0; } static int firmware_show(struct seq_file *seqf, void *unused) { struct ccp_device *ccp = seqf->private; seq_printf(seqf, "%d.%d.%d\n", ccp->firmware_ver[0], ccp->firmware_ver[1], ccp->firmware_ver[2]); return 0; } DEFINE_SHOW_ATTRIBUTE(firmware); static int bootloader_show(struct seq_file *seqf, void *unused) { struct ccp_device *ccp = seqf->private; seq_printf(seqf, "%d.%d\n", ccp->bootloader_ver[0], ccp->bootloader_ver[1]); return 0; } DEFINE_SHOW_ATTRIBUTE(bootloader); static void ccp_debugfs_init(struct ccp_device *ccp) { char name[32]; int ret; scnprintf(name, sizeof(name), "corsaircpro-%s", dev_name(&ccp->hdev->dev)); ccp->debugfs = debugfs_create_dir(name, NULL); ret = get_fw_version(ccp); if (!ret) debugfs_create_file("firmware_version", 0444, ccp->debugfs, ccp, &firmware_fops); ret = get_bl_version(ccp); if (!ret) debugfs_create_file("bootloader_version", 0444, ccp->debugfs, ccp, &bootloader_fops); } static int ccp_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct ccp_device *ccp; int ret; ccp = devm_kzalloc(&hdev->dev, sizeof(*ccp), GFP_KERNEL); if (!ccp) return -ENOMEM; ccp->cmd_buffer = devm_kmalloc(&hdev->dev, OUT_BUFFER_SIZE, GFP_KERNEL); if (!ccp->cmd_buffer) return -ENOMEM; ccp->buffer = devm_kmalloc(&hdev->dev, IN_BUFFER_SIZE, GFP_KERNEL); if (!ccp->buffer) return -ENOMEM; ret = hid_parse(hdev); if (ret) return ret; ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW); if (ret) return ret; ret = hid_hw_open(hdev); if (ret) goto out_hw_stop; ccp->hdev = hdev; hid_set_drvdata(hdev, ccp); mutex_init(&ccp->mutex); spin_lock_init(&ccp->wait_input_report_lock); init_completion(&ccp->wait_input_report); hid_device_io_start(hdev); /* temp and fan connection status only updates when device is powered on */ ret = get_temp_cnct(ccp); if (ret) goto out_hw_close; ret = get_fan_cnct(ccp); if (ret) goto out_hw_close; ccp_debugfs_init(ccp); ccp->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "corsaircpro", ccp, &ccp_chip_info, NULL); if (IS_ERR(ccp->hwmon_dev)) { ret = PTR_ERR(ccp->hwmon_dev); goto out_hw_close; } return 0; out_hw_close: hid_hw_close(hdev); out_hw_stop: hid_hw_stop(hdev); return ret; } static void ccp_remove(struct hid_device *hdev) { struct ccp_device *ccp = hid_get_drvdata(hdev); debugfs_remove_recursive(ccp->debugfs); hwmon_device_unregister(ccp->hwmon_dev); hid_hw_close(hdev); hid_hw_stop(hdev); } static const struct hid_device_id ccp_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_PRODUCT_ID_CORSAIR_COMMANDERPRO) }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_PRODUCT_ID_CORSAIR_1000D) }, { } }; static struct hid_driver ccp_driver = { .name = "corsair-cpro", .id_table = ccp_devices, .probe = ccp_probe, .remove = ccp_remove, .raw_event = ccp_raw_event, }; MODULE_DEVICE_TABLE(hid, ccp_devices); MODULE_DESCRIPTION("Corsair Commander Pro controller driver"); MODULE_LICENSE("GPL"); static int __init ccp_init(void) { return hid_register_driver(&ccp_driver); } static void __exit ccp_exit(void) { hid_unregister_driver(&ccp_driver); } /* * When compiling this driver as built-in, hwmon initcalls will get called before the * hid driver and this driver would fail to register. late_initcall solves this. */ late_initcall(ccp_init); module_exit(ccp_exit); |
| 26240 26386 27142 27318 26222 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_CONTEXT_H #define __X86_KERNEL_FPU_CONTEXT_H #include <asm/fpu/xstate.h> #include <asm/trace/fpu.h> /* Functions related to FPU context tracking */ /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } static inline void fpregs_deactivate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* Internal helper for switch_fpu_return() and signal frame setup */ static inline void fpregs_restore_userregs(void) { struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { /* * This restores _all_ xstate which has not been * established yet. * * If PKRU is enabled, then the PKRU value is already * correct because it was either set in switch_to() or in * flush_thread(). So it is excluded because it might be * not up to date in current->thread.fpu.xsave state. * * XFD state is handled in restore_fpregs_from_fpstate(). */ restore_fpregs_from_fpstate(fpu->fpstate, XFEATURE_MASK_FPSTATE); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } #endif |
| 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 | #ifndef _TCP_DCTCP_H #define _TCP_DCTCP_H static inline void dctcp_ece_ack_cwr(struct sock *sk, u32 ce_state) { struct tcp_sock *tp = tcp_sk(sk); if (ce_state == 1) tp->ecn_flags |= TCP_ECN_DEMAND_CWR; else tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; } /* Minimal DCTP CE state machine: * * S: 0 <- last pkt was non-CE * 1 <- last pkt was CE */ static inline void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, u32 *prior_rcv_nxt, u32 *ce_state) { u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0; if (*ce_state != new_ce_state) { /* CE state has changed, force an immediate ACK to * reflect the new CE state. If an ACK was delayed, * send that first to reflect the prior CE state. */ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { dctcp_ece_ack_cwr(sk, *ce_state); __tcp_send_ack(sk, *prior_rcv_nxt); } inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt; *ce_state = new_ce_state; dctcp_ece_ack_cwr(sk, new_ce_state); } #endif |
| 42 118 123 22 2 123 11 11 11 11 4 1 14 10 4 1 4 140 132 119 13 132 11 2 123 122 9 11 132 14 8 2 10 1 2 3 1 14 114 17 14 14 12 1 11 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008-2014 Mathieu Desnoyers */ #include <linux/module.h> #include <linux/mutex.h> #include <linux/types.h> #include <linux/jhash.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/tracepoint.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/static_key.h> enum tp_func_state { TP_FUNC_0, TP_FUNC_1, TP_FUNC_2, TP_FUNC_N, }; extern tracepoint_ptr_t __start___tracepoints_ptrs[]; extern tracepoint_ptr_t __stop___tracepoints_ptrs[]; enum tp_transition_sync { TP_TRANSITION_SYNC_1_0_1, TP_TRANSITION_SYNC_N_2_1, _NR_TP_TRANSITION_SYNC, }; struct tp_transition_snapshot { unsigned long rcu; bool ongoing; }; /* Protected by tracepoints_mutex */ static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC]; static void tp_rcu_get_state(enum tp_transition_sync sync) { struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync]; /* Keep the latest get_state snapshot. */ snapshot->rcu = get_state_synchronize_rcu(); snapshot->ongoing = true; } static void tp_rcu_cond_sync(enum tp_transition_sync sync) { struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync]; if (!snapshot->ongoing) return; cond_synchronize_rcu(snapshot->rcu); snapshot->ongoing = false; } /* Set to 1 to enable tracepoint debug output */ static const int tracepoint_debug; #ifdef CONFIG_MODULES /* * Tracepoint module list mutex protects the local module list. */ static DEFINE_MUTEX(tracepoint_module_list_mutex); /* Local list of struct tp_module */ static LIST_HEAD(tracepoint_module_list); #endif /* CONFIG_MODULES */ /* * tracepoints_mutex protects the builtin and module tracepoints. * tracepoints_mutex nests inside tracepoint_module_list_mutex. */ static DEFINE_MUTEX(tracepoints_mutex); /* * Note about RCU : * It is used to delay the free of multiple probes array until a quiescent * state is reached. */ struct tp_probes { struct rcu_head rcu; struct tracepoint_func probes[]; }; /* Called in removal of a func but failed to allocate a new tp_funcs */ static void tp_stub_func(void) { return; } static inline void *allocate_probes(int count) { struct tp_probes *p = kmalloc(struct_size(p, probes, count), GFP_KERNEL); return p == NULL ? NULL : p->probes; } static void rcu_free_old_probes(struct rcu_head *head) { kfree(container_of(head, struct tp_probes, rcu)); } static inline void release_probes(struct tracepoint *tp, struct tracepoint_func *old) { if (old) { struct tp_probes *tp_probes = container_of(old, struct tp_probes, probes[0]); if (tracepoint_is_faultable(tp)) call_rcu_tasks_trace(&tp_probes->rcu, rcu_free_old_probes); else call_rcu(&tp_probes->rcu, rcu_free_old_probes); } } static void debug_print_probes(struct tracepoint_func *funcs) { int i; if (!tracepoint_debug || !funcs) return; for (i = 0; funcs[i].func; i++) printk(KERN_DEBUG "Probe %d : %p\n", i, funcs[i].func); } static struct tracepoint_func * func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func, int prio) { struct tracepoint_func *old, *new; int iter_probes; /* Iterate over old probe array. */ int nr_probes = 0; /* Counter for probes */ int pos = -1; /* Insertion position into new array */ if (WARN_ON(!tp_func->func)) return ERR_PTR(-EINVAL); debug_print_probes(*funcs); old = *funcs; if (old) { /* (N -> N+1), (N != 0, 1) probes */ for (iter_probes = 0; old[iter_probes].func; iter_probes++) { if (old[iter_probes].func == tp_stub_func) continue; /* Skip stub functions. */ if (old[iter_probes].func == tp_func->func && old[iter_probes].data == tp_func->data) return ERR_PTR(-EEXIST); nr_probes++; } } /* + 2 : one for new probe, one for NULL func */ new = allocate_probes(nr_probes + 2); if (new == NULL) return ERR_PTR(-ENOMEM); if (old) { nr_probes = 0; for (iter_probes = 0; old[iter_probes].func; iter_probes++) { if (old[iter_probes].func == tp_stub_func) continue; /* Insert before probes of lower priority */ if (pos < 0 && old[iter_probes].prio < prio) pos = nr_probes++; new[nr_probes++] = old[iter_probes]; } if (pos < 0) pos = nr_probes++; /* nr_probes now points to the end of the new array */ } else { pos = 0; nr_probes = 1; /* must point at end of array */ } new[pos] = *tp_func; new[nr_probes].func = NULL; *funcs = new; debug_print_probes(*funcs); return old; } static void *func_remove(struct tracepoint_func **funcs, struct tracepoint_func *tp_func) { int nr_probes = 0, nr_del = 0, i; struct tracepoint_func *old, *new; old = *funcs; if (!old) return ERR_PTR(-ENOENT); debug_print_probes(*funcs); /* (N -> M), (N > 1, M >= 0) probes */ if (tp_func->func) { for (nr_probes = 0; old[nr_probes].func; nr_probes++) { if ((old[nr_probes].func == tp_func->func && old[nr_probes].data == tp_func->data) || old[nr_probes].func == tp_stub_func) nr_del++; } } /* * If probe is NULL, then nr_probes = nr_del = 0, and then the * entire entry will be removed. */ if (nr_probes - nr_del == 0) { /* N -> 0, (N > 1) */ *funcs = NULL; debug_print_probes(*funcs); return old; } else { int j = 0; /* N -> M, (N > 1, M > 0) */ /* + 1 for NULL */ new = allocate_probes(nr_probes - nr_del + 1); if (new) { for (i = 0; old[i].func; i++) { if ((old[i].func != tp_func->func || old[i].data != tp_func->data) && old[i].func != tp_stub_func) new[j++] = old[i]; } new[nr_probes - nr_del].func = NULL; *funcs = new; } else { /* * Failed to allocate, replace the old function * with calls to tp_stub_func. */ for (i = 0; old[i].func; i++) { if (old[i].func == tp_func->func && old[i].data == tp_func->data) WRITE_ONCE(old[i].func, tp_stub_func); } *funcs = old; } } debug_print_probes(*funcs); return old; } /* * Count the number of functions (enum tp_func_state) in a tp_funcs array. */ static enum tp_func_state nr_func_state(const struct tracepoint_func *tp_funcs) { if (!tp_funcs) return TP_FUNC_0; if (!tp_funcs[1].func) return TP_FUNC_1; if (!tp_funcs[2].func) return TP_FUNC_2; return TP_FUNC_N; /* 3 or more */ } static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs) { void *func = tp->iterator; /* Synthetic events do not have static call sites */ if (!tp->static_call_key) return; if (nr_func_state(tp_funcs) == TP_FUNC_1) func = tp_funcs[0].func; __static_call_update(tp->static_call_key, tp->static_call_tramp, func); } /* * Add the probe function to a tracepoint. */ static int tracepoint_add_func(struct tracepoint *tp, struct tracepoint_func *func, int prio, bool warn) { struct tracepoint_func *old, *tp_funcs; int ret; if (tp->ext && tp->ext->regfunc && !static_key_enabled(&tp->key)) { ret = tp->ext->regfunc(); if (ret < 0) return ret; } tp_funcs = rcu_dereference_protected(tp->funcs, lockdep_is_held(&tracepoints_mutex)); old = func_add(&tp_funcs, func, prio); if (IS_ERR(old)) { WARN_ON_ONCE(warn && PTR_ERR(old) != -ENOMEM); return PTR_ERR(old); } /* * rcu_assign_pointer has as smp_store_release() which makes sure * that the new probe callbacks array is consistent before setting * a pointer to it. This array is referenced by __DO_TRACE from * include/linux/tracepoint.h using rcu_dereference_sched(). */ switch (nr_func_state(tp_funcs)) { case TP_FUNC_1: /* 0->1 */ /* * Make sure new static func never uses old data after a * 1->0->1 transition sequence. */ tp_rcu_cond_sync(TP_TRANSITION_SYNC_1_0_1); /* Set static call to first function */ tracepoint_update_call(tp, tp_funcs); /* Both iterator and static call handle NULL tp->funcs */ rcu_assign_pointer(tp->funcs, tp_funcs); static_branch_enable(&tp->key); break; case TP_FUNC_2: /* 1->2 */ /* Set iterator static call */ tracepoint_update_call(tp, tp_funcs); /* * Iterator callback installed before updating tp->funcs. * Requires ordering between RCU assign/dereference and * static call update/call. */ fallthrough; case TP_FUNC_N: /* N->N+1 (N>1) */ rcu_assign_pointer(tp->funcs, tp_funcs); /* * Make sure static func never uses incorrect data after a * N->...->2->1 (N>1) transition sequence. */ if (tp_funcs[0].data != old[0].data) tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); break; default: WARN_ON_ONCE(1); break; } release_probes(tp, old); return 0; } /* * Remove a probe function from a tracepoint. * Note: only waiting an RCU period after setting elem->call to the empty * function insures that the original callback is not used anymore. This insured * by preempt_disable around the call site. */ static int tracepoint_remove_func(struct tracepoint *tp, struct tracepoint_func *func) { struct tracepoint_func *old, *tp_funcs; tp_funcs = rcu_dereference_protected(tp->funcs, lockdep_is_held(&tracepoints_mutex)); old = func_remove(&tp_funcs, func); if (WARN_ON_ONCE(IS_ERR(old))) return PTR_ERR(old); if (tp_funcs == old) /* Failed allocating new tp_funcs, replaced func with stub */ return 0; switch (nr_func_state(tp_funcs)) { case TP_FUNC_0: /* 1->0 */ /* Removed last function */ if (tp->ext && tp->ext->unregfunc && static_key_enabled(&tp->key)) tp->ext->unregfunc(); static_branch_disable(&tp->key); /* Set iterator static call */ tracepoint_update_call(tp, tp_funcs); /* Both iterator and static call handle NULL tp->funcs */ rcu_assign_pointer(tp->funcs, NULL); /* * Make sure new static func never uses old data after a * 1->0->1 transition sequence. */ tp_rcu_get_state(TP_TRANSITION_SYNC_1_0_1); break; case TP_FUNC_1: /* 2->1 */ rcu_assign_pointer(tp->funcs, tp_funcs); /* * Make sure static func never uses incorrect data after a * N->...->2->1 (N>2) transition sequence. If the first * element's data has changed, then force the synchronization * to prevent current readers that have loaded the old data * from calling the new function. */ if (tp_funcs[0].data != old[0].data) tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); tp_rcu_cond_sync(TP_TRANSITION_SYNC_N_2_1); /* Set static call to first function */ tracepoint_update_call(tp, tp_funcs); break; case TP_FUNC_2: /* N->N-1 (N>2) */ fallthrough; case TP_FUNC_N: rcu_assign_pointer(tp->funcs, tp_funcs); /* * Make sure static func never uses incorrect data after a * N->...->2->1 (N>2) transition sequence. */ if (tp_funcs[0].data != old[0].data) tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); break; default: WARN_ON_ONCE(1); break; } release_probes(tp, old); return 0; } /** * tracepoint_probe_register_prio_may_exist - Connect a probe to a tracepoint with priority * @tp: tracepoint * @probe: probe handler * @data: tracepoint data * @prio: priority of this function over other registered functions * * Same as tracepoint_probe_register_prio() except that it will not warn * if the tracepoint is already registered. */ int tracepoint_probe_register_prio_may_exist(struct tracepoint *tp, void *probe, void *data, int prio) { struct tracepoint_func tp_func; int ret; mutex_lock(&tracepoints_mutex); tp_func.func = probe; tp_func.data = data; tp_func.prio = prio; ret = tracepoint_add_func(tp, &tp_func, prio, false); mutex_unlock(&tracepoints_mutex); return ret; } EXPORT_SYMBOL_GPL(tracepoint_probe_register_prio_may_exist); /** * tracepoint_probe_register_prio - Connect a probe to a tracepoint with priority * @tp: tracepoint * @probe: probe handler * @data: tracepoint data * @prio: priority of this function over other registered functions * * Returns 0 if ok, error value on error. * Note: if @tp is within a module, the caller is responsible for * unregistering the probe before the module is gone. This can be * performed either with a tracepoint module going notifier, or from * within module exit functions. */ int tracepoint_probe_register_prio(struct tracepoint *tp, void *probe, void *data, int prio) { struct tracepoint_func tp_func; int ret; mutex_lock(&tracepoints_mutex); tp_func.func = probe; tp_func.data = data; tp_func.prio = prio; ret = tracepoint_add_func(tp, &tp_func, prio, true); mutex_unlock(&tracepoints_mutex); return ret; } EXPORT_SYMBOL_GPL(tracepoint_probe_register_prio); /** * tracepoint_probe_register - Connect a probe to a tracepoint * @tp: tracepoint * @probe: probe handler * @data: tracepoint data * * Returns 0 if ok, error value on error. * Note: if @tp is within a module, the caller is responsible for * unregistering the probe before the module is gone. This can be * performed either with a tracepoint module going notifier, or from * within module exit functions. */ int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data) { return tracepoint_probe_register_prio(tp, probe, data, TRACEPOINT_DEFAULT_PRIO); } EXPORT_SYMBOL_GPL(tracepoint_probe_register); /** * tracepoint_probe_unregister - Disconnect a probe from a tracepoint * @tp: tracepoint * @probe: probe function pointer * @data: tracepoint data * * Returns 0 if ok, error value on error. */ int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data) { struct tracepoint_func tp_func; int ret; mutex_lock(&tracepoints_mutex); tp_func.func = probe; tp_func.data = data; ret = tracepoint_remove_func(tp, &tp_func); mutex_unlock(&tracepoints_mutex); return ret; } EXPORT_SYMBOL_GPL(tracepoint_probe_unregister); static void for_each_tracepoint_range( tracepoint_ptr_t *begin, tracepoint_ptr_t *end, void (*fct)(struct tracepoint *tp, void *priv), void *priv) { tracepoint_ptr_t *iter; if (!begin) return; for (iter = begin; iter < end; iter++) fct(tracepoint_ptr_deref(iter), priv); } #ifdef CONFIG_MODULES bool trace_module_has_bad_taint(struct module *mod) { return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) | (1 << TAINT_UNSIGNED_MODULE) | (1 << TAINT_TEST) | (1 << TAINT_LIVEPATCH)); } static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list); /** * register_tracepoint_module_notifier - register tracepoint coming/going notifier * @nb: notifier block * * Notifiers registered with this function are called on module * coming/going with the tracepoint_module_list_mutex held. * The notifier block callback should expect a "struct tp_module" data * pointer. */ int register_tracepoint_module_notifier(struct notifier_block *nb) { struct tp_module *tp_mod; int ret; mutex_lock(&tracepoint_module_list_mutex); ret = blocking_notifier_chain_register(&tracepoint_notify_list, nb); if (ret) goto end; list_for_each_entry(tp_mod, &tracepoint_module_list, list) (void) nb->notifier_call(nb, MODULE_STATE_COMING, tp_mod); end: mutex_unlock(&tracepoint_module_list_mutex); return ret; } EXPORT_SYMBOL_GPL(register_tracepoint_module_notifier); /** * unregister_tracepoint_module_notifier - unregister tracepoint coming/going notifier * @nb: notifier block * * The notifier block callback should expect a "struct tp_module" data * pointer. */ int unregister_tracepoint_module_notifier(struct notifier_block *nb) { struct tp_module *tp_mod; int ret; mutex_lock(&tracepoint_module_list_mutex); ret = blocking_notifier_chain_unregister(&tracepoint_notify_list, nb); if (ret) goto end; list_for_each_entry(tp_mod, &tracepoint_module_list, list) (void) nb->notifier_call(nb, MODULE_STATE_GOING, tp_mod); end: mutex_unlock(&tracepoint_module_list_mutex); return ret; } EXPORT_SYMBOL_GPL(unregister_tracepoint_module_notifier); /* * Ensure the tracer unregistered the module's probes before the module * teardown is performed. Prevents leaks of probe and data pointers. */ static void tp_module_going_check_quiescent(struct tracepoint *tp, void *priv) { WARN_ON_ONCE(tp->funcs); } static int tracepoint_module_coming(struct module *mod) { struct tp_module *tp_mod; if (!mod->num_tracepoints) return 0; /* * We skip modules that taint the kernel, especially those with different * module headers (for forced load), to make sure we don't cause a crash. * Staging, out-of-tree, unsigned GPL, and test modules are fine. */ if (trace_module_has_bad_taint(mod)) return 0; tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL); if (!tp_mod) return -ENOMEM; tp_mod->mod = mod; mutex_lock(&tracepoint_module_list_mutex); list_add_tail(&tp_mod->list, &tracepoint_module_list); blocking_notifier_call_chain(&tracepoint_notify_list, MODULE_STATE_COMING, tp_mod); mutex_unlock(&tracepoint_module_list_mutex); return 0; } static void tracepoint_module_going(struct module *mod) { struct tp_module *tp_mod; if (!mod->num_tracepoints) return; mutex_lock(&tracepoint_module_list_mutex); list_for_each_entry(tp_mod, &tracepoint_module_list, list) { if (tp_mod->mod == mod) { blocking_notifier_call_chain(&tracepoint_notify_list, MODULE_STATE_GOING, tp_mod); list_del(&tp_mod->list); kfree(tp_mod); /* * Called the going notifier before checking for * quiescence. */ for_each_tracepoint_range(mod->tracepoints_ptrs, mod->tracepoints_ptrs + mod->num_tracepoints, tp_module_going_check_quiescent, NULL); break; } } /* * In the case of modules that were tainted at "coming", we'll simply * walk through the list without finding it. We cannot use the "tainted" * flag on "going", in case a module taints the kernel only after being * loaded. */ mutex_unlock(&tracepoint_module_list_mutex); } static int tracepoint_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; switch (val) { case MODULE_STATE_COMING: ret = tracepoint_module_coming(mod); break; case MODULE_STATE_LIVE: break; case MODULE_STATE_GOING: tracepoint_module_going(mod); break; case MODULE_STATE_UNFORMED: break; } return notifier_from_errno(ret); } static struct notifier_block tracepoint_module_nb = { .notifier_call = tracepoint_module_notify, .priority = 0, }; static __init int init_tracepoints(void) { int ret; ret = register_module_notifier(&tracepoint_module_nb); if (ret) pr_warn("Failed to register tracepoint module enter notifier\n"); return ret; } __initcall(init_tracepoints); /** * for_each_tracepoint_in_module - iteration on all tracepoints in a module * @mod: module * @fct: callback * @priv: private data */ void for_each_tracepoint_in_module(struct module *mod, void (*fct)(struct tracepoint *tp, struct module *mod, void *priv), void *priv) { tracepoint_ptr_t *begin, *end, *iter; lockdep_assert_held(&tracepoint_module_list_mutex); if (!mod) return; begin = mod->tracepoints_ptrs; end = mod->tracepoints_ptrs + mod->num_tracepoints; for (iter = begin; iter < end; iter++) fct(tracepoint_ptr_deref(iter), mod, priv); } /** * for_each_module_tracepoint - iteration on all tracepoints in all modules * @fct: callback * @priv: private data */ void for_each_module_tracepoint(void (*fct)(struct tracepoint *tp, struct module *mod, void *priv), void *priv) { struct tp_module *tp_mod; mutex_lock(&tracepoint_module_list_mutex); list_for_each_entry(tp_mod, &tracepoint_module_list, list) for_each_tracepoint_in_module(tp_mod->mod, fct, priv); mutex_unlock(&tracepoint_module_list_mutex); } #endif /* CONFIG_MODULES */ /** * for_each_kernel_tracepoint - iteration on all kernel tracepoints * @fct: callback * @priv: private data */ void for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv), void *priv) { for_each_tracepoint_range(__start___tracepoints_ptrs, __stop___tracepoints_ptrs, fct, priv); } EXPORT_SYMBOL_GPL(for_each_kernel_tracepoint); #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS /* NB: reg/unreg are called while guarded with the tracepoints_mutex */ static int sys_tracepoint_refcount; int syscall_regfunc(void) { struct task_struct *p, *t; if (!sys_tracepoint_refcount) { read_lock(&tasklist_lock); for_each_process_thread(p, t) { set_task_syscall_work(t, SYSCALL_TRACEPOINT); } read_unlock(&tasklist_lock); } sys_tracepoint_refcount++; return 0; } void syscall_unregfunc(void) { struct task_struct *p, *t; sys_tracepoint_refcount--; if (!sys_tracepoint_refcount) { read_lock(&tasklist_lock); for_each_process_thread(p, t) { clear_task_syscall_work(t, SYSCALL_TRACEPOINT); } read_unlock(&tasklist_lock); } } #endif |
| 250 45 236 100 100 73 74 74 79 22 2 22 1 6 1 22 234 107 234 126 76 200 89 8 19 5 21 2 2 5 5 13 10 249 267 10 261 5 19 3 8 26 255 236 25 32 17 23 8 31 7 234 184 24 222 2 68 1 183 49 224 223 62 182 22 230 122 93 3 119 46 2 9 83 2 99 19 117 2 85 31 114 3 28 65 93 13 3 93 72 51 6 101 106 2 393 3 50 336 5 5 314 2 6 315 316 217 315 194 101 81 16 291 43 106 231 94 217 279 282 281 277 107 91 15 1 114 193 316 289 11 3 81 8 81 43 36 201 3 1 25 7 99 1 1 102 103 99 95 4 2 8 66 2 66 5 80 110 110 78 4 134 2 96 101 8 192 10 72 132 133 22 2 7 22 6 4 16 2 10 15 2 5 24 2 20 21 70 1 5 33 32 2 6 30 27 62 218 1 1 8 3 212 206 32 16 4 43 40 4 2 1 25 1 1 3 3 13 5 14 6 13 6 13 2 13 12 3 14 7 12 32 4 3 26 19 2 12 12 41 3 3 2 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * "splice": joining two ropes together by interweaving their strands. * * This is the "extended pipe" functionality, where a pipe is used as * an arbitrary in-memory buffer. Think of a pipe as a small kernel * buffer that you can use to transfer data from one end to the other. * * The traditional unix read/write is extended with a "splice()" operation * that transfers data buffers to or from a pipe buffer. * * Named by Larry McVoy, original implementation from Linus, extended by * Jens to support splicing to files, network, direct splicing, etc and * fixing lots of bugs. * * Copyright (C) 2005-2006 Jens Axboe <axboe@kernel.dk> * Copyright (C) 2005-2006 Linus Torvalds <torvalds@osdl.org> * Copyright (C) 2006 Ingo Molnar <mingo@elte.hu> * */ #include <linux/bvec.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/gfp.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/sched/signal.h> #include "internal.h" /* * Splice doesn't support FMODE_NOWAIT. Since pipes may set this flag to * indicate they support non-blocking reads or writes, we must clear it * here if set to avoid blocking other users of this pipe if splice is * being done on it. */ static noinline void noinline pipe_clear_nowait(struct file *file) { fmode_t fmode = READ_ONCE(file->f_mode); do { if (!(fmode & FMODE_NOWAIT)) break; } while (!try_cmpxchg(&file->f_mode, &fmode, fmode & ~FMODE_NOWAIT)); } /* * Attempt to steal a page from a pipe buffer. This should perhaps go into * a vm helper function, it's already simplified quite a bit by the * addition of remove_mapping(). If success is returned, the caller may * attempt to reuse this page for another destination. */ static bool page_cache_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct folio *folio = page_folio(buf->page); struct address_space *mapping; folio_lock(folio); mapping = folio_mapping(folio); if (mapping) { WARN_ON(!folio_test_uptodate(folio)); /* * At least for ext2 with nobh option, we need to wait on * writeback completing on this folio, since we'll remove it * from the pagecache. Otherwise truncate wont wait on the * folio, allowing the disk blocks to be reused by someone else * before we actually wrote our data to them. fs corruption * ensues. */ folio_wait_writeback(folio); if (!filemap_release_folio(folio, GFP_KERNEL)) goto out_unlock; /* * If we succeeded in removing the mapping, set LRU flag * and return good. */ if (remove_mapping(mapping, folio)) { buf->flags |= PIPE_BUF_FLAG_LRU; return true; } } /* * Raced with truncate or failed to remove folio from current * address space, unlock and return failure. */ out_unlock: folio_unlock(folio); return false; } static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); buf->flags &= ~PIPE_BUF_FLAG_LRU; } /* * Check whether the contents of buf is OK to access. Since the content * is a page cache page, IO may be in flight. */ static int page_cache_pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct folio *folio = page_folio(buf->page); int err; if (!folio_test_uptodate(folio)) { folio_lock(folio); /* * Folio got truncated/unhashed. This will cause a 0-byte * splice, if this is the first page. */ if (!folio->mapping) { err = -ENODATA; goto error; } /* * Uh oh, read-error from disk. */ if (!folio_test_uptodate(folio)) { err = -EIO; goto error; } /* Folio is ok after all, we are done */ folio_unlock(folio); } return 0; error: folio_unlock(folio); return err; } const struct pipe_buf_operations page_cache_pipe_buf_ops = { .confirm = page_cache_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .try_steal = page_cache_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; static bool user_page_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!(buf->flags & PIPE_BUF_FLAG_GIFT)) return false; buf->flags |= PIPE_BUF_FLAG_LRU; return generic_pipe_buf_try_steal(pipe, buf); } static const struct pipe_buf_operations user_page_pipe_buf_ops = { .release = page_cache_pipe_buf_release, .try_steal = user_page_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; static void wakeup_pipe_readers(struct pipe_inode_info *pipe) { smp_mb(); if (waitqueue_active(&pipe->rd_wait)) wake_up_interruptible(&pipe->rd_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } /** * splice_to_pipe - fill passed data into a pipe * @pipe: pipe to fill * @spd: data to fill * * Description: * @spd contains a map of pages and len/offset tuples, along with * the struct pipe_buf_operations associated with these pages. This * function will link that data to the pipe. * */ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { unsigned int spd_pages = spd->nr_pages; unsigned int tail = pipe->tail; unsigned int head = pipe->head; unsigned int mask = pipe->ring_size - 1; ssize_t ret = 0; int page_nr = 0; if (!spd_pages) return 0; if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } while (!pipe_full(head, tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[head & mask]; buf->page = spd->pages[page_nr]; buf->offset = spd->partial[page_nr].offset; buf->len = spd->partial[page_nr].len; buf->private = spd->partial[page_nr].private; buf->ops = spd->ops; buf->flags = 0; head++; pipe->head = head; page_nr++; ret += buf->len; if (!--spd->nr_pages) break; } if (!ret) ret = -EAGAIN; out: while (page_nr < spd_pages) spd->spd_release(spd, page_nr++); return ret; } EXPORT_SYMBOL_GPL(splice_to_pipe); ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { unsigned int head = pipe->head; unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; int ret; if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; } else if (pipe_full(head, tail, pipe->max_usage)) { ret = -EAGAIN; } else { pipe->bufs[head & mask] = *buf; pipe->head = head + 1; return buf->len; } pipe_buf_release(pipe, buf); return ret; } EXPORT_SYMBOL(add_to_pipe); /* * Check if we need to grow the arrays holding pages and partial page * descriptions. */ int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { unsigned int max_usage = READ_ONCE(pipe->max_usage); spd->nr_pages_max = max_usage; if (max_usage <= PIPE_DEF_BUFFERS) return 0; spd->pages = kmalloc_array(max_usage, sizeof(struct page *), GFP_KERNEL); spd->partial = kmalloc_array(max_usage, sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; kfree(spd->pages); kfree(spd->partial); return -ENOMEM; } void splice_shrink_spd(struct splice_pipe_desc *spd) { if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); kfree(spd->partial); } /** * copy_splice_read - Copy data from a file and splice the copy into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function allocates a bunch of pages sufficient to hold the requested * amount of data (but limited by the remaining pipe capacity), passes it to * the file's ->read_iter() to read into and then splices the used pages into * the pipe. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct iov_iter to; struct bio_vec *bv; struct kiocb kiocb; struct page **pages; ssize_t ret; size_t used, npages, chunk, remain, keep = 0; int i; /* Work out how much data we can actually add into the pipe */ used = pipe_occupancy(pipe->head, pipe->tail); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); npages = DIV_ROUND_UP(len, PAGE_SIZE); bv = kzalloc(array_size(npages, sizeof(bv[0])) + array_size(npages, sizeof(struct page *)), GFP_KERNEL); if (!bv) return -ENOMEM; pages = (struct page **)(bv + npages); npages = alloc_pages_bulk(GFP_USER, npages, pages); if (!npages) { kfree(bv); return -ENOMEM; } remain = len = min_t(size_t, len, npages * PAGE_SIZE); for (i = 0; i < npages; i++) { chunk = min_t(size_t, PAGE_SIZE, remain); bv[i].bv_page = pages[i]; bv[i].bv_offset = 0; bv[i].bv_len = chunk; remain -= chunk; } /* Do the I/O */ iov_iter_bvec(&to, ITER_DEST, bv, npages, len); init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; ret = in->f_op->read_iter(&kiocb, &to); if (ret > 0) { keep = DIV_ROUND_UP(ret, PAGE_SIZE); *ppos = kiocb.ki_pos; } /* * Callers of ->splice_read() expect -EAGAIN on "can't put anything in * there", rather than -EFAULT. */ if (ret == -EFAULT) ret = -EAGAIN; /* Free any pages that didn't get touched at all. */ if (keep < npages) release_pages(pages + keep, npages - keep); /* Push the remaining pages into the pipe. */ remain = ret; for (i = 0; i < keep; i++) { struct pipe_buffer *buf = pipe_head_buf(pipe); chunk = min_t(size_t, remain, PAGE_SIZE); *buf = (struct pipe_buffer) { .ops = &default_pipe_buf_ops, .page = bv[i].bv_page, .offset = 0, .len = chunk, }; pipe->head++; remain -= chunk; } kfree(bv); return ret; } EXPORT_SYMBOL(copy_splice_read); const struct pipe_buf_operations default_pipe_buf_ops = { .release = generic_pipe_buf_release, .try_steal = generic_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Pipe buffer operations for a socket and similar. */ const struct pipe_buf_operations nosteal_pipe_buf_ops = { .release = generic_pipe_buf_release, .get = generic_pipe_buf_get, }; EXPORT_SYMBOL(nosteal_pipe_buf_ops); static void wakeup_pipe_writers(struct pipe_inode_info *pipe) { smp_mb(); if (waitqueue_active(&pipe->wr_wait)) wake_up_interruptible(&pipe->wr_wait); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } /** * splice_from_pipe_feed - feed available data from a pipe to a file * @pipe: pipe to splice from * @sd: information to @actor * @actor: handler that splices the data * * Description: * This function loops over the pipe and calls @actor to do the * actual moving of a single struct pipe_buffer to the desired * destination. It returns when there's no more buffers left in * the pipe or if the requested number of bytes (@sd->total_len) * have been copied. It returns a positive number (one) if the * pipe needs to be filled with more data, zero if the required * number of bytes have been copied and -errno on error. * * This, together with splice_from_pipe_{begin,end,next}, may be * used to implement the functionality of __splice_from_pipe() when * locking is required around copying the pipe buffers to the * destination. */ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { unsigned int head = pipe->head; unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; int ret; while (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; sd->len = buf->len; if (sd->len > sd->total_len) sd->len = sd->total_len; ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; return ret; } ret = actor(pipe, buf, sd); if (ret <= 0) return ret; buf->offset += ret; buf->len -= ret; sd->num_spliced += ret; sd->len -= ret; sd->pos += ret; sd->total_len -= ret; if (!buf->len) { pipe_buf_release(pipe, buf); tail++; pipe->tail = tail; if (pipe->files) sd->need_wakeup = true; } if (!sd->total_len) return 0; } return 1; } /* We know we have a pipe buffer, but maybe it's empty? */ static inline bool eat_empty_buffer(struct pipe_inode_info *pipe) { unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[tail & mask]; if (unlikely(!buf->len)) { pipe_buf_release(pipe, buf); pipe->tail = tail+1; return true; } return false; } /** * splice_from_pipe_next - wait for some data to splice from * @pipe: pipe to splice from * @sd: information about the splice operation * * Description: * This function will wait for some data and return a positive * value (one) if pipe buffers are available. It will return zero * or -errno if no more data needs to be spliced. */ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) { /* * Check for signal early to make process killable when there are * always buffers available */ if (signal_pending(current)) return -ERESTARTSYS; repeat: while (pipe_empty(pipe->head, pipe->tail)) { if (!pipe->writers) return 0; if (sd->num_spliced) return 0; if (sd->flags & SPLICE_F_NONBLOCK) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; if (sd->need_wakeup) { wakeup_pipe_writers(pipe); sd->need_wakeup = false; } pipe_wait_readable(pipe); } if (eat_empty_buffer(pipe)) goto repeat; return 1; } /** * splice_from_pipe_begin - start splicing from pipe * @sd: information about the splice operation * * Description: * This function should be called before a loop containing * splice_from_pipe_next() and splice_from_pipe_feed() to * initialize the necessary fields of @sd. */ static void splice_from_pipe_begin(struct splice_desc *sd) { sd->num_spliced = 0; sd->need_wakeup = false; } /** * splice_from_pipe_end - finish splicing from pipe * @pipe: pipe to splice from * @sd: information about the splice operation * * Description: * This function will wake up pipe writers if necessary. It should * be called after a loop containing splice_from_pipe_next() and * splice_from_pipe_feed(). */ static void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd) { if (sd->need_wakeup) wakeup_pipe_writers(pipe); } /** * __splice_from_pipe - splice data from a pipe to given actor * @pipe: pipe to splice from * @sd: information to @actor * @actor: handler that splices the data * * Description: * This function does little more than loop over the pipe and call * @actor to do the actual moving of a single struct pipe_buffer to * the desired destination. See pipe_to_file, pipe_to_sendmsg, or * pipe_to_user. * */ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { int ret; splice_from_pipe_begin(sd); do { cond_resched(); ret = splice_from_pipe_next(pipe, sd); if (ret > 0) ret = splice_from_pipe_feed(pipe, sd, actor); } while (ret > 0); splice_from_pipe_end(pipe, sd); return sd->num_spliced ? sd->num_spliced : ret; } EXPORT_SYMBOL(__splice_from_pipe); /** * splice_from_pipe - splice data from a pipe to a file * @pipe: pipe to splice from * @out: file to splice to * @ppos: position in @out * @len: how many bytes to splice * @flags: splice modifier flags * @actor: handler that splices the data * * Description: * See __splice_from_pipe. This function locks the pipe inode, * otherwise it's identical to __splice_from_pipe(). * */ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags, splice_actor *actor) { ssize_t ret; struct splice_desc sd = { .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, }; pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, actor); pipe_unlock(pipe); return ret; } /** * iter_file_splice_write - splice data from a pipe to a file * @pipe: pipe info * @out: file to write to * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will either move or copy pages (determined by @flags options) from * the given pipe inode to the given file. * This one is ->write_iter-based. * */ ssize_t iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct splice_desc sd = { .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, }; int nbufs = pipe->max_usage; struct bio_vec *array; ssize_t ret; if (!out->f_op->write_iter) return -EINVAL; array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (unlikely(!array)) return -ENOMEM; pipe_lock(pipe); splice_from_pipe_begin(&sd); while (sd.total_len) { struct kiocb kiocb; struct iov_iter from; unsigned int head, tail, mask; size_t left; int n; ret = splice_from_pipe_next(pipe, &sd); if (ret <= 0) break; if (unlikely(nbufs < pipe->max_usage)) { kfree(array); nbufs = pipe->max_usage; array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (!array) { ret = -ENOMEM; break; } } head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; /* build the vector */ left = sd.total_len; for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t this_len = buf->len; /* zero-length bvecs are not supported, skip them */ if (!this_len) continue; this_len = min(this_len, left); ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; goto done; } bvec_set_page(&array[n], buf->page, this_len, buf->offset); left -= this_len; n++; } iov_iter_bvec(&from, ITER_SOURCE, array, n, sd.total_len - left); init_sync_kiocb(&kiocb, out); kiocb.ki_pos = sd.pos; ret = out->f_op->write_iter(&kiocb, &from); sd.pos = kiocb.ki_pos; if (ret <= 0) break; sd.num_spliced += ret; sd.total_len -= ret; *ppos = sd.pos; /* dismiss the fully eaten buffers, adjust the partial one */ tail = pipe->tail; while (ret) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; if (ret >= buf->len) { ret -= buf->len; buf->len = 0; pipe_buf_release(pipe, buf); tail++; pipe->tail = tail; if (pipe->files) sd.need_wakeup = true; } else { buf->offset += ret; buf->len -= ret; ret = 0; } } } done: kfree(array); splice_from_pipe_end(pipe, &sd); pipe_unlock(pipe); if (sd.num_spliced) ret = sd.num_spliced; return ret; } EXPORT_SYMBOL(iter_file_splice_write); #ifdef CONFIG_NET /** * splice_to_socket - splice data from a pipe to a socket * @pipe: pipe to splice from * @out: socket to write to * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will send @len bytes from the pipe to a network socket. No data copying * is involved. * */ ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct socket *sock = sock_from_file(out); struct bio_vec bvec[16]; struct msghdr msg = {}; ssize_t ret = 0; size_t spliced = 0; bool need_wakeup = false; pipe_lock(pipe); while (len > 0) { unsigned int head, tail, mask, bc = 0; size_t remain = len; /* * Check for signal early to make process killable when there * are always buffers available */ ret = -ERESTARTSYS; if (signal_pending(current)) break; while (pipe_empty(pipe->head, pipe->tail)) { ret = 0; if (!pipe->writers) goto out; if (spliced) goto out; ret = -EAGAIN; if (flags & SPLICE_F_NONBLOCK) goto out; ret = -ERESTARTSYS; if (signal_pending(current)) goto out; if (need_wakeup) { wakeup_pipe_writers(pipe); need_wakeup = false; } pipe_wait_readable(pipe); } head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t seg; if (!buf->len) { tail++; continue; } seg = min_t(size_t, remain, buf->len); ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) ret = 0; break; } bvec_set_page(&bvec[bc++], buf->page, seg, buf->offset); remain -= seg; if (remain == 0 || bc >= ARRAY_SIZE(bvec)) break; tail++; } if (!bc) break; msg.msg_flags = MSG_SPLICE_PAGES; if (flags & SPLICE_F_MORE) msg.msg_flags |= MSG_MORE; if (remain && pipe_occupancy(pipe->head, tail) > 0) msg.msg_flags |= MSG_MORE; if (out->f_flags & O_NONBLOCK) msg.msg_flags |= MSG_DONTWAIT; iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, bvec, bc, len - remain); ret = sock_sendmsg(sock, &msg); if (ret <= 0) break; spliced += ret; len -= ret; tail = pipe->tail; while (ret > 0) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t seg = min_t(size_t, ret, buf->len); buf->offset += seg; buf->len -= seg; ret -= seg; if (!buf->len) { pipe_buf_release(pipe, buf); tail++; } } if (tail != pipe->tail) { pipe->tail = tail; if (pipe->files) need_wakeup = true; } } out: pipe_unlock(pipe); if (need_wakeup) wakeup_pipe_writers(pipe); return spliced ?: ret; } #endif static int warn_unsupported(struct file *file, const char *op) { pr_debug_ratelimited( "splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } /* * Attempt to initiate a splice from pipe to file. */ static ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { if (unlikely(!out->f_op->splice_write)) return warn_unsupported(out, "write"); return out->f_op->splice_write(pipe, out, ppos, len, flags); } /* * Indicate to the caller that there was a premature EOF when reading from the * source and the caller didn't indicate they would be sending more data after * this. */ static void do_splice_eof(struct splice_desc *sd) { if (sd->splice_eof) sd->splice_eof(sd); } /* * Callers already called rw_verify_area() on the entire range. * No need to call it for sub ranges. */ static ssize_t do_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { unsigned int p_space; if (unlikely(!(in->f_mode & FMODE_READ))) return -EBADF; if (!len) return 0; /* Don't try to read more the pipe has space for. */ p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); len = min_t(size_t, len, p_space << PAGE_SHIFT); if (unlikely(len > MAX_RW_COUNT)) len = MAX_RW_COUNT; if (unlikely(!in->f_op->splice_read)) return warn_unsupported(in, "read"); /* * O_DIRECT and DAX don't deal with the pagecache, so we allocate a * buffer, copy into it and splice that into the pipe. */ if ((in->f_flags & O_DIRECT) || IS_DAX(in->f_mapping->host)) return copy_splice_read(in, ppos, pipe, len, flags); return in->f_op->splice_read(in, ppos, pipe, len, flags); } /** * vfs_splice_read - Read data from a file and splice it into a pipe * @in: File to splice from * @ppos: Input file offset * @pipe: Pipe to splice to * @len: Number of bytes to splice * @flags: Splice modifier flags (SPLICE_F_*) * * Splice the requested amount of data from the input file to the pipe. This * is synchronous as the caller must hold the pipe lock across the entire * operation. * * If successful, it returns the amount of data spliced, 0 if it hit the EOF or * a hole and a negative error code otherwise. */ ssize_t vfs_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { ssize_t ret; ret = rw_verify_area(READ, in, ppos, len); if (unlikely(ret < 0)) return ret; return do_splice_read(in, ppos, pipe, len, flags); } EXPORT_SYMBOL_GPL(vfs_splice_read); /** * splice_direct_to_actor - splices data directly between two non-pipes * @in: file to splice from * @sd: actor information on where to splice to * @actor: handles the data splicing * * Description: * This is a special case helper to splice directly between two * points, without requiring an explicit pipe. Internally an allocated * pipe is cached in the process, and reused during the lifetime of * that process. * */ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, splice_direct_actor *actor) { struct pipe_inode_info *pipe; ssize_t ret, bytes; size_t len; int i, flags, more; /* * We require the input to be seekable, as we don't want to randomly * drop data for eg socket -> socket splicing. Use the piped splicing * for that! */ if (unlikely(!(in->f_mode & FMODE_LSEEK))) return -EINVAL; /* * neither in nor out is a pipe, setup an internal pipe attached to * 'out' and transfer the wanted data from 'in' to 'out' through that */ pipe = current->splice_pipe; if (unlikely(!pipe)) { pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; /* * We don't have an immediate reader, but we'll read the stuff * out of the pipe right after the splice_to_pipe(). So set * PIPE_READERS appropriately. */ pipe->readers = 1; current->splice_pipe = pipe; } /* * Do the splice. */ bytes = 0; len = sd->total_len; /* Don't block on output, we have to drain the direct pipe. */ flags = sd->flags; sd->flags &= ~SPLICE_F_NONBLOCK; /* * We signal MORE until we've read sufficient data to fulfill the * request and we keep signalling it if the caller set it. */ more = sd->flags & SPLICE_F_MORE; sd->flags |= SPLICE_F_MORE; WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); while (len) { size_t read_len; loff_t pos = sd->pos, prev_pos = pos; ret = do_splice_read(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) goto read_failure; read_len = ret; sd->total_len = read_len; /* * If we now have sufficient data to fulfill the request then * we clear SPLICE_F_MORE if it was not set initially. */ if (read_len >= len && !more) sd->flags &= ~SPLICE_F_MORE; /* * NOTE: nonblocking mode only applies to the input. We * must not do the output in nonblocking mode as then we * could get stuck data in the internal pipe: */ ret = actor(pipe, sd); if (unlikely(ret <= 0)) { sd->pos = prev_pos; goto out_release; } bytes += ret; len -= ret; sd->pos = pos; if (ret < read_len) { sd->pos = prev_pos + ret; goto out_release; } } done: pipe->tail = pipe->head = 0; file_accessed(in); return bytes; read_failure: /* * If the user did *not* set SPLICE_F_MORE *and* we didn't hit that * "use all of len" case that cleared SPLICE_F_MORE, *and* we did a * "->splice_in()" that returned EOF (ie zero) *and* we have sent at * least 1 byte *then* we will also do the ->splice_eof() call. */ if (ret == 0 && !more && len > 0 && bytes) do_splice_eof(sd); out_release: /* * If we did an incomplete transfer we must release * the pipe buffers in question: */ for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = &pipe->bufs[i]; if (buf->ops) pipe_buf_release(pipe, buf); } if (!bytes) bytes = ret; goto done; } EXPORT_SYMBOL(splice_direct_to_actor); static int direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd) { struct file *file = sd->u.file; long ret; file_start_write(file); ret = do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); file_end_write(file); return ret; } static int splice_file_range_actor(struct pipe_inode_info *pipe, struct splice_desc *sd) { struct file *file = sd->u.file; return do_splice_from(pipe, file, sd->opos, sd->total_len, sd->flags); } static void direct_file_splice_eof(struct splice_desc *sd) { struct file *file = sd->u.file; if (file->f_op->splice_eof) file->f_op->splice_eof(file); } static ssize_t do_splice_direct_actor(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags, splice_direct_actor *actor) { struct splice_desc sd = { .len = len, .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, .splice_eof = direct_file_splice_eof, .opos = opos, }; ssize_t ret; if (unlikely(!(out->f_mode & FMODE_WRITE))) return -EBADF; if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; ret = splice_direct_to_actor(in, &sd, actor); if (ret > 0) *ppos = sd.pos; return ret; } /** * do_splice_direct - splices data directly between two files * @in: file to splice from * @ppos: input file offset * @out: file to splice to * @opos: output file offset * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * For use by do_sendfile(). splice can easily emulate sendfile, but * doing it in the application would incur an extra system call * (splice in + splice out, as compared to just sendfile()). So this helper * can splice directly through a process-private pipe. * * Callers already called rw_verify_area() on the entire range. */ ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags) { return do_splice_direct_actor(in, ppos, out, opos, len, flags, direct_splice_actor); } EXPORT_SYMBOL(do_splice_direct); /** * splice_file_range - splices data between two files for copy_file_range() * @in: file to splice from * @ppos: input file offset * @out: file to splice to * @opos: output file offset * @len: number of bytes to splice * * Description: * For use by ->copy_file_range() methods. * Like do_splice_direct(), but vfs_copy_file_range() already holds * start_file_write() on @out file. * * Callers already called rw_verify_area() on the entire range. */ ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len) { lockdep_assert(file_write_started(out)); return do_splice_direct_actor(in, ppos, out, opos, min_t(size_t, len, MAX_RW_COUNT), 0, splice_file_range_actor); } EXPORT_SYMBOL(splice_file_range); static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) { for (;;) { if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); return -EPIPE; } if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; if (flags & SPLICE_F_NONBLOCK) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; pipe_wait_writable(pipe); } } static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); ssize_t splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags) { ssize_t ret; pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) ret = do_splice_read(in, offset, opipe, len, flags); pipe_unlock(opipe); if (ret > 0) wakeup_pipe_readers(opipe); return ret; } /* * Determine where to splice to/from. */ ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out, loff_t *off_out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; loff_t offset; ssize_t ret; if (unlikely(!(in->f_mode & FMODE_READ) || !(out->f_mode & FMODE_WRITE))) return -EBADF; ipipe = get_pipe_info(in, true); opipe = get_pipe_info(out, true); if (ipipe && opipe) { if (off_in || off_out) return -ESPIPE; /* Splicing to self would be fun, but... */ if (ipipe == opipe) return -EINVAL; if ((in->f_flags | out->f_flags) & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; ret = splice_pipe_to_pipe(ipipe, opipe, len, flags); } else if (ipipe) { if (off_in) return -ESPIPE; if (off_out) { if (!(out->f_mode & FMODE_PWRITE)) return -EINVAL; offset = *off_out; } else { offset = out->f_pos; } if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; ret = rw_verify_area(WRITE, out, &offset, len); if (unlikely(ret < 0)) return ret; if (in->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; file_start_write(out); ret = do_splice_from(ipipe, out, &offset, len, flags); file_end_write(out); if (!off_out) out->f_pos = offset; else *off_out = offset; } else if (opipe) { if (off_out) return -ESPIPE; if (off_in) { if (!(in->f_mode & FMODE_PREAD)) return -EINVAL; offset = *off_in; } else { offset = in->f_pos; } ret = rw_verify_area(READ, in, &offset, len); if (unlikely(ret < 0)) return ret; if (out->f_flags & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; ret = splice_file_to_pipe(in, opipe, &offset, len, flags); if (!off_in) in->f_pos = offset; else *off_in = offset; } else { ret = -EINVAL; } if (ret > 0) { /* * Generate modify out before access in: * do_splice_from() may've already sent modify out, * and this ensures the events get merged. */ fsnotify_modify(out); fsnotify_access(in); } return ret; } static ssize_t __do_splice(struct file *in, loff_t __user *off_in, struct file *out, loff_t __user *off_out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe; struct pipe_inode_info *opipe; loff_t offset, *__off_in = NULL, *__off_out = NULL; ssize_t ret; ipipe = get_pipe_info(in, true); opipe = get_pipe_info(out, true); if (ipipe) { if (off_in) return -ESPIPE; pipe_clear_nowait(in); } if (opipe) { if (off_out) return -ESPIPE; pipe_clear_nowait(out); } if (off_out) { if (copy_from_user(&offset, off_out, sizeof(loff_t))) return -EFAULT; __off_out = &offset; } if (off_in) { if (copy_from_user(&offset, off_in, sizeof(loff_t))) return -EFAULT; __off_in = &offset; } ret = do_splice(in, __off_in, out, __off_out, len, flags); if (ret < 0) return ret; if (__off_out && copy_to_user(off_out, __off_out, sizeof(loff_t))) return -EFAULT; if (__off_in && copy_to_user(off_in, __off_in, sizeof(loff_t))) return -EFAULT; return ret; } static ssize_t iter_to_pipe(struct iov_iter *from, struct pipe_inode_info *pipe, unsigned int flags) { struct pipe_buffer buf = { .ops = &user_page_pipe_buf_ops, .flags = flags }; size_t total = 0; ssize_t ret = 0; while (iov_iter_count(from)) { struct page *pages[16]; ssize_t left; size_t start; int i, n; left = iov_iter_get_pages2(from, pages, ~0UL, 16, &start); if (left <= 0) { ret = left; break; } n = DIV_ROUND_UP(left + start, PAGE_SIZE); for (i = 0; i < n; i++) { int size = min_t(int, left, PAGE_SIZE - start); buf.page = pages[i]; buf.offset = start; buf.len = size; ret = add_to_pipe(pipe, &buf); if (unlikely(ret < 0)) { iov_iter_revert(from, left); // this one got dropped by add_to_pipe() while (++i < n) put_page(pages[i]); goto out; } total += ret; left -= size; start = 0; } } out: return total ? total : ret; } static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { int n = copy_page_to_iter(buf->page, buf->offset, sd->len, sd->u.data); return n == sd->len ? n : -EFAULT; } /* * For lack of a better implementation, implement vmsplice() to userspace * as a simple copy of the pipes pages to the user iov. */ static ssize_t vmsplice_to_user(struct file *file, struct iov_iter *iter, unsigned int flags) { struct pipe_inode_info *pipe = get_pipe_info(file, true); struct splice_desc sd = { .total_len = iov_iter_count(iter), .flags = flags, .u.data = iter }; ssize_t ret = 0; if (!pipe) return -EBADF; pipe_clear_nowait(file); if (sd.total_len) { pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, pipe_to_user); pipe_unlock(pipe); } if (ret > 0) fsnotify_access(file); return ret; } /* * vmsplice splices a user address range into a pipe. It can be thought of * as splice-from-memory, where the regular splice is splice-from-file (or * to file). In both cases the output is a pipe, naturally. */ static ssize_t vmsplice_to_pipe(struct file *file, struct iov_iter *iter, unsigned int flags) { struct pipe_inode_info *pipe; ssize_t ret = 0; unsigned buf_flag = 0; if (flags & SPLICE_F_GIFT) buf_flag = PIPE_BUF_FLAG_GIFT; pipe = get_pipe_info(file, true); if (!pipe) return -EBADF; pipe_clear_nowait(file); pipe_lock(pipe); ret = wait_for_space(pipe, flags); if (!ret) ret = iter_to_pipe(iter, pipe, buf_flag); pipe_unlock(pipe); if (ret > 0) { wakeup_pipe_readers(pipe); fsnotify_modify(file); } return ret; } /* * Note that vmsplice only really supports true splicing _from_ user memory * to a pipe, not the other way around. Splicing from user memory is a simple * operation that can be supported without any funky alignment restrictions * or nasty vm tricks. We simply map in the user memory and fill them into * a pipe. The reverse isn't quite as easy, though. There are two possible * solutions for that: * * - memcpy() the data internally, at which point we might as well just * do a regular read() on the buffer anyway. * - Lots of nasty vm tricks, that are neither fast nor flexible (it * has restriction limitations on both ends of the pipe). * * Currently we punt and implement it as a normal copy, see pipe_to_user(). * */ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov, unsigned long, nr_segs, unsigned int, flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t error; int type; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_WRITE) type = ITER_SOURCE; else if (fd_file(f)->f_mode & FMODE_READ) type = ITER_DEST; else return -EBADF; error = import_iovec(type, uiov, nr_segs, ARRAY_SIZE(iovstack), &iov, &iter); if (error < 0) return error; if (!iov_iter_count(&iter)) error = 0; else if (type == ITER_SOURCE) error = vmsplice_to_pipe(fd_file(f), &iter, flags); else error = vmsplice_to_user(fd_file(f), &iter, flags); kfree(iov); return error; } SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { if (unlikely(!len)) return 0; if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; CLASS(fd, in)(fd_in); if (fd_empty(in)) return -EBADF; CLASS(fd, out)(fd_out); if (fd_empty(out)) return -EBADF; return __do_splice(fd_file(in), off_in, fd_file(out), off_out, len, flags); } /* * Make sure there's data to read. Wait for input if we can, otherwise * return an appropriate error. */ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; /* * Check the pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ if (!pipe_empty(pipe->head, pipe->tail)) return 0; ret = 0; pipe_lock(pipe); while (pipe_empty(pipe->head, pipe->tail)) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (!pipe->writers) break; if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } pipe_wait_readable(pipe); } pipe_unlock(pipe); return ret; } /* * Make sure there's writeable room. Wait for room if we can, otherwise * return an appropriate error. */ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) { int ret; /* * Check pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; ret = 0; pipe_lock(pipe); while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; break; } if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } if (signal_pending(current)) { ret = -ERESTARTSYS; break; } pipe_wait_writable(pipe); } pipe_unlock(pipe); return ret; } /* * Splice contents of ipipe to opipe. */ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; unsigned int i_head, o_head; unsigned int i_tail, o_tail; unsigned int i_mask, o_mask; int ret = 0; bool input_wakeup = false; retry: ret = ipipe_prep(ipipe, flags); if (ret) return ret; ret = opipe_prep(opipe, flags); if (ret) return ret; /* * Potential ABBA deadlock, work around it by ordering lock * grabbing by pipe info address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ pipe_double_lock(ipipe, opipe); i_tail = ipipe->tail; i_mask = ipipe->ring_size - 1; o_head = opipe->head; o_mask = opipe->ring_size - 1; do { size_t o_len; if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } i_head = ipipe->head; o_tail = opipe->tail; if (pipe_empty(i_head, i_tail) && !ipipe->writers) break; /* * Cannot make any progress, because either the input * pipe is empty or the output pipe is full. */ if (pipe_empty(i_head, i_tail) || pipe_full(o_head, o_tail, opipe->max_usage)) { /* Already processed some buffers, break */ if (ret) break; if (flags & SPLICE_F_NONBLOCK) { ret = -EAGAIN; break; } /* * We raced with another reader/writer and haven't * managed to process any buffers. A zero return * value means EOF, so retry instead. */ pipe_unlock(ipipe); pipe_unlock(opipe); goto retry; } ibuf = &ipipe->bufs[i_tail & i_mask]; obuf = &opipe->bufs[o_head & o_mask]; if (len >= ibuf->len) { /* * Simply move the whole buffer from ipipe to opipe */ *obuf = *ibuf; ibuf->ops = NULL; i_tail++; ipipe->tail = i_tail; input_wakeup = true; o_len = obuf->len; o_head++; opipe->head = o_head; } else { /* * Get a reference to this pipe buffer, * so we can copy the contents over. */ if (!pipe_buf_get(ipipe, ibuf)) { if (ret == 0) ret = -EFAULT; break; } *obuf = *ibuf; /* * Don't inherit the gift and merge flags, we need to * prevent multiple steals of this page. */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->flags &= ~PIPE_BUF_FLAG_CAN_MERGE; obuf->len = len; ibuf->offset += len; ibuf->len -= len; o_len = len; o_head++; opipe->head = o_head; } ret += o_len; len -= o_len; } while (len); pipe_unlock(ipipe); pipe_unlock(opipe); /* * If we put data in the output pipe, wakeup any potential readers. */ if (ret > 0) wakeup_pipe_readers(opipe); if (input_wakeup) wakeup_pipe_writers(ipipe); return ret; } /* * Link contents of ipipe to opipe. */ static ssize_t link_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; unsigned int i_head, o_head; unsigned int i_tail, o_tail; unsigned int i_mask, o_mask; ssize_t ret = 0; /* * Potential ABBA deadlock, work around it by ordering lock * grabbing by pipe info address. Otherwise two different processes * could deadlock (one doing tee from A -> B, the other from B -> A). */ pipe_double_lock(ipipe, opipe); i_tail = ipipe->tail; i_mask = ipipe->ring_size - 1; o_head = opipe->head; o_mask = opipe->ring_size - 1; do { if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } i_head = ipipe->head; o_tail = opipe->tail; /* * If we have iterated all input buffers or run out of * output room, break. */ if (pipe_empty(i_head, i_tail) || pipe_full(o_head, o_tail, opipe->max_usage)) break; ibuf = &ipipe->bufs[i_tail & i_mask]; obuf = &opipe->bufs[o_head & o_mask]; /* * Get a reference to this pipe buffer, * so we can copy the contents over. */ if (!pipe_buf_get(ipipe, ibuf)) { if (ret == 0) ret = -EFAULT; break; } *obuf = *ibuf; /* * Don't inherit the gift and merge flag, we need to prevent * multiple steals of this page. */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->flags &= ~PIPE_BUF_FLAG_CAN_MERGE; if (obuf->len > len) obuf->len = len; ret += obuf->len; len -= obuf->len; o_head++; opipe->head = o_head; i_tail++; } while (len); pipe_unlock(ipipe); pipe_unlock(opipe); /* * If we put data in the output pipe, wakeup any potential readers. */ if (ret > 0) wakeup_pipe_readers(opipe); return ret; } /* * This is a tee(1) implementation that works on pipes. It doesn't copy * any data, it simply references the 'in' pages on the 'out' pipe. * The 'flags' used are the SPLICE_F_* variants, currently the only * applicable one is SPLICE_F_NONBLOCK. */ ssize_t do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) { struct pipe_inode_info *ipipe = get_pipe_info(in, true); struct pipe_inode_info *opipe = get_pipe_info(out, true); ssize_t ret = -EINVAL; if (unlikely(!(in->f_mode & FMODE_READ) || !(out->f_mode & FMODE_WRITE))) return -EBADF; /* * Duplicate the contents of ipipe to opipe without actually * copying the data. */ if (ipipe && opipe && ipipe != opipe) { if ((in->f_flags | out->f_flags) & O_NONBLOCK) flags |= SPLICE_F_NONBLOCK; /* * Keep going, unless we encounter an error. The ipipe/opipe * ordering doesn't really matter. */ ret = ipipe_prep(ipipe, flags); if (!ret) { ret = opipe_prep(opipe, flags); if (!ret) ret = link_pipe(ipipe, opipe, len, flags); } } if (ret > 0) { fsnotify_access(in); fsnotify_modify(out); } return ret; } SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { if (unlikely(flags & ~SPLICE_F_ALL)) return -EINVAL; if (unlikely(!len)) return 0; CLASS(fd, in)(fdin); if (fd_empty(in)) return -EBADF; CLASS(fd, out)(fdout); if (fd_empty(out)) return -EBADF; return do_tee(fd_file(in), fd_file(out), len, flags); } |
| 35 34 42 7 35 42 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/isofs/joliet.c * * (C) 1996 Gordon Chaffee * * Joliet: Microsoft's Unicode extensions to iso9660 */ #include <linux/types.h> #include <linux/nls.h> #include "isofs.h" /* * Convert Unicode 16 to UTF-8 or ASCII. */ static int uni16_to_x8(unsigned char *ascii, __be16 *uni, int len, struct nls_table *nls) { __be16 *ip, ch; unsigned char *op; ip = uni; op = ascii; while ((ch = get_unaligned(ip)) && len) { int llen; llen = nls->uni2char(be16_to_cpu(ch), op, NLS_MAX_CHARSET_SIZE); if (llen > 0) op += llen; else *op++ = '?'; ip++; len--; } *op = 0; return (op - ascii); } int get_joliet_filename(struct iso_directory_record * de, unsigned char *outname, struct inode * inode) { struct nls_table *nls; unsigned char len = 0; nls = ISOFS_SB(inode->i_sb)->s_nls_iocharset; if (!nls) { len = utf16s_to_utf8s((const wchar_t *) de->name, de->name_len[0] >> 1, UTF16_BIG_ENDIAN, outname, PAGE_SIZE); } else { len = uni16_to_x8(outname, (__be16 *) de->name, de->name_len[0] >> 1, nls); } if ((len > 2) && (outname[len-2] == ';') && (outname[len-1] == '1')) len -= 2; /* * Windows doesn't like periods at the end of a name, * so neither do we */ while (len >= 2 && (outname[len-1] == '.')) len--; return len; } |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/module.h> #include <linux/err.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/uaccess.h> #ifdef CONFIG_BLOCK #include <linux/bio.h> #endif #include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/osd_client.h> #include <linux/ceph/messenger.h> #include <linux/ceph/decode.h> #include <linux/ceph/auth.h> #include <linux/ceph/pagelist.h> #include <linux/ceph/striper.h> #define OSD_OPREPLY_FRONT_LEN 512 static struct kmem_cache *ceph_osd_request_cache; static const struct ceph_connection_operations osd_con_ops; /* * Implement client access to distributed object storage cluster. * * All data objects are stored within a cluster/cloud of OSDs, or * "object storage devices." (Note that Ceph OSDs have _nothing_ to * do with the T10 OSD extensions to SCSI.) Ceph OSDs are simply * remote daemons serving up and coordinating consistent and safe * access to storage. * * Cluster membership and the mapping of data objects onto storage devices * are described by the osd map. * * We keep track of pending OSD requests (read, write), resubmit * requests to different OSDs when the cluster topology/data layout * change, or retry the affected requests when the communications * channel with an OSD is reset. */ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req); static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req); static void link_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); static void unlink_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); static void clear_backoffs(struct ceph_osd *osd); #if 1 static inline bool rwsem_is_wrlocked(struct rw_semaphore *sem) { bool wrlocked = true; if (unlikely(down_read_trylock(sem))) { wrlocked = false; up_read(sem); } return wrlocked; } static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { WARN_ON(!rwsem_is_locked(&osdc->lock)); } static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { WARN_ON(!rwsem_is_wrlocked(&osdc->lock)); } static inline void verify_osd_locked(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; WARN_ON(!(mutex_is_locked(&osd->lock) && rwsem_is_locked(&osdc->lock)) && !rwsem_is_wrlocked(&osdc->lock)); } static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { WARN_ON(!mutex_is_locked(&lreq->lock)); } #else static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { } static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { } static inline void verify_osd_locked(struct ceph_osd *osd) { } static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { } #endif /* * calculate the mapping of a file extent onto an object, and fill out the * request accordingly. shorten extent as necessary if it crosses an * object boundary. * * fill osd op in request message. */ static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen, u64 *objnum, u64 *objoff, u64 *objlen) { u64 orig_len = *plen; u32 xlen; /* object extent? */ ceph_calc_file_object_mapping(layout, off, orig_len, objnum, objoff, &xlen); *objlen = xlen; if (*objlen < orig_len) { *plen = *objlen; dout(" skipping last %llu, final file extent %llu~%llu\n", orig_len - *plen, off, *plen); } dout("calc_layout objnum=%llx %llu~%llu\n", *objnum, *objoff, *objlen); return 0; } static void ceph_osd_data_init(struct ceph_osd_data *osd_data) { memset(osd_data, 0, sizeof (*osd_data)); osd_data->type = CEPH_OSD_DATA_TYPE_NONE; } /* * Consumes @pages if @own_pages is true. */ static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { osd_data->type = CEPH_OSD_DATA_TYPE_PAGES; osd_data->pages = pages; osd_data->length = length; osd_data->alignment = alignment; osd_data->pages_from_pool = pages_from_pool; osd_data->own_pages = own_pages; } /* * Consumes a ref on @pagelist. */ static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, struct ceph_pagelist *pagelist) { osd_data->type = CEPH_OSD_DATA_TYPE_PAGELIST; osd_data->pagelist = pagelist; } #ifdef CONFIG_BLOCK static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, struct ceph_bio_iter *bio_pos, u32 bio_length) { osd_data->type = CEPH_OSD_DATA_TYPE_BIO; osd_data->bio_pos = *bio_pos; osd_data->bio_length = bio_length; } #endif /* CONFIG_BLOCK */ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data, struct ceph_bvec_iter *bvec_pos, u32 num_bvecs) { osd_data->type = CEPH_OSD_DATA_TYPE_BVECS; osd_data->bvec_pos = *bvec_pos; osd_data->num_bvecs = num_bvecs; } static void ceph_osd_iter_init(struct ceph_osd_data *osd_data, struct iov_iter *iter) { osd_data->type = CEPH_OSD_DATA_TYPE_ITER; osd_data->iter = *iter; } static struct ceph_osd_data * osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which) { BUG_ON(which >= osd_req->r_num_ops); return &osd_req->r_ops[which].raw_data_in; } struct ceph_osd_data * osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req, unsigned int which) { return osd_req_op_data(osd_req, which, extent, osd_data); } EXPORT_SYMBOL(osd_req_op_extent_osd_data); void osd_req_op_raw_data_in_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_raw_data_in(osd_req, which); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_raw_data_in_pages); void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages); void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_pagelist_init(osd_data, pagelist); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist); #ifdef CONFIG_BLOCK void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bio_iter *bio_pos, u32 bio_length) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bio_init(osd_data, bio_pos, bio_length); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio); #endif /* CONFIG_BLOCK */ void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, struct bio_vec *bvecs, u32 num_bvecs, u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { .bvecs = bvecs, .iter = { .bi_size = bytes }, }; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs); void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bvec_iter *bvec_pos) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos); /** * osd_req_op_extent_osd_iter - Set up an operation with an iterator buffer * @osd_req: The request to set up * @which: Index of the operation in which to set the iter * @iter: The buffer iterator */ void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req, unsigned int which, struct iov_iter *iter) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_iter_init(osd_data, iter); } EXPORT_SYMBOL(osd_req_op_extent_osd_iter); static void osd_req_op_cls_request_info_pagelist( struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_info); ceph_osd_data_pagelist_init(osd_data, pagelist); } void osd_req_op_cls_request_data_pagelist( struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_pagelist_init(osd_data, pagelist); osd_req->r_ops[which].cls.indata_len += pagelist->length; osd_req->r_ops[which].indata_len += pagelist->length; } EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist); void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); osd_req->r_ops[which].cls.indata_len += length; osd_req->r_ops[which].indata_len += length; } EXPORT_SYMBOL(osd_req_op_cls_request_data_pages); void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, struct bio_vec *bvecs, u32 num_bvecs, u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { .bvecs = bvecs, .iter = { .bi_size = bytes }, }; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); osd_req->r_ops[which].cls.indata_len += bytes; osd_req->r_ops[which].indata_len += bytes; } EXPORT_SYMBOL(osd_req_op_cls_request_data_bvecs); void osd_req_op_cls_response_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, response_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_cls_response_data_pages); static u64 ceph_osd_data_length(struct ceph_osd_data *osd_data) { switch (osd_data->type) { case CEPH_OSD_DATA_TYPE_NONE: return 0; case CEPH_OSD_DATA_TYPE_PAGES: return osd_data->length; case CEPH_OSD_DATA_TYPE_PAGELIST: return (u64)osd_data->pagelist->length; #ifdef CONFIG_BLOCK case CEPH_OSD_DATA_TYPE_BIO: return (u64)osd_data->bio_length; #endif /* CONFIG_BLOCK */ case CEPH_OSD_DATA_TYPE_BVECS: return osd_data->bvec_pos.iter.bi_size; case CEPH_OSD_DATA_TYPE_ITER: return iov_iter_count(&osd_data->iter); default: WARN(true, "unrecognized data type %d\n", (int)osd_data->type); return 0; } } static void ceph_osd_data_release(struct ceph_osd_data *osd_data) { if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES && osd_data->own_pages) { int num_pages; num_pages = calc_pages_for((u64)osd_data->alignment, (u64)osd_data->length); ceph_release_page_vector(osd_data->pages, num_pages); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { ceph_pagelist_release(osd_data->pagelist); } ceph_osd_data_init(osd_data); } static void osd_req_op_data_release(struct ceph_osd_request *osd_req, unsigned int which) { struct ceph_osd_req_op *op; BUG_ON(which >= osd_req->r_num_ops); op = &osd_req->r_ops[which]; switch (op->op) { case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: kfree(op->extent.sparse_ext); ceph_osd_data_release(&op->extent.osd_data); break; case CEPH_OSD_OP_CALL: ceph_osd_data_release(&op->cls.request_info); ceph_osd_data_release(&op->cls.request_data); ceph_osd_data_release(&op->cls.response_data); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: ceph_osd_data_release(&op->xattr.osd_data); break; case CEPH_OSD_OP_STAT: ceph_osd_data_release(&op->raw_data_in); break; case CEPH_OSD_OP_NOTIFY_ACK: ceph_osd_data_release(&op->notify_ack.request_data); break; case CEPH_OSD_OP_NOTIFY: ceph_osd_data_release(&op->notify.request_data); ceph_osd_data_release(&op->notify.response_data); break; case CEPH_OSD_OP_LIST_WATCHERS: ceph_osd_data_release(&op->list_watchers.response_data); break; case CEPH_OSD_OP_COPY_FROM2: ceph_osd_data_release(&op->copy_from.osd_data); break; default: break; } } /* * Assumes @t is zero-initialized. */ static void target_init(struct ceph_osd_request_target *t) { ceph_oid_init(&t->base_oid); ceph_oloc_init(&t->base_oloc); ceph_oid_init(&t->target_oid); ceph_oloc_init(&t->target_oloc); ceph_osds_init(&t->acting); ceph_osds_init(&t->up); t->size = -1; t->min_size = -1; t->osd = CEPH_HOMELESS_OSD; } static void target_copy(struct ceph_osd_request_target *dest, const struct ceph_osd_request_target *src) { ceph_oid_copy(&dest->base_oid, &src->base_oid); ceph_oloc_copy(&dest->base_oloc, &src->base_oloc); ceph_oid_copy(&dest->target_oid, &src->target_oid); ceph_oloc_copy(&dest->target_oloc, &src->target_oloc); dest->pgid = src->pgid; /* struct */ dest->spgid = src->spgid; /* struct */ dest->pg_num = src->pg_num; dest->pg_num_mask = src->pg_num_mask; ceph_osds_copy(&dest->acting, &src->acting); ceph_osds_copy(&dest->up, &src->up); dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; dest->used_replica = src->used_replica; dest->paused = src->paused; dest->epoch = src->epoch; dest->last_force_resend = src->last_force_resend; dest->osd = src->osd; } static void target_destroy(struct ceph_osd_request_target *t) { ceph_oid_destroy(&t->base_oid); ceph_oloc_destroy(&t->base_oloc); ceph_oid_destroy(&t->target_oid); ceph_oloc_destroy(&t->target_oloc); } /* * requests */ static void request_release_checks(struct ceph_osd_request *req) { WARN_ON(!RB_EMPTY_NODE(&req->r_node)); WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node)); WARN_ON(!list_empty(&req->r_private_item)); WARN_ON(req->r_osd); } static void ceph_osdc_release_request(struct kref *kref) { struct ceph_osd_request *req = container_of(kref, struct ceph_osd_request, r_kref); unsigned int which; dout("%s %p (r_request %p r_reply %p)\n", __func__, req, req->r_request, req->r_reply); request_release_checks(req); if (req->r_request) ceph_msg_put(req->r_request); if (req->r_reply) ceph_msg_put(req->r_reply); for (which = 0; which < req->r_num_ops; which++) osd_req_op_data_release(req, which); target_destroy(&req->r_t); ceph_put_snap_context(req->r_snapc); if (req->r_mempool) mempool_free(req, req->r_osdc->req_mempool); else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS) kmem_cache_free(ceph_osd_request_cache, req); else kfree(req); } void ceph_osdc_get_request(struct ceph_osd_request *req) { dout("%s %p (was %d)\n", __func__, req, kref_read(&req->r_kref)); kref_get(&req->r_kref); } EXPORT_SYMBOL(ceph_osdc_get_request); void ceph_osdc_put_request(struct ceph_osd_request *req) { if (req) { dout("%s %p (was %d)\n", __func__, req, kref_read(&req->r_kref)); kref_put(&req->r_kref, ceph_osdc_release_request); } } EXPORT_SYMBOL(ceph_osdc_put_request); static void request_init(struct ceph_osd_request *req) { /* req only, each op is zeroed in osd_req_op_init() */ memset(req, 0, sizeof(*req)); kref_init(&req->r_kref); init_completion(&req->r_completion); RB_CLEAR_NODE(&req->r_node); RB_CLEAR_NODE(&req->r_mc_node); INIT_LIST_HEAD(&req->r_private_item); target_init(&req->r_t); } struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, bool use_mempool, gfp_t gfp_flags) { struct ceph_osd_request *req; if (use_mempool) { BUG_ON(num_ops > CEPH_OSD_SLAB_OPS); req = mempool_alloc(osdc->req_mempool, gfp_flags); } else if (num_ops <= CEPH_OSD_SLAB_OPS) { req = kmem_cache_alloc(ceph_osd_request_cache, gfp_flags); } else { BUG_ON(num_ops > CEPH_OSD_MAX_OPS); req = kmalloc(struct_size(req, r_ops, num_ops), gfp_flags); } if (unlikely(!req)) return NULL; request_init(req); req->r_osdc = osdc; req->r_mempool = use_mempool; req->r_num_ops = num_ops; req->r_snapid = CEPH_NOSNAP; req->r_snapc = ceph_get_snap_context(snapc); dout("%s req %p\n", __func__, req); return req; } EXPORT_SYMBOL(ceph_osdc_alloc_request); static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc) { return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0); } static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp, int num_request_data_items, int num_reply_data_items) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_msg *msg; int msg_size; WARN_ON(req->r_request || req->r_reply); WARN_ON(ceph_oid_empty(&req->r_base_oid)); WARN_ON(ceph_oloc_empty(&req->r_base_oloc)); /* create request message */ msg_size = CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ msg_size += 4 + 4 + 4; /* hash, osdmap_epoch, flags */ msg_size += CEPH_ENCODING_START_BLK_LEN + sizeof(struct ceph_osd_reqid); /* reqid */ msg_size += sizeof(struct ceph_blkin_trace_info); /* trace */ msg_size += 4 + sizeof(struct ceph_timespec); /* client_inc, mtime */ msg_size += CEPH_ENCODING_START_BLK_LEN + ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */ msg_size += 4 + req->r_base_oid.name_len; /* oid */ msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op); msg_size += 8; /* snapid */ msg_size += 8; /* snap_seq */ msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0); msg_size += 4 + 8; /* retry_attempt, features */ if (req->r_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size, num_request_data_items); else msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size, num_request_data_items, gfp, true); if (!msg) return -ENOMEM; memset(msg->front.iov_base, 0, msg->front.iov_len); req->r_request = msg; /* create reply message */ msg_size = OSD_OPREPLY_FRONT_LEN; msg_size += req->r_base_oid.name_len; msg_size += req->r_num_ops * sizeof(struct ceph_osd_op); if (req->r_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size, num_reply_data_items); else msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size, num_reply_data_items, gfp, true); if (!msg) return -ENOMEM; req->r_reply = msg; return 0; } static bool osd_req_opcode_valid(u16 opcode) { switch (opcode) { #define GENERATE_CASE(op, opcode, str) case CEPH_OSD_OP_##op: return true; __CEPH_FORALL_OSD_OPS(GENERATE_CASE) #undef GENERATE_CASE default: return false; } } static void get_num_data_items(struct ceph_osd_request *req, int *num_request_data_items, int *num_reply_data_items) { struct ceph_osd_req_op *op; *num_request_data_items = 0; *num_reply_data_items = 0; for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) { switch (op->op) { /* request */ case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: case CEPH_OSD_OP_NOTIFY_ACK: case CEPH_OSD_OP_COPY_FROM2: *num_request_data_items += 1; break; /* reply */ case CEPH_OSD_OP_STAT: case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_LIST_WATCHERS: *num_reply_data_items += 1; break; /* both */ case CEPH_OSD_OP_NOTIFY: *num_request_data_items += 1; *num_reply_data_items += 1; break; case CEPH_OSD_OP_CALL: *num_request_data_items += 2; *num_reply_data_items += 1; break; default: WARN_ON(!osd_req_opcode_valid(op->op)); break; } } } /* * oid, oloc and OSD op opcode(s) must be filled in before this function * is called. */ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) { int num_request_data_items, num_reply_data_items; get_num_data_items(req, &num_request_data_items, &num_reply_data_items); return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items, num_reply_data_items); } EXPORT_SYMBOL(ceph_osdc_alloc_messages); /* * This is an osd op init function for opcodes that have no data or * other information associated with them. It also serves as a * common init routine for all the other init functions, below. */ struct ceph_osd_req_op * osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags) { struct ceph_osd_req_op *op; BUG_ON(which >= osd_req->r_num_ops); BUG_ON(!osd_req_opcode_valid(opcode)); op = &osd_req->r_ops[which]; memset(op, 0, sizeof (*op)); op->op = opcode; op->flags = flags; return op; } EXPORT_SYMBOL(osd_req_op_init); void osd_req_op_extent_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq) { struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which, opcode, 0); size_t payload_len = 0; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_SPARSE_READ); op->extent.offset = offset; op->extent.length = length; op->extent.truncate_size = truncate_size; op->extent.truncate_seq = truncate_seq; if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL) payload_len += length; op->indata_len = payload_len; } EXPORT_SYMBOL(osd_req_op_extent_init); void osd_req_op_extent_update(struct ceph_osd_request *osd_req, unsigned int which, u64 length) { struct ceph_osd_req_op *op; u64 previous; BUG_ON(which >= osd_req->r_num_ops); op = &osd_req->r_ops[which]; previous = op->extent.length; if (length == previous) return; /* Nothing to do */ BUG_ON(length > previous); op->extent.length = length; if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL) op->indata_len -= previous - length; } EXPORT_SYMBOL(osd_req_op_extent_update); void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req, unsigned int which, u64 offset_inc) { struct ceph_osd_req_op *op, *prev_op; BUG_ON(which + 1 >= osd_req->r_num_ops); prev_op = &osd_req->r_ops[which]; op = osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags); /* dup previous one */ op->indata_len = prev_op->indata_len; op->outdata_len = prev_op->outdata_len; op->extent = prev_op->extent; /* adjust offset */ op->extent.offset += offset_inc; op->extent.length -= offset_inc; if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL) op->indata_len -= offset_inc; } EXPORT_SYMBOL(osd_req_op_extent_dup_last); int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, const char *class, const char *method) { struct ceph_osd_req_op *op; struct ceph_pagelist *pagelist; size_t payload_len = 0; size_t size; int ret; op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0); pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; op->cls.class_name = class; size = strlen(class); BUG_ON(size > (size_t) U8_MAX); op->cls.class_len = size; ret = ceph_pagelist_append(pagelist, class, size); if (ret) goto err_pagelist_free; payload_len += size; op->cls.method_name = method; size = strlen(method); BUG_ON(size > (size_t) U8_MAX); op->cls.method_len = size; ret = ceph_pagelist_append(pagelist, method, size); if (ret) goto err_pagelist_free; payload_len += size; osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist); op->indata_len = payload_len; return 0; err_pagelist_free: ceph_pagelist_release(pagelist); return ret; } EXPORT_SYMBOL(osd_req_op_cls_init); int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *name, const void *value, size_t size, u8 cmp_op, u8 cmp_mode) { struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which, opcode, 0); struct ceph_pagelist *pagelist; size_t payload_len; int ret; BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR); pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; payload_len = strlen(name); op->xattr.name_len = payload_len; ret = ceph_pagelist_append(pagelist, name, payload_len); if (ret) goto err_pagelist_free; op->xattr.value_len = size; ret = ceph_pagelist_append(pagelist, value, size); if (ret) goto err_pagelist_free; payload_len += size; op->xattr.cmp_op = cmp_op; op->xattr.cmp_mode = cmp_mode; ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist); op->indata_len = payload_len; return 0; err_pagelist_free: ceph_pagelist_release(pagelist); return ret; } EXPORT_SYMBOL(osd_req_op_xattr_init); /* * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; op->watch.gen = gen; } /* * prot_ver, timeout and notify payload (may be empty) should already be * encoded in @request_pl */ static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, u64 cookie, struct ceph_pagelist *request_pl) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); op->notify.cookie = cookie; ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); op->indata_len = request_pl->length; } /* * @flags: CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, unsigned int which, u64 expected_object_size, u64 expected_write_size, u32 flags) { struct ceph_osd_req_op *op; op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_SETALLOCHINT, 0); op->alloc_hint.expected_object_size = expected_object_size; op->alloc_hint.expected_write_size = expected_write_size; op->alloc_hint.flags = flags; /* * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed * not worth a feature bit. Set FAILOK per-op flag to make * sure older osds don't trip over an unsupported opcode. */ op->flags |= CEPH_OSD_OP_FLAG_FAILOK; } EXPORT_SYMBOL(osd_req_op_alloc_hint_init); static void ceph_osdc_msg_data_add(struct ceph_msg *msg, struct ceph_osd_data *osd_data) { u64 length = ceph_osd_data_length(osd_data); if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) { BUG_ON(length > (u64) SIZE_MAX); if (length) ceph_msg_data_add_pages(msg, osd_data->pages, length, osd_data->alignment, false); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { BUG_ON(!length); ceph_msg_data_add_pagelist(msg, osd_data->pagelist); #ifdef CONFIG_BLOCK } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) { ceph_msg_data_add_bio(msg, &osd_data->bio_pos, length); #endif } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BVECS) { ceph_msg_data_add_bvecs(msg, &osd_data->bvec_pos); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_ITER) { ceph_msg_data_add_iter(msg, &osd_data->iter); } else { BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE); } } static u32 osd_req_encode_op(struct ceph_osd_op *dst, const struct ceph_osd_req_op *src) { switch (src->op) { case CEPH_OSD_OP_STAT: break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_ZERO: case CEPH_OSD_OP_TRUNCATE: dst->extent.offset = cpu_to_le64(src->extent.offset); dst->extent.length = cpu_to_le64(src->extent.length); dst->extent.truncate_size = cpu_to_le64(src->extent.truncate_size); dst->extent.truncate_seq = cpu_to_le32(src->extent.truncate_seq); break; case CEPH_OSD_OP_CALL: dst->cls.class_len = src->cls.class_len; dst->cls.method_len = src->cls.method_len; dst->cls.indata_len = cpu_to_le32(src->cls.indata_len); break; case CEPH_OSD_OP_WATCH: dst->watch.cookie = cpu_to_le64(src->watch.cookie); dst->watch.ver = cpu_to_le64(0); dst->watch.op = src->watch.op; dst->watch.gen = cpu_to_le32(src->watch.gen); break; case CEPH_OSD_OP_NOTIFY_ACK: break; case CEPH_OSD_OP_NOTIFY: dst->notify.cookie = cpu_to_le64(src->notify.cookie); break; case CEPH_OSD_OP_LIST_WATCHERS: break; case CEPH_OSD_OP_SETALLOCHINT: dst->alloc_hint.expected_object_size = cpu_to_le64(src->alloc_hint.expected_object_size); dst->alloc_hint.expected_write_size = cpu_to_le64(src->alloc_hint.expected_write_size); dst->alloc_hint.flags = cpu_to_le32(src->alloc_hint.flags); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: dst->xattr.name_len = cpu_to_le32(src->xattr.name_len); dst->xattr.value_len = cpu_to_le32(src->xattr.value_len); dst->xattr.cmp_op = src->xattr.cmp_op; dst->xattr.cmp_mode = src->xattr.cmp_mode; break; case CEPH_OSD_OP_CREATE: case CEPH_OSD_OP_DELETE: break; case CEPH_OSD_OP_COPY_FROM2: dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid); dst->copy_from.src_version = cpu_to_le64(src->copy_from.src_version); dst->copy_from.flags = src->copy_from.flags; dst->copy_from.src_fadvise_flags = cpu_to_le32(src->copy_from.src_fadvise_flags); break; case CEPH_OSD_OP_ASSERT_VER: dst->assert_ver.unused = cpu_to_le64(0); dst->assert_ver.ver = cpu_to_le64(src->assert_ver.ver); break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); WARN_ON(1); return 0; } dst->op = cpu_to_le16(src->op); dst->flags = cpu_to_le32(src->flags); dst->payload_len = cpu_to_le32(src->indata_len); return src->indata_len; } /* * build new request AND message, calculate layout, and adjust file * extent as needed. * * if the file was recently truncated, we include information about its * old and new size so that the object can be updated appropriately. (we * avoid synchronously deleting truncated objects because it's slow.) */ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, struct ceph_file_layout *layout, struct ceph_vino vino, u64 off, u64 *plen, unsigned int which, int num_ops, int opcode, int flags, struct ceph_snap_context *snapc, u32 truncate_seq, u64 truncate_size, bool use_mempool) { struct ceph_osd_request *req; u64 objnum = 0; u64 objoff = 0; u64 objlen = 0; int r; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_SPARSE_READ); req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool, GFP_NOFS); if (!req) { r = -ENOMEM; goto fail; } /* calculate max write size */ r = calc_layout(layout, off, plen, &objnum, &objoff, &objlen); if (r) goto fail; if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) { osd_req_op_init(req, which, opcode, 0); } else { u32 object_size = layout->object_size; u32 object_base = off - objoff; if (!(truncate_seq == 1 && truncate_size == -1ULL)) { if (truncate_size <= object_base) { truncate_size = 0; } else { truncate_size -= object_base; if (truncate_size > object_size) truncate_size = object_size; } } osd_req_op_extent_init(req, which, opcode, objoff, objlen, truncate_size, truncate_seq); } req->r_base_oloc.pool = layout->pool_id; req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns); ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum); req->r_flags = flags | osdc->client->options->read_from_replica; req->r_snapid = vino.snap; if (flags & CEPH_OSD_FLAG_WRITE) req->r_data_offset = off; if (num_ops > 1) { int num_req_ops, num_rep_ops; /* * If this is a multi-op write request, assume that we'll need * request ops. If it's a multi-op read then assume we'll need * reply ops. Anything else and call it -EINVAL. */ if (flags & CEPH_OSD_FLAG_WRITE) { num_req_ops = num_ops; num_rep_ops = 0; } else if (flags & CEPH_OSD_FLAG_READ) { num_req_ops = 0; num_rep_ops = num_ops; } else { r = -EINVAL; goto fail; } r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_req_ops, num_rep_ops); } else { r = ceph_osdc_alloc_messages(req, GFP_NOFS); } if (r) goto fail; return req; fail: ceph_osdc_put_request(req); return ERR_PTR(r); } EXPORT_SYMBOL(ceph_osdc_new_request); int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { WARN_ON(op->op != CEPH_OSD_OP_SPARSE_READ); op->extent.sparse_ext_cnt = cnt; op->extent.sparse_ext = kmalloc_array(cnt, sizeof(*op->extent.sparse_ext), GFP_NOFS); if (!op->extent.sparse_ext) return -ENOMEM; return 0; } EXPORT_SYMBOL(__ceph_alloc_sparse_ext_map); /* * We keep osd requests in an rbtree, sorted by ->r_tid. */ DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node) DEFINE_RB_FUNCS(request_mc, struct ceph_osd_request, r_tid, r_mc_node) /* * Call @fn on each OSD request as long as @fn returns 0. */ static void for_each_request(struct ceph_osd_client *osdc, int (*fn)(struct ceph_osd_request *req, void *arg), void *arg) { struct rb_node *n, *p; for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); if (fn(req, arg)) return; } } for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); if (fn(req, arg)) return; } } static bool osd_homeless(struct ceph_osd *osd) { return osd->o_osd == CEPH_HOMELESS_OSD; } static bool osd_registered(struct ceph_osd *osd) { verify_osdc_locked(osd->o_osdc); return !RB_EMPTY_NODE(&osd->o_node); } /* * Assumes @osd is zero-initialized. */ static void osd_init(struct ceph_osd *osd) { refcount_set(&osd->o_ref, 1); RB_CLEAR_NODE(&osd->o_node); spin_lock_init(&osd->o_requests_lock); osd->o_requests = RB_ROOT; osd->o_linger_requests = RB_ROOT; osd->o_backoff_mappings = RB_ROOT; osd->o_backoffs_by_id = RB_ROOT; INIT_LIST_HEAD(&osd->o_osd_lru); INIT_LIST_HEAD(&osd->o_keepalive_item); osd->o_incarnation = 1; mutex_init(&osd->lock); } static void ceph_init_sparse_read(struct ceph_sparse_read *sr) { kfree(sr->sr_extent); memset(sr, '\0', sizeof(*sr)); sr->sr_state = CEPH_SPARSE_READ_HDR; } static void osd_cleanup(struct ceph_osd *osd) { WARN_ON(!RB_EMPTY_NODE(&osd->o_node)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoff_mappings)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoffs_by_id)); WARN_ON(!list_empty(&osd->o_osd_lru)); WARN_ON(!list_empty(&osd->o_keepalive_item)); ceph_init_sparse_read(&osd->o_sparse_read); if (osd->o_auth.authorizer) { WARN_ON(osd_homeless(osd)); ceph_auth_destroy_authorizer(osd->o_auth.authorizer); } } /* * Track open sessions with osds. */ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) { struct ceph_osd *osd; WARN_ON(onum == CEPH_HOMELESS_OSD); osd = kzalloc(sizeof(*osd), GFP_NOIO | __GFP_NOFAIL); osd_init(osd); osd->o_osdc = osdc; osd->o_osd = onum; osd->o_sparse_op_idx = -1; ceph_init_sparse_read(&osd->o_sparse_read); ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr); return osd; } static struct ceph_osd *get_osd(struct ceph_osd *osd) { if (refcount_inc_not_zero(&osd->o_ref)) { dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1, refcount_read(&osd->o_ref)); return osd; } else { dout("get_osd %p FAIL\n", osd); return NULL; } } static void put_osd(struct ceph_osd *osd) { dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref), refcount_read(&osd->o_ref) - 1); if (refcount_dec_and_test(&osd->o_ref)) { osd_cleanup(osd); kfree(osd); } } DEFINE_RB_FUNCS(osd, struct ceph_osd, o_osd, o_node) static void __move_osd_to_lru(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); BUG_ON(!list_empty(&osd->o_osd_lru)); spin_lock(&osdc->osd_lru_lock); list_add_tail(&osd->o_osd_lru, &osdc->osd_lru); spin_unlock(&osdc->osd_lru_lock); osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl; } static void maybe_move_osd_to_lru(struct ceph_osd *osd) { if (RB_EMPTY_ROOT(&osd->o_requests) && RB_EMPTY_ROOT(&osd->o_linger_requests)) __move_osd_to_lru(osd); } static void __remove_osd_from_lru(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); spin_lock(&osdc->osd_lru_lock); if (!list_empty(&osd->o_osd_lru)) list_del_init(&osd->o_osd_lru); spin_unlock(&osdc->osd_lru_lock); } /* * Close the connection and assign any leftover requests to the * homeless session. */ static void close_osd(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; struct rb_node *n; verify_osdc_wrlocked(osdc); dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); ceph_con_close(&osd->o_con); for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); /* unlink_request() */ dout(" reassigning req %p tid %llu\n", req, req->r_tid); unlink_request(osd, req); link_request(&osdc->homeless_osd, req); } for (n = rb_first(&osd->o_linger_requests); n; ) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); n = rb_next(n); /* unlink_linger() */ dout(" reassigning lreq %p linger_id %llu\n", lreq, lreq->linger_id); unlink_linger(osd, lreq); link_linger(&osdc->homeless_osd, lreq); } clear_backoffs(osd); __remove_osd_from_lru(osd); erase_osd(&osdc->osds, osd); put_osd(osd); } /* * reset osd connect */ static int reopen_osd(struct ceph_osd *osd) { struct ceph_entity_addr *peer_addr; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); if (RB_EMPTY_ROOT(&osd->o_requests) && RB_EMPTY_ROOT(&osd->o_linger_requests)) { close_osd(osd); return -ENODEV; } peer_addr = &osd->o_osdc->osdmap->osd_addr[osd->o_osd]; if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) && !ceph_con_opened(&osd->o_con)) { struct rb_node *n; dout("osd addr hasn't changed and connection never opened, " "letting msgr retry\n"); /* touch each r_stamp for handle_timeout()'s benfit */ for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); req->r_stamp = jiffies; } return -EAGAIN; } ceph_con_close(&osd->o_con); ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, peer_addr); osd->o_incarnation++; return 0; } static struct ceph_osd *lookup_create_osd(struct ceph_osd_client *osdc, int o, bool wrlocked) { struct ceph_osd *osd; if (wrlocked) verify_osdc_wrlocked(osdc); else verify_osdc_locked(osdc); if (o != CEPH_HOMELESS_OSD) osd = lookup_osd(&osdc->osds, o); else osd = &osdc->homeless_osd; if (!osd) { if (!wrlocked) return ERR_PTR(-EAGAIN); osd = create_osd(osdc, o); insert_osd(&osdc->osds, osd); ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, &osdc->osdmap->osd_addr[osd->o_osd]); } dout("%s osdc %p osd%d -> osd %p\n", __func__, osdc, o, osd); return osd; } /* * Create request <-> OSD session relation. * * @req has to be assigned a tid, @osd may be homeless. */ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req) { verify_osd_locked(osd); WARN_ON(!req->r_tid || req->r_osd); dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd, req, req->r_tid); if (!osd_homeless(osd)) __remove_osd_from_lru(osd); else atomic_inc(&osd->o_osdc->num_homeless); get_osd(osd); spin_lock(&osd->o_requests_lock); insert_request(&osd->o_requests, req); spin_unlock(&osd->o_requests_lock); req->r_osd = osd; } static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req) { verify_osd_locked(osd); WARN_ON(req->r_osd != osd); dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd, req, req->r_tid); req->r_osd = NULL; spin_lock(&osd->o_requests_lock); erase_request(&osd->o_requests, req); spin_unlock(&osd->o_requests_lock); put_osd(osd); if (!osd_homeless(osd)) maybe_move_osd_to_lru(osd); else atomic_dec(&osd->o_osdc->num_homeless); } static bool __pool_full(struct ceph_pg_pool_info *pi) { return pi->flags & CEPH_POOL_FLAG_FULL; } static bool have_pool_full(struct ceph_osd_client *osdc) { struct rb_node *n; for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); if (__pool_full(pi)) return true; } return false; } static bool pool_full(struct ceph_osd_client *osdc, s64 pool_id) { struct ceph_pg_pool_info *pi; pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id); if (!pi) return false; return __pool_full(pi); } /* * Returns whether a request should be blocked from being sent * based on the current osdmap and osd_client settings. */ static bool target_should_be_paused(struct ceph_osd_client *osdc, const struct ceph_osd_request_target *t, struct ceph_pg_pool_info *pi) { bool pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); bool pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || __pool_full(pi); WARN_ON(pi->id != t->target_oloc.pool); return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) || ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) || (osdc->osdmap->epoch < osdc->epoch_barrier); } static int pick_random_replica(const struct ceph_osds *acting) { int i = get_random_u32_below(acting->size); dout("%s picked osd%d, primary osd%d\n", __func__, acting->osds[i], acting->primary); return i; } /* * Picks the closest replica based on client's location given by * crush_location option. Prefers the primary if the locality is * the same. */ static int pick_closest_replica(struct ceph_osd_client *osdc, const struct ceph_osds *acting) { struct ceph_options *opt = osdc->client->options; int best_i, best_locality; int i = 0, locality; do { locality = ceph_get_crush_locality(osdc->osdmap, acting->osds[i], &opt->crush_locs); if (i == 0 || (locality >= 0 && best_locality < 0) || (locality >= 0 && best_locality >= 0 && locality < best_locality)) { best_i = i; best_locality = locality; } } while (++i < acting->size); dout("%s picked osd%d with locality %d, primary osd%d\n", __func__, acting->osds[best_i], best_locality, acting->primary); return best_i; } enum calc_target_result { CALC_TARGET_NO_ACTION = 0, CALC_TARGET_NEED_RESEND, CALC_TARGET_POOL_DNE, }; static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_osd_request_target *t, bool any_change) { struct ceph_pg_pool_info *pi; struct ceph_pg pgid, last_pgid; struct ceph_osds up, acting; bool is_read = t->flags & CEPH_OSD_FLAG_READ; bool is_write = t->flags & CEPH_OSD_FLAG_WRITE; bool force_resend = false; bool unpaused = false; bool legacy_change = false; bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); bool recovery_deletes = ceph_osdmap_flag(osdc, CEPH_OSDMAP_RECOVERY_DELETES); enum calc_target_result ct_res; t->epoch = osdc->osdmap->epoch; pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool); if (!pi) { t->osd = CEPH_HOMELESS_OSD; ct_res = CALC_TARGET_POOL_DNE; goto out; } if (osdc->osdmap->epoch == pi->last_force_request_resend) { if (t->last_force_resend < pi->last_force_request_resend) { t->last_force_resend = pi->last_force_request_resend; force_resend = true; } else if (t->last_force_resend == 0) { force_resend = true; } } /* apply tiering */ ceph_oid_copy(&t->target_oid, &t->base_oid); ceph_oloc_copy(&t->target_oloc, &t->base_oloc); if ((t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) { if (is_read && pi->read_tier >= 0) t->target_oloc.pool = pi->read_tier; if (is_write && pi->write_tier >= 0) t->target_oloc.pool = pi->write_tier; pi = ceph_pg_pool_by_id(osdc->osdmap, t->target_oloc.pool); if (!pi) { t->osd = CEPH_HOMELESS_OSD; ct_res = CALC_TARGET_POOL_DNE; goto out; } } __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc, &pgid); last_pgid.pool = pgid.pool; last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask); ceph_pg_to_up_acting_osds(osdc->osdmap, pi, &pgid, &up, &acting); if (any_change && ceph_is_new_interval(&t->acting, &acting, &t->up, &up, t->size, pi->size, t->min_size, pi->min_size, t->pg_num, pi->pg_num, t->sort_bitwise, sort_bitwise, t->recovery_deletes, recovery_deletes, &last_pgid)) force_resend = true; if (t->paused && !target_should_be_paused(osdc, t, pi)) { t->paused = false; unpaused = true; } legacy_change = ceph_pg_compare(&t->pgid, &pgid) || ceph_osds_changed(&t->acting, &acting, t->used_replica || any_change); if (t->pg_num) split = ceph_pg_is_split(&last_pgid, t->pg_num, pi->pg_num); if (legacy_change || force_resend || split) { t->pgid = pgid; /* struct */ ceph_pg_to_primary_shard(osdc->osdmap, pi, &pgid, &t->spgid); ceph_osds_copy(&t->acting, &acting); ceph_osds_copy(&t->up, &up); t->size = pi->size; t->min_size = pi->min_size; t->pg_num = pi->pg_num; t->pg_num_mask = pi->pg_num_mask; t->sort_bitwise = sort_bitwise; t->recovery_deletes = recovery_deletes; if ((t->flags & (CEPH_OSD_FLAG_BALANCE_READS | CEPH_OSD_FLAG_LOCALIZE_READS)) && !is_write && pi->type == CEPH_POOL_TYPE_REP && acting.size > 1) { int pos; WARN_ON(!is_read || acting.osds[0] != acting.primary); if (t->flags & CEPH_OSD_FLAG_BALANCE_READS) { pos = pick_random_replica(&acting); } else { pos = pick_closest_replica(osdc, &acting); } t->osd = acting.osds[pos]; t->used_replica = pos > 0; } else { t->osd = acting.primary; t->used_replica = false; } } if (unpaused || legacy_change || force_resend || split) ct_res = CALC_TARGET_NEED_RESEND; else ct_res = CALC_TARGET_NO_ACTION; out: dout("%s t %p -> %d%d%d%d ct_res %d osd%d\n", __func__, t, unpaused, legacy_change, force_resend, split, ct_res, t->osd); return ct_res; } static struct ceph_spg_mapping *alloc_spg_mapping(void) { struct ceph_spg_mapping *spg; spg = kmalloc(sizeof(*spg), GFP_NOIO); if (!spg) return NULL; RB_CLEAR_NODE(&spg->node); spg->backoffs = RB_ROOT; return spg; } static void free_spg_mapping(struct ceph_spg_mapping *spg) { WARN_ON(!RB_EMPTY_NODE(&spg->node)); WARN_ON(!RB_EMPTY_ROOT(&spg->backoffs)); kfree(spg); } /* * rbtree of ceph_spg_mapping for handling map<spg_t, ...>, similar to * ceph_pg_mapping. Used to track OSD backoffs -- a backoff [range] is * defined only within a specific spgid; it does not pass anything to * children on split, or to another primary. */ DEFINE_RB_FUNCS2(spg_mapping, struct ceph_spg_mapping, spgid, ceph_spg_compare, RB_BYPTR, const struct ceph_spg *, node) static u64 hoid_get_bitwise_key(const struct ceph_hobject_id *hoid) { return hoid->is_max ? 0x100000000ull : hoid->hash_reverse_bits; } static void hoid_get_effective_key(const struct ceph_hobject_id *hoid, void **pkey, size_t *pkey_len) { if (hoid->key_len) { *pkey = hoid->key; *pkey_len = hoid->key_len; } else { *pkey = hoid->oid; *pkey_len = hoid->oid_len; } } static int compare_names(const void *name1, size_t name1_len, const void *name2, size_t name2_len) { int ret; ret = memcmp(name1, name2, min(name1_len, name2_len)); if (!ret) { if (name1_len < name2_len) ret = -1; else if (name1_len > name2_len) ret = 1; } return ret; } static int hoid_compare(const struct ceph_hobject_id *lhs, const struct ceph_hobject_id *rhs) { void *effective_key1, *effective_key2; size_t effective_key1_len, effective_key2_len; int ret; if (lhs->is_max < rhs->is_max) return -1; if (lhs->is_max > rhs->is_max) return 1; if (lhs->pool < rhs->pool) return -1; if (lhs->pool > rhs->pool) return 1; if (hoid_get_bitwise_key(lhs) < hoid_get_bitwise_key(rhs)) return -1; if (hoid_get_bitwise_key(lhs) > hoid_get_bitwise_key(rhs)) return 1; ret = compare_names(lhs->nspace, lhs->nspace_len, rhs->nspace, rhs->nspace_len); if (ret) return ret; hoid_get_effective_key(lhs, &effective_key1, &effective_key1_len); hoid_get_effective_key(rhs, &effective_key2, &effective_key2_len); ret = compare_names(effective_key1, effective_key1_len, effective_key2, effective_key2_len); if (ret) return ret; ret = compare_names(lhs->oid, lhs->oid_len, rhs->oid, rhs->oid_len); if (ret) return ret; if (lhs->snapid < rhs->snapid) return -1; if (lhs->snapid > rhs->snapid) return 1; return 0; } /* * For decoding ->begin and ->end of MOSDBackoff only -- no MIN/MAX * compat stuff here. * * Assumes @hoid is zero-initialized. */ static int decode_hoid(void **p, void *end, struct ceph_hobject_id *hoid) { u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(p, end, 4, "hobject_t", &struct_v, &struct_len); if (ret) return ret; if (struct_v < 4) { pr_err("got struct_v %d < 4 of hobject_t\n", struct_v); goto e_inval; } hoid->key = ceph_extract_encoded_string(p, end, &hoid->key_len, GFP_NOIO); if (IS_ERR(hoid->key)) { ret = PTR_ERR(hoid->key); hoid->key = NULL; return ret; } hoid->oid = ceph_extract_encoded_string(p, end, &hoid->oid_len, GFP_NOIO); if (IS_ERR(hoid->oid)) { ret = PTR_ERR(hoid->oid); hoid->oid = NULL; return ret; } ceph_decode_64_safe(p, end, hoid->snapid, e_inval); ceph_decode_32_safe(p, end, hoid->hash, e_inval); ceph_decode_8_safe(p, end, hoid->is_max, e_inval); hoid->nspace = ceph_extract_encoded_string(p, end, &hoid->nspace_len, GFP_NOIO); if (IS_ERR(hoid->nspace)) { ret = PTR_ERR(hoid->nspace); hoid->nspace = NULL; return ret; } ceph_decode_64_safe(p, end, hoid->pool, e_inval); ceph_hoid_build_hash_cache(hoid); return 0; e_inval: return -EINVAL; } static int hoid_encoding_size(const struct ceph_hobject_id *hoid) { return 8 + 4 + 1 + 8 + /* snapid, hash, is_max, pool */ 4 + hoid->key_len + 4 + hoid->oid_len + 4 + hoid->nspace_len; } static void encode_hoid(void **p, void *end, const struct ceph_hobject_id *hoid) { ceph_start_encoding(p, 4, 3, hoid_encoding_size(hoid)); ceph_encode_string(p, end, hoid->key, hoid->key_len); ceph_encode_string(p, end, hoid->oid, hoid->oid_len); ceph_encode_64(p, hoid->snapid); ceph_encode_32(p, hoid->hash); ceph_encode_8(p, hoid->is_max); ceph_encode_string(p, end, hoid->nspace, hoid->nspace_len); ceph_encode_64(p, hoid->pool); } static void free_hoid(struct ceph_hobject_id *hoid) { if (hoid) { kfree(hoid->key); kfree(hoid->oid); kfree(hoid->nspace); kfree(hoid); } } static struct ceph_osd_backoff *alloc_backoff(void) { struct ceph_osd_backoff *backoff; backoff = kzalloc(sizeof(*backoff), GFP_NOIO); if (!backoff) return NULL; RB_CLEAR_NODE(&backoff->spg_node); RB_CLEAR_NODE(&backoff->id_node); return backoff; } static void free_backoff(struct ceph_osd_backoff *backoff) { WARN_ON(!RB_EMPTY_NODE(&backoff->spg_node)); WARN_ON(!RB_EMPTY_NODE(&backoff->id_node)); free_hoid(backoff->begin); free_hoid(backoff->end); kfree(backoff); } /* * Within a specific spgid, backoffs are managed by ->begin hoid. */ DEFINE_RB_INSDEL_FUNCS2(backoff, struct ceph_osd_backoff, begin, hoid_compare, RB_BYVAL, spg_node); static struct ceph_osd_backoff *lookup_containing_backoff(struct rb_root *root, const struct ceph_hobject_id *hoid) { struct rb_node *n = root->rb_node; while (n) { struct ceph_osd_backoff *cur = rb_entry(n, struct ceph_osd_backoff, spg_node); int cmp; cmp = hoid_compare(hoid, cur->begin); if (cmp < 0) { n = n->rb_left; } else if (cmp > 0) { if (hoid_compare(hoid, cur->end) < 0) return cur; n = n->rb_right; } else { return cur; } } return NULL; } /* * Each backoff has a unique id within its OSD session. */ DEFINE_RB_FUNCS(backoff_by_id, struct ceph_osd_backoff, id, id_node) static void clear_backoffs(struct ceph_osd *osd) { while (!RB_EMPTY_ROOT(&osd->o_backoff_mappings)) { struct ceph_spg_mapping *spg = rb_entry(rb_first(&osd->o_backoff_mappings), struct ceph_spg_mapping, node); while (!RB_EMPTY_ROOT(&spg->backoffs)) { struct ceph_osd_backoff *backoff = rb_entry(rb_first(&spg->backoffs), struct ceph_osd_backoff, spg_node); erase_backoff(&spg->backoffs, backoff); erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); free_backoff(backoff); } erase_spg_mapping(&osd->o_backoff_mappings, spg); free_spg_mapping(spg); } } /* * Set up a temporary, non-owning view into @t. */ static void hoid_fill_from_target(struct ceph_hobject_id *hoid, const struct ceph_osd_request_target *t) { hoid->key = NULL; hoid->key_len = 0; hoid->oid = t->target_oid.name; hoid->oid_len = t->target_oid.name_len; hoid->snapid = CEPH_NOSNAP; hoid->hash = t->pgid.seed; hoid->is_max = false; if (t->target_oloc.pool_ns) { hoid->nspace = t->target_oloc.pool_ns->str; hoid->nspace_len = t->target_oloc.pool_ns->len; } else { hoid->nspace = NULL; hoid->nspace_len = 0; } hoid->pool = t->target_oloc.pool; ceph_hoid_build_hash_cache(hoid); } static bool should_plug_request(struct ceph_osd_request *req) { struct ceph_osd *osd = req->r_osd; struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct ceph_hobject_id hoid; spg = lookup_spg_mapping(&osd->o_backoff_mappings, &req->r_t.spgid); if (!spg) return false; hoid_fill_from_target(&hoid, &req->r_t); backoff = lookup_containing_backoff(&spg->backoffs, &hoid); if (!backoff) return false; dout("%s req %p tid %llu backoff osd%d spgid %llu.%xs%d id %llu\n", __func__, req, req->r_tid, osd->o_osd, backoff->spgid.pgid.pool, backoff->spgid.pgid.seed, backoff->spgid.shard, backoff->id); return true; } /* * Keep get_num_data_items() in sync with this function. */ static void setup_request_data(struct ceph_osd_request *req) { struct ceph_msg *request_msg = req->r_request; struct ceph_msg *reply_msg = req->r_reply; struct ceph_osd_req_op *op; if (req->r_request->num_data_items || req->r_reply->num_data_items) return; WARN_ON(request_msg->data_length || reply_msg->data_length); for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) { switch (op->op) { /* request */ case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: WARN_ON(op->indata_len != op->extent.length); ceph_osdc_msg_data_add(request_msg, &op->extent.osd_data); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: WARN_ON(op->indata_len != op->xattr.name_len + op->xattr.value_len); ceph_osdc_msg_data_add(request_msg, &op->xattr.osd_data); break; case CEPH_OSD_OP_NOTIFY_ACK: ceph_osdc_msg_data_add(request_msg, &op->notify_ack.request_data); break; case CEPH_OSD_OP_COPY_FROM2: ceph_osdc_msg_data_add(request_msg, &op->copy_from.osd_data); break; /* reply */ case CEPH_OSD_OP_STAT: ceph_osdc_msg_data_add(reply_msg, &op->raw_data_in); break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: ceph_osdc_msg_data_add(reply_msg, &op->extent.osd_data); break; case CEPH_OSD_OP_LIST_WATCHERS: ceph_osdc_msg_data_add(reply_msg, &op->list_watchers.response_data); break; /* both */ case CEPH_OSD_OP_CALL: WARN_ON(op->indata_len != op->cls.class_len + op->cls.method_len + op->cls.indata_len); ceph_osdc_msg_data_add(request_msg, &op->cls.request_info); /* optional, can be NONE */ ceph_osdc_msg_data_add(request_msg, &op->cls.request_data); /* optional, can be NONE */ ceph_osdc_msg_data_add(reply_msg, &op->cls.response_data); break; case CEPH_OSD_OP_NOTIFY: ceph_osdc_msg_data_add(request_msg, &op->notify.request_data); ceph_osdc_msg_data_add(reply_msg, &op->notify.response_data); break; } } } static void encode_pgid(void **p, const struct ceph_pg *pgid) { ceph_encode_8(p, 1); ceph_encode_64(p, pgid->pool); ceph_encode_32(p, pgid->seed); ceph_encode_32(p, -1); /* preferred */ } static void encode_spgid(void **p, const struct ceph_spg *spgid) { ceph_start_encoding(p, 1, 1, CEPH_PGID_ENCODING_LEN + 1); encode_pgid(p, &spgid->pgid); ceph_encode_8(p, spgid->shard); } static void encode_oloc(void **p, void *end, const struct ceph_object_locator *oloc) { ceph_start_encoding(p, 5, 4, ceph_oloc_encoding_size(oloc)); ceph_encode_64(p, oloc->pool); ceph_encode_32(p, -1); /* preferred */ ceph_encode_32(p, 0); /* key len */ if (oloc->pool_ns) ceph_encode_string(p, end, oloc->pool_ns->str, oloc->pool_ns->len); else ceph_encode_32(p, 0); } static void encode_request_partial(struct ceph_osd_request *req, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front_alloc_len; u32 data_len = 0; int i; if (req->r_flags & CEPH_OSD_FLAG_WRITE) { /* snapshots aren't writeable */ WARN_ON(req->r_snapid != CEPH_NOSNAP); } else { WARN_ON(req->r_mtime.tv_sec || req->r_mtime.tv_nsec || req->r_data_offset || req->r_snapc); } setup_request_data(req); encode_spgid(&p, &req->r_t.spgid); /* actual spg */ ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */ ceph_encode_32(&p, req->r_osdc->osdmap->epoch); ceph_encode_32(&p, req->r_flags); /* reqid */ ceph_start_encoding(&p, 2, 2, sizeof(struct ceph_osd_reqid)); memset(p, 0, sizeof(struct ceph_osd_reqid)); p += sizeof(struct ceph_osd_reqid); /* trace */ memset(p, 0, sizeof(struct ceph_blkin_trace_info)); p += sizeof(struct ceph_blkin_trace_info); ceph_encode_32(&p, 0); /* client_inc, always 0 */ ceph_encode_timespec64(p, &req->r_mtime); p += sizeof(struct ceph_timespec); encode_oloc(&p, end, &req->r_t.target_oloc); ceph_encode_string(&p, end, req->r_t.target_oid.name, req->r_t.target_oid.name_len); /* ops, can imply data */ ceph_encode_16(&p, req->r_num_ops); for (i = 0; i < req->r_num_ops; i++) { data_len += osd_req_encode_op(p, &req->r_ops[i]); p += sizeof(struct ceph_osd_op); } ceph_encode_64(&p, req->r_snapid); /* snapid */ if (req->r_snapc) { ceph_encode_64(&p, req->r_snapc->seq); ceph_encode_32(&p, req->r_snapc->num_snaps); for (i = 0; i < req->r_snapc->num_snaps; i++) ceph_encode_64(&p, req->r_snapc->snaps[i]); } else { ceph_encode_64(&p, 0); /* snap_seq */ ceph_encode_32(&p, 0); /* snaps len */ } ceph_encode_32(&p, req->r_attempts); /* retry_attempt */ BUG_ON(p > end - 8); /* space for features */ msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */ /* front_len is finalized in encode_request_finish() */ msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); msg->hdr.data_len = cpu_to_le32(data_len); /* * The header "data_off" is a hint to the receiver allowing it * to align received data into its buffers such that there's no * need to re-copy it before writing it to disk (direct I/O). */ msg->hdr.data_off = cpu_to_le16(req->r_data_offset); dout("%s req %p msg %p oid %s oid_len %d\n", __func__, req, msg, req->r_t.target_oid.name, req->r_t.target_oid.name_len); } static void encode_request_finish(struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const partial_end = p + msg->front.iov_len; void *const end = p + msg->front_alloc_len; if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) { /* luminous OSD -- encode features and be done */ p = partial_end; ceph_encode_64(&p, msg->con->peer_features); } else { struct { char spgid[CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1]; __le32 hash; __le32 epoch; __le32 flags; char reqid[CEPH_ENCODING_START_BLK_LEN + sizeof(struct ceph_osd_reqid)]; char trace[sizeof(struct ceph_blkin_trace_info)]; __le32 client_inc; struct ceph_timespec mtime; } __packed head; struct ceph_pg pgid; void *oloc, *oid, *tail; int oloc_len, oid_len, tail_len; int len; /* * Pre-luminous OSD -- reencode v8 into v4 using @head * as a temporary buffer. Encode the raw PG; the rest * is just a matter of moving oloc, oid and tail blobs * around. */ memcpy(&head, p, sizeof(head)); p += sizeof(head); oloc = p; p += CEPH_ENCODING_START_BLK_LEN; pgid.pool = ceph_decode_64(&p); p += 4 + 4; /* preferred, key len */ len = ceph_decode_32(&p); p += len; /* nspace */ oloc_len = p - oloc; oid = p; len = ceph_decode_32(&p); p += len; oid_len = p - oid; tail = p; tail_len = partial_end - p; p = msg->front.iov_base; ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc)); ceph_encode_copy(&p, &head.epoch, sizeof(head.epoch)); ceph_encode_copy(&p, &head.flags, sizeof(head.flags)); ceph_encode_copy(&p, &head.mtime, sizeof(head.mtime)); /* reassert_version */ memset(p, 0, sizeof(struct ceph_eversion)); p += sizeof(struct ceph_eversion); BUG_ON(p >= oloc); memmove(p, oloc, oloc_len); p += oloc_len; pgid.seed = le32_to_cpu(head.hash); encode_pgid(&p, &pgid); /* raw pg */ BUG_ON(p >= oid); memmove(p, oid, oid_len); p += oid_len; /* tail -- ops, snapid, snapc, retry_attempt */ BUG_ON(p >= tail); memmove(p, tail, tail_len); p += tail_len; msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */ } BUG_ON(p > end); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); dout("%s msg %p tid %llu %u+%u+%u v%d\n", __func__, msg, le64_to_cpu(msg->hdr.tid), le32_to_cpu(msg->hdr.front_len), le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len), le16_to_cpu(msg->hdr.version)); } /* * @req has to be assigned a tid and registered. */ static void send_request(struct ceph_osd_request *req) { struct ceph_osd *osd = req->r_osd; verify_osd_locked(osd); WARN_ON(osd->o_osd != req->r_t.osd); /* backoff? */ if (should_plug_request(req)) return; /* * We may have a previously queued request message hanging * around. Cancel it to avoid corrupting the msgr. */ if (req->r_sent) ceph_msg_revoke(req->r_request); req->r_flags |= CEPH_OSD_FLAG_KNOWN_REDIR; if (req->r_attempts) req->r_flags |= CEPH_OSD_FLAG_RETRY; else WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY); encode_request_partial(req, req->r_request); dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d e%u flags 0x%x attempt %d\n", __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed, req->r_t.spgid.pgid.pool, req->r_t.spgid.pgid.seed, req->r_t.spgid.shard, osd->o_osd, req->r_t.epoch, req->r_flags, req->r_attempts); req->r_t.paused = false; req->r_stamp = jiffies; req->r_attempts++; req->r_sent = osd->o_incarnation; req->r_request->hdr.tid = cpu_to_le64(req->r_tid); ceph_con_send(&osd->o_con, ceph_msg_get(req->r_request)); } static void maybe_request_map(struct ceph_osd_client *osdc) { bool continuous = false; verify_osdc_locked(osdc); WARN_ON(!osdc->osdmap->epoch); if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { dout("%s osdc %p continuous\n", __func__, osdc); continuous = true; } else { dout("%s osdc %p onetime\n", __func__, osdc); } if (ceph_monc_want_map(&osdc->client->monc, CEPH_SUB_OSDMAP, osdc->osdmap->epoch + 1, continuous)) ceph_monc_renew_subs(&osdc->client->monc); } static void complete_request(struct ceph_osd_request *req, int err); static void send_map_check(struct ceph_osd_request *req); static void __submit_request(struct ceph_osd_request *req, bool wrlocked) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd *osd; enum calc_target_result ct_res; int err = 0; bool need_send = false; bool promoted = false; WARN_ON(req->r_tid); dout("%s req %p wrlocked %d\n", __func__, req, wrlocked); again: ct_res = calc_target(osdc, &req->r_t, false); if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked) goto promote; osd = lookup_create_osd(osdc, req->r_t.osd, wrlocked); if (IS_ERR(osd)) { WARN_ON(PTR_ERR(osd) != -EAGAIN || wrlocked); goto promote; } if (osdc->abort_err) { dout("req %p abort_err %d\n", req, osdc->abort_err); err = osdc->abort_err; } else if (osdc->osdmap->epoch < osdc->epoch_barrier) { dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch, osdc->epoch_barrier); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { dout("req %p pausewr\n", req); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_READ) && ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("req %p pauserd\n", req); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && !(req->r_flags & (CEPH_OSD_FLAG_FULL_TRY | CEPH_OSD_FLAG_FULL_FORCE)) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || pool_full(osdc, req->r_t.base_oloc.pool))) { dout("req %p full/pool_full\n", req); if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) { err = -ENOSPC; } else { if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) pr_warn_ratelimited("cluster is full (osdmap FULL)\n"); else pr_warn_ratelimited("pool %lld is full or reached quota\n", req->r_t.base_oloc.pool); req->r_t.paused = true; maybe_request_map(osdc); } } else if (!osd_homeless(osd)) { need_send = true; } else { maybe_request_map(osdc); } mutex_lock(&osd->lock); /* * Assign the tid atomically with send_request() to protect * multiple writes to the same object from racing with each * other, resulting in out of order ops on the OSDs. */ req->r_tid = atomic64_inc_return(&osdc->last_tid); link_request(osd, req); if (need_send) send_request(req); else if (err) complete_request(req, err); mutex_unlock(&osd->lock); if (!err && ct_res == CALC_TARGET_POOL_DNE) send_map_check(req); if (promoted) downgrade_write(&osdc->lock); return; promote: up_read(&osdc->lock); down_write(&osdc->lock); wrlocked = true; promoted = true; goto again; } static void account_request(struct ceph_osd_request *req) { WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK)); WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE))); req->r_flags |= CEPH_OSD_FLAG_ONDISK; atomic_inc(&req->r_osdc->num_requests); req->r_start_stamp = jiffies; req->r_start_latency = ktime_get(); } static void submit_request(struct ceph_osd_request *req, bool wrlocked) { ceph_osdc_get_request(req); account_request(req); __submit_request(req, wrlocked); } static void finish_request(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid)); dout("%s req %p tid %llu\n", __func__, req, req->r_tid); req->r_end_latency = ktime_get(); if (req->r_osd) { ceph_init_sparse_read(&req->r_osd->o_sparse_read); unlink_request(req->r_osd, req); } atomic_dec(&osdc->num_requests); /* * If an OSD has failed or returned and a request has been sent * twice, it's possible to get a reply and end up here while the * request message is queued for delivery. We will ignore the * reply, so not a big deal, but better to try and catch it. */ ceph_msg_revoke(req->r_request); ceph_msg_revoke_incoming(req->r_reply); } static void __complete_request(struct ceph_osd_request *req) { dout("%s req %p tid %llu cb %ps result %d\n", __func__, req, req->r_tid, req->r_callback, req->r_result); if (req->r_callback) req->r_callback(req); complete_all(&req->r_completion); ceph_osdc_put_request(req); } static void complete_request_workfn(struct work_struct *work) { struct ceph_osd_request *req = container_of(work, struct ceph_osd_request, r_complete_work); __complete_request(req); } /* * This is open-coded in handle_reply(). */ static void complete_request(struct ceph_osd_request *req, int err) { dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); req->r_result = err; finish_request(req); INIT_WORK(&req->r_complete_work, complete_request_workfn); queue_work(req->r_osdc->completion_wq, &req->r_complete_work); } static void cancel_map_check(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd_request *lookup_req; verify_osdc_wrlocked(osdc); lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid); if (!lookup_req) return; WARN_ON(lookup_req != req); erase_request_mc(&osdc->map_checks, req); ceph_osdc_put_request(req); } static void cancel_request(struct ceph_osd_request *req) { dout("%s req %p tid %llu\n", __func__, req, req->r_tid); cancel_map_check(req); finish_request(req); complete_all(&req->r_completion); ceph_osdc_put_request(req); } static void abort_request(struct ceph_osd_request *req, int err) { dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); cancel_map_check(req); complete_request(req, err); } static int abort_fn(struct ceph_osd_request *req, void *arg) { int err = *(int *)arg; abort_request(req, err); return 0; /* continue iteration */ } /* * Abort all in-flight requests with @err and arrange for all future * requests to be failed immediately. */ void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err) { dout("%s osdc %p err %d\n", __func__, osdc, err); down_write(&osdc->lock); for_each_request(osdc, abort_fn, &err); osdc->abort_err = err; up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_abort_requests); void ceph_osdc_clear_abort_err(struct ceph_osd_client *osdc) { down_write(&osdc->lock); osdc->abort_err = 0; up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_clear_abort_err); static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) { if (likely(eb > osdc->epoch_barrier)) { dout("updating epoch_barrier from %u to %u\n", osdc->epoch_barrier, eb); osdc->epoch_barrier = eb; /* Request map if we're not to the barrier yet */ if (eb > osdc->osdmap->epoch) maybe_request_map(osdc); } } void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) { down_read(&osdc->lock); if (unlikely(eb > osdc->epoch_barrier)) { up_read(&osdc->lock); down_write(&osdc->lock); update_epoch_barrier(osdc, eb); up_write(&osdc->lock); } else { up_read(&osdc->lock); } } EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier); /* * We can end up releasing caps as a result of abort_request(). * In that case, we probably want to ensure that the cap release message * has an updated epoch barrier in it, so set the epoch barrier prior to * aborting the first request. */ static int abort_on_full_fn(struct ceph_osd_request *req, void *arg) { struct ceph_osd_client *osdc = req->r_osdc; bool *victims = arg; if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || pool_full(osdc, req->r_t.base_oloc.pool))) { if (!*victims) { update_epoch_barrier(osdc, osdc->osdmap->epoch); *victims = true; } abort_request(req, -ENOSPC); } return 0; /* continue iteration */ } /* * Drop all pending requests that are stalled waiting on a full condition to * clear, and complete them with ENOSPC as the return code. Set the * osdc->epoch_barrier to the latest map epoch that we've seen if any were * cancelled. */ static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc) { bool victims = false; if (ceph_test_opt(osdc->client, ABORT_ON_FULL) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc))) for_each_request(osdc, abort_on_full_fn, &victims); } static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osdmap *map = osdc->osdmap; verify_osdc_wrlocked(osdc); WARN_ON(!map->epoch); if (req->r_attempts) { /* * We sent a request earlier, which means that * previously the pool existed, and now it does not * (i.e., it was deleted). */ req->r_map_dne_bound = map->epoch; dout("%s req %p tid %llu pool disappeared\n", __func__, req, req->r_tid); } else { dout("%s req %p tid %llu map_dne_bound %u have %u\n", __func__, req, req->r_tid, req->r_map_dne_bound, map->epoch); } if (req->r_map_dne_bound) { if (map->epoch >= req->r_map_dne_bound) { /* we had a new enough map */ pr_info_ratelimited("tid %llu pool does not exist\n", req->r_tid); complete_request(req, -ENOENT); } } else { send_map_check(req); } } static void map_check_cb(struct ceph_mon_generic_request *greq) { struct ceph_osd_client *osdc = &greq->monc->client->osdc; struct ceph_osd_request *req; u64 tid = greq->private_data; WARN_ON(greq->result || !greq->u.newest); down_write(&osdc->lock); req = lookup_request_mc(&osdc->map_checks, tid); if (!req) { dout("%s tid %llu dne\n", __func__, tid); goto out_unlock; } dout("%s req %p tid %llu map_dne_bound %u newest %llu\n", __func__, req, req->r_tid, req->r_map_dne_bound, greq->u.newest); if (!req->r_map_dne_bound) req->r_map_dne_bound = greq->u.newest; erase_request_mc(&osdc->map_checks, req); check_pool_dne(req); ceph_osdc_put_request(req); out_unlock: up_write(&osdc->lock); } static void send_map_check(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd_request *lookup_req; int ret; verify_osdc_wrlocked(osdc); lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid); if (lookup_req) { WARN_ON(lookup_req != req); return; } ceph_osdc_get_request(req); insert_request_mc(&osdc->map_checks, req); ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap", map_check_cb, req->r_tid); WARN_ON(ret); } /* * lingering requests, watch/notify v2 infrastructure */ static void linger_release(struct kref *kref) { struct ceph_osd_linger_request *lreq = container_of(kref, struct ceph_osd_linger_request, kref); dout("%s lreq %p reg_req %p ping_req %p\n", __func__, lreq, lreq->reg_req, lreq->ping_req); WARN_ON(!RB_EMPTY_NODE(&lreq->node)); WARN_ON(!RB_EMPTY_NODE(&lreq->osdc_node)); WARN_ON(!RB_EMPTY_NODE(&lreq->mc_node)); WARN_ON(!list_empty(&lreq->scan_item)); WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd); if (lreq->request_pl) ceph_pagelist_release(lreq->request_pl); if (lreq->notify_id_pages) ceph_release_page_vector(lreq->notify_id_pages, 1); ceph_osdc_put_request(lreq->reg_req); ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } static void linger_put(struct ceph_osd_linger_request *lreq) { if (lreq) kref_put(&lreq->kref, linger_release); } static struct ceph_osd_linger_request * linger_get(struct ceph_osd_linger_request *lreq) { kref_get(&lreq->kref); return lreq; } static struct ceph_osd_linger_request * linger_alloc(struct ceph_osd_client *osdc) { struct ceph_osd_linger_request *lreq; lreq = kzalloc(sizeof(*lreq), GFP_NOIO); if (!lreq) return NULL; kref_init(&lreq->kref); mutex_init(&lreq->lock); RB_CLEAR_NODE(&lreq->node); RB_CLEAR_NODE(&lreq->osdc_node); RB_CLEAR_NODE(&lreq->mc_node); INIT_LIST_HEAD(&lreq->scan_item); INIT_LIST_HEAD(&lreq->pending_lworks); init_completion(&lreq->reg_commit_wait); init_completion(&lreq->notify_finish_wait); lreq->osdc = osdc; target_init(&lreq->t); dout("%s lreq %p\n", __func__, lreq); return lreq; } DEFINE_RB_INSDEL_FUNCS(linger, struct ceph_osd_linger_request, linger_id, node) DEFINE_RB_FUNCS(linger_osdc, struct ceph_osd_linger_request, linger_id, osdc_node) DEFINE_RB_FUNCS(linger_mc, struct ceph_osd_linger_request, linger_id, mc_node) /* * Create linger request <-> OSD session relation. * * @lreq has to be registered, @osd may be homeless. */ static void link_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq) { verify_osd_locked(osd); WARN_ON(!lreq->linger_id || lreq->osd); dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd, osd->o_osd, lreq, lreq->linger_id); if (!osd_homeless(osd)) __remove_osd_from_lru(osd); else atomic_inc(&osd->o_osdc->num_homeless); get_osd(osd); insert_linger(&osd->o_linger_requests, lreq); lreq->osd = osd; } static void unlink_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq) { verify_osd_locked(osd); WARN_ON(lreq->osd != osd); dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd, osd->o_osd, lreq, lreq->linger_id); lreq->osd = NULL; erase_linger(&osd->o_linger_requests, lreq); put_osd(osd); if (!osd_homeless(osd)) maybe_move_osd_to_lru(osd); else atomic_dec(&osd->o_osdc->num_homeless); } static bool __linger_registered(struct ceph_osd_linger_request *lreq) { verify_osdc_locked(lreq->osdc); return !RB_EMPTY_NODE(&lreq->osdc_node); } static bool linger_registered(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; bool registered; down_read(&osdc->lock); registered = __linger_registered(lreq); up_read(&osdc->lock); return registered; } static void linger_register(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; verify_osdc_wrlocked(osdc); WARN_ON(lreq->linger_id); linger_get(lreq); lreq->linger_id = ++osdc->last_linger_id; insert_linger_osdc(&osdc->linger_requests, lreq); } static void linger_unregister(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; verify_osdc_wrlocked(osdc); erase_linger_osdc(&osdc->linger_requests, lreq); linger_put(lreq); } static void cancel_linger_request(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; WARN_ON(!req->r_linger); cancel_request(req); linger_put(lreq); } struct linger_work { struct work_struct work; struct ceph_osd_linger_request *lreq; struct list_head pending_item; unsigned long queued_stamp; union { struct { u64 notify_id; u64 notifier_id; void *payload; /* points into @msg front */ size_t payload_len; struct ceph_msg *msg; /* for ceph_msg_put() */ } notify; struct { int err; } error; }; }; static struct linger_work *lwork_alloc(struct ceph_osd_linger_request *lreq, work_func_t workfn) { struct linger_work *lwork; lwork = kzalloc(sizeof(*lwork), GFP_NOIO); if (!lwork) return NULL; INIT_WORK(&lwork->work, workfn); INIT_LIST_HEAD(&lwork->pending_item); lwork->lreq = linger_get(lreq); return lwork; } static void lwork_free(struct linger_work *lwork) { struct ceph_osd_linger_request *lreq = lwork->lreq; mutex_lock(&lreq->lock); list_del(&lwork->pending_item); mutex_unlock(&lreq->lock); linger_put(lreq); kfree(lwork); } static void lwork_queue(struct linger_work *lwork) { struct ceph_osd_linger_request *lreq = lwork->lreq; struct ceph_osd_client *osdc = lreq->osdc; verify_lreq_locked(lreq); WARN_ON(!list_empty(&lwork->pending_item)); lwork->queued_stamp = jiffies; list_add_tail(&lwork->pending_item, &lreq->pending_lworks); queue_work(osdc->notify_wq, &lwork->work); } static void do_watch_notify(struct work_struct *w) { struct linger_work *lwork = container_of(w, struct linger_work, work); struct ceph_osd_linger_request *lreq = lwork->lreq; if (!linger_registered(lreq)) { dout("%s lreq %p not registered\n", __func__, lreq); goto out; } WARN_ON(!lreq->is_watch); dout("%s lreq %p notify_id %llu notifier_id %llu payload_len %zu\n", __func__, lreq, lwork->notify.notify_id, lwork->notify.notifier_id, lwork->notify.payload_len); lreq->wcb(lreq->data, lwork->notify.notify_id, lreq->linger_id, lwork->notify.notifier_id, lwork->notify.payload, lwork->notify.payload_len); out: ceph_msg_put(lwork->notify.msg); lwork_free(lwork); } static void do_watch_error(struct work_struct *w) { struct linger_work *lwork = container_of(w, struct linger_work, work); struct ceph_osd_linger_request *lreq = lwork->lreq; if (!linger_registered(lreq)) { dout("%s lreq %p not registered\n", __func__, lreq); goto out; } dout("%s lreq %p err %d\n", __func__, lreq, lwork->error.err); lreq->errcb(lreq->data, lreq->linger_id, lwork->error.err); out: lwork_free(lwork); } static void queue_watch_error(struct ceph_osd_linger_request *lreq) { struct linger_work *lwork; lwork = lwork_alloc(lreq, do_watch_error); if (!lwork) { pr_err("failed to allocate error-lwork\n"); return; } lwork->error.err = lreq->last_error; lwork_queue(lwork); } static void linger_reg_commit_complete(struct ceph_osd_linger_request *lreq, int result) { if (!completion_done(&lreq->reg_commit_wait)) { lreq->reg_commit_error = (result <= 0 ? result : 0); complete_all(&lreq->reg_commit_wait); } } static void linger_commit_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->reg_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->reg_req); goto out; } dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); lreq->committed = true; if (!lreq->is_watch) { struct ceph_osd_data *osd_data = osd_req_op_data(req, 0, notify, response_data); void *p = page_address(osd_data->pages[0]); WARN_ON(req->r_ops[0].op != CEPH_OSD_OP_NOTIFY || osd_data->type != CEPH_OSD_DATA_TYPE_PAGES); /* make note of the notify_id */ if (req->r_ops[0].outdata_len >= sizeof(u64)) { lreq->notify_id = ceph_decode_64(&p); dout("lreq %p notify_id %llu\n", lreq, lreq->notify_id); } else { dout("lreq %p no notify_id\n", lreq); } } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static int normalize_watch_error(int err) { /* * Translate ENOENT -> ENOTCONN so that a delete->disconnection * notification and a failure to reconnect because we raced with * the delete appear the same to the user. */ if (err == -ENOENT) err = -ENOTCONN; return err; } static void linger_reconnect_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->reg_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->reg_req); goto out; } dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { if (!lreq->last_error) { lreq->last_error = normalize_watch_error(req->r_result); queue_watch_error(lreq); } } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_request *req; int ret; verify_osdc_wrlocked(osdc); mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); if (lreq->reg_req) { if (lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); ceph_osdc_put_request(lreq->reg_req); } req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); BUG_ON(!req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime; if (lreq->is_watch && lreq->committed) { osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { if (lreq->is_watch) { osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, lreq->linger_id, 0); } else { lreq->notify_id = 0; refcount_inc(&lreq->request_pl->refcnt); osd_req_op_notify_init(req, 0, lreq->linger_id, lreq->request_pl); ceph_osd_data_pages_init( osd_req_op_data(req, 0, notify, response_data), lreq->notify_id_pages, PAGE_SIZE, 0, false, false); } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } ret = ceph_osdc_alloc_messages(req, GFP_NOIO); BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; lreq->reg_req = req; mutex_unlock(&lreq->lock); submit_request(req, true); } static void linger_ping_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->ping_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->ping_req); goto out; } dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); if (lreq->register_gen == req->r_ops[0].watch.gen) { if (!req->r_result) { lreq->watch_valid_thru = lreq->ping_sent; } else if (!lreq->last_error) { lreq->last_error = normalize_watch_error(req->r_result); queue_watch_error(lreq); } } else { dout("lreq %p register_gen %u ignoring old pong %u\n", lreq, lreq->register_gen, req->r_ops[0].watch.gen); } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_request *req; int ret; if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); return; } lreq->ping_sent = jiffies; dout("%s lreq %p linger_id %llu ping_sent %lu register_gen %u\n", __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen); if (lreq->ping_req) { if (lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); ceph_osdc_put_request(lreq->ping_req); } req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); BUG_ON(!req); target_copy(&req->r_t, &lreq->t); osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, lreq->register_gen); req->r_callback = linger_ping_cb; ret = ceph_osdc_alloc_messages(req, GFP_NOIO); BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; lreq->ping_req = req; ceph_osdc_get_request(req); account_request(req); req->r_tid = atomic64_inc_return(&osdc->last_tid); link_request(lreq->osd, req); send_request(req); } static void linger_submit(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd *osd; down_write(&osdc->lock); linger_register(lreq); calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); link_linger(osd, lreq); send_linger(lreq); up_write(&osdc->lock); } static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_linger_request *lookup_lreq; verify_osdc_wrlocked(osdc); lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks, lreq->linger_id); if (!lookup_lreq) return; WARN_ON(lookup_lreq != lreq); erase_linger_mc(&osdc->linger_map_checks, lreq); linger_put(lreq); } /* * @lreq has to be both registered and linked. */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); linger_unregister(lreq); } static void linger_cancel(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; down_write(&osdc->lock); if (__linger_registered(lreq)) __linger_cancel(lreq); up_write(&osdc->lock); } static void send_linger_map_check(struct ceph_osd_linger_request *lreq); static void check_linger_pool_dne(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osdmap *map = osdc->osdmap; verify_osdc_wrlocked(osdc); WARN_ON(!map->epoch); if (lreq->register_gen) { lreq->map_dne_bound = map->epoch; dout("%s lreq %p linger_id %llu pool disappeared\n", __func__, lreq, lreq->linger_id); } else { dout("%s lreq %p linger_id %llu map_dne_bound %u have %u\n", __func__, lreq, lreq->linger_id, lreq->map_dne_bound, map->epoch); } if (lreq->map_dne_bound) { if (map->epoch >= lreq->map_dne_bound) { /* we had a new enough map */ pr_info("linger_id %llu pool does not exist\n", lreq->linger_id); linger_reg_commit_complete(lreq, -ENOENT); __linger_cancel(lreq); } } else { send_linger_map_check(lreq); } } static void linger_map_check_cb(struct ceph_mon_generic_request *greq) { struct ceph_osd_client *osdc = &greq->monc->client->osdc; struct ceph_osd_linger_request *lreq; u64 linger_id = greq->private_data; WARN_ON(greq->result || !greq->u.newest); down_write(&osdc->lock); lreq = lookup_linger_mc(&osdc->linger_map_checks, linger_id); if (!lreq) { dout("%s linger_id %llu dne\n", __func__, linger_id); goto out_unlock; } dout("%s lreq %p linger_id %llu map_dne_bound %u newest %llu\n", __func__, lreq, lreq->linger_id, lreq->map_dne_bound, greq->u.newest); if (!lreq->map_dne_bound) lreq->map_dne_bound = greq->u.newest; erase_linger_mc(&osdc->linger_map_checks, lreq); check_linger_pool_dne(lreq); linger_put(lreq); out_unlock: up_write(&osdc->lock); } static void send_linger_map_check(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_linger_request *lookup_lreq; int ret; verify_osdc_wrlocked(osdc); lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks, lreq->linger_id); if (lookup_lreq) { WARN_ON(lookup_lreq != lreq); return; } linger_get(lreq); insert_linger_mc(&osdc->linger_map_checks, lreq); ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap", linger_map_check_cb, lreq->linger_id); WARN_ON(ret); } static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) { int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, unsigned long timeout) { long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, ceph_timeout_jiffies(timeout)); if (left <= 0) left = left ?: -ETIMEDOUT; else left = lreq->notify_finish_error; /* completed */ return left; } /* * Timeout callback, called every N seconds. When 1 or more OSD * requests has been active for more than N seconds, we send a keepalive * (tag + timestamp) to its OSD to ensure any communications channel * reset is detected. */ static void handle_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, timeout_work.work); struct ceph_options *opts = osdc->client->options; unsigned long cutoff = jiffies - opts->osd_keepalive_timeout; unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout; LIST_HEAD(slow_osds); struct rb_node *n, *p; dout("%s osdc %p\n", __func__, osdc); down_write(&osdc->lock); /* * ping osds that are a bit slow. this ensures that if there * is a break in the TCP connection we will notice, and reopen * a connection with that osd (from the fault callback). */ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); bool found = false; for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); /* abort_request() */ if (time_before(req->r_stamp, cutoff)) { dout(" req %p tid %llu on osd%d is laggy\n", req, req->r_tid, osd->o_osd); found = true; } if (opts->osd_request_timeout && time_before(req->r_start_stamp, expiry_cutoff)) { pr_err_ratelimited("tid %llu on osd%d timeout\n", req->r_tid, osd->o_osd); abort_request(req, -ETIMEDOUT); } } for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) { struct ceph_osd_linger_request *lreq = rb_entry(p, struct ceph_osd_linger_request, node); dout(" lreq %p linger_id %llu is served by osd%d\n", lreq, lreq->linger_id, osd->o_osd); found = true; mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed && !lreq->last_error) send_linger_ping(lreq); mutex_unlock(&lreq->lock); } if (found) list_move_tail(&osd->o_keepalive_item, &slow_osds); } if (opts->osd_request_timeout) { for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); /* abort_request() */ if (time_before(req->r_start_stamp, expiry_cutoff)) { pr_err_ratelimited("tid %llu on osd%d timeout\n", req->r_tid, osdc->homeless_osd.o_osd); abort_request(req, -ETIMEDOUT); } } } if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds)) maybe_request_map(osdc); while (!list_empty(&slow_osds)) { struct ceph_osd *osd = list_first_entry(&slow_osds, struct ceph_osd, o_keepalive_item); list_del_init(&osd->o_keepalive_item); ceph_con_keepalive(&osd->o_con); } up_write(&osdc->lock); schedule_delayed_work(&osdc->timeout_work, osdc->client->options->osd_keepalive_timeout); } static void handle_osds_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, osds_timeout_work.work); unsigned long delay = osdc->client->options->osd_idle_ttl / 4; struct ceph_osd *osd, *nosd; dout("%s osdc %p\n", __func__, osdc); down_write(&osdc->lock); list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { if (time_before(jiffies, osd->lru_ttl)) break; WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests)); close_osd(osd); } up_write(&osdc->lock); schedule_delayed_work(&osdc->osds_timeout_work, round_jiffies_relative(delay)); } static int ceph_oloc_decode(void **p, void *end, struct ceph_object_locator *oloc) { u8 struct_v, struct_cv; u32 len; void *struct_end; int ret = 0; ceph_decode_need(p, end, 1 + 1 + 4, e_inval); struct_v = ceph_decode_8(p); struct_cv = ceph_decode_8(p); if (struct_v < 3) { pr_warn("got v %d < 3 cv %d of ceph_object_locator\n", struct_v, struct_cv); goto e_inval; } if (struct_cv > 6) { pr_warn("got v %d cv %d > 6 of ceph_object_locator\n", struct_v, struct_cv); goto e_inval; } len = ceph_decode_32(p); ceph_decode_need(p, end, len, e_inval); struct_end = *p + len; oloc->pool = ceph_decode_64(p); *p += 4; /* skip preferred */ len = ceph_decode_32(p); if (len > 0) { pr_warn("ceph_object_locator::key is set\n"); goto e_inval; } if (struct_v >= 5) { bool changed = false; len = ceph_decode_32(p); if (len > 0) { ceph_decode_need(p, end, len, e_inval); if (!oloc->pool_ns || ceph_compare_string(oloc->pool_ns, *p, len)) changed = true; *p += len; } else { if (oloc->pool_ns) changed = true; } if (changed) { /* redirect changes namespace */ pr_warn("ceph_object_locator::nspace is changed\n"); goto e_inval; } } if (struct_v >= 6) { s64 hash = ceph_decode_64(p); if (hash != -1) { pr_warn("ceph_object_locator::hash is set\n"); goto e_inval; } } /* skip the rest */ *p = struct_end; out: return ret; e_inval: ret = -EINVAL; goto out; } static int ceph_redirect_decode(void **p, void *end, struct ceph_request_redirect *redir) { u8 struct_v, struct_cv; u32 len; void *struct_end; int ret; ceph_decode_need(p, end, 1 + 1 + 4, e_inval); struct_v = ceph_decode_8(p); struct_cv = ceph_decode_8(p); if (struct_cv > 1) { pr_warn("got v %d cv %d > 1 of ceph_request_redirect\n", struct_v, struct_cv); goto e_inval; } len = ceph_decode_32(p); ceph_decode_need(p, end, len, e_inval); struct_end = *p + len; ret = ceph_oloc_decode(p, end, &redir->oloc); if (ret) goto out; len = ceph_decode_32(p); if (len > 0) { pr_warn("ceph_request_redirect::object_name is set\n"); goto e_inval; } /* skip the rest */ *p = struct_end; out: return ret; e_inval: ret = -EINVAL; goto out; } struct MOSDOpReply { struct ceph_pg pgid; u64 flags; int result; u32 epoch; int num_ops; u32 outdata_len[CEPH_OSD_MAX_OPS]; s32 rval[CEPH_OSD_MAX_OPS]; int retry_attempt; struct ceph_eversion replay_version; u64 user_version; struct ceph_request_redirect redirect; }; static int decode_MOSDOpReply(const struct ceph_msg *msg, struct MOSDOpReply *m) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u16 version = le16_to_cpu(msg->hdr.version); struct ceph_eversion bad_replay_version; u8 decode_redir; u32 len; int ret; int i; ceph_decode_32_safe(&p, end, len, e_inval); ceph_decode_need(&p, end, len, e_inval); p += len; /* skip oid */ ret = ceph_decode_pgid(&p, end, &m->pgid); if (ret) return ret; ceph_decode_64_safe(&p, end, m->flags, e_inval); ceph_decode_32_safe(&p, end, m->result, e_inval); ceph_decode_need(&p, end, sizeof(bad_replay_version), e_inval); memcpy(&bad_replay_version, p, sizeof(bad_replay_version)); p += sizeof(bad_replay_version); ceph_decode_32_safe(&p, end, m->epoch, e_inval); ceph_decode_32_safe(&p, end, m->num_ops, e_inval); if (m->num_ops > ARRAY_SIZE(m->outdata_len)) goto e_inval; ceph_decode_need(&p, end, m->num_ops * sizeof(struct ceph_osd_op), e_inval); for (i = 0; i < m->num_ops; i++) { struct ceph_osd_op *op = p; m->outdata_len[i] = le32_to_cpu(op->payload_len); p += sizeof(*op); } ceph_decode_32_safe(&p, end, m->retry_attempt, e_inval); for (i = 0; i < m->num_ops; i++) ceph_decode_32_safe(&p, end, m->rval[i], e_inval); if (version >= 5) { ceph_decode_need(&p, end, sizeof(m->replay_version), e_inval); memcpy(&m->replay_version, p, sizeof(m->replay_version)); p += sizeof(m->replay_version); ceph_decode_64_safe(&p, end, m->user_version, e_inval); } else { m->replay_version = bad_replay_version; /* struct */ m->user_version = le64_to_cpu(m->replay_version.version); } if (version >= 6) { if (version >= 7) ceph_decode_8_safe(&p, end, decode_redir, e_inval); else decode_redir = 1; } else { decode_redir = 0; } if (decode_redir) { ret = ceph_redirect_decode(&p, end, &m->redirect); if (ret) return ret; } else { ceph_oloc_init(&m->redirect.oloc); } return 0; e_inval: return -EINVAL; } /* * Handle MOSDOpReply. Set ->r_result and call the callback if it is * specified. */ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg) { struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_osd_request *req; struct MOSDOpReply m; u64 tid = le64_to_cpu(msg->hdr.tid); u32 data_len = 0; int ret; int i; dout("%s msg %p tid %llu\n", __func__, msg, tid); down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); goto out_unlock_osdc; } WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num)); mutex_lock(&osd->lock); req = lookup_request(&osd->o_requests, tid); if (!req) { dout("%s osd%d tid %llu unknown\n", __func__, osd->o_osd, tid); goto out_unlock_session; } m.redirect.oloc.pool_ns = req->r_t.target_oloc.pool_ns; ret = decode_MOSDOpReply(msg, &m); m.redirect.oloc.pool_ns = NULL; if (ret) { pr_err("failed to decode MOSDOpReply for tid %llu: %d\n", req->r_tid, ret); ceph_msg_dump(msg); goto fail_request; } dout("%s req %p tid %llu flags 0x%llx pgid %llu.%x epoch %u attempt %d v %u'%llu uv %llu\n", __func__, req, req->r_tid, m.flags, m.pgid.pool, m.pgid.seed, m.epoch, m.retry_attempt, le32_to_cpu(m.replay_version.epoch), le64_to_cpu(m.replay_version.version), m.user_version); if (m.retry_attempt >= 0) { if (m.retry_attempt != req->r_attempts - 1) { dout("req %p tid %llu retry_attempt %d != %d, ignoring\n", req, req->r_tid, m.retry_attempt, req->r_attempts - 1); goto out_unlock_session; } } else { WARN_ON(1); /* MOSDOpReply v4 is assumed */ } if (!ceph_oloc_empty(&m.redirect.oloc)) { dout("req %p tid %llu redirect pool %lld\n", req, req->r_tid, m.redirect.oloc.pool); unlink_request(osd, req); mutex_unlock(&osd->lock); /* * Not ceph_oloc_copy() - changing pool_ns is not * supported. */ req->r_t.target_oloc.pool = m.redirect.oloc.pool; req->r_flags |= CEPH_OSD_FLAG_REDIRECTED | CEPH_OSD_FLAG_IGNORE_OVERLAY | CEPH_OSD_FLAG_IGNORE_CACHE; req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; } if (m.result == -EAGAIN) { dout("req %p tid %llu EAGAIN\n", req, req->r_tid); unlink_request(osd, req); mutex_unlock(&osd->lock); /* * The object is missing on the replica or not (yet) * readable. Clear pgid to force a resend to the primary * via legacy_change. */ req->r_t.pgid.pool = 0; req->r_t.pgid.seed = 0; WARN_ON(!req->r_t.used_replica); req->r_flags &= ~(CEPH_OSD_FLAG_BALANCE_READS | CEPH_OSD_FLAG_LOCALIZE_READS); req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; } if (m.num_ops != req->r_num_ops) { pr_err("num_ops %d != %d for tid %llu\n", m.num_ops, req->r_num_ops, req->r_tid); goto fail_request; } for (i = 0; i < req->r_num_ops; i++) { dout(" req %p tid %llu op %d rval %d len %u\n", req, req->r_tid, i, m.rval[i], m.outdata_len[i]); req->r_ops[i].rval = m.rval[i]; req->r_ops[i].outdata_len = m.outdata_len[i]; data_len += m.outdata_len[i]; } if (data_len != le32_to_cpu(msg->hdr.data_len)) { pr_err("sum of lens %u != %u for tid %llu\n", data_len, le32_to_cpu(msg->hdr.data_len), req->r_tid); goto fail_request; } dout("%s req %p tid %llu result %d data_len %u\n", __func__, req, req->r_tid, m.result, data_len); /* * Since we only ever request ONDISK, we should only ever get * one (type of) reply back. */ WARN_ON(!(m.flags & CEPH_OSD_FLAG_ONDISK)); req->r_version = m.user_version; req->r_result = m.result ?: data_len; finish_request(req); mutex_unlock(&osd->lock); up_read(&osdc->lock); __complete_request(req); return; fail_request: complete_request(req, -EIO); out_unlock_session: mutex_unlock(&osd->lock); out_unlock_osdc: up_read(&osdc->lock); } static void set_pool_was_full(struct ceph_osd_client *osdc) { struct rb_node *n; for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); pi->was_full = __pool_full(pi); } } static bool pool_cleared_full(struct ceph_osd_client *osdc, s64 pool_id) { struct ceph_pg_pool_info *pi; pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id); if (!pi) return false; return pi->was_full && !__pool_full(pi); } static enum calc_target_result recalc_linger_target(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; enum calc_target_result ct_res; ct_res = calc_target(osdc, &lreq->t, true); if (ct_res == CALC_TARGET_NEED_RESEND) { struct ceph_osd *osd; osd = lookup_create_osd(osdc, lreq->t.osd, true); if (osd != lreq->osd) { unlink_linger(lreq->osd, lreq); link_linger(osd, lreq); } } return ct_res; } /* * Requeue requests whose mapping to an OSD has changed. */ static void scan_requests(struct ceph_osd *osd, bool force_resend, bool cleared_full, bool check_pool_cleared_full, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osd_client *osdc = osd->o_osdc; struct rb_node *n; bool force_resend_writes; for (n = rb_first(&osd->o_linger_requests); n; ) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); enum calc_target_result ct_res; n = rb_next(n); /* recalc_linger_target() */ dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); ct_res = recalc_linger_target(lreq); switch (ct_res) { case CALC_TARGET_NO_ACTION: force_resend_writes = cleared_full || (check_pool_cleared_full && pool_cleared_full(osdc, lreq->t.base_oloc.pool)); if (!force_resend && !force_resend_writes) break; fallthrough; case CALC_TARGET_NEED_RESEND: cancel_linger_map_check(lreq); /* * scan_requests() for the previous epoch(s) * may have already added it to the list, since * it's not unlinked here. */ if (list_empty(&lreq->scan_item)) list_add_tail(&lreq->scan_item, need_resend_linger); break; case CALC_TARGET_POOL_DNE: list_del_init(&lreq->scan_item); check_linger_pool_dne(lreq); break; } } for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); enum calc_target_result ct_res; n = rb_next(n); /* unlink_request(), check_pool_dne() */ dout("%s req %p tid %llu\n", __func__, req, req->r_tid); ct_res = calc_target(osdc, &req->r_t, false); switch (ct_res) { case CALC_TARGET_NO_ACTION: force_resend_writes = cleared_full || (check_pool_cleared_full && pool_cleared_full(osdc, req->r_t.base_oloc.pool)); if (!force_resend && (!(req->r_flags & CEPH_OSD_FLAG_WRITE) || !force_resend_writes)) break; fallthrough; case CALC_TARGET_NEED_RESEND: cancel_map_check(req); unlink_request(osd, req); insert_request(need_resend, req); break; case CALC_TARGET_POOL_DNE: check_pool_dne(req); break; } } } static int handle_one_map(struct ceph_osd_client *osdc, void *p, void *end, bool incremental, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osdmap *newmap; struct rb_node *n; bool skipped_map = false; bool was_full; was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL); set_pool_was_full(osdc); if (incremental) newmap = osdmap_apply_incremental(&p, end, ceph_msgr2(osdc->client), osdc->osdmap); else newmap = ceph_osdmap_decode(&p, end, ceph_msgr2(osdc->client)); if (IS_ERR(newmap)) return PTR_ERR(newmap); if (newmap != osdc->osdmap) { /* * Preserve ->was_full before destroying the old map. * For pools that weren't in the old map, ->was_full * should be false. */ for (n = rb_first(&newmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); struct ceph_pg_pool_info *old_pi; old_pi = ceph_pg_pool_by_id(osdc->osdmap, pi->id); if (old_pi) pi->was_full = old_pi->was_full; else WARN_ON(pi->was_full); } if (osdc->osdmap->epoch && osdc->osdmap->epoch + 1 < newmap->epoch) { WARN_ON(incremental); skipped_map = true; } ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = newmap; } was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL); scan_requests(&osdc->homeless_osd, skipped_map, was_full, true, need_resend, need_resend_linger); for (n = rb_first(&osdc->osds); n; ) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); n = rb_next(n); /* close_osd() */ scan_requests(osd, skipped_map, was_full, true, need_resend, need_resend_linger); if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) || memcmp(&osd->o_con.peer_addr, ceph_osd_addr(osdc->osdmap, osd->o_osd), sizeof(struct ceph_entity_addr))) close_osd(osd); } return 0; } static void kick_requests(struct ceph_osd_client *osdc, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osd_linger_request *lreq, *nlreq; enum calc_target_result ct_res; struct rb_node *n; /* make sure need_resend targets reflect latest map */ for (n = rb_first(need_resend); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); if (req->r_t.epoch < osdc->osdmap->epoch) { ct_res = calc_target(osdc, &req->r_t, false); if (ct_res == CALC_TARGET_POOL_DNE) { erase_request(need_resend, req); check_pool_dne(req); } } } for (n = rb_first(need_resend); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); struct ceph_osd *osd; n = rb_next(n); erase_request(need_resend, req); /* before link_request() */ osd = lookup_create_osd(osdc, req->r_t.osd, true); link_request(osd, req); if (!req->r_linger) { if (!osd_homeless(osd) && !req->r_t.paused) send_request(req); } else { cancel_linger_request(req); } } list_for_each_entry_safe(lreq, nlreq, need_resend_linger, scan_item) { if (!osd_homeless(lreq->osd)) send_linger(lreq); list_del_init(&lreq->scan_item); } } /* * Process updated osd map. * * The message contains any number of incremental and full maps, normally * indicating some sort of topology change in the cluster. Kick requests * off to different OSDs as needed. */ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u32 nr_maps, maplen; u32 epoch; struct ceph_fsid fsid; struct rb_root need_resend = RB_ROOT; LIST_HEAD(need_resend_linger); bool handled_incremental = false; bool was_pauserd, was_pausewr; bool pauserd, pausewr; int err; dout("%s have %u\n", __func__, osdc->osdmap->epoch); down_write(&osdc->lock); /* verify fsid */ ceph_decode_need(&p, end, sizeof(fsid), bad); ceph_decode_copy(&p, &fsid, sizeof(fsid)); if (ceph_check_fsid(osdc->client, &fsid) < 0) goto bad; was_pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); was_pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc); /* incremental maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d inc maps\n", nr_maps); while (nr_maps > 0) { ceph_decode_need(&p, end, 2*sizeof(u32), bad); epoch = ceph_decode_32(&p); maplen = ceph_decode_32(&p); ceph_decode_need(&p, end, maplen, bad); if (osdc->osdmap->epoch && osdc->osdmap->epoch + 1 == epoch) { dout("applying incremental map %u len %d\n", epoch, maplen); err = handle_one_map(osdc, p, p + maplen, true, &need_resend, &need_resend_linger); if (err) goto bad; handled_incremental = true; } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); } p += maplen; nr_maps--; } if (handled_incremental) goto done; /* full maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d full maps\n", nr_maps); while (nr_maps) { ceph_decode_need(&p, end, 2*sizeof(u32), bad); epoch = ceph_decode_32(&p); maplen = ceph_decode_32(&p); ceph_decode_need(&p, end, maplen, bad); if (nr_maps > 1) { dout("skipping non-latest full map %u len %d\n", epoch, maplen); } else if (osdc->osdmap->epoch >= epoch) { dout("skipping full map %u len %d, " "older than our %u\n", epoch, maplen, osdc->osdmap->epoch); } else { dout("taking full map %u len %d\n", epoch, maplen); err = handle_one_map(osdc, p, p + maplen, false, &need_resend, &need_resend_linger); if (err) goto bad; } p += maplen; nr_maps--; } done: /* * subscribe to subsequent osdmap updates if full to ensure * we find out when we are no longer full and stop returning * ENOSPC. */ pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc); if (was_pauserd || was_pausewr || pauserd || pausewr || osdc->osdmap->epoch < osdc->epoch_barrier) maybe_request_map(osdc); kick_requests(osdc, &need_resend, &need_resend_linger); ceph_osdc_abort_on_full(osdc); ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP, osdc->osdmap->epoch); up_write(&osdc->lock); wake_up_all(&osdc->client->auth_wq); return; bad: pr_err("osdc handle_map corrupt msg\n"); ceph_msg_dump(msg); up_write(&osdc->lock); } /* * Resubmit requests pending on the given osd. */ static void kick_osd_requests(struct ceph_osd *osd) { struct rb_node *n; clear_backoffs(osd); for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); /* cancel_linger_request() */ if (!req->r_linger) { if (!req->r_t.paused) send_request(req); } else { cancel_linger_request(req); } } for (n = rb_first(&osd->o_linger_requests); n; n = rb_next(n)) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); send_linger(lreq); } } /* * If the osd connection drops, we need to resubmit all requests. */ static void osd_fault(struct ceph_connection *con) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); down_write(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); goto out_unlock; } if (!reopen_osd(osd)) kick_osd_requests(osd); maybe_request_map(osdc); out_unlock: up_write(&osdc->lock); } struct MOSDBackoff { struct ceph_spg spgid; u32 map_epoch; u8 op; u64 id; struct ceph_hobject_id *begin; struct ceph_hobject_id *end; }; static int decode_MOSDBackoff(const struct ceph_msg *msg, struct MOSDBackoff *m) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(&p, end, 1, "spg_t", &struct_v, &struct_len); if (ret) return ret; ret = ceph_decode_pgid(&p, end, &m->spgid.pgid); if (ret) return ret; ceph_decode_8_safe(&p, end, m->spgid.shard, e_inval); ceph_decode_32_safe(&p, end, m->map_epoch, e_inval); ceph_decode_8_safe(&p, end, m->op, e_inval); ceph_decode_64_safe(&p, end, m->id, e_inval); m->begin = kzalloc(sizeof(*m->begin), GFP_NOIO); if (!m->begin) return -ENOMEM; ret = decode_hoid(&p, end, m->begin); if (ret) { free_hoid(m->begin); return ret; } m->end = kzalloc(sizeof(*m->end), GFP_NOIO); if (!m->end) { free_hoid(m->begin); return -ENOMEM; } ret = decode_hoid(&p, end, m->end); if (ret) { free_hoid(m->begin); free_hoid(m->end); return ret; } return 0; e_inval: return -EINVAL; } static struct ceph_msg *create_backoff_message( const struct ceph_osd_backoff *backoff, u32 map_epoch) { struct ceph_msg *msg; void *p, *end; int msg_size; msg_size = CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ msg_size += 4 + 1 + 8; /* map_epoch, op, id */ msg_size += CEPH_ENCODING_START_BLK_LEN + hoid_encoding_size(backoff->begin); msg_size += CEPH_ENCODING_START_BLK_LEN + hoid_encoding_size(backoff->end); msg = ceph_msg_new(CEPH_MSG_OSD_BACKOFF, msg_size, GFP_NOIO, true); if (!msg) return NULL; p = msg->front.iov_base; end = p + msg->front_alloc_len; encode_spgid(&p, &backoff->spgid); ceph_encode_32(&p, map_epoch); ceph_encode_8(&p, CEPH_OSD_BACKOFF_OP_ACK_BLOCK); ceph_encode_64(&p, backoff->id); encode_hoid(&p, end, backoff->begin); encode_hoid(&p, end, backoff->end); BUG_ON(p != end); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.version = cpu_to_le16(1); /* MOSDBackoff v1 */ msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); return msg; } static void handle_backoff_block(struct ceph_osd *osd, struct MOSDBackoff *m) { struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct ceph_msg *msg; dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); spg = lookup_spg_mapping(&osd->o_backoff_mappings, &m->spgid); if (!spg) { spg = alloc_spg_mapping(); if (!spg) { pr_err("%s failed to allocate spg\n", __func__); return; } spg->spgid = m->spgid; /* struct */ insert_spg_mapping(&osd->o_backoff_mappings, spg); } backoff = alloc_backoff(); if (!backoff) { pr_err("%s failed to allocate backoff\n", __func__); return; } backoff->spgid = m->spgid; /* struct */ backoff->id = m->id; backoff->begin = m->begin; m->begin = NULL; /* backoff now owns this */ backoff->end = m->end; m->end = NULL; /* ditto */ insert_backoff(&spg->backoffs, backoff); insert_backoff_by_id(&osd->o_backoffs_by_id, backoff); /* * Ack with original backoff's epoch so that the OSD can * discard this if there was a PG split. */ msg = create_backoff_message(backoff, m->map_epoch); if (!msg) { pr_err("%s failed to allocate msg\n", __func__); return; } ceph_con_send(&osd->o_con, msg); } static bool target_contained_by(const struct ceph_osd_request_target *t, const struct ceph_hobject_id *begin, const struct ceph_hobject_id *end) { struct ceph_hobject_id hoid; int cmp; hoid_fill_from_target(&hoid, t); cmp = hoid_compare(&hoid, begin); return !cmp || (cmp > 0 && hoid_compare(&hoid, end) < 0); } static void handle_backoff_unblock(struct ceph_osd *osd, const struct MOSDBackoff *m) { struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct rb_node *n; dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); backoff = lookup_backoff_by_id(&osd->o_backoffs_by_id, m->id); if (!backoff) { pr_err("%s osd%d spgid %llu.%xs%d id %llu backoff dne\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); return; } if (hoid_compare(backoff->begin, m->begin) && hoid_compare(backoff->end, m->end)) { pr_err("%s osd%d spgid %llu.%xs%d id %llu bad range?\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); /* unblock it anyway... */ } spg = lookup_spg_mapping(&osd->o_backoff_mappings, &backoff->spgid); BUG_ON(!spg); erase_backoff(&spg->backoffs, backoff); erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); free_backoff(backoff); if (RB_EMPTY_ROOT(&spg->backoffs)) { erase_spg_mapping(&osd->o_backoff_mappings, spg); free_spg_mapping(spg); } for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); if (!ceph_spg_compare(&req->r_t.spgid, &m->spgid)) { /* * Match against @m, not @backoff -- the PG may * have split on the OSD. */ if (target_contained_by(&req->r_t, m->begin, m->end)) { /* * If no other installed backoff applies, * resend. */ send_request(req); } } } } static void handle_backoff(struct ceph_osd *osd, struct ceph_msg *msg) { struct ceph_osd_client *osdc = osd->o_osdc; struct MOSDBackoff m; int ret; down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); up_read(&osdc->lock); return; } WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num)); mutex_lock(&osd->lock); ret = decode_MOSDBackoff(msg, &m); if (ret) { pr_err("failed to decode MOSDBackoff: %d\n", ret); ceph_msg_dump(msg); goto out_unlock; } switch (m.op) { case CEPH_OSD_BACKOFF_OP_BLOCK: handle_backoff_block(osd, &m); break; case CEPH_OSD_BACKOFF_OP_UNBLOCK: handle_backoff_unblock(osd, &m); break; default: pr_err("%s osd%d unknown op %d\n", __func__, osd->o_osd, m.op); } free_hoid(m.begin); free_hoid(m.end); out_unlock: mutex_unlock(&osd->lock); up_read(&osdc->lock); } /* * Process osd watch notifications */ static void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; struct ceph_osd_linger_request *lreq; struct linger_work *lwork; u8 proto_ver, opcode; u64 cookie, notify_id; u64 notifier_id = 0; s32 return_code = 0; void *payload = NULL; u32 payload_len = 0; ceph_decode_8_safe(&p, end, proto_ver, bad); ceph_decode_8_safe(&p, end, opcode, bad); ceph_decode_64_safe(&p, end, cookie, bad); p += 8; /* skip ver */ ceph_decode_64_safe(&p, end, notify_id, bad); if (proto_ver >= 1) { ceph_decode_32_safe(&p, end, payload_len, bad); ceph_decode_need(&p, end, payload_len, bad); payload = p; p += payload_len; } if (le16_to_cpu(msg->hdr.version) >= 2) ceph_decode_32_safe(&p, end, return_code, bad); if (le16_to_cpu(msg->hdr.version) >= 3) ceph_decode_64_safe(&p, end, notifier_id, bad); down_read(&osdc->lock); lreq = lookup_linger_osdc(&osdc->linger_requests, cookie); if (!lreq) { dout("%s opcode %d cookie %llu dne\n", __func__, opcode, cookie); goto out_unlock_osdc; } mutex_lock(&lreq->lock); dout("%s opcode %d cookie %llu lreq %p is_watch %d\n", __func__, opcode, cookie, lreq, lreq->is_watch); if (opcode == CEPH_WATCH_EVENT_DISCONNECT) { if (!lreq->last_error) { lreq->last_error = -ENOTCONN; queue_watch_error(lreq); } } else if (!lreq->is_watch) { /* CEPH_WATCH_EVENT_NOTIFY_COMPLETE */ if (lreq->notify_id && lreq->notify_id != notify_id) { dout("lreq %p notify_id %llu != %llu, ignoring\n", lreq, lreq->notify_id, notify_id); } else if (!completion_done(&lreq->notify_finish_wait)) { struct ceph_msg_data *data = msg->num_data_items ? &msg->data[0] : NULL; if (data) { if (lreq->preply_pages) { WARN_ON(data->type != CEPH_MSG_DATA_PAGES); *lreq->preply_pages = data->pages; *lreq->preply_len = data->length; data->own_pages = false; } } lreq->notify_finish_error = return_code; complete_all(&lreq->notify_finish_wait); } } else { /* CEPH_WATCH_EVENT_NOTIFY */ lwork = lwork_alloc(lreq, do_watch_notify); if (!lwork) { pr_err("failed to allocate notify-lwork\n"); goto out_unlock_lreq; } lwork->notify.notify_id = notify_id; lwork->notify.notifier_id = notifier_id; lwork->notify.payload = payload; lwork->notify.payload_len = payload_len; lwork->notify.msg = ceph_msg_get(msg); lwork_queue(lwork); } out_unlock_lreq: mutex_unlock(&lreq->lock); out_unlock_osdc: up_read(&osdc->lock); return; bad: pr_err("osdc handle_watch_notify corrupt msg\n"); } /* * Register request, send initial attempt. */ void ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { down_read(&osdc->lock); submit_request(req, false); up_read(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_start_request); /* * Unregister request. If @req was registered, it isn't completed: * r_result isn't set and __complete_request() isn't invoked. * * If @req wasn't registered, this call may have raced with * handle_reply(), in which case r_result would already be set and * __complete_request() would be getting invoked, possibly even * concurrently with this call. */ void ceph_osdc_cancel_request(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; down_write(&osdc->lock); if (req->r_osd) cancel_request(req); up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_cancel_request); /* * @timeout: in jiffies, 0 means "wait forever" */ static int wait_request_timeout(struct ceph_osd_request *req, unsigned long timeout) { long left; dout("%s req %p tid %llu\n", __func__, req, req->r_tid); left = wait_for_completion_killable_timeout(&req->r_completion, ceph_timeout_jiffies(timeout)); if (left <= 0) { left = left ?: -ETIMEDOUT; ceph_osdc_cancel_request(req); } else { left = req->r_result; /* completed */ } return left; } /* * wait for a request to complete */ int ceph_osdc_wait_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { return wait_request_timeout(req, 0); } EXPORT_SYMBOL(ceph_osdc_wait_request); /* * sync - wait for all in-flight requests to flush. avoid starvation. */ void ceph_osdc_sync(struct ceph_osd_client *osdc) { struct rb_node *n, *p; u64 last_tid = atomic64_read(&osdc->last_tid); again: down_read(&osdc->lock); for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); mutex_lock(&osd->lock); for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); if (req->r_tid > last_tid) break; if (!(req->r_flags & CEPH_OSD_FLAG_WRITE)) continue; ceph_osdc_get_request(req); mutex_unlock(&osd->lock); up_read(&osdc->lock); dout("%s waiting on req %p tid %llu last_tid %llu\n", __func__, req, req->r_tid, last_tid); wait_for_completion(&req->r_completion); ceph_osdc_put_request(req); goto again; } mutex_unlock(&osd->lock); } up_read(&osdc->lock); dout("%s done last_tid %llu\n", __func__, last_tid); } EXPORT_SYMBOL(ceph_osdc_sync); /* * Returns a handle, caller owns a ref. */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, rados_watchcb2_t wcb, rados_watcherrcb_t errcb, void *data) { struct ceph_osd_linger_request *lreq; int ret; lreq = linger_alloc(osdc); if (!lreq) return ERR_PTR(-ENOMEM); lreq->is_watch = true; lreq->wcb = wcb; lreq->errcb = errcb; lreq->data = data; lreq->watch_valid_thru = jiffies; ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime); linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { linger_cancel(lreq); goto err_put_lreq; } return lreq; err_put_lreq: linger_put(lreq); return ERR_PTR(ret); } EXPORT_SYMBOL(ceph_osdc_watch); /* * Releases a ref. * * Times out after mount_timeout to preserve rbd unmap behaviour * introduced in 2894e1d76974 ("rbd: timeout watch teardown on unmap * with mount_timeout"). */ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, struct ceph_osd_linger_request *lreq) { struct ceph_options *opts = osdc->client->options; struct ceph_osd_request *req; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, lreq->linger_id, 0); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); linger_cancel(lreq); linger_put(lreq); ret = wait_request_timeout(req, opts->mount_timeout); out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_unwatch); static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which, u64 notify_id, u64 cookie, void *payload, u32 payload_len) { struct ceph_osd_req_op *op; struct ceph_pagelist *pl; int ret; op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0); pl = ceph_pagelist_alloc(GFP_NOIO); if (!pl) return -ENOMEM; ret = ceph_pagelist_encode_64(pl, notify_id); ret |= ceph_pagelist_encode_64(pl, cookie); if (payload) { ret |= ceph_pagelist_encode_32(pl, payload_len); ret |= ceph_pagelist_append(pl, payload, payload_len); } else { ret |= ceph_pagelist_encode_32(pl, 0); } if (ret) { ceph_pagelist_release(pl); return -ENOMEM; } ceph_osd_data_pagelist_init(&op->notify_ack.request_data, pl); op->indata_len = pl->length; return 0; } int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, u64 notify_id, u64 cookie, void *payload, u32 payload_len) { struct ceph_osd_request *req; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = CEPH_OSD_FLAG_READ; ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload, payload_len); if (ret) goto out_put_req; ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_notify_ack); /* * @timeout: in seconds * * @preply_{pages,len} are initialized both on success and error. * The caller is responsible for: * * ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len)) */ int ceph_osdc_notify(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, void *payload, u32 payload_len, u32 timeout, struct page ***preply_pages, size_t *preply_len) { struct ceph_osd_linger_request *lreq; int ret; WARN_ON(!timeout); if (preply_pages) { *preply_pages = NULL; *preply_len = 0; } lreq = linger_alloc(osdc); if (!lreq) return -ENOMEM; lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; } ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); if (ret) { ret = -ENOMEM; goto out_put_lreq; } /* for notify_id */ lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); if (IS_ERR(lreq->notify_id_pages)) { ret = PTR_ERR(lreq->notify_id_pages); lreq->notify_id_pages = NULL; goto out_put_lreq; } lreq->preply_pages = preply_pages; lreq->preply_len = preply_len; ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_READ; linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) ret = linger_notify_finish_wait(lreq, msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); linger_cancel(lreq); out_put_lreq: linger_put(lreq); return ret; } EXPORT_SYMBOL(ceph_osdc_notify); static int decode_watcher(void **p, void *end, struct ceph_watch_item *item) { u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(p, end, 2, "watch_item_t", &struct_v, &struct_len); if (ret) goto bad; ret = -EINVAL; ceph_decode_copy_safe(p, end, &item->name, sizeof(item->name), bad); ceph_decode_64_safe(p, end, item->cookie, bad); ceph_decode_skip_32(p, end, bad); /* skip timeout seconds */ if (struct_v >= 2) { ret = ceph_decode_entity_addr(p, end, &item->addr); if (ret) goto bad; } else { ret = 0; } dout("%s %s%llu cookie %llu addr %s\n", __func__, ENTITY_NAME(item->name), item->cookie, ceph_pr_addr(&item->addr)); bad: return ret; } static int decode_watchers(void **p, void *end, struct ceph_watch_item **watchers, u32 *num_watchers) { u8 struct_v; u32 struct_len; int i; int ret; ret = ceph_start_decoding(p, end, 1, "obj_list_watch_response_t", &struct_v, &struct_len); if (ret) return ret; *num_watchers = ceph_decode_32(p); *watchers = kcalloc(*num_watchers, sizeof(**watchers), GFP_NOIO); if (!*watchers) return -ENOMEM; for (i = 0; i < *num_watchers; i++) { ret = decode_watcher(p, end, *watchers + i); if (ret) { kfree(*watchers); return ret; } } return 0; } /* * On success, the caller is responsible for: * * kfree(watchers); */ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, struct ceph_watch_item **watchers, u32 *num_watchers) { struct ceph_osd_request *req; struct page **pages; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = CEPH_OSD_FLAG_READ; pages = ceph_alloc_page_vector(1, GFP_NOIO); if (IS_ERR(pages)) { ret = PTR_ERR(pages); goto out_put_req; } osd_req_op_init(req, 0, CEPH_OSD_OP_LIST_WATCHERS, 0); ceph_osd_data_pages_init(osd_req_op_data(req, 0, list_watchers, response_data), pages, PAGE_SIZE, 0, false, true); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); if (ret >= 0) { void *p = page_address(pages[0]); void *const end = p + req->r_ops[0].outdata_len; ret = decode_watchers(&p, end, watchers, num_watchers); } out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_list_watchers); /* * Call all pending notify callbacks - for use after a watch is * unregistered, to make sure no more callbacks for it will be invoked */ void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc) { dout("%s osdc %p\n", __func__, osdc); flush_workqueue(osdc->notify_wq); } EXPORT_SYMBOL(ceph_osdc_flush_notifies); void ceph_osdc_maybe_request_map(struct ceph_osd_client *osdc) { down_read(&osdc->lock); maybe_request_map(osdc); up_read(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_maybe_request_map); /* * Execute an OSD class method on an object. * * @flags: CEPH_OSD_FLAG_* * @resp_len: in/out param for reply length */ int ceph_osdc_call(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, const char *class, const char *method, unsigned int flags, struct page *req_page, size_t req_len, struct page **resp_pages, size_t *resp_len) { struct ceph_osd_request *req; int ret; if (req_len > PAGE_SIZE) return -E2BIG; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = flags; ret = osd_req_op_cls_init(req, 0, class, method); if (ret) goto out_put_req; if (req_page) osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len, 0, false, false); if (resp_pages) osd_req_op_cls_response_data_pages(req, 0, resp_pages, *resp_len, 0, false, false); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); if (ret >= 0) { ret = req->r_ops[0].rval; if (resp_pages) *resp_len = req->r_ops[0].outdata_len; } out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_call); /* * reset all osd connections */ void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc) { struct rb_node *n; down_write(&osdc->lock); for (n = rb_first(&osdc->osds); n; ) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); n = rb_next(n); if (!reopen_osd(osd)) kick_osd_requests(osd); } up_write(&osdc->lock); } /* * init, shutdown */ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) { int err; dout("init\n"); osdc->client = client; init_rwsem(&osdc->lock); osdc->osds = RB_ROOT; INIT_LIST_HEAD(&osdc->osd_lru); spin_lock_init(&osdc->osd_lru_lock); osd_init(&osdc->homeless_osd); osdc->homeless_osd.o_osdc = osdc; osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD; osdc->last_linger_id = CEPH_LINGER_ID_START; osdc->linger_requests = RB_ROOT; osdc->map_checks = RB_ROOT; osdc->linger_map_checks = RB_ROOT; INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout); INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout); err = -ENOMEM; osdc->osdmap = ceph_osdmap_alloc(); if (!osdc->osdmap) goto out; osdc->req_mempool = mempool_create_slab_pool(10, ceph_osd_request_cache); if (!osdc->req_mempool) goto out_map; err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP, PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op"); if (err < 0) goto out_mempool; err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY, PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op_reply"); if (err < 0) goto out_msgpool; err = -ENOMEM; osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify"); if (!osdc->notify_wq) goto out_msgpool_reply; osdc->completion_wq = create_singlethread_workqueue("ceph-completion"); if (!osdc->completion_wq) goto out_notify_wq; schedule_delayed_work(&osdc->timeout_work, osdc->client->options->osd_keepalive_timeout); schedule_delayed_work(&osdc->osds_timeout_work, round_jiffies_relative(osdc->client->options->osd_idle_ttl)); return 0; out_notify_wq: destroy_workqueue(osdc->notify_wq); out_msgpool_reply: ceph_msgpool_destroy(&osdc->msgpool_op_reply); out_msgpool: ceph_msgpool_destroy(&osdc->msgpool_op); out_mempool: mempool_destroy(osdc->req_mempool); out_map: ceph_osdmap_destroy(osdc->osdmap); out: return err; } void ceph_osdc_stop(struct ceph_osd_client *osdc) { destroy_workqueue(osdc->completion_wq); destroy_workqueue(osdc->notify_wq); cancel_delayed_work_sync(&osdc->timeout_work); cancel_delayed_work_sync(&osdc->osds_timeout_work); down_write(&osdc->lock); while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), struct ceph_osd, o_node); close_osd(osd); } up_write(&osdc->lock); WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1); osd_cleanup(&osdc->homeless_osd); WARN_ON(!list_empty(&osdc->osd_lru)); WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_requests)); WARN_ON(!RB_EMPTY_ROOT(&osdc->map_checks)); WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_map_checks)); WARN_ON(atomic_read(&osdc->num_requests)); WARN_ON(atomic_read(&osdc->num_homeless)); ceph_osdmap_destroy(osdc->osdmap); mempool_destroy(osdc->req_mempool); ceph_msgpool_destroy(&osdc->msgpool_op); ceph_msgpool_destroy(&osdc->msgpool_op_reply); } int osd_req_op_copy_from_init(struct ceph_osd_request *req, u64 src_snapid, u64 src_version, struct ceph_object_id *src_oid, struct ceph_object_locator *src_oloc, u32 src_fadvise_flags, u32 dst_fadvise_flags, u32 truncate_seq, u64 truncate_size, u8 copy_from_flags) { struct ceph_osd_req_op *op; struct page **pages; void *p, *end; pages = ceph_alloc_page_vector(1, GFP_KERNEL); if (IS_ERR(pages)) return PTR_ERR(pages); op = osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2, dst_fadvise_flags); op->copy_from.snapid = src_snapid; op->copy_from.src_version = src_version; op->copy_from.flags = copy_from_flags; op->copy_from.src_fadvise_flags = src_fadvise_flags; p = page_address(pages[0]); end = p + PAGE_SIZE; ceph_encode_string(&p, end, src_oid->name, src_oid->name_len); encode_oloc(&p, end, src_oloc); ceph_encode_32(&p, truncate_seq); ceph_encode_64(&p, truncate_size); op->indata_len = PAGE_SIZE - (end - p); ceph_osd_data_pages_init(&op->copy_from.osd_data, pages, op->indata_len, 0, false, true); return 0; } EXPORT_SYMBOL(osd_req_op_copy_from_init); int __init ceph_osdc_setup(void) { size_t size = sizeof(struct ceph_osd_request) + CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op); BUG_ON(ceph_osd_request_cache); ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", size, 0, 0, NULL); return ceph_osd_request_cache ? 0 : -ENOMEM; } void ceph_osdc_cleanup(void) { BUG_ON(!ceph_osd_request_cache); kmem_cache_destroy(ceph_osd_request_cache); ceph_osd_request_cache = NULL; } /* * handle incoming message */ static void osd_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; int type = le16_to_cpu(msg->hdr.type); switch (type) { case CEPH_MSG_OSD_MAP: ceph_osdc_handle_map(osdc, msg); break; case CEPH_MSG_OSD_OPREPLY: handle_reply(osd, msg); break; case CEPH_MSG_OSD_BACKOFF: handle_backoff(osd, msg); break; case CEPH_MSG_WATCH_NOTIFY: handle_watch_notify(osdc, msg); break; default: pr_err("received unknown message type %d %s\n", type, ceph_msg_type_name(type)); } ceph_msg_put(msg); } /* How much sparse data was requested? */ static u64 sparse_data_requested(struct ceph_osd_request *req) { u64 len = 0; if (req->r_flags & CEPH_OSD_FLAG_READ) { int i; for (i = 0; i < req->r_num_ops; ++i) { struct ceph_osd_req_op *op = &req->r_ops[i]; if (op->op == CEPH_OSD_OP_SPARSE_READ) len += op->extent.length; } } return len; } /* * Lookup and return message for incoming reply. Don't try to do * anything about a larger than preallocated data portion of the * message at the moment - for now, just skip the message. */ static struct ceph_msg *get_reply(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_msg *m = NULL; struct ceph_osd_request *req; int front_len = le32_to_cpu(hdr->front_len); int data_len = le32_to_cpu(hdr->data_len); u64 tid = le64_to_cpu(hdr->tid); u64 srlen; down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown, skipping\n", __func__, osd->o_osd); *skip = 1; goto out_unlock_osdc; } WARN_ON(osd->o_osd != le64_to_cpu(hdr->src.num)); mutex_lock(&osd->lock); req = lookup_request(&osd->o_requests, tid); if (!req) { dout("%s osd%d tid %llu unknown, skipping\n", __func__, osd->o_osd, tid); *skip = 1; goto out_unlock_session; } ceph_msg_revoke_incoming(req->r_reply); if (front_len > req->r_reply->front_alloc_len) { pr_warn("%s osd%d tid %llu front %d > preallocated %d\n", __func__, osd->o_osd, req->r_tid, front_len, req->r_reply->front_alloc_len); m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS, false); if (!m) goto out_unlock_session; ceph_msg_put(req->r_reply); req->r_reply = m; } srlen = sparse_data_requested(req); if (!srlen && data_len > req->r_reply->data_length) { pr_warn("%s osd%d tid %llu data %d > preallocated %zu, skipping\n", __func__, osd->o_osd, req->r_tid, data_len, req->r_reply->data_length); m = NULL; *skip = 1; goto out_unlock_session; } m = ceph_msg_get(req->r_reply); m->sparse_read_total = srlen; dout("get_reply tid %lld %p\n", tid, m); out_unlock_session: mutex_unlock(&osd->lock); out_unlock_osdc: up_read(&osdc->lock); return m; } static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) { struct ceph_msg *m; int type = le16_to_cpu(hdr->type); u32 front_len = le32_to_cpu(hdr->front_len); u32 data_len = le32_to_cpu(hdr->data_len); m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false); if (!m) return NULL; if (data_len) { struct page **pages; pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); if (IS_ERR(pages)) { ceph_msg_put(m); return NULL; } ceph_msg_data_add_pages(m, pages, data_len, 0, true); } return m; } static struct ceph_msg *osd_alloc_msg(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip) { struct ceph_osd *osd = con->private; int type = le16_to_cpu(hdr->type); *skip = 0; switch (type) { case CEPH_MSG_OSD_MAP: case CEPH_MSG_OSD_BACKOFF: case CEPH_MSG_WATCH_NOTIFY: return alloc_msg_with_page_vector(hdr); case CEPH_MSG_OSD_OPREPLY: return get_reply(con, hdr, skip); default: pr_warn("%s osd%d unknown msg type %d, skipping\n", __func__, osd->o_osd, type); *skip = 1; return NULL; } } /* * Wrappers to refcount containing ceph_osd struct */ static struct ceph_connection *osd_get_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; if (get_osd(osd)) return con; return NULL; } static void osd_put_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; put_osd(osd); } /* * authentication */ /* * Note: returned pointer is the address of a structure that's * managed separately. Caller must *not* attempt to free it. */ static struct ceph_auth_handshake * osd_get_authorizer(struct ceph_connection *con, int *proto, int force_new) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = __ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD, force_new, proto, NULL, NULL); if (ret) return ERR_PTR(ret); return auth; } static int osd_add_authorizer_challenge(struct ceph_connection *con, void *challenge_buf, int challenge_buf_len) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; return ceph_auth_add_authorizer_challenge(ac, o->o_auth.authorizer, challenge_buf, challenge_buf_len); } static int osd_verify_authorizer_reply(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_verify_authorizer_reply(ac, auth->authorizer, auth->authorizer_reply_buf, auth->authorizer_reply_buf_len, NULL, NULL, NULL, NULL); } static int osd_invalidate_authorizer(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); return ceph_monc_validate_auth(&osdc->client->monc); } static int osd_get_auth_request(struct ceph_connection *con, void *buf, int *buf_len, void **authorizer, int *authorizer_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD, buf, buf_len); if (ret) return ret; *authorizer = auth->authorizer_buf; *authorizer_len = auth->authorizer_buf_len; return 0; } static int osd_handle_auth_reply_more(struct ceph_connection *con, void *reply, int reply_len, void *buf, int *buf_len, void **authorizer, int *authorizer_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = ceph_auth_handle_svc_reply_more(ac, auth, reply, reply_len, buf, buf_len); if (ret) return ret; *authorizer = auth->authorizer_buf; *authorizer_len = auth->authorizer_buf_len; return 0; } static int osd_handle_auth_done(struct ceph_connection *con, u64 global_id, void *reply, int reply_len, u8 *session_key, int *session_key_len, u8 *con_secret, int *con_secret_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_handle_svc_reply_done(ac, auth, reply, reply_len, session_key, session_key_len, con_secret, con_secret_len); } static int osd_handle_auth_bad_method(struct ceph_connection *con, int used_proto, int result, const int *allowed_protos, int proto_cnt, const int *allowed_modes, int mode_cnt) { struct ceph_osd *o = con->private; struct ceph_mon_client *monc = &o->o_osdc->client->monc; int ret; if (ceph_auth_handle_bad_authorizer(monc->auth, CEPH_ENTITY_TYPE_OSD, used_proto, result, allowed_protos, proto_cnt, allowed_modes, mode_cnt)) { ret = ceph_monc_validate_auth(monc); if (ret) return ret; } return -EACCES; } static void osd_reencode_message(struct ceph_msg *msg) { int type = le16_to_cpu(msg->hdr.type); if (type == CEPH_MSG_OSD_OP) encode_request_finish(msg); } static int osd_sign_message(struct ceph_msg *msg) { struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_sign_message(auth, msg); } static int osd_check_message_signature(struct ceph_msg *msg) { struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_check_message_signature(auth, msg); } static void advance_cursor(struct ceph_msg_data_cursor *cursor, size_t len, bool zero) { while (len) { struct page *page; size_t poff, plen; page = ceph_msg_data_next(cursor, &poff, &plen); if (plen > len) plen = len; if (zero) zero_user_segment(page, poff, poff + plen); len -= plen; ceph_msg_data_advance(cursor, plen); } } static int prep_next_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor) { struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; struct ceph_osd_request *req; struct ceph_osd_req_op *op; spin_lock(&o->o_requests_lock); req = lookup_request(&o->o_requests, le64_to_cpu(con->in_msg->hdr.tid)); if (!req) { spin_unlock(&o->o_requests_lock); return -EBADR; } if (o->o_sparse_op_idx < 0) { dout("%s: [%d] starting new sparse read req\n", __func__, o->o_osd); } else { u64 end; op = &req->r_ops[o->o_sparse_op_idx]; WARN_ON_ONCE(op->extent.sparse_ext); /* hand back buffer we took earlier */ op->extent.sparse_ext = sr->sr_extent; sr->sr_extent = NULL; op->extent.sparse_ext_cnt = sr->sr_count; sr->sr_ext_len = 0; dout("%s: [%d] completed extent array len %d cursor->resid %zd\n", __func__, o->o_osd, op->extent.sparse_ext_cnt, cursor->resid); /* Advance to end of data for this operation */ end = ceph_sparse_ext_map_end(op); if (end < sr->sr_req_len) advance_cursor(cursor, sr->sr_req_len - end, false); } ceph_init_sparse_read(sr); /* find next op in this request (if any) */ while (++o->o_sparse_op_idx < req->r_num_ops) { op = &req->r_ops[o->o_sparse_op_idx]; if (op->op == CEPH_OSD_OP_SPARSE_READ) goto found; } /* reset for next sparse read request */ spin_unlock(&o->o_requests_lock); o->o_sparse_op_idx = -1; return 0; found: sr->sr_req_off = op->extent.offset; sr->sr_req_len = op->extent.length; sr->sr_pos = sr->sr_req_off; dout("%s: [%d] new sparse read op at idx %d 0x%llx~0x%llx\n", __func__, o->o_osd, o->o_sparse_op_idx, sr->sr_req_off, sr->sr_req_len); /* hand off request's sparse extent map buffer */ sr->sr_ext_len = op->extent.sparse_ext_cnt; op->extent.sparse_ext_cnt = 0; sr->sr_extent = op->extent.sparse_ext; op->extent.sparse_ext = NULL; spin_unlock(&o->o_requests_lock); return 1; } #ifdef __BIG_ENDIAN static inline void convert_extent_map(struct ceph_sparse_read *sr) { int i; for (i = 0; i < sr->sr_count; i++) { struct ceph_sparse_extent *ext = &sr->sr_extent[i]; ext->off = le64_to_cpu((__force __le64)ext->off); ext->len = le64_to_cpu((__force __le64)ext->len); } } #else static inline void convert_extent_map(struct ceph_sparse_read *sr) { } #endif static int osd_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor, char **pbuf) { struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; u32 count = sr->sr_count; u64 eoff, elen, len = 0; int i, ret; switch (sr->sr_state) { case CEPH_SPARSE_READ_HDR: next_op: ret = prep_next_sparse_read(con, cursor); if (ret <= 0) return ret; /* number of extents */ ret = sizeof(sr->sr_count); *pbuf = (char *)&sr->sr_count; sr->sr_state = CEPH_SPARSE_READ_EXTENTS; break; case CEPH_SPARSE_READ_EXTENTS: /* Convert sr_count to host-endian */ count = le32_to_cpu((__force __le32)sr->sr_count); sr->sr_count = count; dout("[%d] got %u extents\n", o->o_osd, count); if (count > 0) { if (!sr->sr_extent || count > sr->sr_ext_len) { /* no extent array provided, or too short */ kfree(sr->sr_extent); sr->sr_extent = kmalloc_array(count, sizeof(*sr->sr_extent), GFP_NOIO); if (!sr->sr_extent) { pr_err("%s: failed to allocate %u extents\n", __func__, count); return -ENOMEM; } sr->sr_ext_len = count; } ret = count * sizeof(*sr->sr_extent); *pbuf = (char *)sr->sr_extent; sr->sr_state = CEPH_SPARSE_READ_DATA_LEN; break; } /* No extents? Read data len */ fallthrough; case CEPH_SPARSE_READ_DATA_LEN: convert_extent_map(sr); ret = sizeof(sr->sr_datalen); *pbuf = (char *)&sr->sr_datalen; sr->sr_state = CEPH_SPARSE_READ_DATA_PRE; break; case CEPH_SPARSE_READ_DATA_PRE: /* Convert sr_datalen to host-endian */ sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen); for (i = 0; i < count; i++) len += sr->sr_extent[i].len; if (sr->sr_datalen != len) { pr_warn_ratelimited("data len %u != extent len %llu\n", sr->sr_datalen, len); return -EREMOTEIO; } sr->sr_state = CEPH_SPARSE_READ_DATA; fallthrough; case CEPH_SPARSE_READ_DATA: if (sr->sr_index >= count) { sr->sr_state = CEPH_SPARSE_READ_HDR; goto next_op; } eoff = sr->sr_extent[sr->sr_index].off; elen = sr->sr_extent[sr->sr_index].len; dout("[%d] ext %d off 0x%llx len 0x%llx\n", o->o_osd, sr->sr_index, eoff, elen); if (elen > INT_MAX) { dout("Sparse read extent length too long (0x%llx)\n", elen); return -EREMOTEIO; } /* zero out anything from sr_pos to start of extent */ if (sr->sr_pos < eoff) advance_cursor(cursor, eoff - sr->sr_pos, true); /* Set position to end of extent */ sr->sr_pos = eoff + elen; /* send back the new length and nullify the ptr */ cursor->sr_resid = elen; ret = elen; *pbuf = NULL; /* Bump the array index */ ++sr->sr_index; break; } return ret; } static const struct ceph_connection_operations osd_con_ops = { .get = osd_get_con, .put = osd_put_con, .sparse_read = osd_sparse_read, .alloc_msg = osd_alloc_msg, .dispatch = osd_dispatch, .fault = osd_fault, .reencode_message = osd_reencode_message, .get_authorizer = osd_get_authorizer, .add_authorizer_challenge = osd_add_authorizer_challenge, .verify_authorizer_reply = osd_verify_authorizer_reply, .invalidate_authorizer = osd_invalidate_authorizer, .sign_message = osd_sign_message, .check_message_signature = osd_check_message_signature, .get_auth_request = osd_get_auth_request, .handle_auth_reply_more = osd_handle_auth_reply_more, .handle_auth_done = osd_handle_auth_done, .handle_auth_bad_method = osd_handle_auth_bad_method, }; |
| 3 13 53 6 46 30 1 196 1599 1509 287 528 117 84 309 21 519 123 477 477 477 477 479 479 5555 4749 1293 83 5491 43 191 305 83 4693 1212 43 215 104 104 3736 14 3798 5049 313 1566 1 50 1 35 459 113 10 1 25 172 80 17 196 99 96 3400 1446 30 94 3305 1428 64 64 1 324 34 323 206 986 1184 25 2690 3014 984 100 9 20 634 312 35 17 906 9 5 129 37 152 2 2 148 3 145 5 666 7 57 719 177 88 468 41 442 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> #include <linux/file_ref.h> #include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct fileattr; struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) /* File supports atomic writes */ #define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) /* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* FMODE_* bit 13 */ /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) #define FMODE_OPENED ((__force fmode_t)(1 << 19)) #define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* File is embedded in backing_file object */ #define FMODE_BACKING ((__force fmode_t)(1 << 24)) /* * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) /* * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * The two FMODE_NONOTIFY* define which fsnotify events should not be generated * for a file. These are the possible values of (f->f_mode & * FMODE_FSNOTIFY_MASK) and their meaning: * * FMODE_NONOTIFY - suppress all (incl. non-permission) events. * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events. */ #define FMODE_FSNOTIFY_MASK \ (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) #define FMODE_FSNOTIFY_NONE(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS #define FMODE_FSNOTIFY_PERM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) #define FMODE_FSNOTIFY_HSM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0) #else #define FMODE_FSNOTIFY_PERM(mode) 0 #define FMODE_FSNOTIFY_HSM(mode) 0 #endif /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) #define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; /* * The two anonymous unions wrap structures with the same member. * * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which * are a dedicated type requiring the filesystem to use the dedicated * helpers. Other filesystem can continue to use ia_{g,u}id until they * have been ported. * * They always contain the same value. In other words FS_ALLOW_IDMAP * pass down the same value on idmapped mounts as they would on regular * mounts. */ union { kuid_t ia_uid; vfsuid_t ia_vfsuid; }; union { kgid_t ia_gid; vfsgid_t ia_vfsgid; }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC #define IOCB_DONTCACHE (__force int) RWF_DONTCACHE /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) /* * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the * iocb completion can be passed back to the owner for execution from a safe * context rather than needing to be punted through a workqueue. If this * flag is set, the bio completion handling may set iocb->dio_complete to a * handler function and iocb->private to context information for that handler. * The issuer should call the handler with that context information from task * context to complete the processing of the iocb. Note that while this * provides a task context for the dio_complete() callback, it should only be * used on the completion side for non-IO generating completions. It's fine to * call blocking functions from this callback, but they should not wait for * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) #define IOCB_HAS_METADATA (1 << 24) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ { IOCB_HIPRI, "HIPRI" }, \ { IOCB_DSYNC, "DSYNC" }, \ { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ { IOCB_ATOMIC, "ATOMIC" }, \ { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } struct kiocb { struct file *ki_filp; loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ union { /* * Only used for async buffered reads, where it denotes the * page waitqueue associated with completing the read. Valid * IFF IOCB_WAITQ is set. */ struct wait_page_queue *ki_waitq; /* * Can be used for O_DIRECT IO, where the completion handling * is punted back to the issuer of the IO. May only be set * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer * must then check for presence of this handler when ki_complete * is invoked. The data passed in to this handler must be * assigned to ->private when dio_complete is assigned. */ ssize_t (*dio_complete)(void *data); }; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migrate_folio)(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @invalidate_lock: Guards coherency between page cache contents and * file offset->disk block mappings in the filesystem during invalidates. * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @i_private_lock: For use by the owner of the address_space. * @i_private_list: For use by the owner of the address_space. * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_read(struct address_space *mapping) { return down_read_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) /* * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to * cache the ACL. This also means that ->get_inode_acl() can be called in RCU * mode with the LOOKUP_RCU flag. */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 #define IOP_MGTIME 0x0020 #define IOP_CACHED_LINK 0x0040 /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; time64_t i_atime_sec; time64_t i_mtime_sec; time64_t i_ctime_sec; u32 i_atime_nsec; u32 i_mtime_nsec; u32 i_ctime_nsec; u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ u32 i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; union { struct list_head i_devices; int i_linklen; }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_inode_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY struct fsverity_info *i_verity_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { int testlen; /* * TODO: patch it into a debug-only check if relevant macros show up. * In the meantime, since we are suffering strlen even on production kernels * to find the right length, do a fixup if the wrong value got passed. */ testlen = strlen(link); if (testlen != linklen) { WARN_ONCE(1, "bad length passed for symlink [%s] (got %d, expected %d)", link, linklen, testlen); linklen = testlen; } inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; } /* * Get bit address from inode->i_state to use with wait_var_event() * infrastructre. */ #define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, struct inode *inode, u32 bit); static inline void inode_wake_up_bit(struct inode *inode, u32 bit) { /* Caller is responsible for correct memory barriers. */ wake_up_var(inode_state_wait_address(inode, bit)); } struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } static inline void filemap_invalidate_lock(struct address_space *mapping) { down_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock(struct address_space *mapping) { up_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_lock_shared(struct address_space *mapping) { down_read(&mapping->invalidate_lock); } static inline int filemap_invalidate_trylock_shared( struct address_space *mapping) { return down_read_trylock(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock_shared( struct address_space *mapping) { up_read(&mapping->invalidate_lock); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else /* Pairs with smp_store_release() in i_size_write() */ return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else /* * Pairs with smp_load_acquire() in i_size_read() to ensure * changes related to inode size (such as page contents) are * visible before we see the changed inode size. */ smp_store_release(&inode->i_size, i_size); #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /** * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. * @async_size: Numer of pages that were/are not needed immediately * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * * When this structure is passed to ->readahead(), the "most recent" * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; unsigned int size; unsigned int async_size; unsigned int ra_pages; unsigned int mmap_miss; loff_t prev_pos; }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } /** * struct file - Represents a file * @f_ref: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations * @f_mapping: Contents of a cacheable, mappable object. * @private_data: filesystem or driver specific data * @f_inode: cached inode * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener * @f_path: path of the file * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file * @f_owner: file owner * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file * @f_task_work: task work entry point * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; struct address_space *f_mapping; void *private_data; struct inode *f_inode; unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; /* --- cacheline 1 boundary (64 bytes) --- */ struct path f_path; union { /* regular files (with FMODE_ATOMIC_POS) and directories */ struct mutex f_pos_lock; /* pipes */ u64 f_pipe; }; loff_t f_pos; #ifdef CONFIG_SECURITY void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL struct hlist_head *f_ep; #endif union { struct callback_head f_task_work; struct llist_node f_llist; struct file_ra_state f_ra; freeptr_t f_freeptr; }; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { file_ref_inc(&f->f_ref); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); #define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) #define OFFT_OFFSET_MAX type_max(off_t) #endif int file_f_owner_allocate(struct file *file); static inline struct fown_struct *file_f_owner(const struct file *file) { return READ_ONCE(file->f_owner); } extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } /* * file_dentry() is a relic from the days that overlayfs was using files with a * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. * In those days, file_dentry() was needed to get the underlying fs dentry that * matches f_inode. * Files with "fake" path should not exist nowadays, so use an assertion to make * sure that file_dentry() was not papering over filesystem bugs. */ static inline struct dentry *file_dentry(const struct file *file) { struct dentry *dentry = file->f_path.dentry; WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); return dentry; } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_DEAD BIT(21) #define SB_DYING BIT(24) #define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler * const *s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ struct file *s_bdev_file; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif /* * q: why are s_id and s_sysfs_name not the same? both are human * readable strings that identify the filesystem * a: s_id is allowed to change at runtime; it's used in log messages, * and we want to when a device starts out as single device (s_id is dev * name) but then a device is hot added and we have to switch to * identifying it by UUID * but s_sysfs_name is a handle for programmatic access, and can't * change at runtime */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; } /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_uid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_uid field needs to be updated, false if not. */ static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_gid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_gid field needs to be updated, false if not. */ static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && kgid_has_mapping(fs_userns, kgid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), .tv_nsec = inode_get_atime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_atime_sec = ts.tv_sec; inode->i_atime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_atime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), .tv_nsec = inode_get_mtime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_mtime_sec = ts.tv_sec; inode->i_mtime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_mtime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_mtime_to_ts(inode, ts); } /* * Multigrain timestamps * * Conditionally use fine-grained ctime and mtime timestamps when there * are users actively observing them via getattr. The primary use-case * for this is NFS clients that use the ctime to distinguish between * different states of the file, and that are often fooled by multiple * operations that occur in the same coarse-grained timer tick. */ #define I_CTIME_QUERIED ((u32)BIT(31)) static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), .tv_nsec = inode_get_ctime_nsec(inode) }; return ts; } struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } struct timespec64 simple_inode_init_ts(struct inode *inode); /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read(sb->s_writers.rw_sem + level - 1); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held * @sb: the super we write to * @level: the freeze level * * * > 0 - sb freeze level is held * * 0 - sb freeze level is not held * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN */ static inline int __sb_write_started(const struct super_block *sb, int level) { return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); } /** * sb_write_started - check if SB_FREEZE_WRITE is held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE); } /** * sb_write_not_started - check if SB_FREEZE_WRITE is not held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_not_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; } /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_started(file_inode(file)->i_sb); } /** * file_write_not_started - check if SB_FREEZE_WRITE is not held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_not_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_not_started(file_inode(file)->i_sb); } /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); int vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming * @old_mnt_idmap: idmap of the old mount the inode was found from * @old_dir: parent of source * @old_dentry: source * @new_mnt_idmap: idmap of the new mount the inode was found from * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *old_mnt_idmap; struct inode *old_dir; struct dentry *old_dentry; struct mnt_idmap *new_mnt_idmap; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; }; /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct io_uring_cmd; struct offset_ctx; typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); } __randomize_layout; /* Supports async buffered reads */ #define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) /* Supports async buffered writes */ #define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) /* Supports synchronous page faults for mappings */ #define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) /* Supports non-exclusive O_DIRECT writes from multiple threads */ #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Treat loff_t as unsigned (e.g., /dev/mem) */ #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* File system supports uncached read/write buffered IO */ #define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); #define WRAP_DIR_ITER(x) \ static int shared_##x(struct file *file , struct dir_context *ctx) \ { return wrap_directory_iterator(file, ctx, x); } struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); /** * enum freeze_holder - holder of the freeze * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the * same holder aren't allowed. It is however allowed to hold a single * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at * the same time. This is relied upon by some filesystems during online * repair or similar. */ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), }; struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *, enum freeze_holder who); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *, enum freeze_holder who); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); void (*shutdown)(struct super_block *sb); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #else #define IS_POSIXACL(inode) 0 #endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #else #define IS_SWAPFILE(inode) ((void)(inode), 0U) #endif #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } /* * Inode state bits. Protected by inode->i_lock * * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync() (unless I_DIRTY_DATASYNC is also set). * Timestamp updates are the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already * in place because writeback might already be in progress * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? * * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait * upon. There's one free address left. */ #define __I_NEW 0 #define I_NEW (1 << __I_NEW) #define __I_SYNC 1 #define I_SYNC (1 << __I_SYNC) #define __I_LRU_ISOLATING 2 #define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_SYNC (1 << 3) #define I_DIRTY_DATASYNC (1 << 4) #define I_DIRTY_PAGES (1 << 5) #define I_WILL_FREE (1 << 6) #define I_FREEING (1 << 7) #define I_CLEAR (1 << 8) #define I_REFERENCED (1 << 9) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 12) #define I_OVL_INUSE (1 << 13) #define I_CREATING (1 << 14) #define I_DONTCACHE (1 << 15) #define I_SYNC_QUEUED (1 << 16) #define I_PINNING_NETFS_WB (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. * Filesystems should call this if when writing an inode when lazytime is * enabled, they want to opportunistically write the timestamps of other inodes * located very nearby on-disk, e.g. in the same inode block. This returns true * if the given inode is in need of such an opportunistic update. Requires * i_lock, or at least later re-checking under i_lock. */ static inline bool inode_is_dirtytime_only(struct inode *inode) { return (inode->i_state & (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) /** * is_mgtime: is this inode using multigrain timestamps * @inode: inode to test for multigrain timestamps * * Return true if the inode uses multigrain timestamps, false otherwise. */ static inline bool is_mgtime(const struct inode *inode) { return inode->i_opflags & IOP_MGTIME; } extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) ({ \ const struct file_operations *_fops = (fops); \ (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ }) #define fops_put(fops) ({ \ const struct file_operations *_fops = (fops); \ if (_fops) \ module_put((_fops)->owner); \ }) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); int freeze_super(struct super_block *super, enum freeze_holder who); int thaw_super(struct super_block *super, enum freeze_holder who); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { if (WARN_ON(len > sizeof(sb->s_uuid))) len = sizeof(sb->s_uuid); sb->s_uuid_len = len; memcpy(&sb->s_uuid, uuid, len); } /* set sb sysfs name based on sb->s_bdev */ static inline void super_set_sysfs_name_bdev(struct super_block *sb) { snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } /* set sb sysfs name based on sb->s_uuid */ static inline void super_set_sysfs_name_uuid(struct super_block *sb) { WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } /* set sb sysfs name based on sb->s_id */ static inline void super_set_sysfs_name_id(struct super_block *sb) { strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } /* try to use something standard before you use this */ __printf(2, 3) static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); va_end(args); } extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { return mnt_idmap(mnt) != &nop_mnt_idmap; } extern long vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, const char *, int, umode_t); static inline struct file *file_open_root_mnt(struct vfsmount *mnt, const char *name, int flags, umode_t mode) { return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); struct path *backing_file_user_path(struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying * filesystem. When the mapped file path and inode number are displayed to * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the * path and inode number to display to the user, which is the path of the fd * that user has requested to map and the inode number that would be returned * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ static inline const struct inode *file_user_inode(struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); return file_inode(f); } static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) { if (!(flags & AT_EMPTY_PATH)) return getname(name); if (!name) return NULL; return __getname_maybe_null(name); } extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* Helper for the simple case when original dentry is used */ static inline int finish_open_simple(struct file *file, int error) { if (error) return error; return finish_open(file, file->f_path.dentry, NULL); } /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); static inline bool iocb_is_dsync(const struct kiocb *iocb) { return (iocb->ki_flags & IOCB_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host); } /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; filemap_fdatawrite_range_kick(mapping, iocb->ki_pos, iocb->ki_pos + count); } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } /** * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * * This is a variant of sb_start_write() which is a noop on non-regualr file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } /** * file_end_write - drop write access to a superblock of a regular file * @file: the file we wrote to * * Should be matched with a call to file_start_write(). */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_end_write(file_inode(file)->i_sb); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } /* * This is used for regular files where some users -- especially the * currently executed binary in a process, previously handled via * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap * read-write shared) accesses. * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * deny_write_access() denies write access to a file. * allow_write_access() re-enables write access to a file. * * The i_writecount field of an inode can have the following values: * 0: no write access, no denied write access * < 0: (-i_writecount) users that denied write access to the file. * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } /* * Do not prevent write to executable file when watched by pre-content events. * * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at * the time of file open and remains constant for entire lifetime of the file, * so if pre-content watches are added post execution or removed before the end * of the execution, it will not cause i_writecount reference leak. */ static inline int exe_file_deny_write_access(struct file *exe_file) { if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return 0; return deny_write_access(exe_file); } static inline void exe_file_allow_write_access(struct file *exe_file) { if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return; allow_write_access(exe_file); } static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) { file->f_mode &= ~FMODE_FSNOTIFY_MASK; file->f_mode |= mode; } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); /** * is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ static inline bool is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); } #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t); static inline int inode_init_always(struct super_block *sb, struct inode *inode) { return inode_init_always_gfp(sb, inode, GFP_NOFS); } extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); struct inode *iget5_locked_rcu(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } /* * inode->i_lock must be held */ static inline void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ #define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { struct maple_tree mt; unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void simple_offset_destroy(struct offset_ctx *octx); extern const struct file_operations simple_offset_dir_operations; extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); extern int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); #if IS_ENABLED(CONFIG_UNICODE) int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); /** * generic_ci_validate_strict_name - Check if a given name is suitable * for a directory * * This functions checks if the proposed filename is valid for the * parent directory. That means that only valid UTF-8 filenames will be * accepted for casefold directories from filesystems created with the * strict encoding flag. That also means that any name will be * accepted for directories that doesn't have casefold enabled, or * aren't being strict with the encoding. * * @dir: inode of the directory where the new file will be created * @name: name of the new file * * Return: * * True: if the filename is suitable for this directory. It can be * true if a given name is not suitable for a strict encoding * directory, but the directory being used isn't strict * * False if the filename isn't suitable for this directory. This only * happens when a directory is casefolded and the filesystem is strict * about its encoding. */ static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) { if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) return true; /* * A casefold dir must have a encoding set, unless the filesystem * is corrupted */ if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) return true; return !utf8_validate(dir->i_sb->s_encoding, name); } #else static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) { return true; } #endif static inline bool sb_has_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) return !!sb->s_encoding; #else return false; #endif } int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, int rw_type) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; } if (flags & RWF_ATOMIC) { if (rw_type != WRITE) return -EOPNOTSUPP; if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } if (flags & RWF_DONTCACHE) { /* file system must support it */ if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) return -EOPNOTSUPP; /* DAX mappings not supported */ if (IS_DAX(ki->ki_filp->f_mapping->host)) return -EOPNOTSUPP; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { if (IS_APPEND(file_inode(ki->ki_filp))) return -EPERM; ki->ki_flags &= ~IOCB_APPEND; } ki->ki_flags |= kiocb_flags; return 0; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); static inline bool vfs_empty_path(int dfd, const char __user *path) { char c; if (dfd < 0) return false; /* We now allow NULL to be used for empty path. */ if (!path) return true; if (unlikely(get_user(c, path))) return false; return !c; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); #endif /* _LINUX_FS_H */ |
| 3 1 1 10 7 3 2 6 2 8 6 8 1 1 7 3 30 2 3 12 1 12 12 10 2 19 5 14 14 6 6 1 3 1 1 9 68 36 35 20 48 35 6 17 6 2 7 15 75 28 60 75 141 137 5 141 1 1 10 5 5 2 1 56 53 3 2 21 10 3 42 2 42 1 29 11 19 2 19 34 4 9 30 22 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/file.c * * Written 1992,1993 by Werner Almesberger * * regular file handling primitives for fat-based filesystems */ #include <linux/capability.h> #include <linux/module.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/falloc.h> #include "fat.h" static long fat_fallocate(struct file *file, int mode, loff_t offset, loff_t len); static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr) { u32 attr; inode_lock_shared(inode); attr = fat_make_attrs(inode); inode_unlock_shared(inode); return put_user(attr, user_attr); } static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) { struct inode *inode = file_inode(file); struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int is_dir = S_ISDIR(inode->i_mode); u32 attr, oldattr; struct iattr ia; int err; err = get_user(attr, user_attr); if (err) goto out; err = mnt_want_write_file(file); if (err) goto out; inode_lock(inode); /* * ATTR_VOLUME and ATTR_DIR cannot be changed; this also * prevents the user from turning us into a VFAT * longname entry. Also, we obviously can't set * any of the NTFS attributes in the high 24 bits. */ attr &= 0xff & ~(ATTR_VOLUME | ATTR_DIR); /* Merge in ATTR_VOLUME and ATTR_DIR */ attr |= (MSDOS_I(inode)->i_attrs & ATTR_VOLUME) | (is_dir ? ATTR_DIR : 0); oldattr = fat_make_attrs(inode); /* Equivalent to a chmod() */ ia.ia_valid = ATTR_MODE | ATTR_CTIME; ia.ia_ctime = current_time(inode); if (is_dir) ia.ia_mode = fat_make_mode(sbi, attr, S_IRWXUGO); else { ia.ia_mode = fat_make_mode(sbi, attr, S_IRUGO | S_IWUGO | (inode->i_mode & S_IXUGO)); } /* The root directory has no attributes */ if (inode->i_ino == MSDOS_ROOT_INO && attr != ATTR_DIR) { err = -EINVAL; goto out_unlock_inode; } if (sbi->options.sys_immutable && ((attr | oldattr) & ATTR_SYS) && !capable(CAP_LINUX_IMMUTABLE)) { err = -EPERM; goto out_unlock_inode; } /* * The security check is questionable... We single * out the RO attribute for checking by the security * module, just because it maps to a file mode. */ err = security_inode_setattr(file_mnt_idmap(file), file->f_path.dentry, &ia); if (err) goto out_unlock_inode; /* This MUST be done before doing anything irreversible... */ err = fat_setattr(file_mnt_idmap(file), file->f_path.dentry, &ia); if (err) goto out_unlock_inode; fsnotify_change(file->f_path.dentry, ia.ia_valid); if (sbi->options.sys_immutable) { if (attr & ATTR_SYS) inode->i_flags |= S_IMMUTABLE; else inode->i_flags &= ~S_IMMUTABLE; } fat_save_attrs(inode, attr); mark_inode_dirty(inode); out_unlock_inode: inode_unlock(inode); mnt_drop_write_file(file); out: return err; } static int fat_ioctl_get_volume_id(struct inode *inode, u32 __user *user_attr) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); return put_user(sbi->vol_id, user_attr); } static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg) { struct super_block *sb = inode->i_sb; struct fstrim_range __user *user_range; struct fstrim_range range; int err; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; user_range = (struct fstrim_range __user *)arg; if (copy_from_user(&range, user_range, sizeof(range))) return -EFAULT; range.minlen = max_t(unsigned int, range.minlen, bdev_discard_granularity(sb->s_bdev)); err = fat_trim_fs(inode, &range); if (err < 0) return err; if (copy_to_user(user_range, &range, sizeof(range))) return -EFAULT; return 0; } long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); u32 __user *user_attr = (u32 __user *)arg; switch (cmd) { case FAT_IOCTL_GET_ATTRIBUTES: return fat_ioctl_get_attributes(inode, user_attr); case FAT_IOCTL_SET_ATTRIBUTES: return fat_ioctl_set_attributes(filp, user_attr); case FAT_IOCTL_GET_VOLUME_ID: return fat_ioctl_get_volume_id(inode, user_attr); case FITRIM: return fat_ioctl_fitrim(inode, arg); default: return -ENOTTY; /* Inappropriate ioctl for device */ } } static int fat_file_release(struct inode *inode, struct file *filp) { if ((filp->f_mode & FMODE_WRITE) && MSDOS_SB(inode->i_sb)->options.flush) { fat_flush_inodes(inode->i_sb, inode, NULL); set_current_state(TASK_UNINTERRUPTIBLE); io_schedule_timeout(HZ/10); } return 0; } int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { struct inode *inode = filp->f_mapping->host; int err; err = __generic_file_fsync(filp, start, end, datasync); if (err) return err; err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); if (err) return err; return blkdev_issue_flush(inode->i_sb->s_bdev); } const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .release = fat_file_release, .unlocked_ioctl = fat_generic_ioctl, .compat_ioctl = compat_ptr_ioctl, .fsync = fat_file_fsync, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fallocate = fat_fallocate, }; static int fat_cont_expand(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; loff_t start = inode->i_size, count = size - inode->i_size; int err; err = generic_cont_expand_simple(inode, size); if (err) goto out; fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); mark_inode_dirty(inode); if (IS_SYNC(inode)) { int err2; /* * Opencode syncing since we don't have a file open to use * standard fsync path. */ err = filemap_fdatawrite_range(mapping, start, start + count - 1); err2 = sync_mapping_buffers(mapping); if (!err) err = err2; err2 = write_inode_now(inode, 1); if (!err) err = err2; if (!err) { err = filemap_fdatawait_range(mapping, start, start + count - 1); } } out: return err; } /* * Preallocate space for a file. This implements fat's fallocate file * operation, which gets called from sys_fallocate system call. User * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set * we just allocate clusters without zeroing them out. Otherwise we * allocate and zero out clusters via an expanding truncate. */ static long fat_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { int nr_cluster; /* Number of clusters to be allocated */ loff_t mm_bytes; /* Number of bytes to be allocated for file */ loff_t ondisksize; /* block aligned on-disk size in bytes*/ struct inode *inode = file->f_mapping->host; struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); int err = 0; /* No support for hole punch or other fallocate flags. */ if (mode & ~FALLOC_FL_KEEP_SIZE) return -EOPNOTSUPP; /* No support for dir */ if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; inode_lock(inode); if (mode & FALLOC_FL_KEEP_SIZE) { ondisksize = inode->i_blocks << 9; if ((offset + len) <= ondisksize) goto error; /* First compute the number of clusters to be allocated */ mm_bytes = offset + len - ondisksize; nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >> sbi->cluster_bits; /* Start the allocation.We are not zeroing out the clusters */ while (nr_cluster-- > 0) { err = fat_add_cluster(inode); if (err) goto error; } } else { if ((offset + len) <= i_size_read(inode)) goto error; /* This is just an expanding truncate */ err = fat_cont_expand(inode, (offset + len)); } error: inode_unlock(inode); return err; } /* Free all clusters after the skip'th cluster. */ static int fat_free(struct inode *inode, int skip) { struct super_block *sb = inode->i_sb; int err, wait, free_start, i_start, i_logstart; if (MSDOS_I(inode)->i_start == 0) return 0; fat_cache_inval_inode(inode); wait = IS_DIRSYNC(inode); i_start = free_start = MSDOS_I(inode)->i_start; i_logstart = MSDOS_I(inode)->i_logstart; /* First, we write the new file size. */ if (!skip) { MSDOS_I(inode)->i_start = 0; MSDOS_I(inode)->i_logstart = 0; } MSDOS_I(inode)->i_attrs |= ATTR_ARCH; fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); if (wait) { err = fat_sync_inode(inode); if (err) { MSDOS_I(inode)->i_start = i_start; MSDOS_I(inode)->i_logstart = i_logstart; return err; } } else mark_inode_dirty(inode); /* Write a new EOF, and get the remaining cluster chain for freeing. */ if (skip) { struct fat_entry fatent; int ret, fclus, dclus; ret = fat_get_cluster(inode, skip - 1, &fclus, &dclus); if (ret < 0) return ret; else if (ret == FAT_ENT_EOF) return 0; fatent_init(&fatent); ret = fat_ent_read(inode, &fatent, dclus); if (ret == FAT_ENT_EOF) { fatent_brelse(&fatent); return 0; } else if (ret == FAT_ENT_FREE) { fat_fs_error(sb, "%s: invalid cluster chain (i_pos %lld)", __func__, MSDOS_I(inode)->i_pos); ret = -EIO; } else if (ret > 0) { err = fat_ent_write(inode, &fatent, FAT_ENT_EOF, wait); if (err) ret = err; } fatent_brelse(&fatent); if (ret < 0) return ret; free_start = ret; } inode->i_blocks = skip << (MSDOS_SB(sb)->cluster_bits - 9); /* Freeing the remained cluster chain */ return fat_free_clusters(inode, free_start); } void fat_truncate_blocks(struct inode *inode, loff_t offset) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); const unsigned int cluster_size = sbi->cluster_size; int nr_clusters; /* * This protects against truncating a file bigger than it was then * trying to write into the hole. */ if (MSDOS_I(inode)->mmu_private > offset) MSDOS_I(inode)->mmu_private = offset; nr_clusters = (offset + (cluster_size - 1)) >> sbi->cluster_bits; fat_free(inode, nr_clusters); fat_flush_inodes(inode->i_sb, inode, NULL); } int fat_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); generic_fillattr(idmap, request_mask, inode, stat); stat->blksize = sbi->cluster_size; if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) { /* Use i_pos for ino. This is used as fileid of nfs. */ stat->ino = fat_i_pos_read(sbi, inode); } if (sbi->options.isvfat && request_mask & STATX_BTIME) { stat->result_mask |= STATX_BTIME; stat->btime = MSDOS_I(inode)->i_crtime; } return 0; } EXPORT_SYMBOL_GPL(fat_getattr); static int fat_sanitize_mode(const struct msdos_sb_info *sbi, struct inode *inode, umode_t *mode_ptr) { umode_t mask, perm; /* * Note, the basic check is already done by a caller of * (attr->ia_mode & ~FAT_VALID_MODE) */ if (S_ISREG(inode->i_mode)) mask = sbi->options.fs_fmask; else mask = sbi->options.fs_dmask; perm = *mode_ptr & ~(S_IFMT | mask); /* * Of the r and x bits, all (subject to umask) must be present. Of the * w bits, either all (subject to umask) or none must be present. * * If fat_mode_can_hold_ro(inode) is false, can't change w bits. */ if ((perm & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO))) return -EPERM; if (fat_mode_can_hold_ro(inode)) { if ((perm & S_IWUGO) && ((perm & S_IWUGO) != (S_IWUGO & ~mask))) return -EPERM; } else { if ((perm & S_IWUGO) != (S_IWUGO & ~mask)) return -EPERM; } *mode_ptr &= S_IFMT | perm; return 0; } static int fat_allow_set_time(struct mnt_idmap *idmap, struct msdos_sb_info *sbi, struct inode *inode) { umode_t allow_utime = sbi->options.allow_utime; if (!vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid())) { if (vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode))) allow_utime >>= 3; if (allow_utime & MAY_WRITE) return 1; } /* use a default check */ return 0; } #define TIMES_SET_FLAGS (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET) /* valid file mode bits */ #define FAT_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXUGO) int fat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); struct inode *inode = d_inode(dentry); unsigned int ia_valid; int error; /* Check for setting the inode time. */ ia_valid = attr->ia_valid; if (ia_valid & TIMES_SET_FLAGS) { if (fat_allow_set_time(idmap, sbi, inode)) attr->ia_valid &= ~TIMES_SET_FLAGS; } error = setattr_prepare(idmap, dentry, attr); attr->ia_valid = ia_valid; if (error) { if (sbi->options.quiet) error = 0; goto out; } /* * Expand the file. Since inode_setattr() updates ->i_size * before calling the ->truncate(), but FAT needs to fill the * hole before it. XXX: this is no longer true with new truncate * sequence. */ if (attr->ia_valid & ATTR_SIZE) { inode_dio_wait(inode); if (attr->ia_size > inode->i_size) { error = fat_cont_expand(inode, attr->ia_size); if (error || attr->ia_valid == ATTR_SIZE) goto out; attr->ia_valid &= ~ATTR_SIZE; } } if (((attr->ia_valid & ATTR_UID) && (!uid_eq(from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid), sbi->options.fs_uid))) || ((attr->ia_valid & ATTR_GID) && (!gid_eq(from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid), sbi->options.fs_gid))) || ((attr->ia_valid & ATTR_MODE) && (attr->ia_mode & ~FAT_VALID_MODE))) error = -EPERM; if (error) { if (sbi->options.quiet) error = 0; goto out; } /* * We don't return -EPERM here. Yes, strange, but this is too * old behavior. */ if (attr->ia_valid & ATTR_MODE) { if (fat_sanitize_mode(sbi, inode, &attr->ia_mode) < 0) attr->ia_valid &= ~ATTR_MODE; } if (attr->ia_valid & ATTR_SIZE) { error = fat_block_truncate_page(inode, attr->ia_size); if (error) goto out; down_write(&MSDOS_I(inode)->truncate_lock); truncate_setsize(inode, attr->ia_size); fat_truncate_blocks(inode, attr->ia_size); up_write(&MSDOS_I(inode)->truncate_lock); } /* * setattr_copy can't truncate these appropriately, so we'll * copy them ourselves */ if (attr->ia_valid & ATTR_ATIME) fat_truncate_time(inode, &attr->ia_atime, S_ATIME); if (attr->ia_valid & ATTR_CTIME) fat_truncate_time(inode, &attr->ia_ctime, S_CTIME); if (attr->ia_valid & ATTR_MTIME) fat_truncate_time(inode, &attr->ia_mtime, S_MTIME); attr->ia_valid &= ~(ATTR_ATIME|ATTR_CTIME|ATTR_MTIME); setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); out: return error; } EXPORT_SYMBOL_GPL(fat_setattr); const struct inode_operations fat_file_inode_operations = { .setattr = fat_setattr, .getattr = fat_getattr, .update_time = fat_update_time, }; |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Mirics MSi001 silicon tuner driver * * Copyright (C) 2013 Antti Palosaari <crope@iki.fi> * Copyright (C) 2014 Antti Palosaari <crope@iki.fi> */ #include <linux/module.h> #include <linux/gcd.h> #include <media/v4l2-device.h> #include <media/v4l2-ctrls.h> static const struct v4l2_frequency_band bands[] = { { .type = V4L2_TUNER_RF, .index = 0, .capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS, .rangelow = 49000000, .rangehigh = 263000000, }, { .type = V4L2_TUNER_RF, .index = 1, .capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS, .rangelow = 390000000, .rangehigh = 960000000, }, }; struct msi001_dev { struct spi_device *spi; struct v4l2_subdev sd; /* Controls */ struct v4l2_ctrl_handler hdl; struct v4l2_ctrl *bandwidth_auto; struct v4l2_ctrl *bandwidth; struct v4l2_ctrl *lna_gain; struct v4l2_ctrl *mixer_gain; struct v4l2_ctrl *if_gain; unsigned int f_tuner; }; static inline struct msi001_dev *sd_to_msi001_dev(struct v4l2_subdev *sd) { return container_of(sd, struct msi001_dev, sd); } static int msi001_wreg(struct msi001_dev *dev, u32 data) { /* Register format: 4 bits addr + 20 bits value */ return spi_write(dev->spi, &data, 3); }; static int msi001_set_gain(struct msi001_dev *dev, int lna_gain, int mixer_gain, int if_gain) { struct spi_device *spi = dev->spi; int ret; u32 reg; dev_dbg(&spi->dev, "lna=%d mixer=%d if=%d\n", lna_gain, mixer_gain, if_gain); reg = 1 << 0; reg |= (59 - if_gain) << 4; reg |= 0 << 10; reg |= (1 - mixer_gain) << 12; reg |= (1 - lna_gain) << 13; reg |= 4 << 14; reg |= 0 << 17; ret = msi001_wreg(dev, reg); if (ret) goto err; return 0; err: dev_dbg(&spi->dev, "failed %d\n", ret); return ret; }; static int msi001_set_tuner(struct msi001_dev *dev) { struct spi_device *spi = dev->spi; int ret, i; unsigned int uitmp, div_n, k, k_thresh, k_frac, div_lo, f_if1; u32 reg; u64 f_vco; u8 mode, filter_mode; static const struct { u32 rf; u8 mode; u8 div_lo; } band_lut[] = { { 50000000, 0xe1, 16}, /* AM_MODE2, antenna 2 */ {108000000, 0x42, 32}, /* VHF_MODE */ {330000000, 0x44, 16}, /* B3_MODE */ {960000000, 0x48, 4}, /* B45_MODE */ { ~0U, 0x50, 2}, /* BL_MODE */ }; static const struct { u32 freq; u8 filter_mode; } if_freq_lut[] = { { 0, 0x03}, /* Zero IF */ { 450000, 0x02}, /* 450 kHz IF */ {1620000, 0x01}, /* 1.62 MHz IF */ {2048000, 0x00}, /* 2.048 MHz IF */ }; static const struct { u32 freq; u8 val; } bandwidth_lut[] = { { 200000, 0x00}, /* 200 kHz */ { 300000, 0x01}, /* 300 kHz */ { 600000, 0x02}, /* 600 kHz */ {1536000, 0x03}, /* 1.536 MHz */ {5000000, 0x04}, /* 5 MHz */ {6000000, 0x05}, /* 6 MHz */ {7000000, 0x06}, /* 7 MHz */ {8000000, 0x07}, /* 8 MHz */ }; unsigned int f_rf = dev->f_tuner; /* * bandwidth (Hz) * 200000, 300000, 600000, 1536000, 5000000, 6000000, 7000000, 8000000 */ unsigned int bandwidth; /* * intermediate frequency (Hz) * 0, 450000, 1620000, 2048000 */ unsigned int f_if = 0; #define F_REF 24000000 #define DIV_PRE_N 4 #define F_VCO_STEP div_lo dev_dbg(&spi->dev, "f_rf=%d f_if=%d\n", f_rf, f_if); for (i = 0; i < ARRAY_SIZE(band_lut); i++) { if (f_rf <= band_lut[i].rf) { mode = band_lut[i].mode; div_lo = band_lut[i].div_lo; break; } } if (i == ARRAY_SIZE(band_lut)) { ret = -EINVAL; goto err; } /* AM_MODE is upconverted */ if ((mode >> 0) & 0x1) f_if1 = 5 * F_REF; else f_if1 = 0; for (i = 0; i < ARRAY_SIZE(if_freq_lut); i++) { if (f_if == if_freq_lut[i].freq) { filter_mode = if_freq_lut[i].filter_mode; break; } } if (i == ARRAY_SIZE(if_freq_lut)) { ret = -EINVAL; goto err; } /* filters */ bandwidth = dev->bandwidth->val; bandwidth = clamp(bandwidth, 200000U, 8000000U); for (i = 0; i < ARRAY_SIZE(bandwidth_lut); i++) { if (bandwidth <= bandwidth_lut[i].freq) { bandwidth = bandwidth_lut[i].val; break; } } if (i == ARRAY_SIZE(bandwidth_lut)) { ret = -EINVAL; goto err; } dev->bandwidth->val = bandwidth_lut[i].freq; dev_dbg(&spi->dev, "bandwidth selected=%d\n", bandwidth_lut[i].freq); /* * Fractional-N synthesizer * * +---------------------------------------+ * v | * Fref +----+ +-------+ +----+ +------+ +---+ * ------> | PD | --> | VCO | ------> | /4 | --> | /N.F | <-- | K | * +----+ +-------+ +----+ +------+ +---+ * | * | * v * +-------+ Fout * | /Rout | ------> * +-------+ */ /* Calculate PLL integer and fractional control word. */ f_vco = (u64) (f_rf + f_if + f_if1) * div_lo; div_n = div_u64_rem(f_vco, DIV_PRE_N * F_REF, &k); k_thresh = (DIV_PRE_N * F_REF) / F_VCO_STEP; k_frac = div_u64((u64) k * k_thresh, (DIV_PRE_N * F_REF)); /* Find out greatest common divisor and divide to smaller. */ uitmp = gcd(k_thresh, k_frac); k_thresh /= uitmp; k_frac /= uitmp; /* Force divide to reg max. Resolution will be reduced. */ uitmp = DIV_ROUND_UP(k_thresh, 4095); k_thresh = DIV_ROUND_CLOSEST(k_thresh, uitmp); k_frac = DIV_ROUND_CLOSEST(k_frac, uitmp); /* Calculate real RF set. */ uitmp = (unsigned int) F_REF * DIV_PRE_N * div_n; uitmp += (unsigned int) F_REF * DIV_PRE_N * k_frac / k_thresh; uitmp /= div_lo; dev_dbg(&spi->dev, "f_rf=%u:%u f_vco=%llu div_n=%u k_thresh=%u k_frac=%u div_lo=%u\n", f_rf, uitmp, f_vco, div_n, k_thresh, k_frac, div_lo); ret = msi001_wreg(dev, 0x00000e); if (ret) goto err; ret = msi001_wreg(dev, 0x000003); if (ret) goto err; reg = 0 << 0; reg |= mode << 4; reg |= filter_mode << 12; reg |= bandwidth << 14; reg |= 0x02 << 17; reg |= 0x00 << 20; ret = msi001_wreg(dev, reg); if (ret) goto err; reg = 5 << 0; reg |= k_thresh << 4; reg |= 1 << 19; reg |= 1 << 21; ret = msi001_wreg(dev, reg); if (ret) goto err; reg = 2 << 0; reg |= k_frac << 4; reg |= div_n << 16; ret = msi001_wreg(dev, reg); if (ret) goto err; ret = msi001_set_gain(dev, dev->lna_gain->cur.val, dev->mixer_gain->cur.val, dev->if_gain->cur.val); if (ret) goto err; reg = 6 << 0; reg |= 63 << 4; reg |= 4095 << 10; ret = msi001_wreg(dev, reg); if (ret) goto err; return 0; err: dev_dbg(&spi->dev, "failed %d\n", ret); return ret; } static int msi001_standby(struct v4l2_subdev *sd) { struct msi001_dev *dev = sd_to_msi001_dev(sd); return msi001_wreg(dev, 0x000000); } static int msi001_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *v) { struct msi001_dev *dev = sd_to_msi001_dev(sd); struct spi_device *spi = dev->spi; dev_dbg(&spi->dev, "index=%d\n", v->index); strscpy(v->name, "Mirics MSi001", sizeof(v->name)); v->type = V4L2_TUNER_RF; v->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS; v->rangelow = 49000000; v->rangehigh = 960000000; return 0; } static int msi001_s_tuner(struct v4l2_subdev *sd, const struct v4l2_tuner *v) { struct msi001_dev *dev = sd_to_msi001_dev(sd); struct spi_device *spi = dev->spi; dev_dbg(&spi->dev, "index=%d\n", v->index); return 0; } static int msi001_g_frequency(struct v4l2_subdev *sd, struct v4l2_frequency *f) { struct msi001_dev *dev = sd_to_msi001_dev(sd); struct spi_device *spi = dev->spi; dev_dbg(&spi->dev, "tuner=%d\n", f->tuner); f->frequency = dev->f_tuner; return 0; } static int msi001_s_frequency(struct v4l2_subdev *sd, const struct v4l2_frequency *f) { struct msi001_dev *dev = sd_to_msi001_dev(sd); struct spi_device *spi = dev->spi; unsigned int band; dev_dbg(&spi->dev, "tuner=%d type=%d frequency=%u\n", f->tuner, f->type, f->frequency); if (f->frequency < ((bands[0].rangehigh + bands[1].rangelow) / 2)) band = 0; else band = 1; dev->f_tuner = clamp_t(unsigned int, f->frequency, bands[band].rangelow, bands[band].rangehigh); return msi001_set_tuner(dev); } static int msi001_enum_freq_bands(struct v4l2_subdev *sd, struct v4l2_frequency_band *band) { struct msi001_dev *dev = sd_to_msi001_dev(sd); struct spi_device *spi = dev->spi; dev_dbg(&spi->dev, "tuner=%d type=%d index=%d\n", band->tuner, band->type, band->index); if (band->index >= ARRAY_SIZE(bands)) return -EINVAL; band->capability = bands[band->index].capability; band->rangelow = bands[band->index].rangelow; band->rangehigh = bands[band->index].rangehigh; return 0; } static const struct v4l2_subdev_tuner_ops msi001_tuner_ops = { .standby = msi001_standby, .g_tuner = msi001_g_tuner, .s_tuner = msi001_s_tuner, .g_frequency = msi001_g_frequency, .s_frequency = msi001_s_frequency, .enum_freq_bands = msi001_enum_freq_bands, }; static const struct v4l2_subdev_ops msi001_ops = { .tuner = &msi001_tuner_ops, }; static int msi001_s_ctrl(struct v4l2_ctrl *ctrl) { struct msi001_dev *dev = container_of(ctrl->handler, struct msi001_dev, hdl); struct spi_device *spi = dev->spi; int ret; dev_dbg(&spi->dev, "id=%d name=%s val=%d min=%lld max=%lld step=%lld\n", ctrl->id, ctrl->name, ctrl->val, ctrl->minimum, ctrl->maximum, ctrl->step); switch (ctrl->id) { case V4L2_CID_RF_TUNER_BANDWIDTH_AUTO: case V4L2_CID_RF_TUNER_BANDWIDTH: ret = msi001_set_tuner(dev); break; case V4L2_CID_RF_TUNER_LNA_GAIN: ret = msi001_set_gain(dev, dev->lna_gain->val, dev->mixer_gain->cur.val, dev->if_gain->cur.val); break; case V4L2_CID_RF_TUNER_MIXER_GAIN: ret = msi001_set_gain(dev, dev->lna_gain->cur.val, dev->mixer_gain->val, dev->if_gain->cur.val); break; case V4L2_CID_RF_TUNER_IF_GAIN: ret = msi001_set_gain(dev, dev->lna_gain->cur.val, dev->mixer_gain->cur.val, dev->if_gain->val); break; default: dev_dbg(&spi->dev, "unknown control %d\n", ctrl->id); ret = -EINVAL; } return ret; } static const struct v4l2_ctrl_ops msi001_ctrl_ops = { .s_ctrl = msi001_s_ctrl, }; static int msi001_probe(struct spi_device *spi) { struct msi001_dev *dev; int ret; dev_dbg(&spi->dev, "\n"); dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) { ret = -ENOMEM; goto err; } dev->spi = spi; dev->f_tuner = bands[0].rangelow; v4l2_spi_subdev_init(&dev->sd, spi, &msi001_ops); /* Register controls */ v4l2_ctrl_handler_init(&dev->hdl, 5); dev->bandwidth_auto = v4l2_ctrl_new_std(&dev->hdl, &msi001_ctrl_ops, V4L2_CID_RF_TUNER_BANDWIDTH_AUTO, 0, 1, 1, 1); dev->bandwidth = v4l2_ctrl_new_std(&dev->hdl, &msi001_ctrl_ops, V4L2_CID_RF_TUNER_BANDWIDTH, 200000, 8000000, 1, 200000); if (dev->hdl.error) { ret = dev->hdl.error; dev_err(&spi->dev, "Could not initialize controls\n"); /* control init failed, free handler */ goto err_ctrl_handler_free; } v4l2_ctrl_auto_cluster(2, &dev->bandwidth_auto, 0, false); dev->lna_gain = v4l2_ctrl_new_std(&dev->hdl, &msi001_ctrl_ops, V4L2_CID_RF_TUNER_LNA_GAIN, 0, 1, 1, 1); dev->mixer_gain = v4l2_ctrl_new_std(&dev->hdl, &msi001_ctrl_ops, V4L2_CID_RF_TUNER_MIXER_GAIN, 0, 1, 1, 1); dev->if_gain = v4l2_ctrl_new_std(&dev->hdl, &msi001_ctrl_ops, V4L2_CID_RF_TUNER_IF_GAIN, 0, 59, 1, 0); if (dev->hdl.error) { ret = dev->hdl.error; dev_err(&spi->dev, "Could not initialize controls\n"); /* control init failed, free handler */ goto err_ctrl_handler_free; } dev->sd.ctrl_handler = &dev->hdl; return 0; err_ctrl_handler_free: v4l2_ctrl_handler_free(&dev->hdl); kfree(dev); err: return ret; } static void msi001_remove(struct spi_device *spi) { struct v4l2_subdev *sd = spi_get_drvdata(spi); struct msi001_dev *dev = sd_to_msi001_dev(sd); dev_dbg(&spi->dev, "\n"); /* * Registered by v4l2_spi_new_subdev() from master driver, but we must * unregister it from here. Weird. */ v4l2_device_unregister_subdev(&dev->sd); v4l2_ctrl_handler_free(&dev->hdl); kfree(dev); } static const struct spi_device_id msi001_id_table[] = { {"msi001", 0}, {} }; MODULE_DEVICE_TABLE(spi, msi001_id_table); static struct spi_driver msi001_driver = { .driver = { .name = "msi001", .suppress_bind_attrs = true, }, .probe = msi001_probe, .remove = msi001_remove, .id_table = msi001_id_table, }; module_spi_driver(msi001_driver); MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>"); MODULE_DESCRIPTION("Mirics MSi001"); MODULE_LICENSE("GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * LED & force feedback support for BigBen Interactive * * 0x146b:0x0902 "Bigben Interactive Bigben Game Pad" * "Kid-friendly Wired Controller" PS3OFMINIPAD SONY * sold for use with the PS3 * * Copyright (c) 2018 Hanno Zulla <kontakt@hanno.de> */ #include <linux/input.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/leds.h> #include <linux/hid.h> #include "hid-ids.h" /* * The original descriptor for 0x146b:0x0902 * * 0x05, 0x01, // Usage Page (Generic Desktop Ctrls) * 0x09, 0x05, // Usage (Game Pad) * 0xA1, 0x01, // Collection (Application) * 0x15, 0x00, // Logical Minimum (0) * 0x25, 0x01, // Logical Maximum (1) * 0x35, 0x00, // Physical Minimum (0) * 0x45, 0x01, // Physical Maximum (1) * 0x75, 0x01, // Report Size (1) * 0x95, 0x0D, // Report Count (13) * 0x05, 0x09, // Usage Page (Button) * 0x19, 0x01, // Usage Minimum (0x01) * 0x29, 0x0D, // Usage Maximum (0x0D) * 0x81, 0x02, // Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) * 0x95, 0x03, // Report Count (3) * 0x81, 0x01, // Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) * 0x05, 0x01, // Usage Page (Generic Desktop Ctrls) * 0x25, 0x07, // Logical Maximum (7) * 0x46, 0x3B, 0x01, // Physical Maximum (315) * 0x75, 0x04, // Report Size (4) * 0x95, 0x01, // Report Count (1) * 0x65, 0x14, // Unit (System: English Rotation, Length: Centimeter) * 0x09, 0x39, // Usage (Hat switch) * 0x81, 0x42, // Input (Data,Var,Abs,No Wrap,Linear,Preferred State,Null State) * 0x65, 0x00, // Unit (None) * 0x95, 0x01, // Report Count (1) * 0x81, 0x01, // Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) * 0x26, 0xFF, 0x00, // Logical Maximum (255) * 0x46, 0xFF, 0x00, // Physical Maximum (255) * 0x09, 0x30, // Usage (X) * 0x09, 0x31, // Usage (Y) * 0x09, 0x32, // Usage (Z) * 0x09, 0x35, // Usage (Rz) * 0x75, 0x08, // Report Size (8) * 0x95, 0x04, // Report Count (4) * 0x81, 0x02, // Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) * 0x06, 0x00, 0xFF, // Usage Page (Vendor Defined 0xFF00) * 0x09, 0x20, // Usage (0x20) * 0x09, 0x21, // Usage (0x21) * 0x09, 0x22, // Usage (0x22) * 0x09, 0x23, // Usage (0x23) * 0x09, 0x24, // Usage (0x24) * 0x09, 0x25, // Usage (0x25) * 0x09, 0x26, // Usage (0x26) * 0x09, 0x27, // Usage (0x27) * 0x09, 0x28, // Usage (0x28) * 0x09, 0x29, // Usage (0x29) * 0x09, 0x2A, // Usage (0x2A) * 0x09, 0x2B, // Usage (0x2B) * 0x95, 0x0C, // Report Count (12) * 0x81, 0x02, // Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) * 0x0A, 0x21, 0x26, // Usage (0x2621) * 0x95, 0x08, // Report Count (8) * 0xB1, 0x02, // Feature (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position,Non-volatile) * 0x0A, 0x21, 0x26, // Usage (0x2621) * 0x91, 0x02, // Output (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position,Non-volatile) * 0x26, 0xFF, 0x03, // Logical Maximum (1023) * 0x46, 0xFF, 0x03, // Physical Maximum (1023) * 0x09, 0x2C, // Usage (0x2C) * 0x09, 0x2D, // Usage (0x2D) * 0x09, 0x2E, // Usage (0x2E) * 0x09, 0x2F, // Usage (0x2F) * 0x75, 0x10, // Report Size (16) * 0x95, 0x04, // Report Count (4) * 0x81, 0x02, // Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) * 0xC0, // End Collection */ #define PID0902_RDESC_ORIG_SIZE 137 /* * The fixed descriptor for 0x146b:0x0902 * * - map buttons according to gamepad.rst * - assign right stick from Z/Rz to Rx/Ry * - map previously unused analog trigger data to Z/RZ * - simplify feature and output descriptor */ static const __u8 pid0902_rdesc_fixed[] = { 0x05, 0x01, /* Usage Page (Generic Desktop Ctrls) */ 0x09, 0x05, /* Usage (Game Pad) */ 0xA1, 0x01, /* Collection (Application) */ 0x15, 0x00, /* Logical Minimum (0) */ 0x25, 0x01, /* Logical Maximum (1) */ 0x35, 0x00, /* Physical Minimum (0) */ 0x45, 0x01, /* Physical Maximum (1) */ 0x75, 0x01, /* Report Size (1) */ 0x95, 0x0D, /* Report Count (13) */ 0x05, 0x09, /* Usage Page (Button) */ 0x09, 0x05, /* Usage (BTN_WEST) */ 0x09, 0x01, /* Usage (BTN_SOUTH) */ 0x09, 0x02, /* Usage (BTN_EAST) */ 0x09, 0x04, /* Usage (BTN_NORTH) */ 0x09, 0x07, /* Usage (BTN_TL) */ 0x09, 0x08, /* Usage (BTN_TR) */ 0x09, 0x09, /* Usage (BTN_TL2) */ 0x09, 0x0A, /* Usage (BTN_TR2) */ 0x09, 0x0B, /* Usage (BTN_SELECT) */ 0x09, 0x0C, /* Usage (BTN_START) */ 0x09, 0x0E, /* Usage (BTN_THUMBL) */ 0x09, 0x0F, /* Usage (BTN_THUMBR) */ 0x09, 0x0D, /* Usage (BTN_MODE) */ 0x81, 0x02, /* Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0x75, 0x01, /* Report Size (1) */ 0x95, 0x03, /* Report Count (3) */ 0x81, 0x01, /* Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0x05, 0x01, /* Usage Page (Generic Desktop Ctrls) */ 0x25, 0x07, /* Logical Maximum (7) */ 0x46, 0x3B, 0x01, /* Physical Maximum (315) */ 0x75, 0x04, /* Report Size (4) */ 0x95, 0x01, /* Report Count (1) */ 0x65, 0x14, /* Unit (System: English Rotation, Length: Centimeter) */ 0x09, 0x39, /* Usage (Hat switch) */ 0x81, 0x42, /* Input (Data,Var,Abs,No Wrap,Linear,Preferred State,Null State) */ 0x65, 0x00, /* Unit (None) */ 0x95, 0x01, /* Report Count (1) */ 0x81, 0x01, /* Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0x26, 0xFF, 0x00, /* Logical Maximum (255) */ 0x46, 0xFF, 0x00, /* Physical Maximum (255) */ 0x09, 0x30, /* Usage (X) */ 0x09, 0x31, /* Usage (Y) */ 0x09, 0x33, /* Usage (Rx) */ 0x09, 0x34, /* Usage (Ry) */ 0x75, 0x08, /* Report Size (8) */ 0x95, 0x04, /* Report Count (4) */ 0x81, 0x02, /* Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0x95, 0x0A, /* Report Count (10) */ 0x81, 0x01, /* Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0x05, 0x01, /* Usage Page (Generic Desktop Ctrls) */ 0x26, 0xFF, 0x00, /* Logical Maximum (255) */ 0x46, 0xFF, 0x00, /* Physical Maximum (255) */ 0x09, 0x32, /* Usage (Z) */ 0x09, 0x35, /* Usage (Rz) */ 0x95, 0x02, /* Report Count (2) */ 0x81, 0x02, /* Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0x95, 0x08, /* Report Count (8) */ 0x81, 0x01, /* Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0x06, 0x00, 0xFF, /* Usage Page (Vendor Defined 0xFF00) */ 0xB1, 0x02, /* Feature (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position,Non-volatile) */ 0x0A, 0x21, 0x26, /* Usage (0x2621) */ 0x95, 0x08, /* Report Count (8) */ 0x91, 0x02, /* Output (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position,Non-volatile) */ 0x0A, 0x21, 0x26, /* Usage (0x2621) */ 0x95, 0x08, /* Report Count (8) */ 0x81, 0x02, /* Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) */ 0xC0, /* End Collection */ }; #define NUM_LEDS 4 struct bigben_device { struct hid_device *hid; struct hid_report *report; spinlock_t lock; bool removed; u8 led_state; /* LED1 = 1 .. LED4 = 8 */ u8 right_motor_on; /* right motor off/on 0/1 */ u8 left_motor_force; /* left motor force 0-255 */ struct led_classdev *leds[NUM_LEDS]; bool work_led; bool work_ff; struct work_struct worker; }; static inline void bigben_schedule_work(struct bigben_device *bigben) { unsigned long flags; spin_lock_irqsave(&bigben->lock, flags); if (!bigben->removed) schedule_work(&bigben->worker); spin_unlock_irqrestore(&bigben->lock, flags); } static void bigben_worker(struct work_struct *work) { struct bigben_device *bigben = container_of(work, struct bigben_device, worker); struct hid_field *report_field = bigben->report->field[0]; bool do_work_led = false; bool do_work_ff = false; u8 *buf; u32 len; unsigned long flags; buf = hid_alloc_report_buf(bigben->report, GFP_KERNEL); if (!buf) return; len = hid_report_len(bigben->report); /* LED work */ spin_lock_irqsave(&bigben->lock, flags); if (bigben->work_led) { bigben->work_led = false; do_work_led = true; report_field->value[0] = 0x01; /* 1 = led message */ report_field->value[1] = 0x08; /* reserved value, always 8 */ report_field->value[2] = bigben->led_state; report_field->value[3] = 0x00; /* padding */ report_field->value[4] = 0x00; /* padding */ report_field->value[5] = 0x00; /* padding */ report_field->value[6] = 0x00; /* padding */ report_field->value[7] = 0x00; /* padding */ hid_output_report(bigben->report, buf); } spin_unlock_irqrestore(&bigben->lock, flags); if (do_work_led) { hid_hw_raw_request(bigben->hid, bigben->report->id, buf, len, bigben->report->type, HID_REQ_SET_REPORT); } /* FF work */ spin_lock_irqsave(&bigben->lock, flags); if (bigben->work_ff) { bigben->work_ff = false; do_work_ff = true; report_field->value[0] = 0x02; /* 2 = rumble effect message */ report_field->value[1] = 0x08; /* reserved value, always 8 */ report_field->value[2] = bigben->right_motor_on; report_field->value[3] = bigben->left_motor_force; report_field->value[4] = 0xff; /* duration 0-254 (255 = nonstop) */ report_field->value[5] = 0x00; /* padding */ report_field->value[6] = 0x00; /* padding */ report_field->value[7] = 0x00; /* padding */ hid_output_report(bigben->report, buf); } spin_unlock_irqrestore(&bigben->lock, flags); if (do_work_ff) { hid_hw_raw_request(bigben->hid, bigben->report->id, buf, len, bigben->report->type, HID_REQ_SET_REPORT); } kfree(buf); } static int hid_bigben_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { struct hid_device *hid = input_get_drvdata(dev); struct bigben_device *bigben = hid_get_drvdata(hid); u8 right_motor_on; u8 left_motor_force; unsigned long flags; if (!bigben) { hid_err(hid, "no device data\n"); return 0; } if (effect->type != FF_RUMBLE) return 0; right_motor_on = effect->u.rumble.weak_magnitude ? 1 : 0; left_motor_force = effect->u.rumble.strong_magnitude / 256; if (right_motor_on != bigben->right_motor_on || left_motor_force != bigben->left_motor_force) { spin_lock_irqsave(&bigben->lock, flags); bigben->right_motor_on = right_motor_on; bigben->left_motor_force = left_motor_force; bigben->work_ff = true; spin_unlock_irqrestore(&bigben->lock, flags); bigben_schedule_work(bigben); } return 0; } static void bigben_set_led(struct led_classdev *led, enum led_brightness value) { struct device *dev = led->dev->parent; struct hid_device *hid = to_hid_device(dev); struct bigben_device *bigben = hid_get_drvdata(hid); int n; bool work; unsigned long flags; if (!bigben) { hid_err(hid, "no device data\n"); return; } for (n = 0; n < NUM_LEDS; n++) { if (led == bigben->leds[n]) { spin_lock_irqsave(&bigben->lock, flags); if (value == LED_OFF) { work = (bigben->led_state & BIT(n)); bigben->led_state &= ~BIT(n); } else { work = !(bigben->led_state & BIT(n)); bigben->led_state |= BIT(n); } spin_unlock_irqrestore(&bigben->lock, flags); if (work) { bigben->work_led = true; bigben_schedule_work(bigben); } return; } } } static enum led_brightness bigben_get_led(struct led_classdev *led) { struct device *dev = led->dev->parent; struct hid_device *hid = to_hid_device(dev); struct bigben_device *bigben = hid_get_drvdata(hid); int n; if (!bigben) { hid_err(hid, "no device data\n"); return LED_OFF; } for (n = 0; n < NUM_LEDS; n++) { if (led == bigben->leds[n]) return (bigben->led_state & BIT(n)) ? LED_ON : LED_OFF; } return LED_OFF; } static void bigben_remove(struct hid_device *hid) { struct bigben_device *bigben = hid_get_drvdata(hid); unsigned long flags; spin_lock_irqsave(&bigben->lock, flags); bigben->removed = true; spin_unlock_irqrestore(&bigben->lock, flags); cancel_work_sync(&bigben->worker); hid_hw_stop(hid); } static int bigben_probe(struct hid_device *hid, const struct hid_device_id *id) { struct bigben_device *bigben; struct hid_input *hidinput; struct led_classdev *led; char *name; size_t name_sz; int n, error; bigben = devm_kzalloc(&hid->dev, sizeof(*bigben), GFP_KERNEL); if (!bigben) return -ENOMEM; hid_set_drvdata(hid, bigben); bigben->hid = hid; bigben->removed = false; error = hid_parse(hid); if (error) { hid_err(hid, "parse failed\n"); return error; } error = hid_hw_start(hid, HID_CONNECT_DEFAULT & ~HID_CONNECT_FF); if (error) { hid_err(hid, "hw start failed\n"); return error; } bigben->report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 8); if (!bigben->report) { hid_err(hid, "no output report found\n"); error = -ENODEV; goto error_hw_stop; } if (list_empty(&hid->inputs)) { hid_err(hid, "no inputs found\n"); error = -ENODEV; goto error_hw_stop; } hidinput = list_first_entry(&hid->inputs, struct hid_input, list); set_bit(FF_RUMBLE, hidinput->input->ffbit); INIT_WORK(&bigben->worker, bigben_worker); spin_lock_init(&bigben->lock); error = input_ff_create_memless(hidinput->input, NULL, hid_bigben_play_effect); if (error) goto error_hw_stop; name_sz = strlen(dev_name(&hid->dev)) + strlen(":red:bigben#") + 1; for (n = 0; n < NUM_LEDS; n++) { led = devm_kzalloc( &hid->dev, sizeof(struct led_classdev) + name_sz, GFP_KERNEL ); if (!led) { error = -ENOMEM; goto error_hw_stop; } name = (void *)(&led[1]); snprintf(name, name_sz, "%s:red:bigben%d", dev_name(&hid->dev), n + 1 ); led->name = name; led->brightness = (n == 0) ? LED_ON : LED_OFF; led->max_brightness = 1; led->brightness_get = bigben_get_led; led->brightness_set = bigben_set_led; bigben->leds[n] = led; error = devm_led_classdev_register(&hid->dev, led); if (error) goto error_hw_stop; } /* initial state: LED1 is on, no rumble effect */ bigben->led_state = BIT(0); bigben->right_motor_on = 0; bigben->left_motor_force = 0; bigben->work_led = true; bigben->work_ff = true; bigben_schedule_work(bigben); hid_info(hid, "LED and force feedback support for BigBen gamepad\n"); return 0; error_hw_stop: hid_hw_stop(hid); return error; } static const __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc, unsigned int *rsize) { if (*rsize == PID0902_RDESC_ORIG_SIZE) { *rsize = sizeof(pid0902_rdesc_fixed); return pid0902_rdesc_fixed; } else hid_warn(hid, "unexpected rdesc, please submit for review\n"); return rdesc; } static const struct hid_device_id bigben_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_BIGBEN, USB_DEVICE_ID_BIGBEN_PS3OFMINIPAD) }, { } }; MODULE_DEVICE_TABLE(hid, bigben_devices); static struct hid_driver bigben_driver = { .name = "bigben", .id_table = bigben_devices, .probe = bigben_probe, .report_fixup = bigben_report_fixup, .remove = bigben_remove, }; module_hid_driver(bigben_driver); MODULE_DESCRIPTION("LED & force feedback support for BigBen Interactive"); MODULE_LICENSE("GPL"); |
| 20 20 19 27 26 27 20 20 20 20 18 27 27 27 27 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2017 Thomas Gleixner <tglx@linutronix.de> #include <linux/spinlock.h> #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/irq.h> struct cpumap { unsigned int available; unsigned int allocated; unsigned int managed; unsigned int managed_allocated; bool initialized; bool online; unsigned long *managed_map; unsigned long alloc_map[]; }; struct irq_matrix { unsigned int matrix_bits; unsigned int alloc_start; unsigned int alloc_end; unsigned int alloc_size; unsigned int global_available; unsigned int global_reserved; unsigned int systembits_inalloc; unsigned int total_allocated; unsigned int online_maps; struct cpumap __percpu *maps; unsigned long *system_map; unsigned long scratch_map[]; }; #define CREATE_TRACE_POINTS #include <trace/events/irq_matrix.h> /** * irq_alloc_matrix - Allocate a irq_matrix structure and initialize it * @matrix_bits: Number of matrix bits must be <= IRQ_MATRIX_BITS * @alloc_start: From which bit the allocation search starts * @alloc_end: At which bit the allocation search ends, i.e first * invalid bit */ __init struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits, unsigned int alloc_start, unsigned int alloc_end) { unsigned int cpu, matrix_size = BITS_TO_LONGS(matrix_bits); struct irq_matrix *m; m = kzalloc(struct_size(m, scratch_map, matrix_size * 2), GFP_KERNEL); if (!m) return NULL; m->system_map = &m->scratch_map[matrix_size]; m->matrix_bits = matrix_bits; m->alloc_start = alloc_start; m->alloc_end = alloc_end; m->alloc_size = alloc_end - alloc_start; m->maps = __alloc_percpu(struct_size(m->maps, alloc_map, matrix_size * 2), __alignof__(*m->maps)); if (!m->maps) { kfree(m); return NULL; } for_each_possible_cpu(cpu) { struct cpumap *cm = per_cpu_ptr(m->maps, cpu); cm->managed_map = &cm->alloc_map[matrix_size]; } return m; } /** * irq_matrix_online - Bring the local CPU matrix online * @m: Matrix pointer */ void irq_matrix_online(struct irq_matrix *m) { struct cpumap *cm = this_cpu_ptr(m->maps); BUG_ON(cm->online); if (!cm->initialized) { cm->available = m->alloc_size; cm->available -= cm->managed + m->systembits_inalloc; cm->initialized = true; } m->global_available += cm->available; cm->online = true; m->online_maps++; trace_irq_matrix_online(m); } /** * irq_matrix_offline - Bring the local CPU matrix offline * @m: Matrix pointer */ void irq_matrix_offline(struct irq_matrix *m) { struct cpumap *cm = this_cpu_ptr(m->maps); /* Update the global available size */ m->global_available -= cm->available; cm->online = false; m->online_maps--; trace_irq_matrix_offline(m); } static unsigned int matrix_alloc_area(struct irq_matrix *m, struct cpumap *cm, unsigned int num, bool managed) { unsigned int area, start = m->alloc_start; unsigned int end = m->alloc_end; bitmap_or(m->scratch_map, cm->managed_map, m->system_map, end); bitmap_or(m->scratch_map, m->scratch_map, cm->alloc_map, end); area = bitmap_find_next_zero_area(m->scratch_map, end, start, num, 0); if (area >= end) return area; if (managed) bitmap_set(cm->managed_map, area, num); else bitmap_set(cm->alloc_map, area, num); return area; } /* Find the best CPU which has the lowest vector allocation count */ static unsigned int matrix_find_best_cpu(struct irq_matrix *m, const struct cpumask *msk) { unsigned int cpu, best_cpu, maxavl = 0; struct cpumap *cm; best_cpu = UINT_MAX; for_each_cpu(cpu, msk) { cm = per_cpu_ptr(m->maps, cpu); if (!cm->online || cm->available <= maxavl) continue; best_cpu = cpu; maxavl = cm->available; } return best_cpu; } /* Find the best CPU which has the lowest number of managed IRQs allocated */ static unsigned int matrix_find_best_cpu_managed(struct irq_matrix *m, const struct cpumask *msk) { unsigned int cpu, best_cpu, allocated = UINT_MAX; struct cpumap *cm; best_cpu = UINT_MAX; for_each_cpu(cpu, msk) { cm = per_cpu_ptr(m->maps, cpu); if (!cm->online || cm->managed_allocated > allocated) continue; best_cpu = cpu; allocated = cm->managed_allocated; } return best_cpu; } /** * irq_matrix_assign_system - Assign system wide entry in the matrix * @m: Matrix pointer * @bit: Which bit to reserve * @replace: Replace an already allocated vector with a system * vector at the same bit position. * * The BUG_ON()s below are on purpose. If this goes wrong in the * early boot process, then the chance to survive is about zero. * If this happens when the system is life, it's not much better. */ void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace) { struct cpumap *cm = this_cpu_ptr(m->maps); BUG_ON(bit > m->matrix_bits); BUG_ON(m->online_maps > 1 || (m->online_maps && !replace)); set_bit(bit, m->system_map); if (replace) { BUG_ON(!test_and_clear_bit(bit, cm->alloc_map)); cm->allocated--; m->total_allocated--; } if (bit >= m->alloc_start && bit < m->alloc_end) m->systembits_inalloc++; trace_irq_matrix_assign_system(bit, m); } /** * irq_matrix_reserve_managed - Reserve a managed interrupt in a CPU map * @m: Matrix pointer * @msk: On which CPUs the bits should be reserved. * * Can be called for offline CPUs. Note, this will only reserve one bit * on all CPUs in @msk, but it's not guaranteed that the bits are at the * same offset on all CPUs */ int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk) { unsigned int cpu, failed_cpu; for_each_cpu(cpu, msk) { struct cpumap *cm = per_cpu_ptr(m->maps, cpu); unsigned int bit; bit = matrix_alloc_area(m, cm, 1, true); if (bit >= m->alloc_end) goto cleanup; cm->managed++; if (cm->online) { cm->available--; m->global_available--; } trace_irq_matrix_reserve_managed(bit, cpu, m, cm); } return 0; cleanup: failed_cpu = cpu; for_each_cpu(cpu, msk) { if (cpu == failed_cpu) break; irq_matrix_remove_managed(m, cpumask_of(cpu)); } return -ENOSPC; } /** * irq_matrix_remove_managed - Remove managed interrupts in a CPU map * @m: Matrix pointer * @msk: On which CPUs the bits should be removed * * Can be called for offline CPUs * * This removes not allocated managed interrupts from the map. It does * not matter which one because the managed interrupts free their * allocation when they shut down. If not, the accounting is screwed, * but all what can be done at this point is warn about it. */ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) { unsigned int cpu; for_each_cpu(cpu, msk) { struct cpumap *cm = per_cpu_ptr(m->maps, cpu); unsigned int bit, end = m->alloc_end; if (WARN_ON_ONCE(!cm->managed)) continue; /* Get managed bit which are not allocated */ bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); bit = find_first_bit(m->scratch_map, end); if (WARN_ON_ONCE(bit >= end)) continue; clear_bit(bit, cm->managed_map); cm->managed--; if (cm->online) { cm->available++; m->global_available++; } trace_irq_matrix_remove_managed(bit, cpu, m, cm); } } /** * irq_matrix_alloc_managed - Allocate a managed interrupt in a CPU map * @m: Matrix pointer * @msk: Which CPUs to search in * @mapped_cpu: Pointer to store the CPU for which the irq was allocated */ int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, unsigned int *mapped_cpu) { unsigned int bit, cpu, end; struct cpumap *cm; if (cpumask_empty(msk)) return -EINVAL; cpu = matrix_find_best_cpu_managed(m, msk); if (cpu == UINT_MAX) return -ENOSPC; cm = per_cpu_ptr(m->maps, cpu); end = m->alloc_end; /* Get managed bit which are not allocated */ bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); bit = find_first_bit(m->scratch_map, end); if (bit >= end) return -ENOSPC; set_bit(bit, cm->alloc_map); cm->allocated++; cm->managed_allocated++; m->total_allocated++; *mapped_cpu = cpu; trace_irq_matrix_alloc_managed(bit, cpu, m, cm); return bit; } /** * irq_matrix_assign - Assign a preallocated interrupt in the local CPU map * @m: Matrix pointer * @bit: Which bit to mark * * This should only be used to mark preallocated vectors */ void irq_matrix_assign(struct irq_matrix *m, unsigned int bit) { struct cpumap *cm = this_cpu_ptr(m->maps); if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end)) return; if (WARN_ON_ONCE(test_and_set_bit(bit, cm->alloc_map))) return; cm->allocated++; m->total_allocated++; cm->available--; m->global_available--; trace_irq_matrix_assign(bit, smp_processor_id(), m, cm); } /** * irq_matrix_reserve - Reserve interrupts * @m: Matrix pointer * * This is merely a book keeping call. It increments the number of globally * reserved interrupt bits w/o actually allocating them. This allows to * setup interrupt descriptors w/o assigning low level resources to it. * The actual allocation happens when the interrupt gets activated. */ void irq_matrix_reserve(struct irq_matrix *m) { if (m->global_reserved == m->global_available) pr_warn("Interrupt reservation exceeds available resources\n"); m->global_reserved++; trace_irq_matrix_reserve(m); } /** * irq_matrix_remove_reserved - Remove interrupt reservation * @m: Matrix pointer * * This is merely a book keeping call. It decrements the number of globally * reserved interrupt bits. This is used to undo irq_matrix_reserve() when the * interrupt was never in use and a real vector allocated, which undid the * reservation. */ void irq_matrix_remove_reserved(struct irq_matrix *m) { m->global_reserved--; trace_irq_matrix_remove_reserved(m); } /** * irq_matrix_alloc - Allocate a regular interrupt in a CPU map * @m: Matrix pointer * @msk: Which CPUs to search in * @reserved: Allocate previously reserved interrupts * @mapped_cpu: Pointer to store the CPU for which the irq was allocated */ int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, bool reserved, unsigned int *mapped_cpu) { unsigned int cpu, bit; struct cpumap *cm; /* * Not required in theory, but matrix_find_best_cpu() uses * for_each_cpu() which ignores the cpumask on UP . */ if (cpumask_empty(msk)) return -EINVAL; cpu = matrix_find_best_cpu(m, msk); if (cpu == UINT_MAX) return -ENOSPC; cm = per_cpu_ptr(m->maps, cpu); bit = matrix_alloc_area(m, cm, 1, false); if (bit >= m->alloc_end) return -ENOSPC; cm->allocated++; cm->available--; m->total_allocated++; m->global_available--; if (reserved) m->global_reserved--; *mapped_cpu = cpu; trace_irq_matrix_alloc(bit, cpu, m, cm); return bit; } /** * irq_matrix_free - Free allocated interrupt in the matrix * @m: Matrix pointer * @cpu: Which CPU map needs be updated * @bit: The bit to remove * @managed: If true, the interrupt is managed and not accounted * as available. */ void irq_matrix_free(struct irq_matrix *m, unsigned int cpu, unsigned int bit, bool managed) { struct cpumap *cm = per_cpu_ptr(m->maps, cpu); if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end)) return; if (WARN_ON_ONCE(!test_and_clear_bit(bit, cm->alloc_map))) return; cm->allocated--; if(managed) cm->managed_allocated--; if (cm->online) m->total_allocated--; if (!managed) { cm->available++; if (cm->online) m->global_available++; } trace_irq_matrix_free(bit, cpu, m, cm); } /** * irq_matrix_available - Get the number of globally available irqs * @m: Pointer to the matrix to query * @cpudown: If true, the local CPU is about to go down, adjust * the number of available irqs accordingly */ unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown) { struct cpumap *cm = this_cpu_ptr(m->maps); if (!cpudown) return m->global_available; return m->global_available - cm->available; } /** * irq_matrix_reserved - Get the number of globally reserved irqs * @m: Pointer to the matrix to query */ unsigned int irq_matrix_reserved(struct irq_matrix *m) { return m->global_reserved; } /** * irq_matrix_allocated - Get the number of allocated non-managed irqs on the local CPU * @m: Pointer to the matrix to search * * This returns number of allocated non-managed interrupts. */ unsigned int irq_matrix_allocated(struct irq_matrix *m) { struct cpumap *cm = this_cpu_ptr(m->maps); return cm->allocated - cm->managed_allocated; } #ifdef CONFIG_GENERIC_IRQ_DEBUGFS /** * irq_matrix_debug_show - Show detailed allocation information * @sf: Pointer to the seq_file to print to * @m: Pointer to the matrix allocator * @ind: Indentation for the print format * * Note, this is a lockless snapshot. */ void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind) { unsigned int nsys = bitmap_weight(m->system_map, m->matrix_bits); int cpu; seq_printf(sf, "Online bitmaps: %6u\n", m->online_maps); seq_printf(sf, "Global available: %6u\n", m->global_available); seq_printf(sf, "Global reserved: %6u\n", m->global_reserved); seq_printf(sf, "Total allocated: %6u\n", m->total_allocated); seq_printf(sf, "System: %u: %*pbl\n", nsys, m->matrix_bits, m->system_map); seq_printf(sf, "%*s| CPU | avl | man | mac | act | vectors\n", ind, " "); cpus_read_lock(); for_each_online_cpu(cpu) { struct cpumap *cm = per_cpu_ptr(m->maps, cpu); seq_printf(sf, "%*s %4d %4u %4u %4u %4u %*pbl\n", ind, " ", cpu, cm->available, cm->managed, cm->managed_allocated, cm->allocated, m->matrix_bits, cm->alloc_map); } cpus_read_unlock(); } #endif |
| 11 1 1 1 11 11 1 1 11 11 11 11 11 9 9 9 1 9 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache cache handling * * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define FSCACHE_DEBUG_LEVEL CACHE #include <linux/export.h> #include <linux/slab.h> #include "internal.h" static LIST_HEAD(fscache_caches); DECLARE_RWSEM(fscache_addremove_sem); EXPORT_SYMBOL(fscache_addremove_sem); DECLARE_WAIT_QUEUE_HEAD(fscache_clearance_waiters); EXPORT_SYMBOL(fscache_clearance_waiters); static atomic_t fscache_cache_debug_id; /* * Allocate a cache cookie. */ static struct fscache_cache *fscache_alloc_cache(const char *name) { struct fscache_cache *cache; cache = kzalloc(sizeof(*cache), GFP_KERNEL); if (cache) { if (name) { cache->name = kstrdup(name, GFP_KERNEL); if (!cache->name) { kfree(cache); return NULL; } } refcount_set(&cache->ref, 1); INIT_LIST_HEAD(&cache->cache_link); cache->debug_id = atomic_inc_return(&fscache_cache_debug_id); } return cache; } static bool fscache_get_cache_maybe(struct fscache_cache *cache, enum fscache_cache_trace where) { bool success; int ref; success = __refcount_inc_not_zero(&cache->ref, &ref); if (success) trace_fscache_cache(cache->debug_id, ref + 1, where); return success; } /* * Look up a cache cookie. */ struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache) { struct fscache_cache *candidate, *cache, *unnamed = NULL; /* firstly check for the existence of the cache under read lock */ down_read(&fscache_addremove_sem); list_for_each_entry(cache, &fscache_caches, cache_link) { if (cache->name && name && strcmp(cache->name, name) == 0 && fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) goto got_cache_r; if (!cache->name && !name && fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) goto got_cache_r; } if (!name) { list_for_each_entry(cache, &fscache_caches, cache_link) { if (cache->name && fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) goto got_cache_r; } } up_read(&fscache_addremove_sem); /* the cache does not exist - create a candidate */ candidate = fscache_alloc_cache(name); if (!candidate) return ERR_PTR(-ENOMEM); /* write lock, search again and add if still not present */ down_write(&fscache_addremove_sem); list_for_each_entry(cache, &fscache_caches, cache_link) { if (cache->name && name && strcmp(cache->name, name) == 0 && fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) goto got_cache_w; if (!cache->name) { unnamed = cache; if (!name && fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) goto got_cache_w; } } if (unnamed && is_cache && fscache_get_cache_maybe(unnamed, fscache_cache_get_acquire)) goto use_unnamed_cache; if (!name) { list_for_each_entry(cache, &fscache_caches, cache_link) { if (cache->name && fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) goto got_cache_w; } } list_add_tail(&candidate->cache_link, &fscache_caches); trace_fscache_cache(candidate->debug_id, refcount_read(&candidate->ref), fscache_cache_new_acquire); up_write(&fscache_addremove_sem); return candidate; got_cache_r: up_read(&fscache_addremove_sem); return cache; use_unnamed_cache: cache = unnamed; cache->name = candidate->name; candidate->name = NULL; got_cache_w: up_write(&fscache_addremove_sem); kfree(candidate->name); kfree(candidate); return cache; } /** * fscache_acquire_cache - Acquire a cache-level cookie. * @name: The name of the cache. * * Get a cookie to represent an actual cache. If a name is given and there is * a nameless cache record available, this will acquire that and set its name, * directing all the volumes using it to this cache. * * The cache will be switched over to the preparing state if not currently in * use, otherwise -EBUSY will be returned. */ struct fscache_cache *fscache_acquire_cache(const char *name) { struct fscache_cache *cache; ASSERT(name); cache = fscache_lookup_cache(name, true); if (IS_ERR(cache)) return cache; if (!fscache_set_cache_state_maybe(cache, FSCACHE_CACHE_IS_NOT_PRESENT, FSCACHE_CACHE_IS_PREPARING)) { pr_warn("Cache tag %s in use\n", name); fscache_put_cache(cache, fscache_cache_put_cache); return ERR_PTR(-EBUSY); } return cache; } EXPORT_SYMBOL(fscache_acquire_cache); /** * fscache_put_cache - Release a cache-level cookie. * @cache: The cache cookie to be released * @where: An indication of where the release happened * * Release the caller's reference on a cache-level cookie. The @where * indication should give information about the circumstances in which the call * occurs and will be logged through a tracepoint. */ void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where) { unsigned int debug_id; bool zero; int ref; if (IS_ERR_OR_NULL(cache)) return; debug_id = cache->debug_id; zero = __refcount_dec_and_test(&cache->ref, &ref); trace_fscache_cache(debug_id, ref - 1, where); if (zero) { down_write(&fscache_addremove_sem); list_del_init(&cache->cache_link); up_write(&fscache_addremove_sem); kfree(cache->name); kfree(cache); } } /** * fscache_relinquish_cache - Reset cache state and release cookie * @cache: The cache cookie to be released * * Reset the state of a cache and release the caller's reference on a cache * cookie. */ void fscache_relinquish_cache(struct fscache_cache *cache) { enum fscache_cache_trace where = (cache->state == FSCACHE_CACHE_IS_PREPARING) ? fscache_cache_put_prep_failed : fscache_cache_put_relinquish; cache->ops = NULL; cache->cache_priv = NULL; fscache_set_cache_state(cache, FSCACHE_CACHE_IS_NOT_PRESENT); fscache_put_cache(cache, where); } EXPORT_SYMBOL(fscache_relinquish_cache); /** * fscache_add_cache - Declare a cache as being open for business * @cache: The cache-level cookie representing the cache * @ops: Table of cache operations to use * @cache_priv: Private data for the cache record * * Add a cache to the system, making it available for netfs's to use. * * See Documentation/filesystems/caching/backend-api.rst for a complete * description. */ int fscache_add_cache(struct fscache_cache *cache, const struct fscache_cache_ops *ops, void *cache_priv) { int n_accesses; _enter("{%s,%s}", ops->name, cache->name); BUG_ON(fscache_cache_state(cache) != FSCACHE_CACHE_IS_PREPARING); /* Get a ref on the cache cookie and keep its n_accesses counter raised * by 1 to prevent wakeups from transitioning it to 0 until we're * withdrawing caching services from it. */ n_accesses = atomic_inc_return(&cache->n_accesses); trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), n_accesses, fscache_access_cache_pin); down_write(&fscache_addremove_sem); cache->ops = ops; cache->cache_priv = cache_priv; fscache_set_cache_state(cache, FSCACHE_CACHE_IS_ACTIVE); up_write(&fscache_addremove_sem); pr_notice("Cache \"%s\" added (type %s)\n", cache->name, ops->name); _leave(" = 0 [%s]", cache->name); return 0; } EXPORT_SYMBOL(fscache_add_cache); /** * fscache_begin_cache_access - Pin a cache so it can be accessed * @cache: The cache-level cookie * @why: An indication of the circumstances of the access for tracing * * Attempt to pin the cache to prevent it from going away whilst we're * accessing it and returns true if successful. This works as follows: * * (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), * then we return false to indicate access was not permitted. * * (2) If the cache tests as live, then we increment the n_accesses count and * then recheck the liveness, ending the access if it ceased to be live. * * (3) When we end the access, we decrement n_accesses and wake up the any * waiters if it reaches 0. * * (4) Whilst the cache is caching, n_accesses is kept artificially * incremented to prevent wakeups from happening. * * (5) When the cache is taken offline, the state is changed to prevent new * accesses, n_accesses is decremented and we wait for n_accesses to * become 0. */ bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why) { int n_accesses; if (!fscache_cache_is_live(cache)) return false; n_accesses = atomic_inc_return(&cache->n_accesses); smp_mb__after_atomic(); /* Reread live flag after n_accesses */ trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), n_accesses, why); if (!fscache_cache_is_live(cache)) { fscache_end_cache_access(cache, fscache_access_unlive); return false; } return true; } /** * fscache_end_cache_access - Unpin a cache at the end of an access. * @cache: The cache-level cookie * @why: An indication of the circumstances of the access for tracing * * Unpin a cache after we've accessed it. The @why indicator is merely * provided for tracing purposes. */ void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why) { int n_accesses; smp_mb__before_atomic(); n_accesses = atomic_dec_return(&cache->n_accesses); trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), n_accesses, why); if (n_accesses == 0) wake_up_var(&cache->n_accesses); } /** * fscache_io_error - Note a cache I/O error * @cache: The record describing the cache * * Note that an I/O error occurred in a cache and that it should no longer be * used for anything. This also reports the error into the kernel log. * * See Documentation/filesystems/caching/backend-api.rst for a complete * description. */ void fscache_io_error(struct fscache_cache *cache) { if (fscache_set_cache_state_maybe(cache, FSCACHE_CACHE_IS_ACTIVE, FSCACHE_CACHE_GOT_IOERROR)) pr_err("Cache '%s' stopped due to I/O error\n", cache->name); } EXPORT_SYMBOL(fscache_io_error); /** * fscache_withdraw_cache - Withdraw a cache from the active service * @cache: The cache cookie * * Begin the process of withdrawing a cache from service. This stops new * cache-level and volume-level accesses from taking place and waits for * currently ongoing cache-level accesses to end. */ void fscache_withdraw_cache(struct fscache_cache *cache) { int n_accesses; pr_notice("Withdrawing cache \"%s\" (%u objs)\n", cache->name, atomic_read(&cache->object_count)); fscache_set_cache_state(cache, FSCACHE_CACHE_IS_WITHDRAWN); /* Allow wakeups on dec-to-0 */ n_accesses = atomic_dec_return(&cache->n_accesses); trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), n_accesses, fscache_access_cache_unpin); wait_var_event(&cache->n_accesses, atomic_read(&cache->n_accesses) == 0); } EXPORT_SYMBOL(fscache_withdraw_cache); #ifdef CONFIG_PROC_FS static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW"; /* * Generate a list of caches in /proc/fs/fscache/caches */ static int fscache_caches_seq_show(struct seq_file *m, void *v) { struct fscache_cache *cache; if (v == &fscache_caches) { seq_puts(m, "CACHE REF VOLS OBJS ACCES S NAME\n" "======== ===== ===== ===== ===== = ===============\n" ); return 0; } cache = list_entry(v, struct fscache_cache, cache_link); seq_printf(m, "%08x %5d %5d %5d %5d %c %s\n", cache->debug_id, refcount_read(&cache->ref), atomic_read(&cache->n_volumes), atomic_read(&cache->object_count), atomic_read(&cache->n_accesses), fscache_cache_states[cache->state], cache->name ?: "-"); return 0; } static void *fscache_caches_seq_start(struct seq_file *m, loff_t *_pos) __acquires(fscache_addremove_sem) { down_read(&fscache_addremove_sem); return seq_list_start_head(&fscache_caches, *_pos); } static void *fscache_caches_seq_next(struct seq_file *m, void *v, loff_t *_pos) { return seq_list_next(v, &fscache_caches, _pos); } static void fscache_caches_seq_stop(struct seq_file *m, void *v) __releases(fscache_addremove_sem) { up_read(&fscache_addremove_sem); } const struct seq_operations fscache_caches_seq_ops = { .start = fscache_caches_seq_start, .next = fscache_caches_seq_next, .stop = fscache_caches_seq_stop, .show = fscache_caches_seq_show, }; #endif /* CONFIG_PROC_FS */ |
| 10 809 6 815 815 242 109 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _LINUX_RSEQ_H #define _LINUX_RSEQ_H #ifdef CONFIG_RSEQ #include <linux/preempt.h> #include <linux/sched.h> /* * Map the event mask on the user-space ABI enum rseq_cs_flags * for direct mask checks. */ enum rseq_event_mask_bits { RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, }; enum rseq_event_mask { RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), }; static inline void rseq_set_notify_resume(struct task_struct *t) { if (t->rseq) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { if (current->rseq) __rseq_handle_notify_resume(ksig, regs); } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ static inline void rseq_preempt(struct task_struct *t) { __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* rseq_migrate() requires preemption to be disabled. */ static inline void rseq_migrate(struct task_struct *t) { __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* * If parent process has a registered restartable sequences area, the * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } else { t->rseq = current->rseq; t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; } } static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } #else static inline void rseq_set_notify_resume(struct task_struct *t) { } static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) { } static inline void rseq_migrate(struct task_struct *t) { } static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { } static inline void rseq_execve(struct task_struct *t) { } #endif #ifdef CONFIG_DEBUG_RSEQ void rseq_syscall(struct pt_regs *regs); #else static inline void rseq_syscall(struct pt_regs *regs) { } #endif #endif /* _LINUX_RSEQ_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Connection Data Control (CDC) * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #ifndef SMC_CDC_H #define SMC_CDC_H #include <linux/kernel.h> /* max_t */ #include <linux/atomic.h> #include <linux/in.h> #include <linux/compiler.h> #include "smc.h" #include "smc_core.h" #include "smc_wr.h" #define SMC_CDC_MSG_TYPE 0xFE /* in network byte order */ union smc_cdc_cursor { /* SMC cursor */ struct { __be16 reserved; __be16 wrap; __be32 count; }; #ifdef KERNEL_HAS_ATOMIC64 atomic64_t acurs; /* for atomic processing */ #else u64 acurs; /* for atomic processing */ #endif } __aligned(8); /* in network byte order */ struct smc_cdc_msg { struct smc_wr_rx_hdr common; /* .type = 0xFE */ u8 len; /* 44 */ __be16 seqno; __be32 token; union smc_cdc_cursor prod; union smc_cdc_cursor cons; /* piggy backed "ack" */ struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; u8 reserved[18]; }; /* SMC-D cursor format */ union smcd_cdc_cursor { struct { u16 wrap; u32 count; struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; } __packed; #ifdef KERNEL_HAS_ATOMIC64 atomic64_t acurs; /* for atomic processing */ #else u64 acurs; /* for atomic processing */ #endif } __aligned(8); /* CDC message for SMC-D */ struct smcd_cdc_msg { struct smc_wr_rx_hdr common; /* Type = 0xFE */ u8 res1[7]; union smcd_cdc_cursor prod; union smcd_cdc_cursor cons; u8 res3[8]; } __aligned(8); static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn) { return conn->local_rx_ctrl.conn_state_flags.peer_conn_abort || conn->local_rx_ctrl.conn_state_flags.peer_conn_closed; } static inline bool smc_cdc_rxed_any_close_or_senddone( struct smc_connection *conn) { return smc_cdc_rxed_any_close(conn) || conn->local_rx_ctrl.conn_state_flags.peer_done_writing; } static inline void smc_curs_add(int size, union smc_host_cursor *curs, int value) { curs->count += value; if (curs->count >= size) { curs->wrap++; curs->count -= size; } } /* Copy cursor src into tgt */ static inline void smc_curs_copy(union smc_host_cursor *tgt, union smc_host_cursor *src, struct smc_connection *conn) { #ifndef KERNEL_HAS_ATOMIC64 unsigned long flags; spin_lock_irqsave(&conn->acurs_lock, flags); tgt->acurs = src->acurs; spin_unlock_irqrestore(&conn->acurs_lock, flags); #else atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); #endif } static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt, union smc_cdc_cursor *src, struct smc_connection *conn) { #ifndef KERNEL_HAS_ATOMIC64 unsigned long flags; spin_lock_irqsave(&conn->acurs_lock, flags); tgt->acurs = src->acurs; spin_unlock_irqrestore(&conn->acurs_lock, flags); #else atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); #endif } static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, union smcd_cdc_cursor *src, struct smc_connection *conn) { #ifndef KERNEL_HAS_ATOMIC64 unsigned long flags; spin_lock_irqsave(&conn->acurs_lock, flags); tgt->acurs = src->acurs; spin_unlock_irqrestore(&conn->acurs_lock, flags); #else atomic64_set(&tgt->acurs, atomic64_read(&src->acurs)); #endif } /* calculate cursor difference between old and new, where old <= new and * difference cannot exceed size */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) { if (old->wrap != new->wrap) return max_t(int, 0, ((size - old->count) + new->count)); return max_t(int, 0, (new->count - old->count)); } /* calculate cursor difference between old and new - returns negative * value in case old > new */ static inline int smc_curs_comp(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) { if (old->wrap > new->wrap || (old->wrap == new->wrap && old->count > new->count)) return -smc_curs_diff(size, new, old); return smc_curs_diff(size, old, new); } /* calculate cursor difference between old and new, where old <= new and * difference may exceed size */ static inline int smc_curs_diff_large(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) { if (old->wrap < new->wrap) return min_t(int, (size - old->count) + new->count + (new->wrap - old->wrap - 1) * size, size); if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */ return min_t(int, (size - old->count) + new->count + (new->wrap + 0xffff - old->wrap) * size, size); return max_t(int, 0, (new->count - old->count)); } static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, union smc_host_cursor *save, struct smc_connection *conn) { smc_curs_copy(save, local, conn); peer->count = htonl(save->count); peer->wrap = htons(save->wrap); /* peer->reserved = htons(0); must be ensured by caller */ } static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer, struct smc_connection *conn, union smc_host_cursor *save) { struct smc_host_cdc_msg *local = &conn->local_tx_ctrl; peer->common.type = local->common.type; peer->len = local->len; peer->seqno = htons(local->seqno); peer->token = htonl(local->token); smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn); smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn); peer->prod_flags = local->prod_flags; peer->conn_state_flags = local->conn_state_flags; } static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local, union smc_cdc_cursor *peer, struct smc_connection *conn) { union smc_host_cursor temp, old; union smc_cdc_cursor net; smc_curs_copy(&old, local, conn); smc_curs_copy_net(&net, peer, conn); temp.count = ntohl(net.count); temp.wrap = ntohs(net.wrap); if ((old.wrap > temp.wrap) && temp.wrap) return; if ((old.wrap == temp.wrap) && (old.count > temp.count)) return; smc_curs_copy(local, &temp, conn); } static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_cdc_msg *peer, struct smc_connection *conn) { local->common.type = peer->common.type; local->len = peer->len; local->seqno = ntohs(peer->seqno); local->token = ntohl(peer->token); smc_cdc_cursor_to_host(&local->prod, &peer->prod, conn); smc_cdc_cursor_to_host(&local->cons, &peer->cons, conn); local->prod_flags = peer->prod_flags; local->conn_state_flags = peer->conn_state_flags; } static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smcd_cdc_msg *peer, struct smc_connection *conn) { union smc_host_cursor temp; temp.wrap = peer->prod.wrap; temp.count = peer->prod.count; smc_curs_copy(&local->prod, &temp, conn); temp.wrap = peer->cons.wrap; temp.count = peer->cons.count; smc_curs_copy(&local->cons, &temp, conn); local->prod_flags = peer->cons.prod_flags; local->conn_state_flags = peer->cons.conn_state_flags; } static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_cdc_msg *peer, struct smc_connection *conn) { if (conn->lgr->is_smcd) smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer, conn); else smcr_cdc_msg_to_host(local, peer, conn); } struct smc_cdc_tx_pend { struct smc_connection *conn; /* socket connection */ union smc_host_cursor cursor; /* tx sndbuf cursor sent */ union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ u16 ctrl_seq; /* conn. tx sequence # */ }; int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_link *link, struct smc_wr_buf **wr_buf, struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend); int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn); int smcd_cdc_msg_send(struct smc_connection *conn); int smcr_cdc_msg_send_validation(struct smc_connection *conn, struct smc_cdc_tx_pend *pend, struct smc_wr_buf *wr_buf); int smc_cdc_init(void) __init; void smcd_cdc_rx_init(struct smc_connection *conn); #endif /* SMC_CDC_H */ |
| 10372 6 102 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 | // 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->lltx = true; 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; 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"); |
| 9 51 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Global definitions for the ARP (RFC 826) protocol. * * Version: @(#)if_arp.h 1.0.1 04/16/93 * * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1986-1988 * Portions taken from the KA9Q/NOS (v2.00m PA0GRI) source. * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, * Jonathan Layes <layes@loran.com> * Arnaldo Carvalho de Melo <acme@conectiva.com.br> ARPHRD_HWX25 */ #ifndef _LINUX_IF_ARP_H #define _LINUX_IF_ARP_H #include <linux/skbuff.h> #include <uapi/linux/if_arp.h> static inline struct arphdr *arp_hdr(const struct sk_buff *skb) { return (struct arphdr *)skb_network_header(skb); } static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: /* ARP header, device address and 2 IP addresses */ return sizeof(struct arphdr) + dev->addr_len + sizeof(u32) * 2; #endif default: /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; } } static inline bool dev_is_mac_header_xmit(const struct net_device *dev) { switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: /* PPP adds its l2 header automatically in ppp_start_xmit(). * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). */ case ARPHRD_PPP: return false; default: return true; } } #endif /* _LINUX_IF_ARP_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/fs.h> #include <linux/buffer_head.h> #include "amigaffs.h" #include <linux/mutex.h> #include <linux/workqueue.h> /* Ugly macros make the code more pretty. */ #define AFFS_BLOCK(sb, bh, blk) (AFFS_HEAD(bh)->table[AFFS_SB(sb)->s_hashsize-1-(blk)]) #define AFFS_HEAD(bh) ((struct affs_head *)(bh)->b_data) #define AFFS_TAIL(sb, bh) ((struct affs_tail *)((bh)->b_data+(sb)->s_blocksize-sizeof(struct affs_tail))) #define AFFS_ROOT_HEAD(bh) ((struct affs_root_head *)(bh)->b_data) #define AFFS_ROOT_TAIL(sb, bh) ((struct affs_root_tail *)((bh)->b_data+(sb)->s_blocksize-sizeof(struct affs_root_tail))) #define AFFS_DATA_HEAD(bh) ((struct affs_data_head *)(bh)->b_data) #define AFFS_DATA(bh) (((struct affs_data_head *)(bh)->b_data)->data) #define AFFS_CACHE_SIZE PAGE_SIZE #define AFFS_LC_SIZE (AFFS_CACHE_SIZE/sizeof(u32)/2) #define AFFS_AC_SIZE (AFFS_CACHE_SIZE/sizeof(struct affs_ext_key)/2) #define AFFS_AC_MASK (AFFS_AC_SIZE-1) #define AFFSNAMEMAX 30U struct affs_ext_key { u32 ext; /* idx of the extended block */ u32 key; /* block number */ }; /* * affs fs inode data in memory */ struct affs_inode_info { atomic_t i_opencnt; struct mutex i_link_lock; /* Protects internal inode access. */ struct mutex i_ext_lock; /* Protects internal inode access. */ #define i_hash_lock i_ext_lock u32 i_blkcnt; /* block count */ u32 i_extcnt; /* extended block count */ u32 *i_lc; /* linear cache of extended blocks */ u32 i_lc_size; u32 i_lc_shift; u32 i_lc_mask; struct affs_ext_key *i_ac; /* associative cache of extended blocks */ u32 i_ext_last; /* last accessed extended block */ struct buffer_head *i_ext_bh; /* bh of last extended block */ loff_t mmu_private; u32 i_protect; /* unused attribute bits */ u32 i_lastalloc; /* last allocated block */ int i_pa_cnt; /* number of preallocated blocks */ struct inode vfs_inode; }; /* short cut to get to the affs specific inode data */ static inline struct affs_inode_info *AFFS_I(struct inode *inode) { return container_of(inode, struct affs_inode_info, vfs_inode); } /* * super-block data in memory * * Block numbers are adjusted for their actual size * */ struct affs_bm_info { u32 bm_key; /* Disk block number */ u32 bm_free; /* Free blocks in here */ }; struct affs_sb_info { int s_partition_size; /* Partition size in blocks. */ int s_reserved; /* Number of reserved blocks. */ //u32 s_blksize; /* Initial device blksize */ u32 s_data_blksize; /* size of the data block w/o header */ u32 s_root_block; /* FFS root block number. */ int s_hashsize; /* Size of hash table. */ unsigned long s_flags; /* See below. */ kuid_t s_uid; /* uid to override */ kgid_t s_gid; /* gid to override */ umode_t s_mode; /* mode to override */ struct buffer_head *s_root_bh; /* Cached root block. */ struct mutex s_bmlock; /* Protects bitmap access. */ struct affs_bm_info *s_bitmap; /* Bitmap infos. */ u32 s_bmap_count; /* # of bitmap blocks. */ u32 s_bmap_bits; /* # of bits in one bitmap blocks */ u32 s_last_bmap; struct buffer_head *s_bmap_bh; char *s_prefix; /* Prefix for volumes and assigns. */ char s_volume[32]; /* Volume prefix for absolute symlinks. */ spinlock_t symlink_lock; /* protects the previous two */ struct super_block *sb; /* the VFS superblock object */ int work_queued; /* non-zero delayed work is queued */ struct delayed_work sb_work; /* superblock flush delayed work */ spinlock_t work_lock; /* protects sb_work and work_queued */ struct rcu_head rcu; }; #define AFFS_MOUNT_SF_INTL 0x0001 /* International filesystem. */ #define AFFS_MOUNT_SF_BM_VALID 0x0002 /* Bitmap is valid. */ #define AFFS_MOUNT_SF_IMMUTABLE 0x0004 /* Protection bits cannot be changed */ #define AFFS_MOUNT_SF_QUIET 0x0008 /* chmod errors will be not reported */ #define AFFS_MOUNT_SF_SETUID 0x0010 /* Ignore Amiga uid */ #define AFFS_MOUNT_SF_SETGID 0x0020 /* Ignore Amiga gid */ #define AFFS_MOUNT_SF_SETMODE 0x0040 /* Ignore Amiga protection bits */ #define AFFS_MOUNT_SF_MUFS 0x0100 /* Use MUFS uid/gid mapping */ #define AFFS_MOUNT_SF_OFS 0x0200 /* Old filesystem */ #define AFFS_MOUNT_SF_PREFIX 0x0400 /* Buffer for prefix is allocated */ #define AFFS_MOUNT_SF_VERBOSE 0x0800 /* Talk about fs when mounting */ #define AFFS_MOUNT_SF_NO_TRUNCATE 0x1000 /* Don't truncate filenames */ #define affs_clear_opt(o, opt) (o &= ~AFFS_MOUNT_##opt) #define affs_set_opt(o, opt) (o |= AFFS_MOUNT_##opt) #define affs_test_opt(o, opt) ((o) & AFFS_MOUNT_##opt) /* short cut to get to the affs specific sb data */ static inline struct affs_sb_info *AFFS_SB(struct super_block *sb) { return sb->s_fs_info; } void affs_mark_sb_dirty(struct super_block *sb); /* amigaffs.c */ extern int affs_insert_hash(struct inode *inode, struct buffer_head *bh); extern int affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh); extern int affs_remove_header(struct dentry *dentry); extern u32 affs_checksum_block(struct super_block *sb, struct buffer_head *bh); extern void affs_fix_checksum(struct super_block *sb, struct buffer_head *bh); extern void affs_secs_to_datestamp(time64_t secs, struct affs_date *ds); extern umode_t affs_prot_to_mode(u32 prot); extern void affs_mode_to_prot(struct inode *inode); __printf(3, 4) extern void affs_error(struct super_block *sb, const char *function, const char *fmt, ...); __printf(3, 4) extern void affs_warning(struct super_block *sb, const char *function, const char *fmt, ...); extern bool affs_nofilenametruncate(const struct dentry *dentry); extern int affs_check_name(const unsigned char *name, int len, bool notruncate); extern int affs_copy_name(unsigned char *bstr, struct dentry *dentry); /* bitmap. c */ extern u32 affs_count_free_blocks(struct super_block *s); extern void affs_free_block(struct super_block *sb, u32 block); extern u32 affs_alloc_block(struct inode *inode, u32 goal); extern int affs_init_bitmap(struct super_block *sb, int *flags); extern void affs_free_bitmap(struct super_block *sb); /* namei.c */ extern const struct export_operations affs_export_ops; extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len); extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); extern int affs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool); extern int affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); extern int affs_link(struct dentry *olddentry, struct inode *dir, struct dentry *dentry); extern int affs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname); extern int affs_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); /* inode.c */ extern struct inode *affs_new_inode(struct inode *dir); extern int affs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); extern void affs_evict_inode(struct inode *inode); extern struct inode *affs_iget(struct super_block *sb, unsigned long ino); extern int affs_write_inode(struct inode *inode, struct writeback_control *wbc); extern int affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s32 type); /* file.c */ void affs_free_prealloc(struct inode *inode); extern void affs_truncate(struct inode *); int affs_file_fsync(struct file *, loff_t, loff_t, int); /* dir.c */ extern void affs_dir_truncate(struct inode *); /* jump tables */ extern const struct inode_operations affs_file_inode_operations; extern const struct inode_operations affs_dir_inode_operations; extern const struct inode_operations affs_symlink_inode_operations; extern const struct file_operations affs_file_operations; extern const struct file_operations affs_file_operations_ofs; extern const struct file_operations affs_dir_operations; extern const struct address_space_operations affs_symlink_aops; extern const struct address_space_operations affs_aops; extern const struct address_space_operations affs_aops_ofs; extern const struct dentry_operations affs_dentry_operations; extern const struct dentry_operations affs_intl_dentry_operations; static inline bool affs_validblock(struct super_block *sb, int block) { return(block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size); } static inline void affs_set_blocksize(struct super_block *sb, int size) { sb_set_blocksize(sb, size); } static inline struct buffer_head * affs_bread(struct super_block *sb, int block) { pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) return sb_bread(sb, block); return NULL; } static inline struct buffer_head * affs_getblk(struct super_block *sb, int block) { pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) return sb_getblk(sb, block); return NULL; } static inline struct buffer_head * affs_getzeroblk(struct super_block *sb, int block) { struct buffer_head *bh; pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) { bh = sb_getblk(sb, block); lock_buffer(bh); memset(bh->b_data, 0 , sb->s_blocksize); set_buffer_uptodate(bh); unlock_buffer(bh); return bh; } return NULL; } static inline struct buffer_head * affs_getemptyblk(struct super_block *sb, int block) { struct buffer_head *bh; pr_debug("%s: %d\n", __func__, block); if (affs_validblock(sb, block)) { bh = sb_getblk(sb, block); wait_on_buffer(bh); set_buffer_uptodate(bh); return bh; } return NULL; } static inline void affs_brelse(struct buffer_head *bh) { if (bh) pr_debug("%s: %lld\n", __func__, (long long) bh->b_blocknr); brelse(bh); } static inline void affs_adjust_checksum(struct buffer_head *bh, u32 val) { u32 tmp = be32_to_cpu(((__be32 *)bh->b_data)[5]); ((__be32 *)bh->b_data)[5] = cpu_to_be32(tmp - val); } static inline void affs_adjust_bitmapchecksum(struct buffer_head *bh, u32 val) { u32 tmp = be32_to_cpu(((__be32 *)bh->b_data)[0]); ((__be32 *)bh->b_data)[0] = cpu_to_be32(tmp - val); } static inline void affs_lock_link(struct inode *inode) { mutex_lock(&AFFS_I(inode)->i_link_lock); } static inline void affs_unlock_link(struct inode *inode) { mutex_unlock(&AFFS_I(inode)->i_link_lock); } static inline void affs_lock_dir(struct inode *inode) { mutex_lock_nested(&AFFS_I(inode)->i_hash_lock, SINGLE_DEPTH_NESTING); } static inline void affs_unlock_dir(struct inode *inode) { mutex_unlock(&AFFS_I(inode)->i_hash_lock); } static inline void affs_lock_ext(struct inode *inode) { mutex_lock(&AFFS_I(inode)->i_ext_lock); } static inline void affs_unlock_ext(struct inode *inode) { mutex_unlock(&AFFS_I(inode)->i_ext_lock); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Definitions for SMC Connections, Link Groups and Links * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #ifndef _SMC_CORE_H #define _SMC_CORE_H #include <linux/atomic.h> #include <linux/smc.h> #include <linux/pci.h> #include <rdma/ib_verbs.h> #include <net/genetlink.h> #include <net/smc.h> #include "smc.h" #include "smc_ib.h" #include "smc_clc.h" #define SMC_RMBS_PER_LGR_MAX 255 /* max. # of RMBs per link group */ #define SMC_CONN_PER_LGR_MIN 16 /* min. # of connections per link group */ #define SMC_CONN_PER_LGR_MAX 255 /* max. # of connections per link group, * also is the default value for SMC-R v1 and v2.0 */ #define SMC_CONN_PER_LGR_PREFER 255 /* Preferred connections per link group used for * SMC-R v2.1 and later negotiation, vendors or * distributions may modify it to a value between * 16-255 as needed. */ struct smc_lgr_list { /* list of link group definition */ struct list_head list; spinlock_t lock; /* protects list of link groups */ u32 num; /* unique link group number */ }; enum smc_lgr_role { /* possible roles of a link group */ SMC_CLNT, /* client */ SMC_SERV /* server */ }; enum smc_link_state { /* possible states of a link */ SMC_LNK_UNUSED, /* link is unused */ SMC_LNK_INACTIVE, /* link is inactive */ SMC_LNK_ACTIVATING, /* link is being activated */ SMC_LNK_ACTIVE, /* link is active */ }; #define SMC_WR_BUF_SIZE 48 /* size of work request buffer */ #define SMC_WR_BUF_V2_SIZE 8192 /* size of v2 work request buffer */ struct smc_wr_buf { u8 raw[SMC_WR_BUF_SIZE]; }; struct smc_wr_v2_buf { u8 raw[SMC_WR_BUF_V2_SIZE]; }; #define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */ enum smc_wr_reg_state { POSTED, /* ib_wr_reg_mr request posted */ CONFIRMED, /* ib_wr_reg_mr response: successful */ FAILED /* ib_wr_reg_mr response: failure */ }; struct smc_rdma_sge { /* sges for RDMA writes */ struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; }; #define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per * message send */ struct smc_rdma_sges { /* sges per message send */ struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; }; struct smc_rdma_wr { /* work requests per message * send */ struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; }; #define SMC_LGR_ID_SIZE 4 struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ struct ib_pd *roce_pd; /* IB protection domain, * unique for every RoCE QP */ struct ib_qp *roce_qp; /* IB queue pair */ struct ib_qp_attr qp_attr; /* IB queue pair attributes */ struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ struct completion *wr_tx_compl; /* WR send CQE completion */ /* above four vectors have wr_tx_cnt elements and use the same index */ struct ib_send_wr *wr_tx_v2_ib; /* WR send v2 meta data */ struct ib_sge *wr_tx_v2_sge; /* WR send v2 gather meta data*/ struct smc_wr_tx_pend *wr_tx_v2_pend; /* WR send v2 waiting for CQE */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ dma_addr_t wr_tx_v2_dma_addr; /* DMA address of v2 tx buf*/ atomic_long_t wr_tx_id; /* seq # of last sent WR */ unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ struct { struct percpu_ref wr_tx_refs; } ____cacheline_aligned_in_smp; struct completion tx_ref_comp; u8 *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ struct ib_sge *wr_rx_sges; /* WR recv scatter meta data */ /* above three vectors have wr_rx_cnt elements and use the same index */ int wr_rx_sge_cnt; /* rx sge, V1 is 1, V2 is either 2 or 1 */ int wr_rx_buflen; /* buffer len for the first sge, len for the * second sge is lgr shared if rx sge is 2. */ dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/ u64 wr_rx_id; /* seq # of last recv WR */ u64 wr_rx_id_compl; /* seq # of last completed WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ wait_queue_head_t wr_rx_empty_wait; /* wait for RQ empty */ struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ struct { struct percpu_ref wr_reg_refs; } ____cacheline_aligned_in_smp; struct completion reg_ref_comp; enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ u8 sgid_index; /* gid index for vlan id */ u32 peer_qpn; /* QP number of peer */ enum ib_mtu path_mtu; /* used mtu */ enum ib_mtu peer_mtu; /* mtu size of peer */ u32 psn_initial; /* QP tx initial packet seqno */ u32 peer_psn; /* QP rx initial packet seqno */ u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */ u8 peer_gid[SMC_GID_SIZE]; /* gid of peer*/ u8 link_id; /* unique # within link group */ u8 link_uid[SMC_LGR_ID_SIZE]; /* unique lnk id */ u8 peer_link_uid[SMC_LGR_ID_SIZE]; /* peer uid */ u8 link_idx; /* index in lgr link array */ u8 link_is_asym; /* is link asymmetric? */ u8 clearing : 1; /* link is being cleared */ refcount_t refcnt; /* link reference count */ struct smc_link_group *lgr; /* parent link group */ struct work_struct link_down_wrk; /* wrk to bring link down */ char ibname[IB_DEVICE_NAME_MAX]; /* ib device name */ int ndev_ifidx; /* network device ifindex */ enum smc_link_state state; /* state of link */ struct delayed_work llc_testlink_wrk; /* testlink worker */ struct completion llc_testlink_resp; /* wait for rx of testlink */ int llc_testlink_time; /* testlink interval */ atomic_t conn_cnt; /* connections on this link */ }; /* For now we just allow one parallel link per link group. The SMC protocol * allows more (up to 8). */ #define SMC_LINKS_PER_LGR_MAX 3 #define SMC_SINGLE_LINK 0 #define SMC_LINKS_ADD_LNK_MIN 1 /* min. # of links per link group */ #define SMC_LINKS_ADD_LNK_MAX 2 /* max. # of links per link group, also is the * default value for smc-r v1.0 and v2.0 */ #define SMC_LINKS_PER_LGR_MAX_PREFER 2 /* Preferred max links per link group used for * SMC-R v2.1 and later negotiation, vendors or * distributions may modify it to a value between * 1-2 as needed. */ /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */ struct smc_buf_desc { struct list_head list; void *cpu_addr; /* virtual address of buffer */ struct page *pages; int len; /* length of buffer */ u32 used; /* currently used / unused */ union { struct { /* SMC-R */ struct sg_table sgt[SMC_LINKS_PER_LGR_MAX]; /* virtual buffer */ struct ib_mr *mr[SMC_LINKS_PER_LGR_MAX]; /* memory region: for rmb and * vzalloced sndbuf * incl. rkey provided to peer * and lkey provided to local */ u32 order; /* allocation order */ u8 is_conf_rkey; /* confirm_rkey done */ u8 is_reg_mr[SMC_LINKS_PER_LGR_MAX]; /* mem region registered */ u8 is_map_ib[SMC_LINKS_PER_LGR_MAX]; /* mem region mapped to lnk */ u8 is_dma_need_sync; u8 is_reg_err; /* buffer registration err */ u8 is_vm; /* virtually contiguous */ }; struct { /* SMC-D */ unsigned short sba_idx; /* SBA index number */ u64 token; /* DMB token number */ dma_addr_t dma_addr; /* DMA address */ }; }; }; struct smc_rtoken { /* address/key of remote RMB */ u64 dma_addr; u32 rkey; }; #define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */ #define SMC_RMBE_SIZES 16 /* number of distinct RMBE sizes */ /* theoretically, the RFC states that largest size would be 512K, * i.e. compressed 5 and thus 6 sizes (0..5), despite * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15) */ struct smcd_dev; enum smc_lgr_type { /* redundancy state of lgr */ SMC_LGR_NONE, /* no active links, lgr to be deleted */ SMC_LGR_SINGLE, /* 1 active RNIC on each peer */ SMC_LGR_SYMMETRIC, /* 2 active RNICs on each peer */ SMC_LGR_ASYMMETRIC_PEER, /* local has 2, peer 1 active RNICs */ SMC_LGR_ASYMMETRIC_LOCAL, /* local has 1, peer 2 active RNICs */ }; enum smcr_buf_type { /* types of SMC-R sndbufs and RMBs */ SMCR_PHYS_CONT_BUFS = 0, SMCR_VIRT_CONT_BUFS = 1, SMCR_MIXED_BUFS = 2, }; enum smc_llc_flowtype { SMC_LLC_FLOW_NONE = 0, SMC_LLC_FLOW_ADD_LINK = 2, SMC_LLC_FLOW_DEL_LINK = 4, SMC_LLC_FLOW_REQ_ADD_LINK = 5, SMC_LLC_FLOW_RKEY = 6, }; struct smc_llc_qentry; struct smc_llc_flow { enum smc_llc_flowtype type; struct smc_llc_qentry *qentry; }; struct smc_link_group { struct list_head list; struct rb_root conns_all; /* connection tree */ rwlock_t conns_lock; /* protects conns_all */ unsigned int conns_num; /* current # of connections */ unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ struct rw_semaphore rmbs_lock; /* protects rx buffers */ u64 alloc_sndbufs; /* stats of tx buffers */ u64 alloc_rmbs; /* stats of rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ struct work_struct terminate_work; /* abnormal lgr termination */ struct workqueue_struct *tx_wq; /* wq for conn. tx workers */ u8 sync_err : 1; /* lgr no longer fits to peer */ u8 terminating : 1;/* lgr is terminating */ u8 freeing : 1; /* lgr is being freed */ refcount_t refcnt; /* lgr reference count */ bool is_smcd; /* SMC-R or SMC-D */ u8 smc_version; u8 negotiated_eid[SMC_MAX_EID_LEN]; u8 peer_os; /* peer operating system */ u8 peer_smc_release; u8 peer_hostname[SMC_MAX_HOSTNAME_LEN]; union { struct { /* SMC-R */ enum smc_lgr_role role; /* client or server */ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ struct smc_wr_v2_buf *wr_rx_buf_v2; /* WR v2 recv payload buffer */ struct smc_wr_v2_buf *wr_tx_buf_v2; /* WR v2 send payload buffer */ char peer_systemid[SMC_SYSTEMID_LEN]; /* unique system_id of peer */ struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] [SMC_LINKS_PER_LGR_MAX]; /* remote addr/key pairs */ DECLARE_BITMAP(rtokens_used_mask, SMC_RMBS_PER_LGR_MAX); /* used rtoken elements */ u8 next_link_id; enum smc_lgr_type type; enum smcr_buf_type buf_type; /* redundancy state */ u8 pnet_id[SMC_MAX_PNETID_LEN + 1]; /* pnet id of this lgr */ struct list_head llc_event_q; /* queue for llc events */ spinlock_t llc_event_q_lock; /* protects llc_event_q */ struct rw_semaphore llc_conf_mutex; /* protects lgr reconfig. */ struct work_struct llc_add_link_work; struct work_struct llc_del_link_work; struct work_struct llc_event_work; /* llc event worker */ wait_queue_head_t llc_flow_waiter; /* w4 next llc event */ wait_queue_head_t llc_msg_waiter; /* w4 next llc msg */ struct smc_llc_flow llc_flow_lcl; /* llc local control field */ struct smc_llc_flow llc_flow_rmt; /* llc remote control field */ struct smc_llc_qentry *delayed_event; /* arrived when flow active */ spinlock_t llc_flow_lock; /* protects llc flow */ int llc_testlink_time; /* link keep alive time */ u32 llc_termination_rsn; /* rsn code for termination */ u8 nexthop_mac[ETH_ALEN]; u8 uses_gateway; __be32 saddr; /* net namespace */ struct net *net; u8 max_conns; /* max conn can be assigned to lgr */ u8 max_links; /* max links can be added in lgr */ }; struct { /* SMC-D */ struct smcd_gid peer_gid; /* Peer GID (remote) */ struct smcd_dev *smcd; /* ISM device for VLAN reg. */ u8 peer_shutdown : 1; /* peer triggered shutdownn */ }; }; }; struct smc_clc_msg_local; #define GID_LIST_SIZE 2 struct smc_gidlist { u8 len; u8 list[GID_LIST_SIZE][SMC_GID_SIZE]; }; struct smc_init_info_smcrv2 { /* Input fields */ __be32 saddr; struct sock *clc_sk; __be32 daddr; /* Output fields when saddr is set */ struct smc_ib_device *ib_dev_v2; u8 ib_port_v2; u8 ib_gid_v2[SMC_GID_SIZE]; /* Additional output fields when clc_sk and daddr is set as well */ u8 uses_gateway; u8 nexthop_mac[ETH_ALEN]; struct smc_gidlist gidlist; }; #define SMC_MAX_V2_ISM_DEVS SMCD_CLC_MAX_V2_GID_ENTRIES /* max # of proposed non-native ISM devices, * which can't exceed the max # of CHID-GID * entries in CLC proposal SMC-Dv2 extension. */ struct smc_init_info { u8 is_smcd; u8 smc_type_v1; u8 smc_type_v2; u8 release_nr; u8 max_conns; u8 max_links; u8 first_contact_peer; u8 first_contact_local; u16 feature_mask; unsigned short vlan_id; u32 rc; u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ u8 smcr_version; u8 check_smcrv2; u8 peer_gid[SMC_GID_SIZE]; u8 peer_mac[ETH_ALEN]; u8 peer_systemid[SMC_SYSTEMID_LEN]; struct smc_ib_device *ib_dev; u8 ib_gid[SMC_GID_SIZE]; u8 ib_port; u32 ib_clcqpn; struct smc_init_info_smcrv2 smcrv2; /* SMC-D */ struct smcd_gid ism_peer_gid[SMC_MAX_V2_ISM_DEVS + 1]; struct smcd_dev *ism_dev[SMC_MAX_V2_ISM_DEVS + 1]; u16 ism_chid[SMC_MAX_V2_ISM_DEVS + 1]; u8 ism_offered_cnt; /* # of ISM devices offered */ u8 ism_selected; /* index of selected ISM dev*/ u8 smcd_version; }; /* Find the connection associated with the given alert token in the link group. * To use rbtrees we have to implement our own search core. * Requires @conns_lock * @token alert token to search for * @lgr link group to search in * Returns connection associated with token if found, NULL otherwise. */ static inline struct smc_connection *smc_lgr_find_conn( u32 token, struct smc_link_group *lgr) { struct smc_connection *res = NULL; struct rb_node *node; node = lgr->conns_all.rb_node; while (node) { struct smc_connection *cur = rb_entry(node, struct smc_connection, alert_node); if (cur->alert_token_local > token) { node = node->rb_left; } else { if (cur->alert_token_local < token) { node = node->rb_right; } else { res = cur; break; } } } return res; } static inline bool smc_conn_lgr_valid(struct smc_connection *conn) { return conn->lgr && conn->alert_token_local; } /* * Returns true if the specified link is usable. * * usable means the link is ready to receive RDMA messages, map memory * on the link, etc. This doesn't ensure we are able to send RDMA messages * on this link, if sending RDMA messages is needed, use smc_link_sendable() */ static inline bool smc_link_usable(struct smc_link *lnk) { if (lnk->state == SMC_LNK_UNUSED || lnk->state == SMC_LNK_INACTIVE) return false; return true; } /* * Returns true if the specified link is ready to receive AND send RDMA * messages. * * For the client side in first contact, the underlying QP may still in * RESET or RTR when the link state is ACTIVATING, checks in smc_link_usable() * is not strong enough. For those places that need to send any CDC or LLC * messages, use smc_link_sendable(), otherwise, use smc_link_usable() instead */ static inline bool smc_link_sendable(struct smc_link *lnk) { return smc_link_usable(lnk) && lnk->qp_attr.cur_qp_state == IB_QPS_RTS; } static inline bool smc_link_active(struct smc_link *lnk) { return lnk->state == SMC_LNK_ACTIVE; } static inline bool smc_link_shared_v2_rxbuf(struct smc_link *lnk) { return lnk->wr_rx_sge_cnt > 1; } static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) { sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", be16_to_cpu(((__be16 *)gid_raw)[0]), be16_to_cpu(((__be16 *)gid_raw)[1]), be16_to_cpu(((__be16 *)gid_raw)[2]), be16_to_cpu(((__be16 *)gid_raw)[3]), be16_to_cpu(((__be16 *)gid_raw)[4]), be16_to_cpu(((__be16 *)gid_raw)[5]), be16_to_cpu(((__be16 *)gid_raw)[6]), be16_to_cpu(((__be16 *)gid_raw)[7])); } struct smc_pci_dev { __u32 pci_fid; __u16 pci_pchid; __u16 pci_vendor; __u16 pci_device; __u8 pci_id[SMC_PCI_ID_STR_LEN]; }; static inline void smc_set_pci_values(struct pci_dev *pci_dev, struct smc_pci_dev *smc_dev) { smc_dev->pci_vendor = pci_dev->vendor; smc_dev->pci_device = pci_dev->device; snprintf(smc_dev->pci_id, sizeof(smc_dev->pci_id), "%s", pci_name(pci_dev)); #if IS_ENABLED(CONFIG_S390) { /* Set s390 specific PCI information */ struct zpci_dev *zdev; zdev = to_zpci(pci_dev); smc_dev->pci_fid = zdev->fid; smc_dev->pci_pchid = zdev->pchid; } #endif } struct smc_sock; struct smc_clc_msg_accept_confirm; void smc_lgr_cleanup_early(struct smc_link_group *lgr); void smc_lgr_terminate_sched(struct smc_link_group *lgr); void smc_lgr_hold(struct smc_link_group *lgr); void smc_lgr_put(struct smc_link_group *lgr); void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport); void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, unsigned short vlan); void smc_smcd_terminate_all(struct smcd_dev *dev); void smc_smcr_terminate_all(struct smc_ib_device *smcibdev); int smc_buf_create(struct smc_sock *smc, bool is_smcd); int smcd_buf_attach(struct smc_sock *smc); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *link, struct smc_clc_msg_accept_confirm *clc); int smc_rtoken_add(struct smc_link *lnk, __be64 nw_vaddr, __be32 nw_rkey); int smc_rtoken_delete(struct smc_link *lnk, __be32 nw_rkey); void smc_rtoken_set(struct smc_link_group *lgr, int link_idx, int link_idx_new, __be32 nw_rkey_known, __be64 nw_vaddr, __be32 nw_rkey); void smc_rtoken_set2(struct smc_link_group *lgr, int rtok_idx, int link_id, __be64 nw_vaddr, __be32 nw_rkey); void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn); void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn); int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini); int smc_core_init(void); void smc_core_exit(void); int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini); void smcr_link_clear(struct smc_link *lnk, bool log); void smcr_link_hold(struct smc_link *lnk); void smcr_link_put(struct smc_link *lnk); void smc_switch_link_and_count(struct smc_connection *conn, struct smc_link *to_lnk); int smcr_buf_map_lgr(struct smc_link *lnk); int smcr_buf_reg_lgr(struct smc_link *lnk); void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type); void smcr_lgr_set_type_asym(struct smc_link_group *lgr, enum smc_lgr_type new_type, int asym_lnk_idx); int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *rmb_desc); struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err); void smcr_link_down_cond(struct smc_link *lnk); void smcr_link_down_cond_sched(struct smc_link *lnk); int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb); int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb); int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { return link->lgr; } #endif |
| 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 | /* * Copyright (c) 2001 The Regents of the University of Michigan. * All rights reserved. * * Kendrick Smith <kmsmith@umich.edu> * Andy Adamson <kandros@umich.edu> * * 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 the University nor the names of its * contributors may be used to endorse or promote products derived * from this software without specific prior written permission. * * THIS SOFTWARE IS PROVIDED ``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 REGENTS 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/file.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/ratelimit.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> #include <linux/jhash.h> #include <linux/string_helpers.h> #include <linux/fsnotify.h> #include <linux/rhashtable.h> #include <linux/nfs_ssc.h> #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" #include "current_stateid.h" #include "netns.h" #include "pnfs.h" #include "filecache.h" #include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PROC #define all_ones {{ ~0, ~0}, ~0} static const stateid_t one_stateid = { .si_generation = ~0, .si_opaque = all_ones, }; static const stateid_t zero_stateid = { /* all fields zero */ }; static const stateid_t currentstateid = { .si_generation = 1, }; static const stateid_t close_stateid = { .si_generation = 0xffffffffU, }; static u64 current_sessionid = 1; #define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t))) #define ONE_STATEID(stateid) (!memcmp((stateid), &one_stateid, sizeof(stateid_t))) #define CURRENT_STATEID(stateid) (!memcmp((stateid), ¤tstateid, sizeof(stateid_t))) #define CLOSE_STATEID(stateid) (!memcmp((stateid), &close_stateid, sizeof(stateid_t))) /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); static void nfsd4_file_hash_remove(struct nfs4_file *fi); static void deleg_reaper(struct nfsd_net *nn); /* Locking: */ /* * Currently used for the del_recall_lru and file hash table. In an * effort to decrease the scope of the client_mutex, this spinlock may * eventually cover more: */ static DEFINE_SPINLOCK(state_lock); enum nfsd4_st_mutex_lock_subclass { OPEN_STATEID_MUTEX = 0, LOCK_STATEID_MUTEX = 1, }; /* * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for * the refcount on the open stateid to drop. */ static DECLARE_WAIT_QUEUE_HEAD(close_wq); /* * A waitqueue where a writer to clients/#/ctl destroying a client can * wait for cl_rpc_users to drop to 0 and then for the client to be * unhashed. */ static DECLARE_WAIT_QUEUE_HEAD(expiry_wq); static struct kmem_cache *client_slab; static struct kmem_cache *openowner_slab; static struct kmem_cache *lockowner_slab; static struct kmem_cache *file_slab; static struct kmem_cache *stateid_slab; static struct kmem_cache *deleg_slab; static struct kmem_cache *odstate_slab; static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops; static struct workqueue_struct *laundry_wq; int nfsd4_create_laundry_wq(void) { int rc = 0; laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); if (laundry_wq == NULL) rc = -ENOMEM; return rc; } void nfsd4_destroy_laundry_wq(void) { destroy_workqueue(laundry_wq); } static bool is_session_dead(struct nfsd4_session *ses) { return ses->se_dead; } static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me) { if (atomic_read(&ses->se_ref) > ref_held_by_me) return nfserr_jukebox; ses->se_dead = true; return nfs_ok; } static bool is_client_expired(struct nfs4_client *clp) { return clp->cl_time == 0; } static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn, struct nfs4_client *clp) { if (clp->cl_state != NFSD4_ACTIVE) atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0); } static __be32 get_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); if (is_client_expired(clp)) return nfserr_expired; atomic_inc(&clp->cl_rpc_users); nfsd4_dec_courtesy_client_count(nn, clp); clp->cl_state = NFSD4_ACTIVE; return nfs_ok; } /* must be called under the client_lock */ static inline void renew_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); if (is_client_expired(clp)) { WARN_ON(1); printk("%s: client (clientid %08x/%08x) already expired\n", __func__, clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); return; } list_move_tail(&clp->cl_lru, &nn->client_lru); clp->cl_time = ktime_get_boottime_seconds(); nfsd4_dec_courtesy_client_count(nn, clp); clp->cl_state = NFSD4_ACTIVE; } static void put_client_renew_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); if (!atomic_dec_and_test(&clp->cl_rpc_users)) return; if (!is_client_expired(clp)) renew_client_locked(clp); else wake_up_all(&expiry_wq); } static void put_client_renew(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); if (!atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) return; if (!is_client_expired(clp)) renew_client_locked(clp); else wake_up_all(&expiry_wq); spin_unlock(&nn->client_lock); } static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses) { __be32 status; if (is_session_dead(ses)) return nfserr_badsession; status = get_client_locked(ses->se_client); if (status) return status; atomic_inc(&ses->se_ref); return nfs_ok; } static void nfsd4_put_session_locked(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses)) free_session(ses); put_client_renew_locked(clp); } static void nfsd4_put_session(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); spin_lock(&nn->client_lock); nfsd4_put_session_locked(ses); spin_unlock(&nn->client_lock); } static struct nfsd4_blocked_lock * find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, struct nfsd_net *nn) { struct nfsd4_blocked_lock *cur, *found = NULL; spin_lock(&nn->blocked_locks_lock); list_for_each_entry(cur, &lo->lo_blocked, nbl_list) { if (fh_match(fh, &cur->nbl_fh)) { list_del_init(&cur->nbl_list); WARN_ON(list_empty(&cur->nbl_lru)); list_del_init(&cur->nbl_lru); found = cur; break; } } spin_unlock(&nn->blocked_locks_lock); if (found) locks_delete_block(&found->nbl_lock); return found; } static struct nfsd4_blocked_lock * find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, struct nfsd_net *nn) { struct nfsd4_blocked_lock *nbl; nbl = find_blocked_lock(lo, fh, nn); if (!nbl) { nbl = kmalloc(sizeof(*nbl), GFP_KERNEL); if (nbl) { INIT_LIST_HEAD(&nbl->nbl_list); INIT_LIST_HEAD(&nbl->nbl_lru); fh_copy_shallow(&nbl->nbl_fh, fh); locks_init_lock(&nbl->nbl_lock); kref_init(&nbl->nbl_kref); nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client, &nfsd4_cb_notify_lock_ops, NFSPROC4_CLNT_CB_NOTIFY_LOCK); } } return nbl; } static void free_nbl(struct kref *kref) { struct nfsd4_blocked_lock *nbl; nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref); locks_release_private(&nbl->nbl_lock); kfree(nbl); } static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { locks_delete_block(&nbl->nbl_lock); kref_put(&nbl->nbl_kref, free_nbl); } static void remove_blocked_locks(struct nfs4_lockowner *lo) { struct nfs4_client *clp = lo->lo_owner.so_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct nfsd4_blocked_lock *nbl; LIST_HEAD(reaplist); /* Dequeue all blocked locks */ spin_lock(&nn->blocked_locks_lock); while (!list_empty(&lo->lo_blocked)) { nbl = list_first_entry(&lo->lo_blocked, struct nfsd4_blocked_lock, nbl_list); list_del_init(&nbl->nbl_list); WARN_ON(list_empty(&nbl->nbl_lru)); list_move(&nbl->nbl_lru, &reaplist); } spin_unlock(&nn->blocked_locks_lock); /* Now free them */ while (!list_empty(&reaplist)) { nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); free_blocked_lock(nbl); } } static void nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) { struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); locks_delete_block(&nbl->nbl_lock); } static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { trace_nfsd_cb_notify_lock_done(&zero_stateid, task); /* * Since this is just an optimization, we don't try very hard if it * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and * just quit trying on anything else. */ switch (task->tk_status) { case -NFS4ERR_DELAY: rpc_delay(task, 1 * HZ); return 0; default: return 1; } } static void nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) { struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); free_blocked_lock(nbl); } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, .opcode = OP_CB_NOTIFY_LOCK, }; /* * We store the NONE, READ, WRITE, and BOTH bits separately in the * st_{access,deny}_bmap field of the stateid, in order to track not * only what share bits are currently in force, but also what * combinations of share bits previous opens have used. This allows us * to enforce the recommendation in * https://datatracker.ietf.org/doc/html/rfc7530#section-16.19.4 that * the server return an error if the client attempt to downgrade to a * combination of share bits not explicable by closing some of its * previous opens. * * This enforcement is arguably incomplete, since we don't keep * track of access/deny bit combinations; so, e.g., we allow: * * OPEN allow read, deny write * OPEN allow both, deny none * DOWNGRADE allow read, deny none * * which we should reject. * * But you could also argue that our current code is already overkill, * since it only exists to return NFS4ERR_INVAL on incorrect client * behavior. */ static unsigned int bmap_to_share_mode(unsigned long bmap) { int i; unsigned int access = 0; for (i = 1; i < 4; i++) { if (test_bit(i, &bmap)) access |= i; } return access; } /* set share access for a given stateid */ static inline void set_access(u32 access, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << access; WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); stp->st_access_bmap |= mask; } /* clear share access for a given stateid */ static inline void clear_access(u32 access, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << access; WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); stp->st_access_bmap &= ~mask; } /* test whether a given stateid has access */ static inline bool test_access(u32 access, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << access; return (bool)(stp->st_access_bmap & mask); } /* set share deny for a given stateid */ static inline void set_deny(u32 deny, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << deny; WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); stp->st_deny_bmap |= mask; } /* clear share deny for a given stateid */ static inline void clear_deny(u32 deny, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << deny; WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); stp->st_deny_bmap &= ~mask; } /* test whether a given stateid is denying specific access */ static inline bool test_deny(u32 deny, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << deny; return (bool)(stp->st_deny_bmap & mask); } static int nfs4_access_to_omode(u32 access) { switch (access & NFS4_SHARE_ACCESS_BOTH) { case NFS4_SHARE_ACCESS_READ: return O_RDONLY; case NFS4_SHARE_ACCESS_WRITE: return O_WRONLY; case NFS4_SHARE_ACCESS_BOTH: return O_RDWR; } WARN_ON_ONCE(1); return O_RDONLY; } static inline int access_permit_read(struct nfs4_ol_stateid *stp) { return test_access(NFS4_SHARE_ACCESS_READ, stp) || test_access(NFS4_SHARE_ACCESS_BOTH, stp) || test_access(NFS4_SHARE_ACCESS_WRITE, stp); } static inline int access_permit_write(struct nfs4_ol_stateid *stp) { return test_access(NFS4_SHARE_ACCESS_WRITE, stp) || test_access(NFS4_SHARE_ACCESS_BOTH, stp); } static inline struct nfs4_stateowner * nfs4_get_stateowner(struct nfs4_stateowner *sop) { atomic_inc(&sop->so_count); return sop; } static int same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner) { return (sop->so_owner.len == owner->len) && 0 == memcmp(sop->so_owner.data, owner->data, owner->len); } static struct nfs4_openowner * find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, struct nfs4_client *clp) { struct nfs4_stateowner *so; lockdep_assert_held(&clp->cl_lock); list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[hashval], so_strhash) { if (!so->so_is_open_owner) continue; if (same_owner_str(so, &open->op_owner)) return openowner(nfs4_get_stateowner(so)); } return NULL; } static inline u32 opaque_hashval(const void *ptr, int nbytes) { unsigned char *cptr = (unsigned char *) ptr; u32 x = 0; while (nbytes--) { x *= 37; x += *cptr++; } return x; } void put_nfs4_file(struct nfs4_file *fi) { if (refcount_dec_and_test(&fi->fi_ref)) { nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); kfree_rcu(fi, fi_rcu); } } static struct nfsd_file * find_writeable_file_locked(struct nfs4_file *f) { struct nfsd_file *ret; lockdep_assert_held(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } static struct nfsd_file * find_writeable_file(struct nfs4_file *f) { struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = find_writeable_file_locked(f); spin_unlock(&f->fi_lock); return ret; } static struct nfsd_file * find_readable_file_locked(struct nfs4_file *f) { struct nfsd_file *ret; lockdep_assert_held(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_RDONLY]); if (!ret) ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } static struct nfsd_file * find_readable_file(struct nfs4_file *f) { struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = find_readable_file_locked(f); spin_unlock(&f->fi_lock); return ret; } static struct nfsd_file * find_rw_file(struct nfs4_file *f) { struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_RDWR]); spin_unlock(&f->fi_lock); return ret; } struct nfsd_file * find_any_file(struct nfs4_file *f) { struct nfsd_file *ret; if (!f) return NULL; spin_lock(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_RDWR]); if (!ret) { ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) ret = nfsd_file_get(f->fi_fds[O_RDONLY]); } spin_unlock(&f->fi_lock); return ret; } static struct nfsd_file *find_any_file_locked(struct nfs4_file *f) { lockdep_assert_held(&f->fi_lock); if (f->fi_fds[O_RDWR]) return f->fi_fds[O_RDWR]; if (f->fi_fds[O_WRONLY]) return f->fi_fds[O_WRONLY]; if (f->fi_fds[O_RDONLY]) return f->fi_fds[O_RDONLY]; return NULL; } static atomic_long_t num_delegations; unsigned long max_delegations; /* * Open owner state (share locks) */ /* hash tables for lock and open owners */ #define OWNER_HASH_BITS 8 #define OWNER_HASH_SIZE (1 << OWNER_HASH_BITS) #define OWNER_HASH_MASK (OWNER_HASH_SIZE - 1) static unsigned int ownerstr_hashval(struct xdr_netobj *ownername) { unsigned int ret; ret = opaque_hashval(ownername->data, ownername->len); return ret & OWNER_HASH_MASK; } static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp; static const struct rhashtable_params nfs4_file_rhash_params = { .key_len = sizeof_field(struct nfs4_file, fi_inode), .key_offset = offsetof(struct nfs4_file, fi_inode), .head_offset = offsetof(struct nfs4_file, fi_rlist), /* * Start with a single page hash table to reduce resizing churn * on light workloads. */ .min_size = 256, .automatic_shrinking = true, }; /* * Check if courtesy clients have conflicting access and resolve it if possible * * access: is op_share_access if share_access is true. * Check if access mode, op_share_access, would conflict with * the current deny mode of the file 'fp'. * access: is op_share_deny if share_access is false. * Check if the deny mode, op_share_deny, would conflict with * current access of the file 'fp'. * stp: skip checking this entry. * new_stp: normal open, not open upgrade. * * Function returns: * false - access/deny mode conflict with normal client. * true - no conflict or conflict with courtesy client(s) is resolved. */ static bool nfs4_resolve_deny_conflicts_locked(struct nfs4_file *fp, bool new_stp, struct nfs4_ol_stateid *stp, u32 access, bool share_access) { struct nfs4_ol_stateid *st; bool resolvable = true; unsigned char bmap; struct nfsd_net *nn; struct nfs4_client *clp; lockdep_assert_held(&fp->fi_lock); list_for_each_entry(st, &fp->fi_stateids, st_perfile) { /* ignore lock stateid */ if (st->st_openstp) continue; if (st == stp && new_stp) continue; /* check file access against deny mode or vice versa */ bmap = share_access ? st->st_deny_bmap : st->st_access_bmap; if (!(access & bmap_to_share_mode(bmap))) continue; clp = st->st_stid.sc_client; if (try_to_expire_client(clp)) continue; resolvable = false; break; } if (resolvable) { clp = stp->st_stid.sc_client; nn = net_generic(clp->net, nfsd_net_id); mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); } return resolvable; } static void __nfs4_file_get_access(struct nfs4_file *fp, u32 access) { lockdep_assert_held(&fp->fi_lock); if (access & NFS4_SHARE_ACCESS_WRITE) atomic_inc(&fp->fi_access[O_WRONLY]); if (access & NFS4_SHARE_ACCESS_READ) atomic_inc(&fp->fi_access[O_RDONLY]); } static __be32 nfs4_file_get_access(struct nfs4_file *fp, u32 access) { lockdep_assert_held(&fp->fi_lock); /* Does this access mode make sense? */ if (access & ~NFS4_SHARE_ACCESS_BOTH) return nfserr_inval; /* Does it conflict with a deny mode already set? */ if ((access & fp->fi_share_deny) != 0) return nfserr_share_denied; __nfs4_file_get_access(fp, access); return nfs_ok; } static __be32 nfs4_file_check_deny(struct nfs4_file *fp, u32 deny) { /* Common case is that there is no deny mode. */ if (deny) { /* Does this deny mode make sense? */ if (deny & ~NFS4_SHARE_DENY_BOTH) return nfserr_inval; if ((deny & NFS4_SHARE_DENY_READ) && atomic_read(&fp->fi_access[O_RDONLY])) return nfserr_share_denied; if ((deny & NFS4_SHARE_DENY_WRITE) && atomic_read(&fp->fi_access[O_WRONLY])) return nfserr_share_denied; } return nfs_ok; } static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag) { might_lock(&fp->fi_lock); if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) { struct nfsd_file *f1 = NULL; struct nfsd_file *f2 = NULL; swap(f1, fp->fi_fds[oflag]); if (atomic_read(&fp->fi_access[1 - oflag]) == 0) swap(f2, fp->fi_fds[O_RDWR]); spin_unlock(&fp->fi_lock); if (f1) nfsd_file_put(f1); if (f2) nfsd_file_put(f2); } } static void nfs4_file_put_access(struct nfs4_file *fp, u32 access) { WARN_ON_ONCE(access & ~NFS4_SHARE_ACCESS_BOTH); if (access & NFS4_SHARE_ACCESS_WRITE) __nfs4_file_put_access(fp, O_WRONLY); if (access & NFS4_SHARE_ACCESS_READ) __nfs4_file_put_access(fp, O_RDONLY); } /* * Allocate a new open/delegation state counter. This is needed for * pNFS for proper return on close semantics. * * Note that we only allocate it for pNFS-enabled exports, otherwise * all pointers to struct nfs4_clnt_odstate are always NULL. */ static struct nfs4_clnt_odstate * alloc_clnt_odstate(struct nfs4_client *clp) { struct nfs4_clnt_odstate *co; co = kmem_cache_zalloc(odstate_slab, GFP_KERNEL); if (co) { co->co_client = clp; refcount_set(&co->co_odcount, 1); } return co; } static void hash_clnt_odstate_locked(struct nfs4_clnt_odstate *co) { struct nfs4_file *fp = co->co_file; lockdep_assert_held(&fp->fi_lock); list_add(&co->co_perfile, &fp->fi_clnt_odstate); } static inline void get_clnt_odstate(struct nfs4_clnt_odstate *co) { if (co) refcount_inc(&co->co_odcount); } static void put_clnt_odstate(struct nfs4_clnt_odstate *co) { struct nfs4_file *fp; if (!co) return; fp = co->co_file; if (refcount_dec_and_lock(&co->co_odcount, &fp->fi_lock)) { list_del(&co->co_perfile); spin_unlock(&fp->fi_lock); nfsd4_return_all_file_layouts(co->co_client, fp); kmem_cache_free(odstate_slab, co); } } static struct nfs4_clnt_odstate * find_or_hash_clnt_odstate(struct nfs4_file *fp, struct nfs4_clnt_odstate *new) { struct nfs4_clnt_odstate *co; struct nfs4_client *cl; if (!new) return NULL; cl = new->co_client; spin_lock(&fp->fi_lock); list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) { if (co->co_client == cl) { get_clnt_odstate(co); goto out; } } co = new; co->co_file = fp; hash_clnt_odstate_locked(new); out: spin_unlock(&fp->fi_lock); return co; } struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, void (*sc_free)(struct nfs4_stid *)) { struct nfs4_stid *stid; int new_id; stid = kmem_cache_zalloc(slab, GFP_KERNEL); if (!stid) return NULL; idr_preload(GFP_KERNEL); spin_lock(&cl->cl_lock); /* Reserving 0 for start of file in nfsdfs "states" file: */ new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 1, 0, GFP_NOWAIT); spin_unlock(&cl->cl_lock); idr_preload_end(); if (new_id < 0) goto out_free; stid->sc_free = sc_free; stid->sc_client = cl; stid->sc_stateid.si_opaque.so_id = new_id; stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; /* Will be incremented before return to client: */ refcount_set(&stid->sc_count, 1); spin_lock_init(&stid->sc_lock); INIT_LIST_HEAD(&stid->sc_cp_list); /* * It shouldn't be a problem to reuse an opaque stateid value. * I don't think it is for 4.1. But with 4.0 I worry that, for * example, a stray write retransmission could be accepted by * the server when it should have been rejected. Therefore, * adopt a trick from the sctp code to attempt to maximize the * amount of time until an id is reused, by ensuring they always * "increase" (mod INT_MAX): */ return stid; out_free: kmem_cache_free(slab, stid); return NULL; } /* * Create a unique stateid_t to represent each COPY. */ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, unsigned char cs_type) { int new_id; stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); stid->cs_stid.si_opaque.so_id = new_id; stid->cs_stid.si_generation = 1; spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) return 0; stid->cs_type = cs_type; return 1; } int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy) { return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID); } struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, struct nfs4_stid *p_stid) { struct nfs4_cpntf_state *cps; cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL); if (!cps) return NULL; cps->cpntf_time = ktime_get_boottime_seconds(); refcount_set(&cps->cp_stateid.cs_count, 1); if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) goto out_free; spin_lock(&nn->s2s_cp_lock); list_add(&cps->cp_list, &p_stid->sc_cp_list); spin_unlock(&nn->s2s_cp_lock); return cps; out_free: kfree(cps); return NULL; } void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; if (copy->cp_stateid.cs_type != NFS4_COPY_STID) return; nn = net_generic(copy->cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); idr_remove(&nn->s2s_cp_stateids, copy->cp_stateid.cs_stid.si_opaque.so_id); spin_unlock(&nn->s2s_cp_lock); } static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid) { struct nfs4_cpntf_state *cps; struct nfsd_net *nn; nn = net_generic(net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); while (!list_empty(&stid->sc_cp_list)) { cps = list_first_entry(&stid->sc_cp_list, struct nfs4_cpntf_state, cp_list); _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); } static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) { struct nfs4_stid *stid; stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid); if (!stid) return NULL; return openlockstateid(stid); } static void nfs4_free_deleg(struct nfs4_stid *stid) { struct nfs4_delegation *dp = delegstateid(stid); WARN_ON_ONCE(!list_empty(&stid->sc_cp_list)); WARN_ON_ONCE(!list_empty(&dp->dl_perfile)); WARN_ON_ONCE(!list_empty(&dp->dl_perclnt)); WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru)); kmem_cache_free(deleg_slab, stid); atomic_long_dec(&num_delegations); } /* * When we recall a delegation, we should be careful not to hand it * out again straight away. * To ensure this we keep a pair of bloom filters ('new' and 'old') * in which the filehandles of recalled delegations are "stored". * If a filehandle appear in either filter, a delegation is blocked. * When a delegation is recalled, the filehandle is stored in the "new" * filter. * Every 30 seconds we swap the filters and clear the "new" one, * unless both are empty of course. This results in delegations for a * given filehandle being blocked for between 30 and 60 seconds. * * Each filter is 256 bits. We hash the filehandle to 32bit and use the * low 3 bytes as hash-table indices. * * 'blocked_delegations_lock', which is always taken in block_delegations(), * is used to manage concurrent access. Testing does not need the lock * except when swapping the two filters. */ static DEFINE_SPINLOCK(blocked_delegations_lock); static struct bloom_pair { int entries, old_entries; time64_t swap_time; int new; /* index into 'set' */ DECLARE_BITMAP(set[2], 256); } blocked_delegations; static int delegation_blocked(struct knfsd_fh *fh) { u32 hash; struct bloom_pair *bd = &blocked_delegations; if (bd->entries == 0) return 0; if (ktime_get_seconds() - bd->swap_time > 30) { spin_lock(&blocked_delegations_lock); if (ktime_get_seconds() - bd->swap_time > 30) { bd->entries -= bd->old_entries; bd->old_entries = bd->entries; bd->new = 1-bd->new; memset(bd->set[bd->new], 0, sizeof(bd->set[0])); bd->swap_time = ktime_get_seconds(); } spin_unlock(&blocked_delegations_lock); } hash = jhash(&fh->fh_raw, fh->fh_size, 0); if (test_bit(hash&255, bd->set[0]) && test_bit((hash>>8)&255, bd->set[0]) && test_bit((hash>>16)&255, bd->set[0])) return 1; if (test_bit(hash&255, bd->set[1]) && test_bit((hash>>8)&255, bd->set[1]) && test_bit((hash>>16)&255, bd->set[1])) return 1; return 0; } static void block_delegations(struct knfsd_fh *fh) { u32 hash; struct bloom_pair *bd = &blocked_delegations; hash = jhash(&fh->fh_raw, fh->fh_size, 0); spin_lock(&blocked_delegations_lock); __set_bit(hash&255, bd->set[bd->new]); __set_bit((hash>>8)&255, bd->set[bd->new]); __set_bit((hash>>16)&255, bd->set[bd->new]); if (bd->entries == 0) bd->swap_time = ktime_get_seconds(); bd->entries += 1; spin_unlock(&blocked_delegations_lock); } static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate, u32 dl_type) { struct nfs4_delegation *dp; struct nfs4_stid *stid; long n; dprintk("NFSD alloc_init_deleg\n"); n = atomic_long_inc_return(&num_delegations); if (n < 0 || n > max_delegations) goto out_dec; if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg); if (stid == NULL) goto out_dec; dp = delegstateid(stid); /* * delegation seqid's are never incremented. The 4.1 special * meaning of seqid 0 isn't meaningful, really, but let's avoid * 0 anyway just for consistency and use 1: */ dp->dl_stid.sc_stateid.si_generation = 1; INIT_LIST_HEAD(&dp->dl_perfile); INIT_LIST_HEAD(&dp->dl_perclnt); INIT_LIST_HEAD(&dp->dl_recall_lru); dp->dl_clnt_odstate = odstate; get_clnt_odstate(odstate); dp->dl_type = dl_type; dp->dl_retries = 1; dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client, &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR); dp->dl_cb_fattr.ncf_file_modified = false; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; out_dec: atomic_long_dec(&num_delegations); return NULL; } void nfs4_put_stid(struct nfs4_stid *s) { struct nfs4_file *fp = s->sc_file; struct nfs4_client *clp = s->sc_client; might_lock(&clp->cl_lock); if (!refcount_dec_and_lock(&s->sc_count, &clp->cl_lock)) { wake_up_all(&close_wq); return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); if (s->sc_status & SC_STATUS_ADMIN_REVOKED) atomic_dec(&s->sc_client->cl_admin_revoked); nfs4_free_cpntf_statelist(clp->net, s); spin_unlock(&clp->cl_lock); s->sc_free(s); if (fp) put_nfs4_file(fp); } void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) { stateid_t *src = &stid->sc_stateid; spin_lock(&stid->sc_lock); if (unlikely(++src->si_generation == 0)) src->si_generation = 1; memcpy(dst, src, sizeof(*dst)); spin_unlock(&stid->sc_lock); } static void put_deleg_file(struct nfs4_file *fp) { struct nfsd_file *nf = NULL; spin_lock(&fp->fi_lock); if (--fp->fi_delegees == 0) swap(nf, fp->fi_deleg_file); spin_unlock(&fp->fi_lock); if (nf) nfsd_file_put(nf); } static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; struct nfsd_file *nf = fp->fi_deleg_file; WARN_ON_ONCE(!fp->fi_delegees); kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); put_deleg_file(fp); } static void destroy_unhashed_deleg(struct nfs4_delegation *dp) { put_clnt_odstate(dp->dl_clnt_odstate); nfs4_unlock_deleg_lease(dp); nfs4_put_stid(&dp->dl_stid); } /** * nfs4_delegation_exists - Discover if this delegation already exists * @clp: a pointer to the nfs4_client we're granting a delegation to * @fp: a pointer to the nfs4_file we're granting a delegation on * * Return: * On success: true iff an existing delegation is found */ static bool nfs4_delegation_exists(struct nfs4_client *clp, struct nfs4_file *fp) { struct nfs4_delegation *searchdp = NULL; struct nfs4_client *searchclp = NULL; lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) { searchclp = searchdp->dl_stid.sc_client; if (clp == searchclp) { return true; } } return false; } /** * hash_delegation_locked - Add a delegation to the appropriate lists * @dp: a pointer to the nfs4_delegation we are adding. * @fp: a pointer to the nfs4_file we're granting a delegation on * * Return: * On success: NULL if the delegation was successfully hashed. * * On error: -EAGAIN if one was previously granted to this * nfs4_client for this nfs4_file. Delegation is not hashed. * */ static int hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) { struct nfs4_client *clp = dp->dl_stid.sc_client; lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); lockdep_assert_held(&clp->cl_lock); if (nfs4_delegation_exists(clp, fp)) return -EAGAIN; refcount_inc(&dp->dl_stid.sc_count); dp->dl_stid.sc_type = SC_TYPE_DELEG; list_add(&dp->dl_perfile, &fp->fi_delegations); list_add(&dp->dl_perclnt, &clp->cl_delegations); return 0; } static bool delegation_hashed(struct nfs4_delegation *dp) { return !(list_empty(&dp->dl_perfile)); } static bool unhash_delegation_locked(struct nfs4_delegation *dp, unsigned short statusmask) { struct nfs4_file *fp = dp->dl_stid.sc_file; lockdep_assert_held(&state_lock); if (!delegation_hashed(dp)) return false; if (statusmask == SC_STATUS_REVOKED && dp->dl_stid.sc_client->cl_minorversion == 0) statusmask = SC_STATUS_CLOSED; dp->dl_stid.sc_status |= statusmask; if (statusmask & SC_STATUS_ADMIN_REVOKED) atomic_inc(&dp->dl_stid.sc_client->cl_admin_revoked); /* Ensure that deleg break won't try to requeue it */ ++dp->dl_time; spin_lock(&fp->fi_lock); list_del_init(&dp->dl_perclnt); list_del_init(&dp->dl_recall_lru); list_del_init(&dp->dl_perfile); spin_unlock(&fp->fi_lock); return true; } static void destroy_delegation(struct nfs4_delegation *dp) { bool unhashed; spin_lock(&state_lock); unhashed = unhash_delegation_locked(dp, SC_STATUS_CLOSED); spin_unlock(&state_lock); if (unhashed) destroy_unhashed_deleg(dp); } /** * revoke_delegation - perform nfs4 delegation structure cleanup * @dp: pointer to the delegation * * This function assumes that it's called either from the administrative * interface (nfsd4_revoke_states()) that's revoking a specific delegation * stateid or it's called from a laundromat thread (nfsd4_landromat()) that * determined that this specific state has expired and needs to be revoked * (both mark state with the appropriate stid sc_status mode). It is also * assumed that a reference was taken on the @dp state. * * If this function finds that the @dp state is SC_STATUS_FREED it means * that a FREE_STATEID operation for this stateid has been processed and * we can proceed to removing it from recalled list. However, if @dp state * isn't marked SC_STATUS_FREED, it means we need place it on the cl_revoked * list and wait for the FREE_STATEID to arrive from the client. At the same * time, we need to mark it as SC_STATUS_FREEABLE to indicate to the * nfsd4_free_stateid() function that this stateid has already been added * to the cl_revoked list and that nfsd4_free_stateid() is now responsible * for removing it from the list. Inspection of where the delegation state * in the revocation process is protected by the clp->cl_lock. */ static void revoke_delegation(struct nfs4_delegation *dp) { struct nfs4_client *clp = dp->dl_stid.sc_client; WARN_ON(!list_empty(&dp->dl_recall_lru)); WARN_ON_ONCE(!(dp->dl_stid.sc_status & (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED))); trace_nfsd_stid_revoke(&dp->dl_stid); spin_lock(&clp->cl_lock); if (dp->dl_stid.sc_status & SC_STATUS_FREED) { list_del_init(&dp->dl_recall_lru); goto out; } list_add(&dp->dl_recall_lru, &clp->cl_revoked); dp->dl_stid.sc_status |= SC_STATUS_FREEABLE; out: spin_unlock(&clp->cl_lock); destroy_unhashed_deleg(dp); } /* * SETCLIENTID state */ static unsigned int clientid_hashval(u32 id) { return id & CLIENT_HASH_MASK; } static unsigned int clientstr_hashval(struct xdr_netobj name) { return opaque_hashval(name.data, 8) & CLIENT_HASH_MASK; } /* * A stateid that had a deny mode associated with it is being released * or downgraded. Recalculate the deny mode on the file. */ static void recalculate_deny_mode(struct nfs4_file *fp) { struct nfs4_ol_stateid *stp; u32 old_deny; spin_lock(&fp->fi_lock); old_deny = fp->fi_share_deny; fp->fi_share_deny = 0; list_for_each_entry(stp, &fp->fi_stateids, st_perfile) { fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap); if (fp->fi_share_deny == old_deny) break; } spin_unlock(&fp->fi_lock); } static void reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp) { int i; bool change = false; for (i = 1; i < 4; i++) { if ((i & deny) != i) { change = true; clear_deny(i, stp); } } /* Recalculate per-file deny mode if there was a change */ if (change) recalculate_deny_mode(stp->st_stid.sc_file); } /* release all access and file references for a given stateid */ static void release_all_access(struct nfs4_ol_stateid *stp) { int i; struct nfs4_file *fp = stp->st_stid.sc_file; if (fp && stp->st_deny_bmap != 0) recalculate_deny_mode(fp); for (i = 1; i < 4; i++) { if (test_access(i, stp)) nfs4_file_put_access(stp->st_stid.sc_file, i); clear_access(i, stp); } } static inline void nfs4_free_stateowner(struct nfs4_stateowner *sop) { kfree(sop->so_owner.data); sop->so_ops->so_free(sop); } static void nfs4_put_stateowner(struct nfs4_stateowner *sop) { struct nfs4_client *clp = sop->so_client; might_lock(&clp->cl_lock); if (!atomic_dec_and_lock(&sop->so_count, &clp->cl_lock)) return; sop->so_ops->so_unhash(sop); spin_unlock(&clp->cl_lock); nfs4_free_stateowner(sop); } static bool nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp) { return list_empty(&stp->st_perfile); } static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_file *fp = stp->st_stid.sc_file; lockdep_assert_held(&stp->st_stateowner->so_client->cl_lock); if (list_empty(&stp->st_perfile)) return false; spin_lock(&fp->fi_lock); list_del_init(&stp->st_perfile); spin_unlock(&fp->fi_lock); list_del(&stp->st_perstateowner); return true; } static void nfs4_free_ol_stateid(struct nfs4_stid *stid) { struct nfs4_ol_stateid *stp = openlockstateid(stid); put_clnt_odstate(stp->st_clnt_odstate); release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); WARN_ON(!list_empty(&stid->sc_cp_list)); kmem_cache_free(stateid_slab, stid); } static void nfs4_free_lock_stateid(struct nfs4_stid *stid) { struct nfs4_ol_stateid *stp = openlockstateid(stid); struct nfs4_lockowner *lo = lockowner(stp->st_stateowner); struct nfsd_file *nf; nf = find_any_file(stp->st_stid.sc_file); if (nf) { get_file(nf->nf_file); filp_close(nf->nf_file, (fl_owner_t)lo); nfsd_file_put(nf); } nfs4_free_ol_stateid(stid); } /* * Put the persistent reference to an already unhashed generic stateid, while * holding the cl_lock. If it's the last reference, then put it onto the * reaplist for later destruction. */ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { struct nfs4_stid *s = &stp->st_stid; struct nfs4_client *clp = s->sc_client; lockdep_assert_held(&clp->cl_lock); WARN_ON_ONCE(!list_empty(&stp->st_locks)); if (!refcount_dec_and_test(&s->sc_count)) { wake_up_all(&close_wq); return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); if (s->sc_status & SC_STATUS_ADMIN_REVOKED) atomic_dec(&s->sc_client->cl_admin_revoked); list_add(&stp->st_locks, reaplist); } static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); if (!unhash_ol_stateid(stp)) return false; list_del_init(&stp->st_locks); stp->st_stid.sc_status |= SC_STATUS_CLOSED; return true; } static void release_lock_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_client *clp = stp->st_stid.sc_client; bool unhashed; spin_lock(&clp->cl_lock); unhashed = unhash_lock_stateid(stp); spin_unlock(&clp->cl_lock); if (unhashed) nfs4_put_stid(&stp->st_stid); } static void unhash_lockowner_locked(struct nfs4_lockowner *lo) { struct nfs4_client *clp = lo->lo_owner.so_client; lockdep_assert_held(&clp->cl_lock); list_del_init(&lo->lo_owner.so_strhash); } /* * Free a list of generic stateids that were collected earlier after being * fully unhashed. */ static void free_ol_stateid_reaplist(struct list_head *reaplist) { struct nfs4_ol_stateid *stp; struct nfs4_file *fp; might_sleep(); while (!list_empty(reaplist)) { stp = list_first_entry(reaplist, struct nfs4_ol_stateid, st_locks); list_del(&stp->st_locks); fp = stp->st_stid.sc_file; stp->st_stid.sc_free(&stp->st_stid); if (fp) put_nfs4_file(fp); } } static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, struct list_head *reaplist) { struct nfs4_ol_stateid *stp; lockdep_assert_held(&open_stp->st_stid.sc_client->cl_lock); while (!list_empty(&open_stp->st_locks)) { stp = list_entry(open_stp->st_locks.next, struct nfs4_ol_stateid, st_locks); unhash_lock_stateid(stp); put_ol_stateid_locked(stp, reaplist); } } static bool unhash_open_stateid(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); if (!unhash_ol_stateid(stp)) return false; release_open_stateid_locks(stp, reaplist); return true; } static void release_open_stateid(struct nfs4_ol_stateid *stp) { LIST_HEAD(reaplist); spin_lock(&stp->st_stid.sc_client->cl_lock); stp->st_stid.sc_status |= SC_STATUS_CLOSED; if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); spin_unlock(&stp->st_stid.sc_client->cl_lock); free_ol_stateid_reaplist(&reaplist); } static bool nfs4_openowner_unhashed(struct nfs4_openowner *oo) { lockdep_assert_held(&oo->oo_owner.so_client->cl_lock); return list_empty(&oo->oo_owner.so_strhash) && list_empty(&oo->oo_perclient); } static void unhash_openowner_locked(struct nfs4_openowner *oo) { struct nfs4_client *clp = oo->oo_owner.so_client; lockdep_assert_held(&clp->cl_lock); list_del_init(&oo->oo_owner.so_strhash); list_del_init(&oo->oo_perclient); } static void release_last_closed_stateid(struct nfs4_openowner *oo) { struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net, nfsd_net_id); struct nfs4_ol_stateid *s; spin_lock(&nn->client_lock); s = oo->oo_last_closed_stid; if (s) { list_del_init(&oo->oo_close_lru); oo->oo_last_closed_stid = NULL; } spin_unlock(&nn->client_lock); if (s) nfs4_put_stid(&s->st_stid); } static void release_openowner(struct nfs4_openowner *oo) { struct nfs4_ol_stateid *stp; struct nfs4_client *clp = oo->oo_owner.so_client; LIST_HEAD(reaplist); spin_lock(&clp->cl_lock); unhash_openowner_locked(oo); while (!list_empty(&oo->oo_owner.so_stateids)) { stp = list_first_entry(&oo->oo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); release_last_closed_stateid(oo); nfs4_put_stateowner(&oo->oo_owner); } static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, struct super_block *sb, unsigned int sc_types) { unsigned long id, tmp; struct nfs4_stid *stid; spin_lock(&clp->cl_lock); idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) if ((stid->sc_type & sc_types) && stid->sc_status == 0 && stid->sc_file->fi_inode->i_sb == sb) { refcount_inc(&stid->sc_count); break; } spin_unlock(&clp->cl_lock); return stid; } /** * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem * @net: used to identify instance of nfsd (there is one per net namespace) * @sb: super_block used to identify target filesystem * * All nfs4 states (open, lock, delegation, layout) held by the server instance * and associated with a file on the given filesystem will be revoked resulting * in any files being closed and so all references from nfsd to the filesystem * being released. Thus nfsd will no longer prevent the filesystem from being * unmounted. * * The clients which own the states will subsequently being notified that the * states have been "admin-revoked". */ void nfsd4_revoke_states(struct net *net, struct super_block *sb) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); unsigned int idhashval; unsigned int sc_types; sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; spin_lock(&nn->client_lock); for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { struct list_head *head = &nn->conf_id_hashtbl[idhashval]; struct nfs4_client *clp; retry: list_for_each_entry(clp, head, cl_idhash) { struct nfs4_stid *stid = find_one_sb_stid(clp, sb, sc_types); if (stid) { struct nfs4_ol_stateid *stp; struct nfs4_delegation *dp; struct nfs4_layout_stateid *ls; spin_unlock(&nn->client_lock); switch (stid->sc_type) { case SC_TYPE_OPEN: stp = openlockstateid(stid); mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); spin_lock(&clp->cl_lock); if (stid->sc_status == 0) { stid->sc_status |= SC_STATUS_ADMIN_REVOKED; atomic_inc(&clp->cl_admin_revoked); spin_unlock(&clp->cl_lock); release_all_access(stp); } else spin_unlock(&clp->cl_lock); mutex_unlock(&stp->st_mutex); break; case SC_TYPE_LOCK: stp = openlockstateid(stid); mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); spin_lock(&clp->cl_lock); if (stid->sc_status == 0) { struct nfs4_lockowner *lo = lockowner(stp->st_stateowner); struct nfsd_file *nf; stid->sc_status |= SC_STATUS_ADMIN_REVOKED; atomic_inc(&clp->cl_admin_revoked); spin_unlock(&clp->cl_lock); nf = find_any_file(stp->st_stid.sc_file); if (nf) { get_file(nf->nf_file); filp_close(nf->nf_file, (fl_owner_t)lo); nfsd_file_put(nf); } release_all_access(stp); } else spin_unlock(&clp->cl_lock); mutex_unlock(&stp->st_mutex); break; case SC_TYPE_DELEG: refcount_inc(&stid->sc_count); dp = delegstateid(stid); spin_lock(&state_lock); if (!unhash_delegation_locked( dp, SC_STATUS_ADMIN_REVOKED)) dp = NULL; spin_unlock(&state_lock); if (dp) revoke_delegation(dp); break; case SC_TYPE_LAYOUT: ls = layoutstateid(stid); nfsd4_close_layout(ls); break; } nfs4_put_stid(stid); spin_lock(&nn->client_lock); if (clp->cl_minorversion == 0) /* Allow cleanup after a lease period. * store_release ensures cleanup will * see any newly revoked states if it * sees the time updated. */ nn->nfs40_last_revoke = ktime_get_boottime_seconds(); goto retry; } } } spin_unlock(&nn->client_lock); } static inline int hash_sessionid(struct nfs4_sessionid *sessionid) { struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid; return sid->sequence % SESSION_HASH_SIZE; } #ifdef CONFIG_SUNRPC_DEBUG static inline void dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) { u32 *ptr = (u32 *)(&sessionid->data[0]); dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]); } #else static inline void dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) { } #endif /* * Bump the seqid on cstate->replay_owner, and clear replay_owner if it * won't be used for replay. */ void nfsd4_bump_seqid(struct nfsd4_compound_state *cstate, __be32 nfserr) { struct nfs4_stateowner *so = cstate->replay_owner; if (nfserr == nfserr_replay_me) return; if (!seqid_mutating_err(ntohl(nfserr))) { nfsd4_cstate_clear_replay(cstate); return; } if (!so) return; if (so->so_is_open_owner) release_last_closed_stateid(openowner(so)); so->so_seqid++; return; } static void gen_sessionid(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd4_sessionid *sid; sid = (struct nfsd4_sessionid *)ses->se_sessionid.data; sid->clientid = clp->cl_clientid; sid->sequence = current_sessionid++; sid->reserved = 0; } /* * The protocol defines ca_maxresponssize_cached to include the size of * the rpc header, but all we need to cache is the data starting after * the end of the initial SEQUENCE operation--the rest we regenerate * each time. Therefore we can advertise a ca_maxresponssize_cached * value that is the number of bytes in our cache plus a few additional * bytes. In order to stay on the safe side, and not promise more than * we can cache, those additional bytes must be the minimum possible: 24 * bytes of rpc header (xid through accept state, with AUTH_NULL * verifier), 12 for the compound header (with zero-length tag), and 44 * for the SEQUENCE op response: */ #define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44) static struct shrinker *nfsd_slot_shrinker; static DEFINE_SPINLOCK(nfsd_session_list_lock); static LIST_HEAD(nfsd_session_list); /* The sum of "target_slots-1" on every session. The shrinker can push this * down, though it can take a little while for the memory to actually * be freed. The "-1" is because we can never free slot 0 while the * session is active. */ static atomic_t nfsd_total_target_slots = ATOMIC_INIT(0); static void free_session_slots(struct nfsd4_session *ses, int from) { int i; if (from >= ses->se_fchannel.maxreqs) return; for (i = from; i < ses->se_fchannel.maxreqs; i++) { struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); /* * Save the seqid in case we reactivate this slot. * This will never require a memory allocation so GFP * flag is irrelevant */ xa_store(&ses->se_slots, i, xa_mk_value(slot->sl_seqid), 0); free_svc_cred(&slot->sl_cred); kfree(slot); } ses->se_fchannel.maxreqs = from; if (ses->se_target_maxslots > from) { int new_target = from ?: 1; atomic_sub(ses->se_target_maxslots - new_target, &nfsd_total_target_slots); ses->se_target_maxslots = new_target; } } /** * reduce_session_slots - reduce the target max-slots of a session if possible * @ses: The session to affect * @dec: how much to decrease the target by * * This interface can be used by a shrinker to reduce the target max-slots * for a session so that some slots can eventually be freed. * It uses spin_trylock() as it may be called in a context where another * spinlock is held that has a dependency on client_lock. As shrinkers are * best-effort, skiping a session is client_lock is already held has no * great coast * * Return value: * The number of slots that the target was reduced by. */ static int reduce_session_slots(struct nfsd4_session *ses, int dec) { struct nfsd_net *nn = net_generic(ses->se_client->net, nfsd_net_id); int ret = 0; if (ses->se_target_maxslots <= 1) return ret; if (!spin_trylock(&nn->client_lock)) return ret; ret = min(dec, ses->se_target_maxslots-1); ses->se_target_maxslots -= ret; atomic_sub(ret, &nfsd_total_target_slots); ses->se_slot_gen += 1; if (ses->se_slot_gen == 0) { int i; ses->se_slot_gen = 1; for (i = 0; i < ses->se_fchannel.maxreqs; i++) { struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); slot->sl_generation = 0; } } spin_unlock(&nn->client_lock); return ret; } /* * We don't actually need to cache the rpc and session headers, so we * can allocate a little less for each slot: */ static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca) { u32 size; if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ) size = 0; else size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; return size + sizeof(struct nfsd4_slot); } static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, struct nfsd4_channel_attrs *battrs) { int numslots = fattrs->maxreqs; int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; struct nfsd4_slot *slot; int i; new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; xa_init(&new->se_slots); /* allocate each struct nfsd4_slot and data cache in one piece */ slot = kzalloc(slotsize, GFP_KERNEL); if (!slot || xa_is_err(xa_store(&new->se_slots, 0, slot, GFP_KERNEL))) goto out_free; for (i = 1; i < numslots; i++) { const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; slot = kzalloc(slotsize, gfp); if (!slot) break; if (xa_is_err(xa_store(&new->se_slots, i, slot, gfp))) { kfree(slot); break; } } fattrs->maxreqs = i; memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); new->se_target_maxslots = i; atomic_add(i - 1, &nfsd_total_target_slots); new->se_cb_slot_avail = ~0U; new->se_cb_highest_slot = min(battrs->maxreqs - 1, NFSD_BC_SLOT_TABLE_SIZE - 1); spin_lock_init(&new->se_lock); return new; out_free: kfree(slot); xa_destroy(&new->se_slots); kfree(new); return NULL; } static void free_conn(struct nfsd4_conn *c) { svc_xprt_put(c->cn_xprt); kfree(c); } static void nfsd4_conn_lost(struct svc_xpt_user *u) { struct nfsd4_conn *c = container_of(u, struct nfsd4_conn, cn_xpt_user); struct nfs4_client *clp = c->cn_session->se_client; trace_nfsd_cb_lost(clp); spin_lock(&clp->cl_lock); if (!list_empty(&c->cn_persession)) { list_del(&c->cn_persession); free_conn(c); } nfsd4_probe_callback(clp); spin_unlock(&clp->cl_lock); } static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags) { struct nfsd4_conn *conn; conn = kmalloc(sizeof(struct nfsd4_conn), GFP_KERNEL); if (!conn) return NULL; svc_xprt_get(rqstp->rq_xprt); conn->cn_xprt = rqstp->rq_xprt; conn->cn_flags = flags; INIT_LIST_HEAD(&conn->cn_xpt_user.list); return conn; } static void __nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses) { conn->cn_session = ses; list_add(&conn->cn_persession, &ses->se_conns); } static void nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; spin_lock(&clp->cl_lock); __nfsd4_hash_conn(conn, ses); spin_unlock(&clp->cl_lock); } static int nfsd4_register_conn(struct nfsd4_conn *conn) { conn->cn_xpt_user.callback = nfsd4_conn_lost; return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user); } static void nfsd4_init_conn(struct svc_rqst *rqstp, struct nfsd4_conn *conn, struct nfsd4_session *ses) { int ret; nfsd4_hash_conn(conn, ses); ret = nfsd4_register_conn(conn); if (ret) /* oops; xprt is already down: */ nfsd4_conn_lost(&conn->cn_xpt_user); /* We may have gained or lost a callback channel: */ nfsd4_probe_callback_sync(ses->se_client); } static struct nfsd4_conn *alloc_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_create_session *cses) { u32 dir = NFS4_CDFC4_FORE; if (cses->flags & SESSION4_BACK_CHAN) dir |= NFS4_CDFC4_BACK; return alloc_conn(rqstp, dir); } /* must be called under client_lock */ static void nfsd4_del_conns(struct nfsd4_session *s) { struct nfs4_client *clp = s->se_client; struct nfsd4_conn *c; spin_lock(&clp->cl_lock); while (!list_empty(&s->se_conns)) { c = list_first_entry(&s->se_conns, struct nfsd4_conn, cn_persession); list_del_init(&c->cn_persession); spin_unlock(&clp->cl_lock); unregister_xpt_user(c->cn_xprt, &c->cn_xpt_user); free_conn(c); spin_lock(&clp->cl_lock); } spin_unlock(&clp->cl_lock); } static void __free_session(struct nfsd4_session *ses) { free_session_slots(ses, 0); xa_destroy(&ses->se_slots); kfree(ses); } static void free_session(struct nfsd4_session *ses) { nfsd4_del_conns(ses); __free_session(ses); } static unsigned long nfsd_slot_count(struct shrinker *s, struct shrink_control *sc) { unsigned long cnt = atomic_read(&nfsd_total_target_slots); return cnt ? cnt : SHRINK_EMPTY; } static unsigned long nfsd_slot_scan(struct shrinker *s, struct shrink_control *sc) { struct nfsd4_session *ses; unsigned long scanned = 0; unsigned long freed = 0; spin_lock(&nfsd_session_list_lock); list_for_each_entry(ses, &nfsd_session_list, se_all_sessions) { freed += reduce_session_slots(ses, 1); scanned += 1; if (scanned >= sc->nr_to_scan) { /* Move starting point for next scan */ list_move(&nfsd_session_list, &ses->se_all_sessions); break; } } spin_unlock(&nfsd_session_list_lock); sc->nr_scanned = scanned; return freed; } static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) { int idx; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); new->se_client = clp; gen_sessionid(new); INIT_LIST_HEAD(&new->se_conns); atomic_set(&new->se_ref, 0); new->se_dead = false; new->se_cb_prog = cses->callback_prog; new->se_cb_sec = cses->cb_sec; for (idx = 0; idx < NFSD_BC_SLOT_TABLE_SIZE; ++idx) new->se_cb_seq_nr[idx] = 1; idx = hash_sessionid(&new->se_sessionid); list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]); spin_lock(&clp->cl_lock); list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); spin_lock(&nfsd_session_list_lock); list_add_tail(&new->se_all_sessions, &nfsd_session_list); spin_unlock(&nfsd_session_list_lock); { struct sockaddr *sa = svc_addr(rqstp); /* * This is a little silly; with sessions there's no real * use for the callback address. Use the peer address * as a reasonable default for now, but consider fixing * the rpc client not to require an address in the * future: */ rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa); clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa); } } /* caller must hold client_lock */ static struct nfsd4_session * __find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net) { struct nfsd4_session *elem; int idx; struct nfsd_net *nn = net_generic(net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); dump_sessionid(__func__, sessionid); idx = hash_sessionid(sessionid); /* Search in the appropriate list */ list_for_each_entry(elem, &nn->sessionid_hashtbl[idx], se_hash) { if (!memcmp(elem->se_sessionid.data, sessionid->data, NFS4_MAX_SESSIONID_LEN)) { return elem; } } dprintk("%s: session not found\n", __func__); return NULL; } static struct nfsd4_session * find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net, __be32 *ret) { struct nfsd4_session *session; __be32 status = nfserr_badsession; session = __find_in_sessionid_hashtbl(sessionid, net); if (!session) goto out; status = nfsd4_get_session_locked(session); if (status) session = NULL; out: *ret = status; return session; } /* caller must hold client_lock */ static void unhash_session(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); list_del(&ses->se_hash); spin_lock(&ses->se_client->cl_lock); list_del(&ses->se_perclnt); spin_unlock(&ses->se_client->cl_lock); spin_lock(&nfsd_session_list_lock); list_del(&ses->se_all_sessions); spin_unlock(&nfsd_session_list_lock); } /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */ static int STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) { /* * We're assuming the clid was not given out from a boot * precisely 2^32 (about 136 years) before this one. That seems * a safe assumption: */ if (clid->cl_boot == (u32)nn->boot_time) return 0; trace_nfsd_clid_stale(clid); return 1; } static struct nfs4_client *alloc_client(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client *clp; int i; if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients && atomic_read(&nn->nfsd_courtesy_clients) > 0) mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; xdr_netobj_dup(&clp->cl_name, &name, GFP_KERNEL); if (clp->cl_name.data == NULL) goto err_no_name; clp->cl_ownerstr_hashtbl = kmalloc_array(OWNER_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!clp->cl_ownerstr_hashtbl) goto err_no_hashtbl; clp->cl_callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0); if (!clp->cl_callback_wq) goto err_no_callback_wq; for (i = 0; i < OWNER_HASH_SIZE; i++) INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]); INIT_LIST_HEAD(&clp->cl_sessions); idr_init(&clp->cl_stateids); atomic_set(&clp->cl_rpc_users, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; clp->cl_state = NFSD4_ACTIVE; atomic_inc(&nn->nfs4_client_count); atomic_set(&clp->cl_delegs_in_recall, 0); INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); INIT_LIST_HEAD(&clp->cl_lru); INIT_LIST_HEAD(&clp->cl_revoked); #ifdef CONFIG_NFSD_PNFS INIT_LIST_HEAD(&clp->cl_lo_states); #endif INIT_LIST_HEAD(&clp->async_copies); spin_lock_init(&clp->async_lock); spin_lock_init(&clp->cl_lock); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; err_no_callback_wq: kfree(clp->cl_ownerstr_hashtbl); err_no_hashtbl: kfree(clp->cl_name.data); err_no_name: kmem_cache_free(client_slab, clp); return NULL; } static void __free_client(struct kref *k) { struct nfsdfs_client *c = container_of(k, struct nfsdfs_client, cl_ref); struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs); free_svc_cred(&clp->cl_cred); destroy_workqueue(clp->cl_callback_wq); kfree(clp->cl_ownerstr_hashtbl); kfree(clp->cl_name.data); kfree(clp->cl_nii_domain.data); kfree(clp->cl_nii_name.data); idr_destroy(&clp->cl_stateids); kfree(clp->cl_ra); kmem_cache_free(client_slab, clp); } static void drop_client(struct nfs4_client *clp) { kref_put(&clp->cl_nfsdfs.cl_ref, __free_client); } static void free_client(struct nfs4_client *clp) { while (!list_empty(&clp->cl_sessions)) { struct nfsd4_session *ses; ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, se_perclnt); list_del(&ses->se_perclnt); WARN_ON_ONCE(atomic_read(&ses->se_ref)); free_session(ses); } rpc_destroy_wait_queue(&clp->cl_cb_waitq); if (clp->cl_nfsd_dentry) { nfsd_client_rmdir(clp->cl_nfsd_dentry); clp->cl_nfsd_dentry = NULL; wake_up_all(&expiry_wq); } drop_client(clp); } /* must be called under the client_lock */ static void unhash_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct nfsd4_session *ses; lockdep_assert_held(&nn->client_lock); /* Mark the client as expired! */ clp->cl_time = 0; /* Make it invisible */ if (!list_empty(&clp->cl_idhash)) { list_del_init(&clp->cl_idhash); if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) rb_erase(&clp->cl_namenode, &nn->conf_name_tree); else rb_erase(&clp->cl_namenode, &nn->unconf_name_tree); } list_del_init(&clp->cl_lru); spin_lock(&clp->cl_lock); spin_lock(&nfsd_session_list_lock); list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) { list_del_init(&ses->se_hash); list_del_init(&ses->se_all_sessions); } spin_unlock(&nfsd_session_list_lock); spin_unlock(&clp->cl_lock); } static void unhash_client(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); spin_lock(&nn->client_lock); unhash_client_locked(clp); spin_unlock(&nn->client_lock); } static __be32 mark_client_expired_locked(struct nfs4_client *clp) { int users = atomic_read(&clp->cl_rpc_users); trace_nfsd_mark_client_expired(clp, users); if (users) return nfserr_jukebox; unhash_client_locked(clp); return nfs_ok; } static void __destroy_client(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; LIST_HEAD(reaplist); spin_lock(&state_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); while (!list_empty(&reaplist)) { dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); destroy_unhashed_deleg(dp); } while (!list_empty(&clp->cl_revoked)) { dp = list_entry(clp->cl_revoked.next, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); nfs4_put_stid(&dp->dl_stid); } while (!list_empty(&clp->cl_openowners)) { oo = list_entry(clp->cl_openowners.next, struct nfs4_openowner, oo_perclient); nfs4_get_stateowner(&oo->oo_owner); release_openowner(oo); } for (i = 0; i < OWNER_HASH_SIZE; i++) { struct nfs4_stateowner *so, *tmp; list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i], so_strhash) { /* Should be no openowners at this point */ WARN_ON_ONCE(so->so_is_open_owner); remove_blocked_locks(lockowner(so)); } } nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_copy(clp); nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); atomic_add_unless(&nn->nfs4_client_count, -1, 0); nfsd4_dec_courtesy_client_count(nn, clp); free_client(clp); wake_up_all(&expiry_wq); } static void destroy_client(struct nfs4_client *clp) { unhash_client(clp); __destroy_client(clp); } static void inc_reclaim_complete(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); if (!nn->track_reclaim_completes) return; if (!nfsd4_find_reclaim_client(clp->cl_name, nn)) return; if (atomic_inc_return(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) { printk(KERN_INFO "NFSD: all clients done reclaiming, ending NFSv4 grace period (net %x)\n", clp->net->ns.inum); nfsd4_end_grace(nn); } } static void expire_client(struct nfs4_client *clp) { unhash_client(clp); nfsd4_client_record_remove(clp); __destroy_client(clp); } static void copy_verf(struct nfs4_client *target, nfs4_verifier *source) { memcpy(target->cl_verifier.data, source->data, sizeof(target->cl_verifier.data)); } static void copy_clid(struct nfs4_client *target, struct nfs4_client *source) { target->cl_clientid.cl_boot = source->cl_clientid.cl_boot; target->cl_clientid.cl_id = source->cl_clientid.cl_id; } static int copy_cred(struct svc_cred *target, struct svc_cred *source) { target->cr_principal = kstrdup(source->cr_principal, GFP_KERNEL); target->cr_raw_principal = kstrdup(source->cr_raw_principal, GFP_KERNEL); target->cr_targ_princ = kstrdup(source->cr_targ_princ, GFP_KERNEL); if ((source->cr_principal && !target->cr_principal) || (source->cr_raw_principal && !target->cr_raw_principal) || (source->cr_targ_princ && !target->cr_targ_princ)) return -ENOMEM; target->cr_flavor = source->cr_flavor; target->cr_uid = source->cr_uid; target->cr_gid = source->cr_gid; target->cr_group_info = source->cr_group_info; get_group_info(target->cr_group_info); target->cr_gss_mech = source->cr_gss_mech; if (source->cr_gss_mech) gss_mech_get(source->cr_gss_mech); return 0; } static int compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) { if (o1->len < o2->len) return -1; if (o1->len > o2->len) return 1; return memcmp(o1->data, o2->data, o1->len); } static int same_verf(nfs4_verifier *v1, nfs4_verifier *v2) { return 0 == memcmp(v1->data, v2->data, sizeof(v1->data)); } static int same_clid(clientid_t *cl1, clientid_t *cl2) { return (cl1->cl_boot == cl2->cl_boot) && (cl1->cl_id == cl2->cl_id); } static bool groups_equal(struct group_info *g1, struct group_info *g2) { int i; if (g1->ngroups != g2->ngroups) return false; for (i=0; i<g1->ngroups; i++) if (!gid_eq(g1->gid[i], g2->gid[i])) return false; return true; } /* * RFC 3530 language requires clid_inuse be returned when the * "principal" associated with a requests differs from that previously * used. We use uid, gid's, and gss principal string as our best * approximation. We also don't want to allow non-gss use of a client * established using gss: in theory cr_principal should catch that * change, but in practice cr_principal can be null even in the gss case * since gssd doesn't always pass down a principal string. */ static bool is_gss_cred(struct svc_cred *cr) { /* Is cr_flavor one of the gss "pseudoflavors"?: */ return (cr->cr_flavor > RPC_AUTH_MAXFLAVOR); } static bool same_creds(struct svc_cred *cr1, struct svc_cred *cr2) { if ((is_gss_cred(cr1) != is_gss_cred(cr2)) || (!uid_eq(cr1->cr_uid, cr2->cr_uid)) || (!gid_eq(cr1->cr_gid, cr2->cr_gid)) || !groups_equal(cr1->cr_group_info, cr2->cr_group_info)) return false; /* XXX: check that cr_targ_princ fields match ? */ if (cr1->cr_principal == cr2->cr_principal) return true; if (!cr1->cr_principal || !cr2->cr_principal) return false; return 0 == strcmp(cr1->cr_principal, cr2->cr_principal); } static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp) { struct svc_cred *cr = &rqstp->rq_cred; u32 service; if (!cr->cr_gss_mech) return false; service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor); return service == RPC_GSS_SVC_INTEGRITY || service == RPC_GSS_SVC_PRIVACY; } bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp) { struct svc_cred *cr = &rqstp->rq_cred; if (!cl->cl_mach_cred) return true; if (cl->cl_cred.cr_gss_mech != cr->cr_gss_mech) return false; if (!svc_rqst_integrity_protected(rqstp)) return false; if (cl->cl_cred.cr_raw_principal) return 0 == strcmp(cl->cl_cred.cr_raw_principal, cr->cr_raw_principal); if (!cr->cr_principal) return false; return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal); } static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn) { __be32 verf[2]; /* * This is opaque to client, so no need to byte-swap. Use * __force to keep sparse happy */ verf[0] = (__force __be32)(u32)ktime_get_real_seconds(); verf[1] = (__force __be32)nn->clverifier_counter++; memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data)); } static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn) { clp->cl_clientid.cl_boot = (u32)nn->boot_time; clp->cl_clientid.cl_id = nn->clientid_counter++; gen_confirm(clp, nn); } static struct nfs4_stid * find_stateid_locked(struct nfs4_client *cl, stateid_t *t) { struct nfs4_stid *ret; ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id); if (!ret || !ret->sc_type) return NULL; return ret; } static struct nfs4_stid * find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, unsigned short typemask, unsigned short ok_states) { struct nfs4_stid *s; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, t); if (s != NULL) { if ((s->sc_status & ~ok_states) == 0 && (typemask & s->sc_type)) refcount_inc(&s->sc_count); else s = NULL; } spin_unlock(&cl->cl_lock); return s; } static struct nfs4_client *get_nfsdfs_clp(struct inode *inode) { struct nfsdfs_client *nc; nc = get_nfsdfs_client(inode); if (!nc) return NULL; return container_of(nc, struct nfs4_client, cl_nfsdfs); } static void seq_quote_mem(struct seq_file *m, char *data, int len) { seq_puts(m, "\""); seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\"); seq_puts(m, "\""); } static const char *cb_state2str(int state) { switch (state) { case NFSD4_CB_UP: return "UP"; case NFSD4_CB_UNKNOWN: return "UNKNOWN"; case NFSD4_CB_DOWN: return "DOWN"; case NFSD4_CB_FAULT: return "FAULT"; } return "UNDEFINED"; } static int client_info_show(struct seq_file *m, void *v) { struct inode *inode = file_inode(m->file); struct nfsd4_session *ses; struct nfs4_client *clp; u64 clid; clp = get_nfsdfs_clp(inode); if (!clp) return -ENXIO; memcpy(&clid, &clp->cl_clientid, sizeof(clid)); seq_printf(m, "clientid: 0x%llx\n", clid); seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr); if (clp->cl_state == NFSD4_COURTESY) seq_puts(m, "status: courtesy\n"); else if (clp->cl_state == NFSD4_EXPIRABLE) seq_puts(m, "status: expirable\n"); else if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) seq_puts(m, "status: confirmed\n"); else seq_puts(m, "status: unconfirmed\n"); seq_printf(m, "seconds from last renew: %lld\n", ktime_get_boottime_seconds() - clp->cl_time); seq_puts(m, "name: "); seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len); seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); if (clp->cl_nii_domain.data) { seq_puts(m, "Implementation domain: "); seq_quote_mem(m, clp->cl_nii_domain.data, clp->cl_nii_domain.len); seq_puts(m, "\nImplementation name: "); seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len); seq_printf(m, "\nImplementation time: [%lld, %ld]\n", clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec); } seq_printf(m, "callback state: %s\n", cb_state2str(clp->cl_cb_state)); seq_printf(m, "callback address: \"%pISpc\"\n", &clp->cl_cb_conn.cb_addr); seq_printf(m, "admin-revoked states: %d\n", atomic_read(&clp->cl_admin_revoked)); spin_lock(&clp->cl_lock); seq_printf(m, "session slots:"); list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) seq_printf(m, " %u", ses->se_fchannel.maxreqs); seq_printf(m, "\nsession target slots:"); list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) seq_printf(m, " %u", ses->se_target_maxslots); spin_unlock(&clp->cl_lock); seq_puts(m, "\n"); drop_client(clp); return 0; } DEFINE_SHOW_ATTRIBUTE(client_info); static void *states_start(struct seq_file *s, loff_t *pos) __acquires(&clp->cl_lock) { struct nfs4_client *clp = s->private; unsigned long id = *pos; void *ret; spin_lock(&clp->cl_lock); ret = idr_get_next_ul(&clp->cl_stateids, &id); *pos = id; return ret; } static void *states_next(struct seq_file *s, void *v, loff_t *pos) { struct nfs4_client *clp = s->private; unsigned long id = *pos; void *ret; id = *pos; id++; ret = idr_get_next_ul(&clp->cl_stateids, &id); *pos = id; return ret; } static void states_stop(struct seq_file *s, void *v) __releases(&clp->cl_lock) { struct nfs4_client *clp = s->private; spin_unlock(&clp->cl_lock); } static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f) { seq_printf(s, "filename: \"%pD2\"", f->nf_file); } static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) { struct inode *inode = file_inode(f->nf_file); seq_printf(s, "superblock: \"%02x:%02x:%ld\"", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo) { seq_puts(s, "owner: "); seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len); } static void nfs4_show_stateid(struct seq_file *s, stateid_t *stid) { seq_printf(s, "0x%.8x", stid->si_generation); seq_printf(s, "%12phN", &stid->si_opaque); } static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_ol_stateid *ols; struct nfs4_file *nf; struct nfsd_file *file; struct nfs4_stateowner *oo; unsigned int access, deny; ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: open, "); access = bmap_to_share_mode(ols->st_access_bmap); deny = bmap_to_share_mode(ols->st_deny_bmap); seq_printf(s, "access: %s%s, ", access & NFS4_SHARE_ACCESS_READ ? "r" : "-", access & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); seq_printf(s, "deny: %s%s, ", deny & NFS4_SHARE_ACCESS_READ ? "r" : "-", deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); if (nf) { spin_lock(&nf->fi_lock); file = find_any_file_locked(nf); if (file) { nfs4_show_superblock(s, file); seq_puts(s, ", "); nfs4_show_fname(s, file); seq_puts(s, ", "); } spin_unlock(&nf->fi_lock); } else seq_puts(s, "closed, "); nfs4_show_owner(s, oo); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); return 0; } static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_ol_stateid *ols; struct nfs4_file *nf; struct nfsd_file *file; struct nfs4_stateowner *oo; ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: lock, "); spin_lock(&nf->fi_lock); file = find_any_file_locked(nf); if (file) { /* * Note: a lock stateid isn't really the same thing as a lock, * it's the locking state held by one owner on a file, and there * may be multiple (or no) lock ranges associated with it. * (Same for the matter is true of open stateids.) */ nfs4_show_superblock(s, file); /* XXX: open stateid? */ seq_puts(s, ", "); nfs4_show_fname(s, file); seq_puts(s, ", "); } nfs4_show_owner(s, oo); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); spin_unlock(&nf->fi_lock); return 0; } static char *nfs4_show_deleg_type(u32 dl_type) { switch (dl_type) { case OPEN_DELEGATE_READ: return "r"; case OPEN_DELEGATE_WRITE: return "w"; case OPEN_DELEGATE_READ_ATTRS_DELEG: return "ra"; case OPEN_DELEGATE_WRITE_ATTRS_DELEG: return "wa"; } return "?"; } static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_delegation *ds; struct nfs4_file *nf; struct nfsd_file *file; ds = delegstateid(st); nf = st->sc_file; seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: deleg, "); seq_printf(s, "access: %s", nfs4_show_deleg_type(ds->dl_type)); /* XXX: lease time, whether it's being recalled. */ spin_lock(&nf->fi_lock); file = nf->fi_deleg_file; if (file) { seq_puts(s, ", "); nfs4_show_superblock(s, file); seq_puts(s, ", "); nfs4_show_fname(s, file); } spin_unlock(&nf->fi_lock); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); return 0; } static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_layout_stateid *ls; struct nfsd_file *file; ls = container_of(st, struct nfs4_layout_stateid, ls_stid); seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: layout"); /* XXX: What else would be useful? */ spin_lock(&ls->ls_stid.sc_file->fi_lock); file = ls->ls_file; if (file) { seq_puts(s, ", "); nfs4_show_superblock(s, file); seq_puts(s, ", "); nfs4_show_fname(s, file); } spin_unlock(&ls->ls_stid.sc_file->fi_lock); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); return 0; } static int states_show(struct seq_file *s, void *v) { struct nfs4_stid *st = v; switch (st->sc_type) { case SC_TYPE_OPEN: return nfs4_show_open(s, st); case SC_TYPE_LOCK: return nfs4_show_lock(s, st); case SC_TYPE_DELEG: return nfs4_show_deleg(s, st); case SC_TYPE_LAYOUT: return nfs4_show_layout(s, st); default: return 0; /* XXX: or SEQ_SKIP? */ } /* XXX: copy stateids? */ } static struct seq_operations states_seq_ops = { .start = states_start, .next = states_next, .stop = states_stop, .show = states_show }; static int client_states_open(struct inode *inode, struct file *file) { struct seq_file *s; struct nfs4_client *clp; int ret; clp = get_nfsdfs_clp(inode); if (!clp) return -ENXIO; ret = seq_open(file, &states_seq_ops); if (ret) return ret; s = file->private_data; s->private = clp; return 0; } static int client_opens_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct nfs4_client *clp = m->private; /* XXX: alternatively, we could get/drop in seq start/stop */ drop_client(clp); return seq_release(inode, file); } static const struct file_operations client_states_fops = { .open = client_states_open, .read = seq_read, .llseek = seq_lseek, .release = client_opens_release, }; /* * Normally we refuse to destroy clients that are in use, but here the * administrator is telling us to just do it. We also want to wait * so the caller has a guarantee that the client's locks are gone by * the time the write returns: */ static void force_expire_client(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); bool already_expired; trace_nfsd_clid_admin_expired(&clp->cl_clientid); spin_lock(&nn->client_lock); clp->cl_time = 0; spin_unlock(&nn->client_lock); wait_event(expiry_wq, atomic_read(&clp->cl_rpc_users) == 0); spin_lock(&nn->client_lock); already_expired = list_empty(&clp->cl_lru); if (!already_expired) unhash_client_locked(clp); spin_unlock(&nn->client_lock); if (!already_expired) expire_client(clp); else wait_event(expiry_wq, clp->cl_nfsd_dentry == NULL); } static ssize_t client_ctl_write(struct file *file, const char __user *buf, size_t size, loff_t *pos) { char *data; struct nfs4_client *clp; data = simple_transaction_get(file, buf, size); if (IS_ERR(data)) return PTR_ERR(data); if (size != 7 || 0 != memcmp(data, "expire\n", 7)) return -EINVAL; clp = get_nfsdfs_clp(file_inode(file)); if (!clp) return -ENXIO; force_expire_client(clp); drop_client(clp); return 7; } static const struct file_operations client_ctl_fops = { .write = client_ctl_write, .release = simple_transaction_release, }; static const struct tree_descr client_files[] = { [0] = {"info", &client_info_fops, S_IRUSR}, [1] = {"states", &client_states_fops, S_IRUSR}, [2] = {"ctl", &client_ctl_fops, S_IWUSR}, [3] = {""}, }; static int nfsd4_cb_recall_any_done(struct nfsd4_callback *cb, struct rpc_task *task) { trace_nfsd_cb_recall_any_done(cb, task); switch (task->tk_status) { case -NFS4ERR_DELAY: rpc_delay(task, 2 * HZ); return 0; default: return 1; } } static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); drop_client(clp); } static int nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_cb_fattr *ncf = container_of(cb, struct nfs4_cb_fattr, ncf_getattr); struct nfs4_delegation *dp = container_of(ncf, struct nfs4_delegation, dl_cb_fattr); trace_nfsd_cb_getattr_done(&dp->dl_stid.sc_stateid, task); ncf->ncf_cb_status = task->tk_status; switch (task->tk_status) { case -NFS4ERR_DELAY: rpc_delay(task, 2 * HZ); return 0; default: return 1; } } static void nfsd4_cb_getattr_release(struct nfsd4_callback *cb) { struct nfs4_cb_fattr *ncf = container_of(cb, struct nfs4_cb_fattr, ncf_getattr); struct nfs4_delegation *dp = container_of(ncf, struct nfs4_delegation, dl_cb_fattr); clear_and_wake_up_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags); nfs4_put_stid(&dp->dl_stid); } static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { .done = nfsd4_cb_recall_any_done, .release = nfsd4_cb_recall_any_release, .opcode = OP_CB_RECALL_ANY, }; static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = { .done = nfsd4_cb_getattr_done, .release = nfsd4_cb_getattr_release, .opcode = OP_CB_GETATTR, }; static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf) { struct nfs4_delegation *dp = container_of(ncf, struct nfs4_delegation, dl_cb_fattr); if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags)) return; /* set to proper status when nfsd4_cb_getattr_done runs */ ncf->ncf_cb_status = NFS4ERR_IO; refcount_inc(&dp->dl_stid.sc_count); nfsd4_run_cb(&ncf->ncf_getattr); } static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { struct nfs4_client *clp; struct sockaddr *sa = svc_addr(rqstp); int ret; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct dentry *dentries[ARRAY_SIZE(client_files)]; clp = alloc_client(name, nn); if (clp == NULL) return NULL; ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred); if (ret) { free_client(clp); return NULL; } gen_clid(clp, nn); kref_init(&clp->cl_nfsdfs.cl_ref); nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL); clp->cl_time = ktime_get_boottime_seconds(); copy_verf(clp, verf); memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); clp->cl_cb_session = NULL; clp->net = net; clp->cl_nfsd_dentry = nfsd_client_mkdir( nn, &clp->cl_nfsdfs, clp->cl_clientid.cl_id - nn->clientid_base, client_files, dentries); clp->cl_nfsd_info_dentry = dentries[0]; if (!clp->cl_nfsd_dentry) { free_client(clp); return NULL; } clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL); if (!clp->cl_ra) { free_client(clp); return NULL; } clp->cl_ra_time = 0; nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops, NFSPROC4_CLNT_CB_RECALL_ANY); return clp; } static void add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root) { struct rb_node **new = &(root->rb_node), *parent = NULL; struct nfs4_client *clp; while (*new) { clp = rb_entry(*new, struct nfs4_client, cl_namenode); parent = *new; if (compare_blob(&clp->cl_name, &new_clp->cl_name) > 0) new = &((*new)->rb_left); else new = &((*new)->rb_right); } rb_link_node(&new_clp->cl_namenode, parent, new); rb_insert_color(&new_clp->cl_namenode, root); } static struct nfs4_client * find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root) { int cmp; struct rb_node *node = root->rb_node; struct nfs4_client *clp; while (node) { clp = rb_entry(node, struct nfs4_client, cl_namenode); cmp = compare_blob(&clp->cl_name, name); if (cmp > 0) node = node->rb_left; else if (cmp < 0) node = node->rb_right; else return clp; } return NULL; } static void add_to_unconfirmed(struct nfs4_client *clp) { unsigned int idhashval; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); clear_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags); add_clp_to_name_tree(clp, &nn->unconf_name_tree); idhashval = clientid_hashval(clp->cl_clientid.cl_id); list_add(&clp->cl_idhash, &nn->unconf_id_hashtbl[idhashval]); renew_client_locked(clp); } static void move_to_confirmed(struct nfs4_client *clp) { unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id); struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]); rb_erase(&clp->cl_namenode, &nn->unconf_name_tree); add_clp_to_name_tree(clp, &nn->conf_name_tree); set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags); trace_nfsd_clid_confirmed(&clp->cl_clientid); renew_client_locked(clp); } static struct nfs4_client * find_client_in_id_table(struct list_head *tbl, clientid_t *clid, bool sessions) { struct nfs4_client *clp; unsigned int idhashval = clientid_hashval(clid->cl_id); list_for_each_entry(clp, &tbl[idhashval], cl_idhash) { if (same_clid(&clp->cl_clientid, clid)) { if ((bool)clp->cl_minorversion != sessions) return NULL; renew_client_locked(clp); return clp; } } return NULL; } static struct nfs4_client * find_confirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct list_head *tbl = nn->conf_id_hashtbl; lockdep_assert_held(&nn->client_lock); return find_client_in_id_table(tbl, clid, sessions); } static struct nfs4_client * find_unconfirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct list_head *tbl = nn->unconf_id_hashtbl; lockdep_assert_held(&nn->client_lock); return find_client_in_id_table(tbl, clid, sessions); } static bool clp_used_exchangeid(struct nfs4_client *clp) { return clp->cl_exchange_flags != 0; } static struct nfs4_client * find_confirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn) { lockdep_assert_held(&nn->client_lock); return find_clp_in_name_tree(name, &nn->conf_name_tree); } static struct nfs4_client * find_unconfirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn) { lockdep_assert_held(&nn->client_lock); return find_clp_in_name_tree(name, &nn->unconf_name_tree); } static void gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_rqst *rqstp) { struct nfs4_cb_conn *conn = &clp->cl_cb_conn; struct sockaddr *sa = svc_addr(rqstp); u32 scopeid = rpc_get_scope_id(sa); unsigned short expected_family; /* Currently, we only support tcp and tcp6 for the callback channel */ if (se->se_callback_netid_len == 3 && !memcmp(se->se_callback_netid_val, "tcp", 3)) expected_family = AF_INET; else if (se->se_callback_netid_len == 4 && !memcmp(se->se_callback_netid_val, "tcp6", 4)) expected_family = AF_INET6; else goto out_err; conn->cb_addrlen = rpc_uaddr2sockaddr(clp->net, se->se_callback_addr_val, se->se_callback_addr_len, (struct sockaddr *)&conn->cb_addr, sizeof(conn->cb_addr)); if (!conn->cb_addrlen || conn->cb_addr.ss_family != expected_family) goto out_err; if (conn->cb_addr.ss_family == AF_INET6) ((struct sockaddr_in6 *)&conn->cb_addr)->sin6_scope_id = scopeid; conn->cb_prog = se->se_callback_prog; conn->cb_ident = se->se_callback_ident; memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen); trace_nfsd_cb_args(clp, conn); return; out_err: conn->cb_addr.ss_family = AF_UNSPEC; conn->cb_addrlen = 0; trace_nfsd_cb_nodelegs(clp); return; } /* * Cache a reply. nfsd4_check_resp_size() has bounded the cache size. */ static void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) { struct xdr_buf *buf = resp->xdr->buf; struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; dprintk("--> %s slot %p\n", __func__, slot); slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; slot->sl_status = resp->cstate.status; free_svc_cred(&slot->sl_cred); copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred); if (!nfsd4_cache_this(resp)) { slot->sl_flags &= ~NFSD4_SLOT_CACHED; return; } slot->sl_flags |= NFSD4_SLOT_CACHED; base = resp->cstate.data_offset; slot->sl_datalen = buf->len - base; if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen)) WARN(1, "%s: sessions DRC could not cache compound\n", __func__); return; } /* * Encode the replay sequence operation from the slot values. * If cachethis is FALSE encode the uncached rep error on the next * operation which sets resp->p and increments resp->opcnt for * nfs4svc_encode_compoundres. * */ static __be32 nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args, struct nfsd4_compoundres *resp) { struct nfsd4_op *op; struct nfsd4_slot *slot = resp->cstate.slot; /* Encode the replayed sequence operation */ op = &args->ops[resp->opcnt - 1]; nfsd4_encode_operation(resp, op); if (slot->sl_flags & NFSD4_SLOT_CACHED) return op->status; if (args->opcnt == 1) { /* * The original operation wasn't a solo sequence--we * always cache those--so this retry must not match the * original: */ op->status = nfserr_seq_false_retry; } else { op = &args->ops[resp->opcnt++]; op->status = nfserr_retry_uncached_rep; nfsd4_encode_operation(resp, op); } return op->status; } /* * The sequence operation is not cached because we can use the slot and * session values. */ static __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq) { struct nfsd4_slot *slot = resp->cstate.slot; struct xdr_stream *xdr = resp->xdr; __be32 *p; __be32 status; dprintk("--> %s slot %p\n", __func__, slot); status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp); if (status) return status; p = xdr_reserve_space(xdr, slot->sl_datalen); if (!p) { WARN_ON_ONCE(1); return nfserr_serverfault; } xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen); xdr_commit_encode(xdr); resp->opcnt = slot->sl_opcnt; return slot->sl_status; } /* * Set the exchange_id flags returned by the server. */ static void nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) { #ifdef CONFIG_NFSD_PNFS new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS; #else new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS; #endif /* Referrals are supported, Migration is not. */ new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER; /* set the wire flags to return to client. */ clid->flags = new->cl_exchange_flags; } static bool client_has_openowners(struct nfs4_client *clp) { struct nfs4_openowner *oo; list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) { if (!list_empty(&oo->oo_owner.so_stateids)) return true; } return false; } static bool client_has_state(struct nfs4_client *clp) { return client_has_openowners(clp) #ifdef CONFIG_NFSD_PNFS || !list_empty(&clp->cl_lo_states) #endif || !list_empty(&clp->cl_delegations) || !list_empty(&clp->cl_sessions) || nfsd4_has_active_async_copies(clp); } static __be32 copy_impl_id(struct nfs4_client *clp, struct nfsd4_exchange_id *exid) { if (!exid->nii_domain.data) return 0; xdr_netobj_dup(&clp->cl_nii_domain, &exid->nii_domain, GFP_KERNEL); if (!clp->cl_nii_domain.data) return nfserr_jukebox; xdr_netobj_dup(&clp->cl_nii_name, &exid->nii_name, GFP_KERNEL); if (!clp->cl_nii_name.data) return nfserr_jukebox; clp->cl_nii_time = exid->nii_time; return 0; } __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_exchange_id *exid = &u->exchange_id; struct nfs4_client *conf, *new; struct nfs4_client *unconf = NULL; __be32 status; char addr_str[INET6_ADDRSTRLEN]; nfs4_verifier verf = exid->verifier; struct sockaddr *sa = svc_addr(rqstp); bool update = exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); rpc_ntop(sa, addr_str, sizeof(addr_str)); dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p " "ip_addr=%s flags %x, spa_how %u\n", __func__, rqstp, exid, exid->clname.len, exid->clname.data, addr_str, exid->flags, exid->spa_how); exid->server_impl_name = kasprintf(GFP_KERNEL, "%s %s %s %s", utsname()->sysname, utsname()->release, utsname()->version, utsname()->machine); if (!exid->server_impl_name) return nfserr_jukebox; if (exid->flags & ~EXCHGID4_FLAG_MASK_A) return nfserr_inval; new = create_client(exid->clname, rqstp, &verf); if (new == NULL) return nfserr_jukebox; status = copy_impl_id(new, exid); if (status) goto out_nolock; switch (exid->spa_how) { case SP4_MACH_CRED: exid->spo_must_enforce[0] = 0; exid->spo_must_enforce[1] = ( 1 << (OP_BIND_CONN_TO_SESSION - 32) | 1 << (OP_EXCHANGE_ID - 32) | 1 << (OP_CREATE_SESSION - 32) | 1 << (OP_DESTROY_SESSION - 32) | 1 << (OP_DESTROY_CLIENTID - 32)); exid->spo_must_allow[0] &= (1 << (OP_CLOSE) | 1 << (OP_OPEN_DOWNGRADE) | 1 << (OP_LOCKU) | 1 << (OP_DELEGRETURN)); exid->spo_must_allow[1] &= ( 1 << (OP_TEST_STATEID - 32) | 1 << (OP_FREE_STATEID - 32)); if (!svc_rqst_integrity_protected(rqstp)) { status = nfserr_inval; goto out_nolock; } /* * Sometimes userspace doesn't give us a principal. * Which is a bug, really. Anyway, we can't enforce * MACH_CRED in that case, better to give up now: */ if (!new->cl_cred.cr_principal && !new->cl_cred.cr_raw_principal) { status = nfserr_serverfault; goto out_nolock; } new->cl_mach_cred = true; break; case SP4_NONE: break; default: /* checked by xdr code */ WARN_ON_ONCE(1); fallthrough; case SP4_SSV: status = nfserr_encr_alg_unsupp; goto out_nolock; } /* Cases below refer to rfc 5661 section 18.35.4: */ spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&exid->clname, nn); if (conf) { bool creds_match = same_creds(&conf->cl_cred, &rqstp->rq_cred); bool verfs_match = same_verf(&verf, &conf->cl_verifier); if (update) { if (!clp_used_exchangeid(conf)) { /* buggy client */ status = nfserr_inval; goto out; } if (!nfsd4_mach_creds_match(conf, rqstp)) { status = nfserr_wrong_cred; goto out; } if (!creds_match) { /* case 9 */ status = nfserr_perm; goto out; } if (!verfs_match) { /* case 8 */ status = nfserr_not_same; goto out; } /* case 6 */ exid->flags |= EXCHGID4_FLAG_CONFIRMED_R; trace_nfsd_clid_confirmed_r(conf); goto out_copy; } if (!creds_match) { /* case 3 */ if (client_has_state(conf)) { status = nfserr_clid_inuse; trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } goto out_new; } if (verfs_match) { /* case 2 */ conf->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R; trace_nfsd_clid_confirmed_r(conf); goto out_copy; } /* case 5, client reboot */ trace_nfsd_clid_verf_mismatch(conf, rqstp, &verf); conf = NULL; goto out_new; } if (update) { /* case 7 */ status = nfserr_noent; goto out; } unconf = find_unconfirmed_client_by_name(&exid->clname, nn); if (unconf) /* case 4, possible retry or client restart */ unhash_client_locked(unconf); /* case 1, new owner ID */ trace_nfsd_clid_fresh(new); out_new: if (conf) { status = mark_client_expired_locked(conf); if (status) goto out; trace_nfsd_clid_replaced(&conf->cl_clientid); } new->cl_minorversion = cstate->minorversion; new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0]; new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1]; /* Contrived initial CREATE_SESSION response */ new->cl_cs_slot.sl_status = nfserr_seq_misordered; add_to_unconfirmed(new); swap(new, conf); out_copy: exid->clientid.cl_boot = conf->cl_clientid.cl_boot; exid->clientid.cl_id = conf->cl_clientid.cl_id; exid->seqid = conf->cl_cs_slot.sl_seqid + 1; nfsd4_set_ex_flags(conf, exid); exid->nii_domain.len = sizeof("kernel.org") - 1; exid->nii_domain.data = "kernel.org"; /* * Note that RFC 8881 places no length limit on * nii_name, but this implementation permits no * more than NFS4_OPAQUE_LIMIT bytes. */ exid->nii_name.len = strlen(exid->server_impl_name); if (exid->nii_name.len > NFS4_OPAQUE_LIMIT) exid->nii_name.len = NFS4_OPAQUE_LIMIT; exid->nii_name.data = exid->server_impl_name; /* just send zeros - the date is in nii_name */ exid->nii_time.tv_sec = 0; exid->nii_time.tv_nsec = 0; dprintk("nfsd4_exchange_id seqid %d flags %x\n", conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags); status = nfs_ok; out: spin_unlock(&nn->client_lock); out_nolock: if (new) expire_client(new); if (unconf) { trace_nfsd_clid_expire_unconf(&unconf->cl_clientid); expire_client(unconf); } return status; } void nfsd4_exchange_id_release(union nfsd4_op_u *u) { struct nfsd4_exchange_id *exid = &u->exchange_id; kfree(exid->server_impl_name); } static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, u8 flags) { /* The slot is in use, and no response has been sent. */ if (flags & NFSD4_SLOT_INUSE) { if (seqid == slot_seqid) return nfserr_jukebox; else return nfserr_seq_misordered; } /* Note unsigned 32-bit arithmetic handles wraparound: */ if (likely(seqid == slot_seqid + 1)) return nfs_ok; if ((flags & NFSD4_SLOT_REUSED) && seqid == 1) return nfs_ok; if (seqid == slot_seqid) return nfserr_replay_cache; return nfserr_seq_misordered; } /* * Cache the create session result into the create session single DRC * slot cache by saving the xdr structure. sl_seqid has been set. * Do this for solo or embedded create session operations. */ static void nfsd4_cache_create_session(struct nfsd4_create_session *cr_ses, struct nfsd4_clid_slot *slot, __be32 nfserr) { slot->sl_status = nfserr; memcpy(&slot->sl_cr_ses, cr_ses, sizeof(*cr_ses)); } static __be32 nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses, struct nfsd4_clid_slot *slot) { memcpy(cr_ses, &slot->sl_cr_ses, sizeof(*cr_ses)); return slot->sl_status; } #define NFSD_MIN_REQ_HDR_SEQ_SZ ((\ 2 * 2 + /* credential,verifier: AUTH_NULL, length 0 */ \ 1 + /* MIN tag is length with zero, only length */ \ 3 + /* version, opcount, opcode */ \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ /* seqid, slotID, slotID, cache */ \ 4 ) * sizeof(__be32)) #define NFSD_MIN_RESP_HDR_SEQ_SZ ((\ 2 + /* verifier: AUTH_NULL, length 0 */\ 1 + /* status */ \ 1 + /* MIN tag is length with zero, only length */ \ 3 + /* opcount, opcode, opstatus*/ \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ /* seqid, slotID, slotID, slotID, status */ \ 5 ) * sizeof(__be32)) static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn) { u32 maxrpc = nn->nfsd_serv->sv_max_mesg; if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ) return nfserr_toosmall; if (ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ) return nfserr_toosmall; ca->headerpadsz = 0; ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc); ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc); ca->maxops = min_t(u32, ca->maxops, NFSD_MAX_OPS_PER_COMPOUND); ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); return nfs_ok; } /* * Server's NFSv4.1 backchannel support is AUTH_SYS-only for now. * These are based on similar macros in linux/sunrpc/msg_prot.h . */ #define RPC_MAX_HEADER_WITH_AUTH_SYS \ (RPC_CALLHDRSIZE + 2 * (2 + UNX_CALLSLACK)) #define RPC_MAX_REPHEADER_WITH_AUTH_SYS \ (RPC_REPHDRSIZE + (2 + NUL_REPLYSLACK)) #define NFSD_CB_MAX_REQ_SZ ((NFS4_enc_cb_recall_sz + \ RPC_MAX_HEADER_WITH_AUTH_SYS) * sizeof(__be32)) #define NFSD_CB_MAX_RESP_SZ ((NFS4_dec_cb_recall_sz + \ RPC_MAX_REPHEADER_WITH_AUTH_SYS) * \ sizeof(__be32)) static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca) { ca->headerpadsz = 0; if (ca->maxreq_sz < NFSD_CB_MAX_REQ_SZ) return nfserr_toosmall; if (ca->maxresp_sz < NFSD_CB_MAX_RESP_SZ) return nfserr_toosmall; ca->maxresp_cached = 0; if (ca->maxops < 2) return nfserr_toosmall; return nfs_ok; } static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs) { switch (cbs->flavor) { case RPC_AUTH_NULL: case RPC_AUTH_UNIX: return nfs_ok; default: /* * GSS case: the spec doesn't allow us to return this * error. But it also doesn't allow us not to support * GSS. * I'd rather this fail hard than return some error the * client might think it can already handle: */ return nfserr_encr_alg_unsupp; } } __be32 nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; struct nfsd4_clid_slot *cs_slot; struct nfs4_client *old = NULL; struct nfsd4_session *new; struct nfsd4_conn *conn; __be32 status = 0; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (cr_ses->flags & ~SESSION4_FLAG_MASK_A) return nfserr_inval; status = nfsd4_check_cb_sec(&cr_ses->cb_sec); if (status) return status; status = check_forechannel_attrs(&cr_ses->fore_channel, nn); if (status) return status; status = check_backchannel_attrs(&cr_ses->back_channel); if (status) goto out_err; status = nfserr_jukebox; new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel); if (!new) goto out_err; conn = alloc_conn_from_crses(rqstp, cr_ses); if (!conn) goto out_free_session; spin_lock(&nn->client_lock); /* RFC 8881 Section 18.36.4 Phase 1: Client record look-up. */ unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn); conf = find_confirmed_client(&cr_ses->clientid, true, nn); if (!conf && !unconf) { status = nfserr_stale_clientid; goto out_free_conn; } /* RFC 8881 Section 18.36.4 Phase 2: Sequence ID processing. */ if (conf) { cs_slot = &conf->cl_cs_slot; trace_nfsd_slot_seqid_conf(conf, cr_ses); } else { cs_slot = &unconf->cl_cs_slot; trace_nfsd_slot_seqid_unconf(unconf, cr_ses); } status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); switch (status) { case nfs_ok: cs_slot->sl_seqid++; cr_ses->seqid = cs_slot->sl_seqid; break; case nfserr_replay_cache: status = nfsd4_replay_create_session(cr_ses, cs_slot); fallthrough; case nfserr_jukebox: /* The server MUST NOT cache NFS4ERR_DELAY */ goto out_free_conn; default: goto out_cache_error; } /* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */ if (conf) { status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(conf, rqstp)) goto out_cache_error; } else { status = nfserr_clid_inuse; if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) { trace_nfsd_clid_cred_mismatch(unconf, rqstp); goto out_cache_error; } status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(unconf, rqstp)) goto out_cache_error; old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = mark_client_expired_locked(old); if (status) goto out_expired_error; trace_nfsd_clid_replaced(&old->cl_clientid); } move_to_confirmed(unconf); conf = unconf; } /* RFC 8881 Section 18.36.4 Phase 4: Session creation. */ status = nfs_ok; /* Persistent sessions are not supported */ cr_ses->flags &= ~SESSION4_PERSIST; /* Upshifting from TCP to RDMA is not supported */ cr_ses->flags &= ~SESSION4_RDMA; /* Report the correct number of backchannel slots */ cr_ses->back_channel.maxreqs = new->se_cb_highest_slot + 1; init_session(rqstp, new, conf, cr_ses); nfsd4_get_session_locked(new); memcpy(cr_ses->sessionid.data, new->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); /* cache solo and embedded create sessions under the client_lock */ nfsd4_cache_create_session(cr_ses, cs_slot, status); spin_unlock(&nn->client_lock); if (conf == unconf) fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); /* init connection and backchannel */ nfsd4_init_conn(rqstp, conn, new); nfsd4_put_session(new); if (old) expire_client(old); return status; out_expired_error: /* * Revert the slot seq_nr change so the server will process * the client's resend instead of returning a cached response. */ if (status == nfserr_jukebox) { cs_slot->sl_seqid--; cr_ses->seqid = cs_slot->sl_seqid; goto out_free_conn; } out_cache_error: nfsd4_cache_create_session(cr_ses, cs_slot, status); out_free_conn: spin_unlock(&nn->client_lock); free_conn(conn); out_free_session: __free_session(new); out_err: return status; } static __be32 nfsd4_map_bcts_dir(u32 *dir) { switch (*dir) { case NFS4_CDFC4_FORE: case NFS4_CDFC4_BACK: return nfs_ok; case NFS4_CDFC4_FORE_OR_BOTH: case NFS4_CDFC4_BACK_OR_BOTH: *dir = NFS4_CDFC4_BOTH; return nfs_ok; } return nfserr_inval; } __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; struct nfsd4_session *session = cstate->session; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); __be32 status; status = nfsd4_check_cb_sec(&bc->bc_cb_sec); if (status) return status; spin_lock(&nn->client_lock); session->se_cb_prog = bc->bc_cb_program; session->se_cb_sec = bc->bc_cb_sec; spin_unlock(&nn->client_lock); nfsd4_probe_callback(session->se_client); return nfs_ok; } static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s) { struct nfsd4_conn *c; list_for_each_entry(c, &s->se_conns, cn_persession) { if (c->cn_xprt == xpt) { return c; } } return NULL; } static __be32 nfsd4_match_existing_connection(struct svc_rqst *rqst, struct nfsd4_session *session, u32 req, struct nfsd4_conn **conn) { struct nfs4_client *clp = session->se_client; struct svc_xprt *xpt = rqst->rq_xprt; struct nfsd4_conn *c; __be32 status; /* Following the last paragraph of RFC 5661 Section 18.34.3: */ spin_lock(&clp->cl_lock); c = __nfsd4_find_conn(xpt, session); if (!c) status = nfserr_noent; else if (req == c->cn_flags) status = nfs_ok; else if (req == NFS4_CDFC4_FORE_OR_BOTH && c->cn_flags != NFS4_CDFC4_BACK) status = nfs_ok; else if (req == NFS4_CDFC4_BACK_OR_BOTH && c->cn_flags != NFS4_CDFC4_FORE) status = nfs_ok; else status = nfserr_inval; spin_unlock(&clp->cl_lock); if (status == nfs_ok && conn) *conn = c; return status; } __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; __be32 status; struct nfsd4_conn *conn; struct nfsd4_session *session; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (!nfsd4_last_compound_op(rqstp)) return nfserr_not_only_op; spin_lock(&nn->client_lock); session = find_in_sessionid_hashtbl(&bcts->sessionid, net, &status); spin_unlock(&nn->client_lock); if (!session) goto out_no_session; status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(session->se_client, rqstp)) goto out; status = nfsd4_match_existing_connection(rqstp, session, bcts->dir, &conn); if (status == nfs_ok) { if (bcts->dir == NFS4_CDFC4_FORE_OR_BOTH || bcts->dir == NFS4_CDFC4_BACK) conn->cn_flags |= NFS4_CDFC4_BACK; nfsd4_probe_callback(session->se_client); goto out; } if (status == nfserr_inval) goto out; status = nfsd4_map_bcts_dir(&bcts->dir); if (status) goto out; conn = alloc_conn(rqstp, bcts->dir); status = nfserr_jukebox; if (!conn) goto out; nfsd4_init_conn(rqstp, conn, session); status = nfs_ok; out: nfsd4_put_session(session); out_no_session: return status; } static bool nfsd4_compound_in_session(struct nfsd4_compound_state *cstate, struct nfs4_sessionid *sid) { if (!cstate->session) return false; return !memcmp(sid, &cstate->session->se_sessionid, sizeof(*sid)); } __be32 nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfs4_sessionid *sessionid = &u->destroy_session.sessionid; struct nfsd4_session *ses; __be32 status; int ref_held_by_me = 0; struct net *net = SVC_NET(r); struct nfsd_net *nn = net_generic(net, nfsd_net_id); status = nfserr_not_only_op; if (nfsd4_compound_in_session(cstate, sessionid)) { if (!nfsd4_last_compound_op(r)) goto out; ref_held_by_me++; } dump_sessionid(__func__, sessionid); spin_lock(&nn->client_lock); ses = find_in_sessionid_hashtbl(sessionid, net, &status); if (!ses) goto out_client_lock; status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(ses->se_client, r)) goto out_put_session; status = mark_session_dead_locked(ses, 1 + ref_held_by_me); if (status) goto out_put_session; unhash_session(ses); spin_unlock(&nn->client_lock); nfsd4_probe_callback_sync(ses->se_client); spin_lock(&nn->client_lock); status = nfs_ok; out_put_session: nfsd4_put_session_locked(ses); out_client_lock: spin_unlock(&nn->client_lock); out: return status; } static __be32 nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd4_conn *c; __be32 status = nfs_ok; int ret; spin_lock(&clp->cl_lock); c = __nfsd4_find_conn(new->cn_xprt, ses); if (c) goto out_free; status = nfserr_conn_not_bound_to_session; if (clp->cl_mach_cred) goto out_free; __nfsd4_hash_conn(new, ses); spin_unlock(&clp->cl_lock); ret = nfsd4_register_conn(new); if (ret) /* oops; xprt is already down: */ nfsd4_conn_lost(&new->cn_xpt_user); return nfs_ok; out_free: spin_unlock(&clp->cl_lock); free_conn(new); return status; } static bool nfsd4_session_too_many_ops(struct svc_rqst *rqstp, struct nfsd4_session *session) { struct nfsd4_compoundargs *args = rqstp->rq_argp; return args->opcnt > session->se_fchannel.maxops; } static bool nfsd4_request_too_big(struct svc_rqst *rqstp, struct nfsd4_session *session) { struct xdr_buf *xb = &rqstp->rq_arg; return xb->len > session->se_fchannel.maxreq_sz; } static bool replay_matches_cache(struct svc_rqst *rqstp, struct nfsd4_sequence *seq, struct nfsd4_slot *slot) { struct nfsd4_compoundargs *argp = rqstp->rq_argp; if ((bool)(slot->sl_flags & NFSD4_SLOT_CACHETHIS) != (bool)seq->cachethis) return false; /* * If there's an error then the reply can have fewer ops than * the call. */ if (slot->sl_opcnt < argp->opcnt && !slot->sl_status) return false; /* * But if we cached a reply with *more* ops than the call you're * sending us now, then this new call is clearly not really a * replay of the old one: */ if (slot->sl_opcnt > argp->opcnt) return false; /* This is the only check explicitly called by spec: */ if (!same_creds(&rqstp->rq_cred, &slot->sl_cred)) return false; /* * There may be more comparisons we could actually do, but the * spec doesn't require us to catch every case where the calls * don't match (that would require caching the call as well as * the reply), so we don't bother. */ return true; } __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_sequence *seq = &u->sequence; struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_stream *xdr = resp->xdr; struct nfsd4_session *session; struct nfs4_client *clp; struct nfsd4_slot *slot; struct nfsd4_conn *conn; __be32 status; int buflen; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (resp->opcnt != 1) return nfserr_sequence_pos; /* * Will be either used or freed by nfsd4_sequence_check_conn * below. */ conn = alloc_conn(rqstp, NFS4_CDFC4_FORE); if (!conn) return nfserr_jukebox; spin_lock(&nn->client_lock); session = find_in_sessionid_hashtbl(&seq->sessionid, net, &status); if (!session) goto out_no_session; clp = session->se_client; status = nfserr_too_many_ops; if (nfsd4_session_too_many_ops(rqstp, session)) goto out_put_session; status = nfserr_req_too_big; if (nfsd4_request_too_big(rqstp, session)) goto out_put_session; status = nfserr_badslot; if (seq->slotid >= session->se_fchannel.maxreqs) goto out_put_session; slot = xa_load(&session->se_slots, seq->slotid); dprintk("%s: slotid %d\n", __func__, seq->slotid); trace_nfsd_slot_seqid_sequence(clp, seq, slot); status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) goto out_put_session; status = nfserr_seq_false_retry; if (!replay_matches_cache(rqstp, seq, slot)) goto out_put_session; cstate->slot = slot; cstate->session = session; cstate->clp = clp; /* Return the cached reply status and set cstate->status * for nfsd4_proc_compound processing */ status = nfsd4_replay_cache_entry(resp, seq); cstate->status = nfserr_replay_cache; goto out; } if (status) goto out_put_session; status = nfsd4_sequence_check_conn(conn, session); conn = NULL; if (status) goto out_put_session; if (session->se_target_maxslots < session->se_fchannel.maxreqs && slot->sl_generation == session->se_slot_gen && seq->maxslots <= session->se_target_maxslots) /* Client acknowledged our reduce maxreqs */ free_session_slots(session, session->se_target_maxslots); buflen = (seq->cachethis) ? session->se_fchannel.maxresp_cached : session->se_fchannel.maxresp_sz; status = (seq->cachethis) ? nfserr_rep_too_big_to_cache : nfserr_rep_too_big; if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack)) goto out_put_session; svc_reserve(rqstp, buflen); status = nfs_ok; /* Success! accept new slot seqid */ slot->sl_seqid = seq->seqid; slot->sl_flags &= ~NFSD4_SLOT_REUSED; slot->sl_flags |= NFSD4_SLOT_INUSE; slot->sl_generation = session->se_slot_gen; if (seq->cachethis) slot->sl_flags |= NFSD4_SLOT_CACHETHIS; else slot->sl_flags &= ~NFSD4_SLOT_CACHETHIS; cstate->slot = slot; cstate->session = session; cstate->clp = clp; /* * If the client ever uses the highest available slot, * gently try to allocate another 20%. This allows * fairly quick growth without grossly over-shooting what * the client might use. */ if (seq->slotid == session->se_fchannel.maxreqs - 1 && session->se_target_maxslots >= session->se_fchannel.maxreqs && session->se_fchannel.maxreqs < NFSD_MAX_SLOTS_PER_SESSION) { int s = session->se_fchannel.maxreqs; int cnt = DIV_ROUND_UP(s, 5); void *prev_slot; do { /* * GFP_NOWAIT both allows allocation under a * spinlock, and only succeeds if there is * plenty of memory. */ slot = kzalloc(slot_bytes(&session->se_fchannel), GFP_NOWAIT); prev_slot = xa_load(&session->se_slots, s); if (xa_is_value(prev_slot) && slot) { slot->sl_seqid = xa_to_value(prev_slot); slot->sl_flags |= NFSD4_SLOT_REUSED; } if (slot && !xa_is_err(xa_store(&session->se_slots, s, slot, GFP_NOWAIT))) { s += 1; session->se_fchannel.maxreqs = s; atomic_add(s - session->se_target_maxslots, &nfsd_total_target_slots); session->se_target_maxslots = s; } else { kfree(slot); slot = NULL; } } while (slot && --cnt > 0); } seq->maxslots = max(session->se_target_maxslots, seq->maxslots); seq->target_maxslots = session->se_target_maxslots; out: switch (clp->cl_cb_state) { case NFSD4_CB_DOWN: seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; break; case NFSD4_CB_FAULT: seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; break; default: seq->status_flags = 0; } if (!list_empty(&clp->cl_revoked)) seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; if (atomic_read(&clp->cl_admin_revoked)) seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) free_conn(conn); spin_unlock(&nn->client_lock); return status; out_put_session: nfsd4_put_session_locked(session); goto out_no_session; } void nfsd4_sequence_done(struct nfsd4_compoundres *resp) { struct nfsd4_compound_state *cs = &resp->cstate; if (nfsd4_has_session(cs)) { if (cs->status != nfserr_replay_cache) { nfsd4_store_cache_entry(resp); cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE; } /* Drop session reference that was taken in nfsd4_sequence() */ nfsd4_put_session(cs->session); } else if (cs->clp) put_client_renew(cs->clp); } __be32 nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; struct nfs4_client *conf, *unconf; struct nfs4_client *clp = NULL; __be32 status = 0; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); spin_lock(&nn->client_lock); unconf = find_unconfirmed_client(&dc->clientid, true, nn); conf = find_confirmed_client(&dc->clientid, true, nn); WARN_ON_ONCE(conf && unconf); if (conf) { if (client_has_state(conf)) { status = nfserr_clientid_busy; goto out; } status = mark_client_expired_locked(conf); if (status) goto out; clp = conf; } else if (unconf) clp = unconf; else { status = nfserr_stale_clientid; goto out; } if (!nfsd4_mach_creds_match(clp, rqstp)) { clp = NULL; status = nfserr_wrong_cred; goto out; } trace_nfsd_clid_destroyed(&clp->cl_clientid); unhash_client_locked(clp); out: spin_unlock(&nn->client_lock); if (clp) expire_client(clp); return status; } __be32 nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; struct nfs4_client *clp = cstate->clp; __be32 status = 0; if (rc->rca_one_fs) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; /* * We don't take advantage of the rca_one_fs case. * That's OK, it's optional, we can safely ignore it. */ return nfs_ok; } status = nfserr_complete_already; if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) goto out; status = nfserr_stale_clientid; if (is_client_expired(clp)) /* * The following error isn't really legal. * But we only get here if the client just explicitly * destroyed the client. Surely it no longer cares what * error it gets back on an operation for the dead * client. */ goto out; status = nfs_ok; trace_nfsd_clid_reclaim_complete(&clp->cl_clientid); nfsd4_client_record_create(clp); inc_reclaim_complete(clp); out: return status; } __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_setclientid *setclid = &u->setclientid; struct xdr_netobj clname = setclid->se_name; nfs4_verifier clverifier = setclid->se_verf; struct nfs4_client *conf, *new; struct nfs4_client *unconf = NULL; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); new = create_client(clname, rqstp, &clverifier); if (new == NULL) return nfserr_jukebox; spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&clname, nn); if (conf && client_has_state(conf)) { status = nfserr_clid_inuse; if (clp_used_exchangeid(conf)) goto out; if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } } unconf = find_unconfirmed_client_by_name(&clname, nn); if (unconf) unhash_client_locked(unconf); if (conf) { if (same_verf(&conf->cl_verifier, &clverifier)) { copy_clid(new, conf); gen_confirm(new, nn); } else trace_nfsd_clid_verf_mismatch(conf, rqstp, &clverifier); } else trace_nfsd_clid_fresh(new); new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); add_to_unconfirmed(new); setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot; setclid->se_clientid.cl_id = new->cl_clientid.cl_id; memcpy(setclid->se_confirm.data, new->cl_confirm.data, sizeof(setclid->se_confirm.data)); new = NULL; status = nfs_ok; out: spin_unlock(&nn->client_lock); if (new) free_client(new); if (unconf) { trace_nfsd_clid_expire_unconf(&unconf->cl_clientid); expire_client(unconf); } return status; } __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_setclientid_confirm *setclientid_confirm = &u->setclientid_confirm; struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; nfs4_verifier confirm = setclientid_confirm->sc_confirm; clientid_t * clid = &setclientid_confirm->sc_clientid; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (STALE_CLIENTID(clid, nn)) return nfserr_stale_clientid; spin_lock(&nn->client_lock); conf = find_confirmed_client(clid, false, nn); unconf = find_unconfirmed_client(clid, false, nn); /* * We try hard to give out unique clientid's, so if we get an * attempt to confirm the same clientid with a different cred, * the client may be buggy; this should never happen. * * Nevertheless, RFC 7530 recommends INUSE for this case: */ status = nfserr_clid_inuse; if (unconf && !same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { trace_nfsd_clid_cred_mismatch(unconf, rqstp); goto out; } if (conf && !same_creds(&conf->cl_cred, &rqstp->rq_cred)) { trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } if (!unconf || !same_verf(&confirm, &unconf->cl_confirm)) { if (conf && same_verf(&confirm, &conf->cl_confirm)) { status = nfs_ok; } else status = nfserr_stale_clientid; goto out; } status = nfs_ok; if (conf) { old = unconf; unhash_client_locked(old); nfsd4_change_callback(conf, &unconf->cl_cb_conn); } else { old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = nfserr_clid_inuse; if (client_has_state(old) && !same_creds(&unconf->cl_cred, &old->cl_cred)) { old = NULL; goto out; } status = mark_client_expired_locked(old); if (status) { old = NULL; goto out; } trace_nfsd_clid_replaced(&old->cl_clientid); } move_to_confirmed(unconf); conf = unconf; } get_client_locked(conf); spin_unlock(&nn->client_lock); if (conf == unconf) fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); nfsd4_probe_callback(conf); spin_lock(&nn->client_lock); put_client_renew_locked(conf); out: spin_unlock(&nn->client_lock); if (old) expire_client(old); return status; } static struct nfs4_file *nfsd4_alloc_file(void) { return kmem_cache_alloc(file_slab, GFP_KERNEL); } /* OPEN Share state helper functions */ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) { refcount_set(&fp->fi_ref, 1); spin_lock_init(&fp->fi_lock); INIT_LIST_HEAD(&fp->fi_stateids); INIT_LIST_HEAD(&fp->fi_delegations); INIT_LIST_HEAD(&fp->fi_clnt_odstate); fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle); fp->fi_deleg_file = NULL; fp->fi_had_conflict = false; fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); fp->fi_aliased = false; fp->fi_inode = d_inode(fh->fh_dentry); #ifdef CONFIG_NFSD_PNFS INIT_LIST_HEAD(&fp->fi_lo_states); atomic_set(&fp->fi_lo_recalls, 0); #endif } void nfsd4_free_slabs(void) { kmem_cache_destroy(client_slab); kmem_cache_destroy(openowner_slab); kmem_cache_destroy(lockowner_slab); kmem_cache_destroy(file_slab); kmem_cache_destroy(stateid_slab); kmem_cache_destroy(deleg_slab); kmem_cache_destroy(odstate_slab); } int nfsd4_init_slabs(void) { client_slab = KMEM_CACHE(nfs4_client, 0); if (client_slab == NULL) goto out; openowner_slab = KMEM_CACHE(nfs4_openowner, 0); if (openowner_slab == NULL) goto out_free_client_slab; lockowner_slab = KMEM_CACHE(nfs4_lockowner, 0); if (lockowner_slab == NULL) goto out_free_openowner_slab; file_slab = KMEM_CACHE(nfs4_file, 0); if (file_slab == NULL) goto out_free_lockowner_slab; stateid_slab = KMEM_CACHE(nfs4_ol_stateid, 0); if (stateid_slab == NULL) goto out_free_file_slab; deleg_slab = KMEM_CACHE(nfs4_delegation, 0); if (deleg_slab == NULL) goto out_free_stateid_slab; odstate_slab = KMEM_CACHE(nfs4_clnt_odstate, 0); if (odstate_slab == NULL) goto out_free_deleg_slab; return 0; out_free_deleg_slab: kmem_cache_destroy(deleg_slab); out_free_stateid_slab: kmem_cache_destroy(stateid_slab); out_free_file_slab: kmem_cache_destroy(file_slab); out_free_lockowner_slab: kmem_cache_destroy(lockowner_slab); out_free_openowner_slab: kmem_cache_destroy(openowner_slab); out_free_client_slab: kmem_cache_destroy(client_slab); out: return -ENOMEM; } static unsigned long nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { int count; struct nfsd_net *nn = shrink->private_data; count = atomic_read(&nn->nfsd_courtesy_clients); if (!count) count = atomic_long_read(&num_delegations); if (count) queue_work(laundry_wq, &nn->nfsd_shrinker_work); return (unsigned long)count; } static unsigned long nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) { return SHRINK_STOP; } void nfsd4_init_leases_net(struct nfsd_net *nn) { struct sysinfo si; u64 max_clients; nn->nfsd4_lease = 90; /* default lease time */ nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; nn->track_reclaim_completes = false; nn->clverifier_counter = get_random_u32(); nn->clientid_base = get_random_u32(); nn->clientid_counter = nn->clientid_base + 1; nn->s2s_cp_cl_id = nn->clientid_counter++; atomic_set(&nn->nfs4_client_count, 0); si_meminfo(&si); max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024); max_clients *= NFS4_CLIENTS_PER_GB; nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); atomic_set(&nn->nfsd_courtesy_clients, 0); } enum rp_lock { RP_UNLOCKED, RP_LOCKED, RP_UNHASHED, }; static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; rp->rp_locked = RP_UNLOCKED; } static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so) { if (!nfsd4_has_session(cstate)) { wait_var_event(&so->so_replay.rp_locked, cmpxchg(&so->so_replay.rp_locked, RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); if (so->so_replay.rp_locked == RP_UNHASHED) return -EAGAIN; cstate->replay_owner = nfs4_get_stateowner(so); } return 0; } void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) { struct nfs4_stateowner *so = cstate->replay_owner; if (so != NULL) { cstate->replay_owner = NULL; store_release_wake_up(&so->so_replay.rp_locked, RP_UNLOCKED); nfs4_put_stateowner(so); } } static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj *owner, struct nfs4_client *clp) { struct nfs4_stateowner *sop; sop = kmem_cache_alloc(slab, GFP_KERNEL); if (!sop) return NULL; xdr_netobj_dup(&sop->so_owner, owner, GFP_KERNEL); if (!sop->so_owner.data) { kmem_cache_free(slab, sop); return NULL; } INIT_LIST_HEAD(&sop->so_stateids); sop->so_client = clp; init_nfs4_replay(&sop->so_replay); atomic_set(&sop->so_count, 1); return sop; } static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, unsigned int strhashval) { lockdep_assert_held(&clp->cl_lock); list_add(&oo->oo_owner.so_strhash, &clp->cl_ownerstr_hashtbl[strhashval]); list_add(&oo->oo_perclient, &clp->cl_openowners); } static void nfs4_unhash_openowner(struct nfs4_stateowner *so) { unhash_openowner_locked(openowner(so)); } static void nfs4_free_openowner(struct nfs4_stateowner *so) { struct nfs4_openowner *oo = openowner(so); kmem_cache_free(openowner_slab, oo); } static const struct nfs4_stateowner_operations openowner_ops = { .so_unhash = nfs4_unhash_openowner, .so_free = nfs4_free_openowner, }; static struct nfs4_ol_stateid * nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_ol_stateid *local, *ret = NULL; struct nfs4_openowner *oo = open->op_openowner; lockdep_assert_held(&fp->fi_lock); list_for_each_entry(local, &fp->fi_stateids, st_perfile) { /* ignore lock owners */ if (local->st_stateowner->so_is_open_owner == 0) continue; if (local->st_stateowner != &oo->oo_owner) continue; if (local->st_stid.sc_type == SC_TYPE_OPEN && !local->st_stid.sc_status) { ret = local; refcount_inc(&ret->st_stid.sc_count); break; } } return ret; } static void nfsd4_drop_revoked_stid(struct nfs4_stid *s) __releases(&s->sc_client->cl_lock) { struct nfs4_client *cl = s->sc_client; LIST_HEAD(reaplist); struct nfs4_ol_stateid *stp; struct nfs4_delegation *dp; bool unhashed; switch (s->sc_type) { case SC_TYPE_OPEN: stp = openlockstateid(s); if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); spin_unlock(&cl->cl_lock); free_ol_stateid_reaplist(&reaplist); break; case SC_TYPE_LOCK: stp = openlockstateid(s); unhashed = unhash_lock_stateid(stp); spin_unlock(&cl->cl_lock); if (unhashed) nfs4_put_stid(s); break; case SC_TYPE_DELEG: dp = delegstateid(s); list_del_init(&dp->dl_recall_lru); spin_unlock(&cl->cl_lock); nfs4_put_stid(s); break; default: spin_unlock(&cl->cl_lock); } } static void nfsd40_drop_revoked_stid(struct nfs4_client *cl, stateid_t *stid) { /* NFSv4.0 has no way for the client to tell the server * that it can forget an admin-revoked stateid. * So we keep it around until the first time that the * client uses it, and drop it the first time * nfserr_admin_revoked is returned. * For v4.1 and later we wait until explicitly told * to free the stateid. */ if (cl->cl_minorversion == 0) { struct nfs4_stid *st; spin_lock(&cl->cl_lock); st = find_stateid_locked(cl, stid); if (st) nfsd4_drop_revoked_stid(st); else spin_unlock(&cl->cl_lock); } } static __be32 nfsd4_verify_open_stid(struct nfs4_stid *s) { __be32 ret = nfs_ok; if (s->sc_status & SC_STATUS_ADMIN_REVOKED) ret = nfserr_admin_revoked; else if (s->sc_status & SC_STATUS_REVOKED) ret = nfserr_deleg_revoked; else if (s->sc_status & SC_STATUS_CLOSED) ret = nfserr_bad_stateid; return ret; } /* Lock the stateid st_mutex, and deal with races with CLOSE */ static __be32 nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp) { __be32 ret; mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); ret = nfsd4_verify_open_stid(&stp->st_stid); if (ret == nfserr_admin_revoked) nfsd40_drop_revoked_stid(stp->st_stid.sc_client, &stp->st_stid.sc_stateid); if (ret != nfs_ok) mutex_unlock(&stp->st_mutex); return ret; } static struct nfs4_ol_stateid * nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_ol_stateid *stp; for (;;) { spin_lock(&fp->fi_lock); stp = nfsd4_find_existing_open(fp, open); spin_unlock(&fp->fi_lock); if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok) break; nfs4_put_stid(&stp->st_stid); } return stp; } static struct nfs4_openowner * find_or_alloc_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, struct nfsd4_compound_state *cstate) { struct nfs4_client *clp = cstate->clp; struct nfs4_openowner *oo, *new = NULL; retry: spin_lock(&clp->cl_lock); oo = find_openstateowner_str(strhashval, open, clp); if (!oo && new) { hash_openowner(new, clp, strhashval); spin_unlock(&clp->cl_lock); return new; } spin_unlock(&clp->cl_lock); if (oo && !(oo->oo_flags & NFS4_OO_CONFIRMED)) { /* Replace unconfirmed owners without checking for replay. */ release_openowner(oo); oo = NULL; } if (oo) { if (new) nfs4_free_stateowner(&new->oo_owner); return oo; } new = alloc_stateowner(openowner_slab, &open->op_owner, clp); if (!new) return NULL; new->oo_owner.so_ops = &openowner_ops; new->oo_owner.so_is_open_owner = 1; new->oo_owner.so_seqid = open->op_seqid; new->oo_flags = 0; if (nfsd4_has_session(cstate)) new->oo_flags |= NFS4_OO_CONFIRMED; new->oo_time = 0; new->oo_last_closed_stid = NULL; INIT_LIST_HEAD(&new->oo_close_lru); goto retry; } static struct nfs4_ol_stateid * init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_openowner *oo = open->op_openowner; struct nfs4_ol_stateid *retstp = NULL; struct nfs4_ol_stateid *stp; stp = open->op_stp; /* We are moving these outside of the spinlocks to avoid the warnings */ mutex_init(&stp->st_mutex); mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&oo->oo_owner.so_client->cl_lock); spin_lock(&fp->fi_lock); if (nfs4_openowner_unhashed(oo)) { mutex_unlock(&stp->st_mutex); stp = NULL; goto out_unlock; } retstp = nfsd4_find_existing_open(fp, open); if (retstp) goto out_unlock; open->op_stp = NULL; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = SC_TYPE_OPEN; INIT_LIST_HEAD(&stp->st_locks); stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&oo->oo_owner.so_client->cl_lock); if (retstp) { /* Handle races with CLOSE */ if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { nfs4_put_stid(&retstp->st_stid); goto retry; } /* To keep mutex tracking happy */ mutex_unlock(&stp->st_mutex); stp = retstp; } return stp; } /* * In the 4.0 case we need to keep the owners around a little while to handle * CLOSE replay. We still do need to release any file access that is held by * them before returning however. */ static void move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) { struct nfs4_ol_stateid *last; struct nfs4_openowner *oo = openowner(s->st_stateowner); struct nfsd_net *nn = net_generic(s->st_stid.sc_client->net, nfsd_net_id); dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo); /* * We know that we hold one reference via nfsd4_close, and another * "persistent" reference for the client. If the refcount is higher * than 2, then there are still calls in progress that are using this * stateid. We can't put the sc_file reference until they are finished. * Wait for the refcount to drop to 2. Since it has been unhashed, * there should be no danger of the refcount going back up again at * this point. * Some threads with a reference might be waiting for rp_locked, * so tell them to stop waiting. */ store_release_wake_up(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2); release_all_access(s); if (s->st_stid.sc_file) { put_nfs4_file(s->st_stid.sc_file); s->st_stid.sc_file = NULL; } spin_lock(&nn->client_lock); last = oo->oo_last_closed_stid; oo->oo_last_closed_stid = s; list_move_tail(&oo->oo_close_lru, &nn->close_lru); oo->oo_time = ktime_get_boottime_seconds(); spin_unlock(&nn->client_lock); if (last) nfs4_put_stid(&last->st_stid); } static noinline_for_stack struct nfs4_file * nfsd4_file_hash_lookup(const struct svc_fh *fhp) { struct inode *inode = d_inode(fhp->fh_dentry); struct rhlist_head *tmp, *list; struct nfs4_file *fi; rcu_read_lock(); list = rhltable_lookup(&nfs4_file_rhltable, &inode, nfs4_file_rhash_params); rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { if (refcount_inc_not_zero(&fi->fi_ref)) { rcu_read_unlock(); return fi; } } } rcu_read_unlock(); return NULL; } /* * On hash insertion, identify entries with the same inode but * distinct filehandles. They will all be on the list returned * by rhltable_lookup(). * * inode->i_lock prevents racing insertions from adding an entry * for the same inode/fhp pair twice. */ static noinline_for_stack struct nfs4_file * nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp) { struct inode *inode = d_inode(fhp->fh_dentry); struct rhlist_head *tmp, *list; struct nfs4_file *ret = NULL; bool alias_found = false; struct nfs4_file *fi; int err; rcu_read_lock(); spin_lock(&inode->i_lock); list = rhltable_lookup(&nfs4_file_rhltable, &inode, nfs4_file_rhash_params); rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { if (refcount_inc_not_zero(&fi->fi_ref)) ret = fi; } else fi->fi_aliased = alias_found = true; } if (ret) goto out_unlock; nfsd4_file_init(fhp, new); err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist, nfs4_file_rhash_params); if (err) goto out_unlock; new->fi_aliased = alias_found; ret = new; out_unlock: spin_unlock(&inode->i_lock); rcu_read_unlock(); return ret; } static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi) { rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist, nfs4_file_rhash_params); } /* * Called to check deny when READ with all zero stateid or * WRITE with all zero or all one stateid */ static __be32 nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) { struct nfs4_file *fp; __be32 ret = nfs_ok; fp = nfsd4_file_hash_lookup(current_fh); if (!fp) return ret; /* Check for conflicting share reservations */ spin_lock(&fp->fi_lock); if (fp->fi_share_deny & deny_type) ret = nfserr_locked; spin_unlock(&fp->fi_lock); put_nfs4_file(fp); return ret; } static bool nfsd4_deleg_present(const struct inode *inode) { struct file_lock_context *ctx = locks_inode_context(inode); return ctx && !list_empty_careful(&ctx->flc_lease); } /** * nfsd_wait_for_delegreturn - wait for delegations to be returned * @rqstp: the RPC transaction being executed * @inode: in-core inode of the file being waited for * * The timeout prevents deadlock if all nfsd threads happen to be * tied up waiting for returning delegations. * * Return values: * %true: delegation was returned * %false: timed out waiting for delegreturn */ bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode) { long __maybe_unused timeo; timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode), NFSD_DELEGRETURN_TIMEOUT); trace_nfsd_delegret_wakeup(rqstp, inode, timeo); return timeo > 0; } static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) { struct nfs4_delegation *dp = cb_to_delegation(cb); struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net, nfsd_net_id); block_delegations(&dp->dl_stid.sc_file->fi_fhandle); /* * We can't do this in nfsd_break_deleg_cb because it is * already holding inode->i_lock. * * If the dl_time != 0, then we know that it has already been * queued for a lease break. Don't queue it again. */ spin_lock(&state_lock); if (delegation_hashed(dp) && dp->dl_time == 0) { dp->dl_time = ktime_get_boottime_seconds(); list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru); } spin_unlock(&state_lock); } static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_delegation *dp = cb_to_delegation(cb); trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task); if (dp->dl_stid.sc_status) /* CLOSED or REVOKED */ return 1; switch (task->tk_status) { case 0: return 1; case -NFS4ERR_DELAY: rpc_delay(task, 2 * HZ); return 0; case -EBADHANDLE: case -NFS4ERR_BAD_STATEID: /* * Race: client probably got cb_recall before open reply * granting delegation. */ if (dp->dl_retries--) { rpc_delay(task, 2 * HZ); return 0; } fallthrough; default: return 1; } } static void nfsd4_cb_recall_release(struct nfsd4_callback *cb) { struct nfs4_delegation *dp = cb_to_delegation(cb); nfs4_put_stid(&dp->dl_stid); } static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = { .prepare = nfsd4_cb_recall_prepare, .done = nfsd4_cb_recall_done, .release = nfsd4_cb_recall_release, .opcode = OP_CB_RECALL, }; static void nfsd_break_one_deleg(struct nfs4_delegation *dp) { /* * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease * callback (and since the lease code is serialized by the * flc_lock) we know the server hasn't removed the lease yet, and * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall)); } /* Called from break_lease() with flc_lock held. */ static bool nfsd_break_deleg_cb(struct file_lease *fl) { struct nfs4_delegation *dp = (struct nfs4_delegation *) fl->c.flc_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; struct nfs4_client *clp = dp->dl_stid.sc_client; struct nfsd_net *nn; trace_nfsd_cb_recall(&dp->dl_stid); dp->dl_recalled = true; atomic_inc(&clp->cl_delegs_in_recall); if (try_to_expire_client(clp)) { nn = net_generic(clp->net, nfsd_net_id); mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); } /* * We don't want the locks code to timeout the lease for us; * we'll remove it ourself if a delegation isn't returned * in time: */ fl->fl_break_time = 0; fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); return false; } /** * nfsd_breaker_owns_lease - Check if lease conflict was resolved * @fl: Lock state to check * * Return values: * %true: Lease conflict was resolved * %false: Lease conflict was not resolved. */ static bool nfsd_breaker_owns_lease(struct file_lease *fl) { struct nfs4_delegation *dl = fl->c.flc_owner; struct svc_rqst *rqst; struct nfs4_client *clp; rqst = nfsd_current_rqst(); if (!nfsd_v4client(rqst)) return false; clp = *(rqst->rq_lease_breaker); return dl->dl_stid.sc_client == clp; } static int nfsd_change_deleg_cb(struct file_lease *onlist, int arg, struct list_head *dispose) { struct nfs4_delegation *dp = (struct nfs4_delegation *) onlist->c.flc_owner; struct nfs4_client *clp = dp->dl_stid.sc_client; if (arg & F_UNLCK) { if (dp->dl_recalled) atomic_dec(&clp->cl_delegs_in_recall); return lease_modify(onlist, arg, dispose); } else return -EAGAIN; } static const struct lease_manager_operations nfsd_lease_mng_ops = { .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, }; static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so, u32 seqid) { if (nfsd4_has_session(cstate)) return nfs_ok; if (seqid == so->so_seqid - 1) return nfserr_replay_me; if (seqid == so->so_seqid) return nfs_ok; return nfserr_bad_seqid; } static struct nfs4_client *lookup_clientid(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct nfs4_client *found; spin_lock(&nn->client_lock); found = find_confirmed_client(clid, sessions, nn); if (found) atomic_inc(&found->cl_rpc_users); spin_unlock(&nn->client_lock); return found; } static __be32 set_client(clientid_t *clid, struct nfsd4_compound_state *cstate, struct nfsd_net *nn) { if (cstate->clp) { if (!same_clid(&cstate->clp->cl_clientid, clid)) return nfserr_stale_clientid; return nfs_ok; } if (STALE_CLIENTID(clid, nn)) return nfserr_stale_clientid; /* * We're in the 4.0 case (otherwise the SEQUENCE op would have * set cstate->clp), so session = false: */ cstate->clp = lookup_clientid(clid, false, nn); if (!cstate->clp) return nfserr_expired; return nfs_ok; } __be32 nfsd4_process_open1(struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct nfsd_net *nn) { clientid_t *clientid = &open->op_clientid; struct nfs4_client *clp = NULL; unsigned int strhashval; struct nfs4_openowner *oo = NULL; __be32 status; /* * In case we need it later, after we've already created the * file and don't want to risk a further failure: */ open->op_file = nfsd4_alloc_file(); if (open->op_file == NULL) return nfserr_jukebox; status = set_client(clientid, cstate, nn); if (status) return status; clp = cstate->clp; strhashval = ownerstr_hashval(&open->op_owner); retry: oo = find_or_alloc_open_stateowner(strhashval, open, cstate); open->op_openowner = oo; if (!oo) return nfserr_jukebox; if (nfsd4_cstate_assign_replay(cstate, &oo->oo_owner) == -EAGAIN) { nfs4_put_stateowner(&oo->oo_owner); goto retry; } status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid); if (status) return status; open->op_stp = nfs4_alloc_open_stateid(clp); if (!open->op_stp) return nfserr_jukebox; if (nfsd4_has_session(cstate) && (cstate->current_fh.fh_export->ex_flags & NFSEXP_PNFS)) { open->op_odstate = alloc_clnt_odstate(clp); if (!open->op_odstate) return nfserr_jukebox; } return nfs_ok; } static inline __be32 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags) { if (!(flags & RD_STATE) && deleg_is_read(dp->dl_type)) return nfserr_openmode; else return nfs_ok; } static int share_access_to_flags(u32 share_access) { return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE; } static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, stateid_t *s) { struct nfs4_stid *ret; ret = find_stateid_by_type(cl, s, SC_TYPE_DELEG, SC_STATUS_REVOKED); if (!ret) return NULL; return delegstateid(ret); } static bool nfsd4_is_deleg_cur(struct nfsd4_open *open) { return open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR || open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH; } static __be32 nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open, struct nfs4_delegation **dp) { int flags; __be32 status = nfserr_bad_stateid; struct nfs4_delegation *deleg; deleg = find_deleg_stateid(cl, &open->op_delegate_stateid); if (deleg == NULL) goto out; if (deleg->dl_stid.sc_status & SC_STATUS_ADMIN_REVOKED) { nfs4_put_stid(&deleg->dl_stid); status = nfserr_admin_revoked; goto out; } if (deleg->dl_stid.sc_status & SC_STATUS_REVOKED) { nfs4_put_stid(&deleg->dl_stid); nfsd40_drop_revoked_stid(cl, &open->op_delegate_stateid); status = nfserr_deleg_revoked; goto out; } flags = share_access_to_flags(open->op_share_access); status = nfs4_check_delegmode(deleg, flags); if (status) { nfs4_put_stid(&deleg->dl_stid); goto out; } *dp = deleg; out: if (!nfsd4_is_deleg_cur(open)) return nfs_ok; if (status) return status; open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; return nfs_ok; } static inline int nfs4_access_to_access(u32 nfs4_access) { int flags = 0; if (nfs4_access & NFS4_SHARE_ACCESS_READ) flags |= NFSD_MAY_READ; if (nfs4_access & NFS4_SHARE_ACCESS_WRITE) flags |= NFSD_MAY_WRITE; return flags; } static inline __be32 nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, struct nfsd4_open *open) { struct iattr iattr = { .ia_valid = ATTR_SIZE, .ia_size = 0, }; struct nfsd_attrs attrs = { .na_iattr = &iattr, }; if (!open->op_truncate) return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; return nfsd_setattr(rqstp, fh, &attrs, NULL); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open, bool new_stp) { struct nfsd_file *nf = NULL; __be32 status; int oflag = nfs4_access_to_omode(open->op_share_access); int access = nfs4_access_to_access(open->op_share_access); unsigned char old_access_bmap, old_deny_bmap; spin_lock(&fp->fi_lock); /* * Are we trying to set a deny mode that would conflict with * current access? */ status = nfs4_file_check_deny(fp, open->op_share_deny); if (status != nfs_ok) { if (status != nfserr_share_denied) { spin_unlock(&fp->fi_lock); goto out; } if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, stp, open->op_share_deny, false)) status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } /* set access to the file */ status = nfs4_file_get_access(fp, open->op_share_access); if (status != nfs_ok) { if (status != nfserr_share_denied) { spin_unlock(&fp->fi_lock); goto out; } if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, stp, open->op_share_access, true)) status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } /* Set access bits in stateid */ old_access_bmap = stp->st_access_bmap; set_access(open->op_share_access, stp); /* Set new deny mask */ old_deny_bmap = stp->st_deny_bmap; set_deny(open->op_share_deny, stp); fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH); if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); status = nfsd_file_acquire_opened(rqstp, cur_fh, access, open->op_filp, &nf); if (status != nfs_ok) goto out_put_access; spin_lock(&fp->fi_lock); if (!fp->fi_fds[oflag]) { fp->fi_fds[oflag] = nf; nf = NULL; } } spin_unlock(&fp->fi_lock); if (nf) nfsd_file_put(nf); status = nfserrno(nfsd_open_break_lease(cur_fh->fh_dentry->d_inode, access)); if (status) goto out_put_access; status = nfsd4_truncate(rqstp, cur_fh, open); if (status) goto out_put_access; out: return status; out_put_access: stp->st_access_bmap = old_access_bmap; nfs4_file_put_access(fp, open->op_share_access); reset_union_bmap_deny(bmap_to_share_mode(old_deny_bmap), stp); goto out; } static __be32 nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open) { __be32 status; unsigned char old_deny_bmap = stp->st_deny_bmap; if (!test_access(open->op_share_access, stp)) return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open, false); /* test and set deny mode */ spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); switch (status) { case nfs_ok: set_deny(open->op_share_deny, stp); fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH); break; case nfserr_share_denied: if (nfs4_resolve_deny_conflicts_locked(fp, false, stp, open->op_share_deny, false)) status = nfserr_jukebox; break; } spin_unlock(&fp->fi_lock); if (status != nfs_ok) return status; status = nfsd4_truncate(rqstp, cur_fh, open); if (status != nfs_ok) reset_union_bmap_deny(old_deny_bmap, stp); return status; } /* Should we give out recallable state?: */ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) { if (clp->cl_cb_state == NFSD4_CB_UP) return true; /* * In the sessions case, since we don't have to establish a * separate connection for callbacks, we assume it's OK * until we hear otherwise: */ return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp) { struct file_lease *fl; fl = locks_alloc_lease(); if (!fl) return NULL; fl->fl_lmops = &nfsd_lease_mng_ops; fl->c.flc_flags = FL_DELEG; fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK; fl->c.flc_owner = (fl_owner_t)dp; fl->c.flc_pid = current->tgid; fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; return fl; } static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, struct nfs4_file *fp) { struct nfs4_ol_stateid *st; struct file *f = fp->fi_deleg_file->nf_file; struct inode *ino = file_inode(f); int writes; writes = atomic_read(&ino->i_writecount); if (!writes) return 0; /* * There could be multiple filehandles (hence multiple * nfs4_files) referencing this file, but that's not too * common; let's just give up in that case rather than * trying to go look up all the clients using that other * nfs4_file as well: */ if (fp->fi_aliased) return -EAGAIN; /* * If there's a close in progress, make sure that we see it * clear any fi_fds[] entries before we see it decrement * i_writecount: */ smp_mb__after_atomic(); if (fp->fi_fds[O_WRONLY]) writes--; if (fp->fi_fds[O_RDWR]) writes--; if (writes > 0) return -EAGAIN; /* There may be non-NFSv4 writers */ /* * It's possible there are non-NFSv4 write opens in progress, * but if they haven't incremented i_writecount yet then they * also haven't called break lease yet; so, they'll break this * lease soon enough. So, all that's left to check for is NFSv4 * opens: */ spin_lock(&fp->fi_lock); list_for_each_entry(st, &fp->fi_stateids, st_perfile) { if (st->st_openstp == NULL /* it's an open */ && access_permit_write(st) && st->st_stid.sc_client != clp) { spin_unlock(&fp->fi_lock); return -EAGAIN; } } spin_unlock(&fp->fi_lock); /* * There's a small chance that we could be racing with another * NFSv4 open. However, any open that hasn't added itself to * the fi_stateids list also hasn't called break_lease yet; so, * they'll break this lease soon enough. */ return 0; } /* * It's possible that between opening the dentry and setting the delegation, * that it has been renamed or unlinked. Redo the lookup to verify that this * hasn't happened. */ static int nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, struct svc_fh *parent) { struct svc_export *exp; struct dentry *child; __be32 err; err = nfsd_lookup_dentry(open->op_rqstp, parent, open->op_fname, open->op_fnamelen, &exp, &child); if (err) return -EAGAIN; exp_put(exp); dput(child); if (child != file_dentry(fp->fi_deleg_file->nf_file)) return -EAGAIN; return 0; } /* * We avoid breaking delegations held by a client due to its own activity, but * clearing setuid/setgid bits on a write is an implicit activity and the client * may not notice and continue using the old mode. Avoid giving out a delegation * on setuid/setgid files when the client is requesting an open for write. */ static int nfsd4_verify_setuid_write(struct nfsd4_open *open, struct nfsd_file *nf) { struct inode *inode = file_inode(nf->nf_file); if ((open->op_share_access & NFS4_SHARE_ACCESS_WRITE) && (inode->i_mode & (S_ISUID|S_ISGID))) return -EAGAIN; return 0; } static struct nfs4_delegation * nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent) { bool deleg_ts = open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS; struct nfs4_client *clp = stp->st_stid.sc_client; struct nfs4_file *fp = stp->st_stid.sc_file; struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; struct nfsd_file *nf = NULL; struct file_lease *fl; int status = 0; u32 dl_type; /* * The fi_had_conflict and nfs_get_existing_delegation checks * here are just optimizations; we'll need to recheck them at * the end: */ if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); /* * Try for a write delegation first. RFC8881 section 10.4 says: * * "An OPEN_DELEGATE_WRITE delegation allows the client to handle, * on its own, all opens." * * Furthermore the client can use a write delegation for most READ * operations as well, so we require a O_RDWR file here. * * Offer a write delegation in the case of a BOTH open, and ensure * we get the O_RDWR descriptor. */ if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == NFS4_SHARE_ACCESS_BOTH) { nf = find_rw_file(fp); dl_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; } /* * If the file is being opened O_RDONLY or we couldn't get a O_RDWR * file for some reason, then try for a read delegation instead. */ if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) { nf = find_readable_file(fp); dl_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; } if (!nf) return ERR_PTR(-EAGAIN); spin_lock(&state_lock); spin_lock(&fp->fi_lock); if (nfs4_delegation_exists(clp, fp)) status = -EAGAIN; else if (nfsd4_verify_setuid_write(open, nf)) status = -EAGAIN; else if (!fp->fi_deleg_file) { fp->fi_deleg_file = nf; /* increment early to prevent fi_deleg_file from being * cleared */ fp->fi_delegees = 1; nf = NULL; } else fp->fi_delegees++; spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); if (nf) nfsd_file_put(nf); if (status) return ERR_PTR(status); status = -ENOMEM; dp = alloc_init_deleg(clp, fp, odstate, dl_type); if (!dp) goto out_delegees; fl = nfs4_alloc_init_lease(dp); if (!fl) goto out_clnt_odstate; status = kernel_setlease(fp->fi_deleg_file->nf_file, fl->c.flc_type, &fl, NULL); if (fl) locks_free_lease(fl); if (status) goto out_clnt_odstate; if (parent) { status = nfsd4_verify_deleg_dentry(open, fp, parent); if (status) goto out_unlock; } status = nfsd4_check_conflicting_opens(clp, fp); if (status) goto out_unlock; /* * Now that the deleg is set, check again to ensure that nothing * raced in and changed the mode while we weren't looking. */ status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file); if (status) goto out_unlock; status = -EAGAIN; if (fp->fi_had_conflict) goto out_unlock; spin_lock(&state_lock); spin_lock(&clp->cl_lock); spin_lock(&fp->fi_lock); status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); spin_unlock(&state_lock); if (status) goto out_unlock; return dp; out_unlock: kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); out_clnt_odstate: put_clnt_odstate(dp->dl_clnt_odstate); nfs4_put_stid(&dp->dl_stid); out_delegees: put_deleg_file(fp); return ERR_PTR(status); } static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) { open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; if (status == -EAGAIN) open->op_why_no_deleg = WND4_CONTENTION; else { open->op_why_no_deleg = WND4_RESOURCE; switch (open->op_deleg_want) { case OPEN4_SHARE_ACCESS_WANT_READ_DELEG: case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG: case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG: break; case OPEN4_SHARE_ACCESS_WANT_CANCEL: open->op_why_no_deleg = WND4_CANCELLED; break; case OPEN4_SHARE_ACCESS_WANT_NO_DELEG: WARN_ON_ONCE(1); } } } static bool nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh, struct kstat *stat) { struct nfsd_file *nf = find_rw_file(dp->dl_stid.sc_file); struct path path; int rc; if (!nf) return false; path.mnt = currentfh->fh_export->ex_path.mnt; path.dentry = file_dentry(nf->nf_file); rc = vfs_getattr(&path, stat, (STATX_MODE | STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE), AT_STATX_SYNC_AS_STAT); nfsd_file_put(nf); return rc == 0; } /* * The Linux NFS server does not offer write delegations to NFSv4.0 * clients in order to avoid conflicts between write delegations and * GETATTRs requesting CHANGE or SIZE attributes. * * With NFSv4.1 and later minorversions, the SEQUENCE operation that * begins each COMPOUND contains a client ID. Delegation recall can * be avoided when the server recognizes the client sending a * GETATTR also holds write delegation it conflicts with. * * However, the NFSv4.0 protocol does not enable a server to * determine that a GETATTR originated from the client holding the * conflicting delegation versus coming from some other client. Per * RFC 7530 Section 16.7.5, the server must recall or send a * CB_GETATTR even when the GETATTR originates from the client that * holds the conflicting delegation. * * An NFSv4.0 client can trigger a pathological situation if it * always sends a DELEGRETURN preceded by a conflicting GETATTR in * the same COMPOUND. COMPOUND execution will always stop at the * GETATTR and the DELEGRETURN will never get executed. The server * eventually revokes the delegation, which can result in loss of * open or lock state. */ static void nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *currentfh) { bool deleg_ts = open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS; struct nfs4_openowner *oo = openowner(stp->st_stateowner); struct nfs4_client *clp = stp->st_stid.sc_client; struct svc_fh *parent = NULL; struct nfs4_delegation *dp; struct kstat stat; int status = 0; int cb_up; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); open->op_recall = false; switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_PREVIOUS: if (!cb_up) open->op_recall = true; break; case NFS4_OPEN_CLAIM_NULL: parent = currentfh; fallthrough; case NFS4_OPEN_CLAIM_FH: /* * Let's not give out any delegations till everyone's * had the chance to reclaim theirs, *and* until * NLM locks have all been reclaimed: */ if (locks_in_grace(clp->net)) goto out_no_deleg; if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED)) goto out_no_deleg; if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE && !clp->cl_minorversion) goto out_no_deleg; break; default: goto out_no_deleg; } dp = nfs4_set_delegation(open, stp, parent); if (IS_ERR(dp)) goto out_no_deleg; memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { if (!nfs4_delegation_stat(dp, currentfh, &stat)) { nfs4_put_stid(&dp->dl_stid); destroy_delegation(dp); goto out_no_deleg; } open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; dp->dl_cb_fattr.ncf_cur_fsize = stat.size; dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); } else { open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); } nfs4_put_stid(&dp->dl_stid); return; out_no_deleg: open->op_delegate_type = OPEN_DELEGATE_NONE; if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && open->op_delegate_type != OPEN_DELEGATE_NONE) { dprintk("NFSD: WARNING: refusing delegation reclaim\n"); open->op_recall = true; } /* 4.1 client asking for a delegation? */ if (open->op_deleg_want) nfsd4_open_deleg_none_ext(open, status); return; } static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, struct nfs4_delegation *dp) { if (deleg_is_write(dp->dl_type)) { if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_READ_DELEG) { open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; } else if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG) { open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; } } /* Otherwise the client must be confused wanting a delegation * it already has, therefore we don't return * OPEN_DELEGATE_NONE_EXT and reason. */ } /* Are we returning only a delegation stateid? */ static bool open_xor_delegation(struct nfsd4_open *open) { if (!(open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION)) return false; /* Did we actually get a delegation? */ if (!deleg_is_read(open->op_delegate_type) && !deleg_is_write(open->op_delegate_type)) return false; return true; } /** * nfsd4_process_open2 - finish open processing * @rqstp: the RPC transaction being executed * @current_fh: NFSv4 COMPOUND's current filehandle * @open: OPEN arguments * * If successful, (1) truncate the file if open->op_truncate was * set, (2) set open->op_stateid, (3) set open->op_delegation. * * Returns %nfs_ok on success; otherwise an nfs4stat value in * network byte order is returned. */ __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfs4_client *cl = open->op_openowner->oo_owner.so_client; struct nfs4_file *fp = NULL; struct nfs4_ol_stateid *stp = NULL; struct nfs4_delegation *dp = NULL; __be32 status; bool new_stp = false; /* * Lookup file; if found, lookup stateid and check open request, * and check for delegations in the process of being recalled. * If not found, create the nfs4_file struct */ fp = nfsd4_file_hash_insert(open->op_file, current_fh); if (unlikely(!fp)) return nfserr_jukebox; if (fp != open->op_file) { status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; stp = nfsd4_find_and_lock_existing_open(fp, open); } else { open->op_file = NULL; status = nfserr_bad_stateid; if (nfsd4_is_deleg_cur(open)) goto out; } if (!stp) { stp = init_open_stateid(fp, open); if (!stp) { status = nfserr_jukebox; goto out; } if (!open->op_stp) new_stp = true; } /* * OPEN the file, or upgrade an existing OPEN. * If truncate fails, the OPEN fails. * * stp is already locked. */ if (!new_stp) { /* Stateid was found, this is an OPEN upgrade */ status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); if (status) { mutex_unlock(&stp->st_mutex); goto out; } } else { status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true); if (status) { release_open_stateid(stp); mutex_unlock(&stp->st_mutex); goto out; } stp->st_clnt_odstate = find_or_hash_clnt_odstate(fp, open->op_odstate); if (stp->st_clnt_odstate == open->op_odstate) open->op_odstate = NULL; } nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_NO_DELEG) { open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_WANTED; goto nodeleg; } } /* * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. */ nfs4_open_delegation(open, stp, &resp->cstate.current_fh); /* * If there is an existing open stateid, it must be updated and * returned. Only respect WANT_OPEN_XOR_DELEGATION when a new * open stateid would have to be created. */ if (new_stp && open_xor_delegation(open)) { memcpy(&open->op_stateid, &zero_stateid, sizeof(open->op_stateid)); open->op_rflags |= OPEN4_RESULT_NO_OPEN_STATEID; release_open_stateid(stp); } nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ if (open->op_delegate_type == OPEN_DELEGATE_NONE && dp && open->op_deleg_want) nfsd4_deleg_xgrade_none_ext(open, dp); if (fp) put_nfs4_file(fp); if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; /* * To finish the open response, we just need to set the rflags. */ open->op_rflags |= NFS4_OPEN_RESULT_LOCKTYPE_POSIX; if (nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK; else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED)) open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM; if (dp) nfs4_put_stid(&dp->dl_stid); if (stp) nfs4_put_stid(&stp->st_stid); return status; } void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { if (open->op_openowner) nfs4_put_stateowner(&open->op_openowner->oo_owner); if (open->op_file) kmem_cache_free(file_slab, open->op_file); if (open->op_stp) nfs4_put_stid(&open->op_stp->st_stid); if (open->op_odstate) kmem_cache_free(odstate_slab, open->op_odstate); } __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { clientid_t *clid = &u->renew; struct nfs4_client *clp; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); trace_nfsd_clid_renew(clid); status = set_client(clid, cstate, nn); if (status) return status; clp = cstate->clp; if (!list_empty(&clp->cl_delegations) && clp->cl_cb_state != NFSD4_CB_UP) return nfserr_cb_path_down; return nfs_ok; } void nfsd4_end_grace(struct nfsd_net *nn) { /* do nothing if grace period already ended */ if (nn->grace_ended) return; trace_nfsd_grace_complete(nn); nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 * client will still be allowed to reclaim after it comes back up, * even if it hasn't yet had a chance to reclaim state this time. * */ nfsd4_record_grace_done(nn); /* * At this point, NFSv4 clients can still reclaim. But if the * server crashes, any that have not yet reclaimed will be out * of luck on the next boot. * * (NFSv4.1+ clients are considered to have reclaimed once they * call RECLAIM_COMPLETE. NFSv4.0 clients are considered to * have reclaimed after their first OPEN.) */ locks_end_grace(&nn->nfsd4_manager); /* * At this point, and once lockd and/or any other containers * exit their grace period, further reclaims will fail and * regular locking can resume. */ } /* * If we've waited a lease period but there are still clients trying to * reclaim, wait a little longer to give them a chance to finish. */ static bool clients_still_reclaiming(struct nfsd_net *nn) { time64_t double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; if (nn->track_reclaim_completes && atomic_read(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) return false; if (!nn->somebody_reclaimed) return false; nn->somebody_reclaimed = false; /* * If we've given them *two* lease times to reclaim, and they're * still not done, give up: */ if (ktime_get_boottime_seconds() > double_grace_period_end) return false; return true; } struct laundry_time { time64_t cutoff; time64_t new_timeo; }; static bool state_expired(struct laundry_time *lt, time64_t last_refresh) { time64_t time_remaining; if (last_refresh < lt->cutoff) return true; time_remaining = last_refresh - lt->cutoff; lt->new_timeo = min(lt->new_timeo, time_remaining); return false; } #ifdef CONFIG_NFSD_V4_2_INTER_SSC void nfsd4_ssc_init_umount_work(struct nfsd_net *nn) { spin_lock_init(&nn->nfsd_ssc_lock); INIT_LIST_HEAD(&nn->nfsd_ssc_mount_list); init_waitqueue_head(&nn->nfsd_ssc_waitq); } /* * This is called when nfsd is being shutdown, after all inter_ssc * cleanup were done, to destroy the ssc delayed unmount list. */ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn) { struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *tmp; spin_lock(&nn->nfsd_ssc_lock); list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { list_del(&ni->nsui_list); spin_unlock(&nn->nfsd_ssc_lock); mntput(ni->nsui_vfsmount); kfree(ni); spin_lock(&nn->nfsd_ssc_lock); } spin_unlock(&nn->nfsd_ssc_lock); } static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) { bool do_wakeup = false; struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *tmp; spin_lock(&nn->nfsd_ssc_lock); list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { if (time_after(jiffies, ni->nsui_expire)) { if (refcount_read(&ni->nsui_refcnt) > 1) continue; /* mark being unmount */ ni->nsui_busy = true; spin_unlock(&nn->nfsd_ssc_lock); mntput(ni->nsui_vfsmount); spin_lock(&nn->nfsd_ssc_lock); /* waiters need to start from begin of list */ list_del(&ni->nsui_list); kfree(ni); /* wakeup ssc_connect waiters */ do_wakeup = true; continue; } break; } if (do_wakeup) wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); } #endif /* Check if any lock belonging to this lockowner has any blockers */ static bool nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo) { struct file_lock_context *ctx; struct nfs4_ol_stateid *stp; struct nfs4_file *nf; list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { nf = stp->st_stid.sc_file; ctx = locks_inode_context(nf->fi_inode); if (!ctx) continue; if (locks_owner_has_blockers(ctx, lo)) return true; } return false; } static bool nfs4_anylock_blockers(struct nfs4_client *clp) { int i; struct nfs4_stateowner *so; struct nfs4_lockowner *lo; if (atomic_read(&clp->cl_delegs_in_recall)) return true; spin_lock(&clp->cl_lock); for (i = 0; i < OWNER_HASH_SIZE; i++) { list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[i], so_strhash) { if (so->so_is_open_owner) continue; lo = lockowner(so); if (nfs4_lockowner_has_blockers(lo)) { spin_unlock(&clp->cl_lock); return true; } } } spin_unlock(&clp->cl_lock); return false; } static void nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist, struct laundry_time *lt) { unsigned int maxreap, reapcnt = 0; struct list_head *pos, *next; struct nfs4_client *clp; maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ? NFSD_CLIENT_MAX_TRIM_PER_RUN : 0; INIT_LIST_HEAD(reaplist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (clp->cl_state == NFSD4_EXPIRABLE) goto exp_client; if (!state_expired(lt, clp->cl_time)) break; if (!atomic_read(&clp->cl_rpc_users)) { if (clp->cl_state == NFSD4_ACTIVE) atomic_inc(&nn->nfsd_courtesy_clients); clp->cl_state = NFSD4_COURTESY; } if (!client_has_state(clp)) goto exp_client; if (!nfs4_anylock_blockers(clp)) if (reapcnt >= maxreap) continue; exp_client: if (!mark_client_expired_locked(clp)) { list_add(&clp->cl_lru, reaplist); reapcnt++; } } spin_unlock(&nn->client_lock); } static void nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist) { unsigned int maxreap = 0, reapcnt = 0; struct list_head *pos, *next; struct nfs4_client *clp; maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN; INIT_LIST_HEAD(reaplist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (clp->cl_state == NFSD4_ACTIVE) break; if (reapcnt >= maxreap) break; if (!mark_client_expired_locked(clp)) { list_add(&clp->cl_lru, reaplist); reapcnt++; } } spin_unlock(&nn->client_lock); } static void nfs4_process_client_reaplist(struct list_head *reaplist) { struct list_head *pos, *next; struct nfs4_client *clp; list_for_each_safe(pos, next, reaplist) { clp = list_entry(pos, struct nfs4_client, cl_lru); trace_nfsd_clid_purged(&clp->cl_clientid); list_del_init(&clp->cl_lru); expire_client(clp); } } static void nfs40_clean_admin_revoked(struct nfsd_net *nn, struct laundry_time *lt) { struct nfs4_client *clp; spin_lock(&nn->client_lock); if (nn->nfs40_last_revoke == 0 || nn->nfs40_last_revoke > lt->cutoff) { spin_unlock(&nn->client_lock); return; } nn->nfs40_last_revoke = 0; retry: list_for_each_entry(clp, &nn->client_lru, cl_lru) { unsigned long id, tmp; struct nfs4_stid *stid; if (atomic_read(&clp->cl_admin_revoked) == 0) continue; spin_lock(&clp->cl_lock); idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { refcount_inc(&stid->sc_count); spin_unlock(&nn->client_lock); /* this function drops ->cl_lock */ nfsd4_drop_revoked_stid(stid); nfs4_put_stid(stid); spin_lock(&nn->client_lock); goto retry; } spin_unlock(&clp->cl_lock); } spin_unlock(&nn->client_lock); } static time64_t nfs4_laundromat(struct nfsd_net *nn) { struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct nfs4_ol_stateid *stp; struct nfsd4_blocked_lock *nbl; struct list_head *pos, *next, reaplist; struct laundry_time lt = { .cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease, .new_timeo = nn->nfsd4_lease }; struct nfs4_cpntf_state *cps; copy_stateid_t *cps_t; int i; if (clients_still_reclaiming(nn)) { lt.new_timeo = 0; goto out; } nfsd4_end_grace(nn); spin_lock(&nn->s2s_cp_lock); idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) { cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID && state_expired(<, cps->cpntf_time)) _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); nfsd4_async_copy_reaper(nn); nfs4_get_client_reaplist(nn, &reaplist, <); nfs4_process_client_reaplist(&reaplist); nfs40_clean_admin_revoked(nn, <); spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(<, dp->dl_time)) break; refcount_inc(&dp->dl_stid.sc_count); unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); while (!list_empty(&reaplist)) { dp = list_first_entry(&reaplist, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); revoke_delegation(dp); } spin_lock(&nn->client_lock); while (!list_empty(&nn->close_lru)) { oo = list_first_entry(&nn->close_lru, struct nfs4_openowner, oo_close_lru); if (!state_expired(<, oo->oo_time)) break; list_del_init(&oo->oo_close_lru); stp = oo->oo_last_closed_stid; oo->oo_last_closed_stid = NULL; spin_unlock(&nn->client_lock); nfs4_put_stid(&stp->st_stid); spin_lock(&nn->client_lock); } spin_unlock(&nn->client_lock); /* * It's possible for a client to try and acquire an already held lock * that is being held for a long time, and then lose interest in it. * So, we clean out any un-revisited request after a lease period * under the assumption that the client is no longer interested. * * RFC5661, sec. 9.6 states that the client must not rely on getting * notifications and must continue to poll for locks, even when the * server supports them. Thus this shouldn't lead to clients blocking * indefinitely once the lock does become free. */ BUG_ON(!list_empty(&reaplist)); spin_lock(&nn->blocked_locks_lock); while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); if (!state_expired(<, nbl->nbl_time)) break; list_move(&nbl->nbl_lru, &reaplist); list_del_init(&nbl->nbl_list); } spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); free_blocked_lock(nbl); } #ifdef CONFIG_NFSD_V4_2_INTER_SSC /* service the server-to-server copy delayed unmount list */ nfsd4_ssc_expire_umount(nn); #endif if (atomic_long_read(&num_delegations) >= max_delegations) deleg_reaper(nn); out: return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); } static void laundromat_main(struct work_struct *); static void laundromat_main(struct work_struct *laundry) { time64_t t; struct delayed_work *dwork = to_delayed_work(laundry); struct nfsd_net *nn = container_of(dwork, struct nfsd_net, laundromat_work); t = nfs4_laundromat(nn); queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } static void courtesy_client_reaper(struct nfsd_net *nn) { struct list_head reaplist; nfs4_get_courtesy_client_reaplist(nn, &reaplist); nfs4_process_client_reaplist(&reaplist); } static void deleg_reaper(struct nfsd_net *nn) { struct list_head *pos, *next; struct nfs4_client *clp; LIST_HEAD(cblist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (clp->cl_state != NFSD4_ACTIVE || list_empty(&clp->cl_delegations) || atomic_read(&clp->cl_delegs_in_recall) || test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || (ktime_get_boottime_seconds() - clp->cl_ra_time < 5)) { continue; } list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ kref_get(&clp->cl_nfsdfs.cl_ref); set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); clp->cl_ra_time = ktime_get_boottime_seconds(); } spin_unlock(&nn->client_lock); while (!list_empty(&cblist)) { clp = list_first_entry(&cblist, struct nfs4_client, cl_ra_cblist); list_del_init(&clp->cl_ra_cblist); clp->cl_ra->ra_keep = 0; clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG) | BIT(RCA4_TYPE_MASK_WDATA_DLG); trace_nfsd_cb_recall_any(clp->cl_ra); nfsd4_run_cb(&clp->cl_ra->ra_cb); } } static void nfsd4_state_shrinker_worker(struct work_struct *work) { struct nfsd_net *nn = container_of(work, struct nfsd_net, nfsd_shrinker_work); courtesy_client_reaper(nn); deleg_reaper(nn); } static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) return nfserr_bad_stateid; return nfs_ok; } static __be32 nfs4_check_openmode(struct nfs4_ol_stateid *stp, int flags) { __be32 status = nfserr_openmode; /* For lock stateid's, we test the parent open, not the lock: */ if (stp->st_openstp) stp = stp->st_openstp; if ((flags & WR_STATE) && !access_permit_write(stp)) goto out; if ((flags & RD_STATE) && !access_permit_read(stp)) goto out; status = nfs_ok; out: return status; } static inline __be32 check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, int flags) { if (ONE_STATEID(stateid) && (flags & RD_STATE)) return nfs_ok; else if (opens_in_grace(net)) { /* Answer in remaining cases depends on existence of * conflicting state; so we must wait out the grace period. */ return nfserr_grace; } else if (flags & WR_STATE) return nfs4_share_conflict(current_fh, NFS4_SHARE_DENY_WRITE); else /* (flags & RD_STATE) && ZERO_STATEID(stateid) */ return nfs4_share_conflict(current_fh, NFS4_SHARE_DENY_READ); } static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session) { /* * When sessions are used the stateid generation number is ignored * when it is zero. */ if (has_session && in->si_generation == 0) return nfs_ok; if (in->si_generation == ref->si_generation) return nfs_ok; /* If the client sends us a stateid from the future, it's buggy: */ if (nfsd4_stateid_generation_after(in, ref)) return nfserr_bad_stateid; /* * However, we could see a stateid from the past, even from a * non-buggy client. For example, if the client sends a lock * while some IO is outstanding, the lock may bump si_generation * while the IO is still in flight. The client could avoid that * situation by waiting for responses on all the IO requests, * but better performance may result in retrying IO that * receives an old_stateid error if requests are rarely * reordered in flight: */ return nfserr_old_stateid; } static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_stid *s, bool has_session) { __be32 ret; spin_lock(&s->sc_lock); ret = nfsd4_verify_open_stid(s); if (ret == nfs_ok) ret = check_stateid_generation(in, &s->sc_stateid, has_session); spin_unlock(&s->sc_lock); if (ret == nfserr_admin_revoked) nfsd40_drop_revoked_stid(s->sc_client, &s->sc_stateid); return ret; } static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols) { if (ols->st_stateowner->so_is_open_owner && !(openowner(ols->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED)) return nfserr_bad_stateid; return nfs_ok; } static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) { struct nfs4_stid *s; __be32 status = nfserr_bad_stateid; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return status; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s) goto out_unlock; status = nfsd4_stid_check_stateid_generation(stateid, s, 1); if (status) goto out_unlock; status = nfsd4_verify_open_stid(s); if (status) goto out_unlock; switch (s->sc_type) { case SC_TYPE_DELEG: status = nfs_ok; break; case SC_TYPE_OPEN: case SC_TYPE_LOCK: status = nfsd4_check_openowner_confirmed(openlockstateid(s)); break; default: printk("unknown stateid type %x\n", s->sc_type); status = nfserr_bad_stateid; } out_unlock: spin_unlock(&cl->cl_lock); if (status == nfserr_admin_revoked) nfsd40_drop_revoked_stid(cl, stateid); return status; } __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned short typemask, unsigned short statusmask, struct nfs4_stid **s, struct nfsd_net *nn) { __be32 status; struct nfs4_stid *stid; bool return_revoked = false; /* * only return revoked delegations if explicitly asked. * otherwise we report revoked or bad_stateid status. */ if (statusmask & SC_STATUS_REVOKED) return_revoked = true; if (typemask & SC_TYPE_DELEG) /* Always allow REVOKED for DELEG so we can * retturn the appropriate error. */ statusmask |= SC_STATUS_REVOKED; statusmask |= SC_STATUS_ADMIN_REVOKED; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return nfserr_bad_stateid; status = set_client(&stateid->si_opaque.so_clid, cstate, nn); if (status == nfserr_stale_clientid) { if (cstate->session) return nfserr_bad_stateid; return nfserr_stale_stateid; } if (status) return status; stid = find_stateid_by_type(cstate->clp, stateid, typemask, statusmask); if (!stid) return nfserr_bad_stateid; if ((stid->sc_status & SC_STATUS_REVOKED) && !return_revoked) { nfs4_put_stid(stid); return nfserr_deleg_revoked; } if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { nfsd40_drop_revoked_stid(cstate->clp, stateid); nfs4_put_stid(stid); return nfserr_admin_revoked; } *s = stid; return nfs_ok; } static struct nfsd_file * nfs4_find_file(struct nfs4_stid *s, int flags) { struct nfsd_file *ret = NULL; if (!s || s->sc_status) return NULL; switch (s->sc_type) { case SC_TYPE_DELEG: spin_lock(&s->sc_file->fi_lock); ret = nfsd_file_get(s->sc_file->fi_deleg_file); spin_unlock(&s->sc_file->fi_lock); break; case SC_TYPE_OPEN: case SC_TYPE_LOCK: if (flags & RD_STATE) ret = find_readable_file(s->sc_file); else ret = find_writeable_file(s->sc_file); } return ret; } static __be32 nfs4_check_olstateid(struct nfs4_ol_stateid *ols, int flags) { __be32 status; status = nfsd4_check_openowner_confirmed(ols); if (status) return status; return nfs4_check_openmode(ols, flags); } static __be32 nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, struct nfsd_file **nfp, int flags) { int acc = (flags & RD_STATE) ? NFSD_MAY_READ : NFSD_MAY_WRITE; struct nfsd_file *nf; __be32 status; nf = nfs4_find_file(s, flags); if (nf) { status = nfsd_permission(&rqstp->rq_cred, fhp->fh_export, fhp->fh_dentry, acc | NFSD_MAY_OWNER_OVERRIDE); if (status) { nfsd_file_put(nf); goto out; } } else { status = nfsd_file_acquire(rqstp, fhp, acc, &nf); if (status) return status; } *nfp = nf; out: return status; } static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); if (!refcount_dec_and_test(&cps->cp_stateid.cs_count)) return; list_del(&cps->cp_list); idr_remove(&nn->s2s_cp_stateids, cps->cp_stateid.cs_stid.si_opaque.so_id); kfree(cps); } /* * A READ from an inter server to server COPY will have a * copy stateid. Look up the copy notify stateid from the * idr structure and take a reference on it. */ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, struct nfs4_client *clp, struct nfs4_cpntf_state **cps) { copy_stateid_t *cps_t; struct nfs4_cpntf_state *state = NULL; if (st->si_opaque.so_clid.cl_id != nn->s2s_cp_cl_id) return nfserr_bad_stateid; spin_lock(&nn->s2s_cp_lock); cps_t = idr_find(&nn->s2s_cp_stateids, st->si_opaque.so_id); if (cps_t) { state = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) { state = NULL; goto unlock; } if (!clp) refcount_inc(&state->cp_stateid.cs_count); else _free_cpntf_state_locked(nn, state); } unlock: spin_unlock(&nn->s2s_cp_lock); if (!state) return nfserr_bad_stateid; if (!clp) *cps = state; return 0; } static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st, struct nfs4_stid **stid) { __be32 status; struct nfs4_cpntf_state *cps = NULL; struct nfs4_client *found; status = manage_cpntf_state(nn, st, NULL, &cps); if (status) return status; cps->cpntf_time = ktime_get_boottime_seconds(); status = nfserr_expired; found = lookup_clientid(&cps->cp_p_clid, true, nn); if (!found) goto out; *stid = find_stateid_by_type(found, &cps->cp_p_stateid, SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, 0); if (*stid) status = nfs_ok; else status = nfserr_bad_stateid; put_client_renew(found); out: nfs4_put_cpntf_state(nn, cps); return status; } void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { spin_lock(&nn->s2s_cp_lock); _free_cpntf_state_locked(nn, cps); spin_unlock(&nn->s2s_cp_lock); } /** * nfs4_preprocess_stateid_op - find and prep stateid for an operation * @rqstp: incoming request from client * @cstate: current compound state * @fhp: filehandle associated with requested stateid * @stateid: stateid (provided by client) * @flags: flags describing type of operation to be done * @nfp: optional nfsd_file return pointer (may be NULL) * @cstid: optional returned nfs4_stid pointer (may be NULL) * * Given info from the client, look up a nfs4_stid for the operation. On * success, it returns a reference to the nfs4_stid and/or the nfsd_file * associated with it. */ __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct svc_fh *fhp, stateid_t *stateid, int flags, struct nfsd_file **nfp, struct nfs4_stid **cstid) { struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfs4_stid *s = NULL; __be32 status; if (nfp) *nfp = NULL; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { status = check_special_stateids(net, fhp, stateid, flags); goto done; } status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, 0, &s, nn); if (status == nfserr_bad_stateid) status = find_cpntf_state(nn, stateid, &s); if (status) return status; status = nfsd4_stid_check_stateid_generation(stateid, s, nfsd4_has_session(cstate)); if (status) goto out; switch (s->sc_type) { case SC_TYPE_DELEG: status = nfs4_check_delegmode(delegstateid(s), flags); break; case SC_TYPE_OPEN: case SC_TYPE_LOCK: status = nfs4_check_olstateid(openlockstateid(s), flags); break; } if (status) goto out; status = nfs4_check_fh(fhp, s); done: if (status == nfs_ok && nfp) status = nfs4_check_file(rqstp, fhp, s, nfp, flags); out: if (s) { if (!status && cstid) *cstid = s; else nfs4_put_stid(s); } return status; } /* * Test if the stateid is valid */ __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; struct nfs4_client *cl = cstate->clp; list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list) stateid->ts_id_status = nfsd4_validate_stateid(cl, &stateid->ts_id_stateid); return nfs_ok; } static __be32 nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) { struct nfs4_ol_stateid *stp = openlockstateid(s); __be32 ret; ret = nfsd4_lock_ol_stateid(stp); if (ret) goto out_put_stid; ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) goto out; ret = nfserr_locks_held; if (check_for_locks(stp->st_stid.sc_file, lockowner(stp->st_stateowner))) goto out; release_lock_stateid(stp); ret = nfs_ok; out: mutex_unlock(&stp->st_mutex); out_put_stid: nfs4_put_stid(s); return ret; } __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_free_stateid *free_stateid = &u->free_stateid; stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; struct nfs4_client *cl = cstate->clp; __be32 ret = nfserr_bad_stateid; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s || s->sc_status & SC_STATUS_CLOSED) goto out_unlock; if (s->sc_status & SC_STATUS_ADMIN_REVOKED) { nfsd4_drop_revoked_stid(s); ret = nfs_ok; goto out; } spin_lock(&s->sc_lock); switch (s->sc_type) { case SC_TYPE_DELEG: if (s->sc_status & SC_STATUS_REVOKED) { s->sc_status |= SC_STATUS_CLOSED; spin_unlock(&s->sc_lock); dp = delegstateid(s); if (s->sc_status & SC_STATUS_FREEABLE) list_del_init(&dp->dl_recall_lru); s->sc_status |= SC_STATUS_FREED; spin_unlock(&cl->cl_lock); nfs4_put_stid(s); ret = nfs_ok; goto out; } ret = nfserr_locks_held; break; case SC_TYPE_OPEN: ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) break; ret = nfserr_locks_held; break; case SC_TYPE_LOCK: spin_unlock(&s->sc_lock); refcount_inc(&s->sc_count); spin_unlock(&cl->cl_lock); ret = nfsd4_free_lock_stateid(stateid, s); goto out; } spin_unlock(&s->sc_lock); out_unlock: spin_unlock(&cl->cl_lock); out: return ret; } static inline int setlkflg (int type) { return (type == NFS4_READW_LT || type == NFS4_READ_LT) ? RD_STATE : WR_STATE; } static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_t *stateid, u32 seqid, struct nfs4_ol_stateid *stp) { struct svc_fh *current_fh = &cstate->current_fh; struct nfs4_stateowner *sop = stp->st_stateowner; __be32 status; status = nfsd4_check_seqid(cstate, sop, seqid); if (status) return status; status = nfsd4_lock_ol_stateid(stp); if (status != nfs_ok) return status; status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); if (status == nfs_ok) status = nfs4_check_fh(current_fh, &stp->st_stid); if (status != nfs_ok) mutex_unlock(&stp->st_mutex); return status; } /** * nfs4_preprocess_seqid_op - find and prep an ol_stateid for a seqid-morphing op * @cstate: compund state * @seqid: seqid (provided by client) * @stateid: stateid (provided by client) * @typemask: mask of allowable types for this operation * @statusmask: mask of allowed states: 0 or STID_CLOSED * @stpp: return pointer for the stateid found * @nn: net namespace for request * * Given a stateid+seqid from a client, look up an nfs4_ol_stateid and * return it in @stpp. On a nfs_ok return, the returned stateid will * have its st_mutex locked. */ static __be32 nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, stateid_t *stateid, unsigned short typemask, unsigned short statusmask, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { __be32 status; struct nfs4_stid *s; struct nfs4_ol_stateid *stp = NULL; trace_nfsd_preprocess(seqid, stateid); *stpp = NULL; retry: status = nfsd4_lookup_stateid(cstate, stateid, typemask, statusmask, &s, nn); if (status) return status; stp = openlockstateid(s); if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) { nfs4_put_stateowner(stp->st_stateowner); goto retry; } status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp); if (!status) *stpp = stp; else nfs4_put_stid(&stp->st_stid); return status; } static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, stateid_t *stateid, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; status = nfs4_preprocess_seqid_op(cstate, seqid, stateid, SC_TYPE_OPEN, 0, &stp, nn); if (status) return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } *stpp = stp; return nfs_ok; } __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_open_confirm *oc = &u->open_confirm; __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_open_confirm on file %pd\n", cstate->current_fh.fh_dentry); status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); if (status) return status; status = nfs4_preprocess_seqid_op(cstate, oc->oc_seqid, &oc->oc_req_stateid, SC_TYPE_OPEN, 0, &stp, nn); if (status) goto out; oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; if (oo->oo_flags & NFS4_OO_CONFIRMED) { mutex_unlock(&stp->st_mutex); goto put_stateid; } oo->oo_flags |= NFS4_OO_CONFIRMED; nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); trace_nfsd_open_confirm(oc->oc_seqid, &stp->st_stid.sc_stateid); nfsd4_client_record_create(oo->oo_owner.so_client); status = nfs_ok; put_stateid: nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); return status; } static inline void nfs4_stateid_downgrade_bit(struct nfs4_ol_stateid *stp, u32 access) { if (!test_access(access, stp)) return; nfs4_file_put_access(stp->st_stid.sc_file, access); clear_access(access, stp); } static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_access) { switch (to_access) { case NFS4_SHARE_ACCESS_READ: nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_WRITE); nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_BOTH); break; case NFS4_SHARE_ACCESS_WRITE: nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_READ); nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_BOTH); break; case NFS4_SHARE_ACCESS_BOTH: break; default: WARN_ON_ONCE(1); } } __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_open_downgrade *od = &u->open_downgrade; __be32 status; struct nfs4_ol_stateid *stp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_open_downgrade on file %pd\n", cstate->current_fh.fh_dentry); /* We don't yet support WANT bits: */ if (od->od_deleg_want) dprintk("NFSD: %s: od_deleg_want=0x%x ignored\n", __func__, od->od_deleg_want); status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid, &od->od_stateid, &stp, nn); if (status) goto out; status = nfserr_inval; if (!test_access(od->od_share_access, stp)) { dprintk("NFSD: access not a subset of current bitmap: 0x%hhx, input access=%08x\n", stp->st_access_bmap, od->od_share_access); goto put_stateid; } if (!test_deny(od->od_share_deny, stp)) { dprintk("NFSD: deny not a subset of current bitmap: 0x%hhx, input deny=%08x\n", stp->st_deny_bmap, od->od_share_deny); goto put_stateid; } nfs4_stateid_downgrade(stp, od->od_share_access); reset_union_bmap_deny(od->od_share_deny, stp); nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid); status = nfs_ok; put_stateid: mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); return status; } static bool nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) { struct nfs4_client *clp = s->st_stid.sc_client; bool unhashed; LIST_HEAD(reaplist); struct nfs4_ol_stateid *stp; spin_lock(&clp->cl_lock); unhashed = unhash_open_stateid(s, &reaplist); if (clp->cl_minorversion) { if (unhashed) put_ol_stateid_locked(s, &reaplist); spin_unlock(&clp->cl_lock); list_for_each_entry(stp, &reaplist, st_locks) nfs4_free_cpntf_statelist(clp->net, &stp->st_stid); free_ol_stateid_reaplist(&reaplist); return false; } else { spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); return unhashed; } } /* * nfs4_unlock_state() called after encode */ __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_close *close = &u->close; __be32 status; struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); bool need_move_to_close_list; dprintk("NFSD: nfsd4_close on file %pd\n", cstate->current_fh.fh_dentry); status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, &close->cl_stateid, SC_TYPE_OPEN, SC_STATUS_CLOSED, &stp, nn); nfsd4_bump_seqid(cstate, status); if (status) goto out; spin_lock(&stp->st_stid.sc_client->cl_lock); stp->st_stid.sc_status |= SC_STATUS_CLOSED; spin_unlock(&stp->st_stid.sc_client->cl_lock); /* * Technically we don't _really_ have to increment or copy it, since * it should just be gone after this operation and we clobber the * copied value below, but we continue to do so here just to ensure * that racing ops see that there was a state change. */ nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); need_move_to_close_list = nfsd4_close_open_stateid(stp); mutex_unlock(&stp->st_mutex); if (need_move_to_close_list) move_to_close_lru(stp, net); /* v4.1+ suggests that we send a special stateid in here, since the * clients should just ignore this anyway. Since this is not useful * for v4.0 clients either, we set it to the special close_stateid * universally. * * See RFC5661 section 18.2.4, and RFC7530 section 16.2.5 */ memcpy(&close->cl_stateid, &close_stateid, sizeof(close->cl_stateid)); /* put reference from nfs4_preprocess_seqid_op */ nfs4_put_stid(&stp->st_stid); out: return status; } __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_delegreturn *dr = &u->delegreturn; struct nfs4_delegation *dp; stateid_t *stateid = &dr->dr_stateid; struct nfs4_stid *s; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) return status; status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED | SC_STATUS_FREEABLE, &s, nn); if (status) goto out; dp = delegstateid(s); status = nfsd4_stid_check_stateid_generation(stateid, &dp->dl_stid, nfsd4_has_session(cstate)); if (status) goto put_stateid; trace_nfsd_deleg_return(stateid); destroy_delegation(dp); smp_mb__after_atomic(); wake_up_var(d_inode(cstate->current_fh.fh_dentry)); put_stateid: nfs4_put_stid(&dp->dl_stid); out: return status; } /* last octet in a range */ static inline u64 last_byte_offset(u64 start, u64 len) { u64 end; WARN_ON_ONCE(!len); end = start + len; return end > start ? end - 1: NFS4_MAX_UINT64; } /* * TODO: Linux file offsets are _signed_ 64-bit quantities, which means that * we can't properly handle lock requests that go beyond the (2^63 - 1)-th * byte, because of sign extension problems. Since NFSv4 calls for 64-bit * locking, this prevents us from being completely protocol-compliant. The * real solution to this problem is to start using unsigned file offsets in * the VFS, but this is a very deep change! */ static inline void nfs4_transform_lock_offset(struct file_lock *lock) { if (lock->fl_start < 0) lock->fl_start = OFFSET_MAX; if (lock->fl_end < 0) lock->fl_end = OFFSET_MAX; } static fl_owner_t nfsd4_lm_get_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; nfs4_get_stateowner(&lo->lo_owner); return owner; } static void nfsd4_lm_put_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; if (lo) nfs4_put_stateowner(&lo->lo_owner); } /* return pointer to struct nfs4_client if client is expirable */ static bool nfsd4_lm_lock_expirable(struct file_lock *cfl) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *) cfl->c.flc_owner; struct nfs4_client *clp = lo->lo_owner.so_client; struct nfsd_net *nn; if (try_to_expire_client(clp)) { nn = net_generic(clp->net, nfsd_net_id); mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); return true; } return false; } /* schedule laundromat to run immediately and wait for it to complete */ static void nfsd4_lm_expire_lock(void) { flush_workqueue(laundry_wq); } static void nfsd4_lm_notify(struct file_lock *fl) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *) fl->c.flc_owner; struct net *net = lo->lo_owner.so_client->net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfsd4_blocked_lock *nbl = container_of(fl, struct nfsd4_blocked_lock, nbl_lock); bool queue = false; /* An empty list means that something else is going to be using it */ spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list)) { list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); queue = true; } spin_unlock(&nn->blocked_locks_lock); if (queue) { trace_nfsd_cb_notify_lock(lo, nbl); nfsd4_run_cb(&nbl->nbl_cb); } } static const struct lock_manager_operations nfsd_posix_mng_ops = { .lm_mod_owner = THIS_MODULE, .lm_notify = nfsd4_lm_notify, .lm_get_owner = nfsd4_lm_get_owner, .lm_put_owner = nfsd4_lm_put_owner, .lm_lock_expirable = nfsd4_lm_lock_expirable, .lm_expire_lock = nfsd4_lm_expire_lock, }; static inline void nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) { struct nfs4_lockowner *lo; if (fl->fl_lmops == &nfsd_posix_mng_ops) { lo = (struct nfs4_lockowner *) fl->c.flc_owner; xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner, GFP_KERNEL); if (!deny->ld_owner.data) /* We just don't care that much */ goto nevermind; deny->ld_clientid = lo->lo_owner.so_client->cl_clientid; } else { nevermind: deny->ld_owner.len = 0; deny->ld_owner.data = NULL; deny->ld_clientid.cl_boot = 0; deny->ld_clientid.cl_id = 0; } deny->ld_start = fl->fl_start; deny->ld_length = NFS4_MAX_UINT64; if (fl->fl_end != NFS4_MAX_UINT64) deny->ld_length = fl->fl_end - fl->fl_start + 1; deny->ld_type = NFS4_READ_LT; if (fl->c.flc_type != F_RDLCK) deny->ld_type = NFS4_WRITE_LT; } static struct nfs4_lockowner * find_lockowner_str_locked(struct nfs4_client *clp, struct xdr_netobj *owner) { unsigned int strhashval = ownerstr_hashval(owner); struct nfs4_stateowner *so; lockdep_assert_held(&clp->cl_lock); list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[strhashval], so_strhash) { if (so->so_is_open_owner) continue; if (same_owner_str(so, owner)) return lockowner(nfs4_get_stateowner(so)); } return NULL; } static struct nfs4_lockowner * find_lockowner_str(struct nfs4_client *clp, struct xdr_netobj *owner) { struct nfs4_lockowner *lo; spin_lock(&clp->cl_lock); lo = find_lockowner_str_locked(clp, owner); spin_unlock(&clp->cl_lock); return lo; } static void nfs4_unhash_lockowner(struct nfs4_stateowner *sop) { unhash_lockowner_locked(lockowner(sop)); } static void nfs4_free_lockowner(struct nfs4_stateowner *sop) { struct nfs4_lockowner *lo = lockowner(sop); kmem_cache_free(lockowner_slab, lo); } static const struct nfs4_stateowner_operations lockowner_ops = { .so_unhash = nfs4_unhash_lockowner, .so_free = nfs4_free_lockowner, }; /* * Alloc a lock owner structure. * Called in nfsd4_lock - therefore, OPEN and OPEN_CONFIRM (if needed) has * occurred. * * strhashval = ownerstr_hashval */ static struct nfs4_lockowner * alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, struct nfs4_ol_stateid *open_stp, struct nfsd4_lock *lock) { struct nfs4_lockowner *lo, *ret; lo = alloc_stateowner(lockowner_slab, &lock->lk_new_owner, clp); if (!lo) return NULL; INIT_LIST_HEAD(&lo->lo_blocked); INIT_LIST_HEAD(&lo->lo_owner.so_stateids); lo->lo_owner.so_is_open_owner = 0; lo->lo_owner.so_seqid = lock->lk_new_lock_seqid; lo->lo_owner.so_ops = &lockowner_ops; spin_lock(&clp->cl_lock); ret = find_lockowner_str_locked(clp, &lock->lk_new_owner); if (ret == NULL) { list_add(&lo->lo_owner.so_strhash, &clp->cl_ownerstr_hashtbl[strhashval]); ret = lo; } else nfs4_free_stateowner(&lo->lo_owner); spin_unlock(&clp->cl_lock); return ret; } static struct nfs4_ol_stateid * find_lock_stateid(const struct nfs4_lockowner *lo, const struct nfs4_ol_stateid *ost) { struct nfs4_ol_stateid *lst; lockdep_assert_held(&ost->st_stid.sc_client->cl_lock); /* If ost is not hashed, ost->st_locks will not be valid */ if (!nfs4_ol_stateid_unhashed(ost)) list_for_each_entry(lst, &ost->st_locks, st_locks) { if (lst->st_stateowner == &lo->lo_owner) { refcount_inc(&lst->st_stid.sc_count); return lst; } } return NULL; } static struct nfs4_ol_stateid * init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, struct nfs4_file *fp, struct inode *inode, struct nfs4_ol_stateid *open_stp) { struct nfs4_client *clp = lo->lo_owner.so_client; struct nfs4_ol_stateid *retstp; mutex_init(&stp->st_mutex); mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&clp->cl_lock); if (nfs4_ol_stateid_unhashed(open_stp)) goto out_close; retstp = find_lock_stateid(lo, open_stp); if (retstp) goto out_found; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = SC_TYPE_LOCK; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; spin_lock(&fp->fi_lock); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); return stp; out_found: spin_unlock(&clp->cl_lock); if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { nfs4_put_stid(&retstp->st_stid); goto retry; } /* To keep mutex tracking happy */ mutex_unlock(&stp->st_mutex); return retstp; out_close: spin_unlock(&clp->cl_lock); mutex_unlock(&stp->st_mutex); return NULL; } static struct nfs4_ol_stateid * find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, struct inode *inode, struct nfs4_ol_stateid *ost, bool *new) { struct nfs4_stid *ns = NULL; struct nfs4_ol_stateid *lst; struct nfs4_openowner *oo = openowner(ost->st_stateowner); struct nfs4_client *clp = oo->oo_owner.so_client; *new = false; spin_lock(&clp->cl_lock); lst = find_lock_stateid(lo, ost); spin_unlock(&clp->cl_lock); if (lst != NULL) { if (nfsd4_lock_ol_stateid(lst) == nfs_ok) goto out; nfs4_put_stid(&lst->st_stid); } ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid); if (ns == NULL) return NULL; lst = init_lock_stateid(openlockstateid(ns), lo, fi, inode, ost); if (lst == openlockstateid(ns)) *new = true; else nfs4_put_stid(ns); out: return lst; } static int check_lock_length(u64 offset, u64 length) { return ((length == 0) || ((length != NFS4_MAX_UINT64) && (length > ~offset))); } static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access) { struct nfs4_file *fp = lock_stp->st_stid.sc_file; lockdep_assert_held(&fp->fi_lock); if (test_access(access, lock_stp)) return; __nfs4_file_get_access(fp, access); set_access(access, lock_stp); } static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, struct nfs4_ol_stateid **plst, bool *new) { __be32 status; struct nfs4_file *fi = ost->st_stid.sc_file; struct nfs4_openowner *oo = openowner(ost->st_stateowner); struct nfs4_client *cl = oo->oo_owner.so_client; struct inode *inode = d_inode(cstate->current_fh.fh_dentry); struct nfs4_lockowner *lo; struct nfs4_ol_stateid *lst; unsigned int strhashval; lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { strhashval = ownerstr_hashval(&lock->lk_new_owner); lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock); if (lo == NULL) return nfserr_jukebox; } else { /* with an existing lockowner, seqids must be the same */ status = nfserr_bad_seqid; if (!cstate->minorversion && lock->lk_new_lock_seqid != lo->lo_owner.so_seqid) goto out; } lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); if (lst == NULL) { status = nfserr_jukebox; goto out; } status = nfs_ok; *plst = lst; out: nfs4_put_stateowner(&lo->lo_owner); return status; } /* * LOCK operation */ __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_lock *lock = &u->lock; struct nfs4_openowner *open_sop = NULL; struct nfs4_lockowner *lock_sop = NULL; struct nfs4_ol_stateid *lock_stp = NULL; struct nfs4_ol_stateid *open_stp = NULL; struct nfs4_file *fp; struct nfsd_file *nf = NULL; struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; __be32 status = 0; int lkflg; int err; bool new = false; unsigned char type; unsigned int flags = FL_POSIX; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n", (long long) lock->lk_offset, (long long) lock->lk_length); if (check_lock_length(lock->lk_offset, lock->lk_length)) return nfserr_inval; status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); if (status != nfs_ok) return status; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) /* See rfc 5661 18.10.3: given clientid is ignored: */ memcpy(&lock->lk_new_clientid, &cstate->clp->cl_clientid, sizeof(clientid_t)); /* validate and update open stateid and open seqid */ status = nfs4_preprocess_confirmed_seqid_op(cstate, lock->lk_new_open_seqid, &lock->lk_new_open_stateid, &open_stp, nn); if (status) goto out; mutex_unlock(&open_stp->st_mutex); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, &lock->lk_new_clientid)) goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, &lock->lk_old_lock_stateid, SC_TYPE_LOCK, 0, &lock_stp, nn); } if (status) goto out; lock_sop = lockowner(lock_stp->st_stateowner); lkflg = setlkflg(lock->lk_type); status = nfs4_check_openmode(lock_stp, lkflg); if (status) goto out; status = nfserr_grace; if (locks_in_grace(net) && !lock->lk_reclaim) goto out; status = nfserr_no_grace; if (!locks_in_grace(net) && lock->lk_reclaim) goto out; if (lock->lk_reclaim) flags |= FL_RECLAIM; fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: fallthrough; case NFS4_READ_LT: spin_lock(&fp->fi_lock); nf = find_readable_file_locked(fp); if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ); spin_unlock(&fp->fi_lock); type = F_RDLCK; break; case NFS4_WRITEW_LT: fallthrough; case NFS4_WRITE_LT: spin_lock(&fp->fi_lock); nf = find_writeable_file_locked(fp); if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE); spin_unlock(&fp->fi_lock); type = F_WRLCK; break; default: status = nfserr_inval; goto out; } if (!nf) { status = nfserr_openmode; goto out; } if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) && nfsd4_has_session(cstate) && locks_can_async_lock(nf->nf_file->f_op)) flags |= FL_SLEEP; nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { dprintk("NFSD: %s: unable to allocate block!\n", __func__); status = nfserr_jukebox; goto out; } file_lock = &nbl->nbl_lock; file_lock->c.flc_type = type; file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); file_lock->c.flc_pid = current->tgid; file_lock->c.flc_file = nf->nf_file; file_lock->c.flc_flags = flags; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = lock->lk_offset; file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length); nfs4_transform_lock_offset(file_lock); conflock = locks_alloc_lock(); if (!conflock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); status = nfserr_jukebox; goto out; } if (flags & FL_SLEEP) { nbl->nbl_time = ktime_get_boottime_seconds(); spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); kref_get(&nbl->nbl_kref); spin_unlock(&nn->blocked_locks_lock); } err = vfs_lock_file(nf->nf_file, F_SETLK, file_lock, conflock); switch (err) { case 0: /* success! */ nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid); status = 0; if (lock->lk_reclaim) nn->somebody_reclaimed = true; break; case FILE_LOCK_DEFERRED: kref_put(&nbl->nbl_kref, free_nbl); nbl = NULL; fallthrough; case -EAGAIN: /* conflock holds conflicting lock */ status = nfserr_denied; dprintk("NFSD: nfsd4_lock: conflicting lock found!\n"); nfs4_set_lock_denied(conflock, &lock->lk_denied); break; case -EDEADLK: status = nfserr_deadlock; break; default: dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err); status = nfserrno(err); break; } out: if (nbl) { /* dequeue it if we queued it before */ if (flags & FL_SLEEP) { spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list) && !list_empty(&nbl->nbl_lru)) { list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); kref_put(&nbl->nbl_kref, free_nbl); } /* nbl can use one of lists to be linked to reaplist */ spin_unlock(&nn->blocked_locks_lock); } free_blocked_lock(nbl); } if (nf) nfsd_file_put(nf); if (lock_stp) { /* Bump seqid manually if the 4.0 replay owner is openowner */ if (cstate->replay_owner && cstate->replay_owner != &lock_sop->lo_owner && seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. */ if (status && new) release_lock_stateid(lock_stp); mutex_unlock(&lock_stp->st_mutex); nfs4_put_stid(&lock_stp->st_stid); } if (open_stp) nfs4_put_stid(&open_stp->st_stid); nfsd4_bump_seqid(cstate, status); if (conflock) locks_free_lock(conflock); return status; } void nfsd4_lock_release(union nfsd4_op_u *u) { struct nfsd4_lock *lock = &u->lock; struct nfsd4_lock_denied *deny = &lock->lk_denied; kfree(deny->ld_owner.data); } /* * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN, * so we do a temporary open here just to get an open file to pass to * vfs_test_lock. */ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock) { struct nfsd_file *nf; struct inode *inode; __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf); if (err) return err; inode = fhp->fh_dentry->d_inode; inode_lock(inode); /* to block new leases till after test_lock: */ err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (err) goto out; lock->c.flc_file = nf->nf_file; err = nfserrno(vfs_test_lock(nf->nf_file, lock)); lock->c.flc_file = NULL; out: inode_unlock(inode); nfsd_file_put(nf); return err; } /* * LOCKT operation */ __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_lockt *lockt = &u->lockt; struct file_lock *file_lock = NULL; struct nfs4_lockowner *lo = NULL; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (locks_in_grace(SVC_NET(rqstp))) return nfserr_grace; if (check_lock_length(lockt->lt_offset, lockt->lt_length)) return nfserr_inval; if (!nfsd4_has_session(cstate)) { status = set_client(&lockt->lt_clientid, cstate, nn); if (status) goto out; } if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) goto out; file_lock = locks_alloc_lock(); if (!file_lock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); status = nfserr_jukebox; goto out; } switch (lockt->lt_type) { case NFS4_READ_LT: case NFS4_READW_LT: file_lock->c.flc_type = F_RDLCK; break; case NFS4_WRITE_LT: case NFS4_WRITEW_LT: file_lock->c.flc_type = F_WRLCK; break; default: dprintk("NFSD: nfs4_lockt: bad lock type!\n"); status = nfserr_inval; goto out; } lo = find_lockowner_str(cstate->clp, &lockt->lt_owner); if (lo) file_lock->c.flc_owner = (fl_owner_t)lo; file_lock->c.flc_pid = current->tgid; file_lock->c.flc_flags = FL_POSIX; file_lock->fl_start = lockt->lt_offset; file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length); nfs4_transform_lock_offset(file_lock); status = nfsd_test_lock(rqstp, &cstate->current_fh, file_lock); if (status) goto out; if (file_lock->c.flc_type != F_UNLCK) { status = nfserr_denied; nfs4_set_lock_denied(file_lock, &lockt->lt_denied); } out: if (lo) nfs4_put_stateowner(&lo->lo_owner); if (file_lock) locks_free_lock(file_lock); return status; } void nfsd4_lockt_release(union nfsd4_op_u *u) { struct nfsd4_lockt *lockt = &u->lockt; struct nfsd4_lock_denied *deny = &lockt->lt_denied; kfree(deny->ld_owner.data); } __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_locku *locku = &u->locku; struct nfs4_ol_stateid *stp; struct nfsd_file *nf = NULL; struct file_lock *file_lock = NULL; __be32 status; int err; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_locku: start=%Ld length=%Ld\n", (long long) locku->lu_offset, (long long) locku->lu_length); if (check_lock_length(locku->lu_offset, locku->lu_length)) return nfserr_inval; status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, &locku->lu_stateid, SC_TYPE_LOCK, 0, &stp, nn); if (status) goto out; nf = find_any_file(stp->st_stid.sc_file); if (!nf) { status = nfserr_lock_range; goto put_stateid; } file_lock = locks_alloc_lock(); if (!file_lock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); status = nfserr_jukebox; goto put_file; } file_lock->c.flc_type = F_UNLCK; file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); file_lock->c.flc_pid = current->tgid; file_lock->c.flc_file = nf->nf_file; file_lock->c.flc_flags = FL_POSIX; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = locku->lu_offset; file_lock->fl_end = last_byte_offset(locku->lu_offset, locku->lu_length); nfs4_transform_lock_offset(file_lock); err = vfs_lock_file(nf->nf_file, F_SETLK, file_lock, NULL); if (err) { dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid); put_file: nfsd_file_put(nf); put_stateid: mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); if (file_lock) locks_free_lock(file_lock); return status; out_nfserr: status = nfserrno(err); goto put_file; } /* * returns * true: locks held by lockowner * false: no locks held by lockowner */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; spin_lock(&fp->fi_lock); nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); goto out; } inode = file_inode(nf->nf_file); flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); for_each_file_lock(fl, &flctx->flc_posix) { if (fl->c.flc_owner == (fl_owner_t)lowner) { status = true; break; } } spin_unlock(&flctx->flc_lock); } out: spin_unlock(&fp->fi_lock); return status; } /** * nfsd4_release_lockowner - process NFSv4.0 RELEASE_LOCKOWNER operations * @rqstp: RPC transaction * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * * Check if there are any locks still held and if not, free the lockowner * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found * %nfserr_locks_held: lockowner still in use * %nfserr_stale_clientid: clientid no longer active * %nfserr_expired: clientid not recognized */ __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); clientid_t *clid = &rlockowner->rl_clientid; struct nfs4_ol_stateid *stp; struct nfs4_lockowner *lo; struct nfs4_client *clp; LIST_HEAD(reaplist); __be32 status; dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); status = set_client(clid, cstate, nn); if (status) return status; clp = cstate->clp; spin_lock(&clp->cl_lock); lo = find_lockowner_str_locked(clp, &rlockowner->rl_owner); if (!lo) { spin_unlock(&clp->cl_lock); return nfs_ok; } list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { if (check_for_locks(stp->st_stid.sc_file, lo)) { spin_unlock(&clp->cl_lock); nfs4_put_stateowner(&lo->lo_owner); return nfserr_locks_held; } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { stp = list_first_entry(&lo->lo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); unhash_lock_stateid(stp); put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); return nfs_ok; } static inline struct nfs4_client_reclaim * alloc_reclaim(void) { return kmalloc(sizeof(struct nfs4_client_reclaim), GFP_KERNEL); } bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client_reclaim *crp; crp = nfsd4_find_reclaim_client(name, nn); return (crp && crp->cr_clp); } /* * failure => all reset bets are off, nfserr_no_grace... * * The caller is responsible for freeing name.data if NULL is returned (it * will be freed in nfs4_remove_reclaim_record in the normal case). */ struct nfs4_client_reclaim * nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp; crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); INIT_LIST_HEAD(&crp->cr_strhash); list_add(&crp->cr_strhash, &nn->reclaim_str_hashtbl[strhashval]); crp->cr_name.data = name.data; crp->cr_name.len = name.len; crp->cr_princhash.data = princhash.data; crp->cr_princhash.len = princhash.len; crp->cr_clp = NULL; nn->reclaim_str_hashtbl_size++; } return crp; } void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *crp, struct nfsd_net *nn) { list_del(&crp->cr_strhash); kfree(crp->cr_name.data); kfree(crp->cr_princhash.data); kfree(crp); nn->reclaim_str_hashtbl_size--; } void nfs4_release_reclaim(struct nfsd_net *nn) { struct nfs4_client_reclaim *crp = NULL; int i; for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->reclaim_str_hashtbl[i])) { crp = list_entry(nn->reclaim_str_hashtbl[i].next, struct nfs4_client_reclaim, cr_strhash); nfs4_remove_reclaim_record(crp, nn); } } WARN_ON_ONCE(nn->reclaim_str_hashtbl_size); } /* * called from OPEN, CLAIM_PREVIOUS with a new clientid. */ struct nfs4_client_reclaim * nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; strhashval = clientstr_hashval(name); list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { if (compare_blob(&crp->cr_name, &name) == 0) { return crp; } } return NULL; } __be32 nfs4_check_open_reclaim(struct nfs4_client *clp) { if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) return nfserr_no_grace; if (nfsd4_client_record_check(clp)) return nfserr_reclaim_bad; return nfs_ok; } /* * Since the lifetime of a delegation isn't limited to that of an open, a * client may quite reasonably hang on to a delegation as long as it has * the inode cached. This becomes an obvious problem the first time a * client's inode cache approaches the size of the server's total memory. * * For now we avoid this problem by imposing a hard limit on the number * of delegations, which varies according to the server's memory size. */ static void set_max_delegations(void) { /* * Allow at most 4 delegations per megabyte of RAM. Quick * estimates suggest that in the worst case (where every delegation * is for a different inode), a delegation could take about 1.5K, * giving a worst case usage of about 6% of memory. */ max_delegations = nr_free_buffer_pages() >> (20 - 2 - PAGE_SHIFT); } static int nfs4_state_create_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int i; nn->conf_id_hashtbl = kmalloc_array(CLIENT_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!nn->conf_id_hashtbl) goto err; nn->unconf_id_hashtbl = kmalloc_array(CLIENT_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!nn->unconf_id_hashtbl) goto err_unconf_id; nn->sessionid_hashtbl = kmalloc_array(SESSION_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!nn->sessionid_hashtbl) goto err_sessionid; for (i = 0; i < CLIENT_HASH_SIZE; i++) { INIT_LIST_HEAD(&nn->conf_id_hashtbl[i]); INIT_LIST_HEAD(&nn->unconf_id_hashtbl[i]); } for (i = 0; i < SESSION_HASH_SIZE; i++) INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]); nn->conf_name_tree = RB_ROOT; nn->unconf_name_tree = RB_ROOT; nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); INIT_LIST_HEAD(&nn->close_lru); INIT_LIST_HEAD(&nn->del_recall_lru); spin_lock_init(&nn->client_lock); spin_lock_init(&nn->s2s_cp_lock); idr_init(&nn->s2s_cp_stateids); atomic_set(&nn->pending_async_copies, 0); spin_lock_init(&nn->blocked_locks_lock); INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); nn->nfsd_client_shrinker = shrinker_alloc(0, "nfsd-client"); if (!nn->nfsd_client_shrinker) goto err_shrinker; nn->nfsd_client_shrinker->scan_objects = nfsd4_state_shrinker_scan; nn->nfsd_client_shrinker->count_objects = nfsd4_state_shrinker_count; nn->nfsd_client_shrinker->private_data = nn; shrinker_register(nn->nfsd_client_shrinker); return 0; err_shrinker: put_net(net); kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: kfree(nn->conf_id_hashtbl); err: return -ENOMEM; } static void nfs4_state_destroy_net(struct net *net) { int i; struct nfs4_client *clp = NULL; struct nfsd_net *nn = net_generic(net, nfsd_net_id); for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->conf_id_hashtbl[i])) { clp = list_entry(nn->conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); destroy_client(clp); } } WARN_ON(!list_empty(&nn->blocked_locks_lru)); for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->unconf_id_hashtbl[i])) { clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); destroy_client(clp); } } kfree(nn->sessionid_hashtbl); kfree(nn->unconf_id_hashtbl); kfree(nn->conf_id_hashtbl); put_net(net); } int nfs4_state_start_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; ret = nfs4_state_create_net(net); if (ret) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); trace_nfsd_grace_start(nn); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; skip_grace: printk(KERN_INFO "NFSD: no clients to reclaim, skipping NFSv4 grace period (net %x)\n", net->ns.inum); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_lease * HZ); nfsd4_end_grace(nn); return 0; } /* initialization to perform when the nfsd service is started: */ int nfs4_state_start(void) { int ret; ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params); if (ret) return ret; nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot"); if (!nfsd_slot_shrinker) { rhltable_destroy(&nfs4_file_rhltable); return -ENOMEM; } nfsd_slot_shrinker->count_objects = nfsd_slot_count; nfsd_slot_shrinker->scan_objects = nfsd_slot_scan; shrinker_register(nfsd_slot_shrinker); set_max_delegations(); return 0; } void nfs4_state_shutdown_net(struct net *net) { struct nfs4_delegation *dp = NULL; struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); shrinker_free(nn->nfsd_client_shrinker); cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); INIT_LIST_HEAD(&reaplist); spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); list_for_each_safe(pos, next, &reaplist) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); destroy_unhashed_deleg(dp); } nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_shutdown_umount(nn); #endif } void nfs4_state_shutdown(void) { rhltable_destroy(&nfs4_file_rhltable); shrinker_free(nfsd_slot_shrinker); } static void get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid)) memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t)); } static void put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { if (cstate->minorversion) { memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t)); SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } } void clear_current_stateid(struct nfsd4_compound_state *cstate) { CLEAR_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } /* * functions to set current state id */ void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->open_downgrade.od_stateid); } void nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->open.op_stateid); } void nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->close.cl_stateid); } void nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->lock.lk_resp_stateid); } /* * functions to consume current state id */ void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->open_downgrade.od_stateid); } void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->delegreturn.dr_stateid); } void nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->free_stateid.fr_stateid); } void nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->setattr.sa_stateid); } void nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->close.cl_stateid); } void nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->locku.lu_stateid); } void nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->read.rd_stateid); } void nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->write.wr_stateid); } /** * set_cb_time - vet and set the timespec for a cb_getattr update * @cb: timestamp from the CB_GETATTR response * @orig: original timestamp in the inode * @now: current time * * Given a timestamp in a CB_GETATTR response, check it against the * current timestamp in the inode and the current time. Returns true * if the inode's timestamp needs to be updated, and false otherwise. * @cb may also be changed if the timestamp needs to be clamped. */ static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig, const struct timespec64 *now) { /* * "When the time presented is before the original time, then the * update is ignored." Also no need to update if there is no change. */ if (timespec64_compare(cb, orig) <= 0) return false; /* * "When the time presented is in the future, the server can either * clamp the new time to the current time, or it may * return NFS4ERR_DELAY to the client, allowing it to retry." */ if (timespec64_compare(cb, now) > 0) { /* clamp it */ *cb = *now; } return true; } static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp) { struct inode *inode = d_inode(dentry); struct timespec64 now = current_time(inode); struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; struct iattr attrs = { }; int ret; if (deleg_attrs_deleg(dp->dl_type)) { struct timespec64 atime = inode_get_atime(inode); struct timespec64 mtime = inode_get_mtime(inode); attrs.ia_atime = ncf->ncf_cb_atime; attrs.ia_mtime = ncf->ncf_cb_mtime; if (set_cb_time(&attrs.ia_atime, &atime, &now)) attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; if (set_cb_time(&attrs.ia_mtime, &mtime, &now)) { attrs.ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET; attrs.ia_ctime = attrs.ia_mtime; } } else { attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME; attrs.ia_mtime = attrs.ia_ctime = now; } if (!attrs.ia_valid) return 0; attrs.ia_valid |= ATTR_DELEG; inode_lock(inode); ret = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); inode_unlock(inode); return ret; } /** * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict * @rqstp: RPC transaction context * @dentry: dentry of inode to be checked for a conflict * @pdp: returned WRITE delegation, if one was found * * This function is called when there is a conflict between a write * delegation and a change/size GETATTR from another client. The server * must either use the CB_GETATTR to get the current values of the * attributes from the client that holds the delegation or recall the * delegation before replying to the GETATTR. See RFC 8881 section * 18.7.4. * * Returns 0 if there is no conflict; otherwise an nfs_stat * code is returned. If @pdp is set to a non-NULL value, then the * caller must put the reference. */ __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, struct nfs4_delegation **pdp) { __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct file_lock_context *ctx; struct nfs4_delegation *dp = NULL; struct file_lease *fl; struct nfs4_cb_fattr *ncf; struct inode *inode = d_inode(dentry); ctx = locks_inode_context(inode); if (!ctx) return nfs_ok; #define NON_NFSD_LEASE ((void *)1) spin_lock(&ctx->flc_lock); for_each_file_lock(fl, &ctx->flc_lease) { if (fl->c.flc_flags == FL_LAYOUT) continue; if (fl->c.flc_type == F_WRLCK) { if (fl->fl_lmops == &nfsd_lease_mng_ops) dp = fl->c.flc_owner; else dp = NON_NFSD_LEASE; } break; } if (dp == NULL || dp == NON_NFSD_LEASE || dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) { spin_unlock(&ctx->flc_lock); if (dp == NON_NFSD_LEASE) { status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (status != nfserr_jukebox || !nfsd_wait_for_delegreturn(rqstp, inode)) return status; } return 0; } nfsd_stats_wdeleg_getattr_inc(nn); refcount_inc(&dp->dl_stid.sc_count); ncf = &dp->dl_cb_fattr; nfs4_cb_getattr(&dp->dl_cb_fattr); spin_unlock(&ctx->flc_lock); wait_on_bit_timeout(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, TASK_INTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT); if (ncf->ncf_cb_status) { /* Recall delegation only if client didn't respond */ status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (status != nfserr_jukebox || !nfsd_wait_for_delegreturn(rqstp, inode)) goto out_status; } if (!ncf->ncf_file_modified && (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) ncf->ncf_file_modified = true; if (ncf->ncf_file_modified) { int err; /* * Per section 10.4.3 of RFC 8881, the server would * not update the file's metadata with the client's * modified size */ err = cb_getattr_update_times(dentry, dp); if (err) { status = nfserrno(err); goto out_status; } ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; *pdp = dp; return nfs_ok; } status = nfs_ok; out_status: nfs4_put_stid(&dp->dl_stid); return status; } |
| 21 1965 1 63 2 93 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_USB_H #define __LINUX_USB_H #include <linux/mod_devicetable.h> #include <linux/usb/ch9.h> #define USB_MAJOR 180 #define USB_DEVICE_MAJOR 189 #ifdef __KERNEL__ #include <linux/errno.h> /* for -ENODEV */ #include <linux/delay.h> /* for mdelay() */ #include <linux/interrupt.h> /* for in_interrupt() */ #include <linux/list.h> /* for struct list_head */ #include <linux/kref.h> /* for struct kref */ #include <linux/device.h> /* for struct device */ #include <linux/fs.h> /* for struct file_operations */ #include <linux/completion.h> /* for struct completion */ #include <linux/sched.h> /* for current && schedule_timeout */ #include <linux/mutex.h> /* for struct mutex */ #include <linux/pm_runtime.h> /* for runtime PM */ struct usb_device; struct usb_driver; /*-------------------------------------------------------------------------*/ /* * Host-side wrappers for standard USB descriptors ... these are parsed * from the data provided by devices. Parsing turns them from a flat * sequence of descriptors into a hierarchy: * * - devices have one (usually) or more configs; * - configs have one (often) or more interfaces; * - interfaces have one (usually) or more settings; * - each interface setting has zero or (usually) more endpoints. * - a SuperSpeed endpoint has a companion descriptor * * And there might be other descriptors mixed in with those. * * Devices may also have class-specific or vendor-specific descriptors. */ struct ep_device; /** * struct usb_host_endpoint - host-side endpoint descriptor and queue * @desc: descriptor for this endpoint, wMaxPacketSize in native byteorder * @ss_ep_comp: SuperSpeed companion descriptor for this endpoint * @ssp_isoc_ep_comp: SuperSpeedPlus isoc companion descriptor for this endpoint * @urb_list: urbs queued to this endpoint; maintained by usbcore * @hcpriv: for use by HCD; typically holds hardware dma queue head (QH) * with one or more transfer descriptors (TDs) per urb * @ep_dev: ep_device for sysfs info * @extra: descriptors following this endpoint in the configuration * @extralen: how many bytes of "extra" are valid * @enabled: URBs may be submitted to this endpoint * @streams: number of USB-3 streams allocated on the endpoint * * USB requests are always queued to a given endpoint, identified by a * descriptor within an active interface in a given USB configuration. */ struct usb_host_endpoint { struct usb_endpoint_descriptor desc; struct usb_ss_ep_comp_descriptor ss_ep_comp; struct usb_ssp_isoc_ep_comp_descriptor ssp_isoc_ep_comp; struct list_head urb_list; void *hcpriv; struct ep_device *ep_dev; /* For sysfs info */ unsigned char *extra; /* Extra descriptors */ int extralen; int enabled; int streams; }; /* host-side wrapper for one interface setting's parsed descriptors */ struct usb_host_interface { struct usb_interface_descriptor desc; int extralen; unsigned char *extra; /* Extra descriptors */ /* array of desc.bNumEndpoints endpoints associated with this * interface setting. these will be in no particular order. */ struct usb_host_endpoint *endpoint; char *string; /* iInterface string, if present */ }; enum usb_interface_condition { USB_INTERFACE_UNBOUND = 0, USB_INTERFACE_BINDING, USB_INTERFACE_BOUND, USB_INTERFACE_UNBINDING, }; int __must_check usb_find_common_endpoints(struct usb_host_interface *alt, struct usb_endpoint_descriptor **bulk_in, struct usb_endpoint_descriptor **bulk_out, struct usb_endpoint_descriptor **int_in, struct usb_endpoint_descriptor **int_out); int __must_check usb_find_common_endpoints_reverse(struct usb_host_interface *alt, struct usb_endpoint_descriptor **bulk_in, struct usb_endpoint_descriptor **bulk_out, struct usb_endpoint_descriptor **int_in, struct usb_endpoint_descriptor **int_out); static inline int __must_check usb_find_bulk_in_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **bulk_in) { return usb_find_common_endpoints(alt, bulk_in, NULL, NULL, NULL); } static inline int __must_check usb_find_bulk_out_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **bulk_out) { return usb_find_common_endpoints(alt, NULL, bulk_out, NULL, NULL); } static inline int __must_check usb_find_int_in_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **int_in) { return usb_find_common_endpoints(alt, NULL, NULL, int_in, NULL); } static inline int __must_check usb_find_int_out_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **int_out) { return usb_find_common_endpoints(alt, NULL, NULL, NULL, int_out); } static inline int __must_check usb_find_last_bulk_in_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **bulk_in) { return usb_find_common_endpoints_reverse(alt, bulk_in, NULL, NULL, NULL); } static inline int __must_check usb_find_last_bulk_out_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **bulk_out) { return usb_find_common_endpoints_reverse(alt, NULL, bulk_out, NULL, NULL); } static inline int __must_check usb_find_last_int_in_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **int_in) { return usb_find_common_endpoints_reverse(alt, NULL, NULL, int_in, NULL); } static inline int __must_check usb_find_last_int_out_endpoint(struct usb_host_interface *alt, struct usb_endpoint_descriptor **int_out) { return usb_find_common_endpoints_reverse(alt, NULL, NULL, NULL, int_out); } enum usb_wireless_status { USB_WIRELESS_STATUS_NA = 0, USB_WIRELESS_STATUS_DISCONNECTED, USB_WIRELESS_STATUS_CONNECTED, }; /** * struct usb_interface - what usb device drivers talk to * @altsetting: array of interface structures, one for each alternate * setting that may be selected. Each one includes a set of * endpoint configurations. They will be in no particular order. * @cur_altsetting: the current altsetting. * @num_altsetting: number of altsettings defined. * @intf_assoc: interface association descriptor * @minor: the minor number assigned to this interface, if this * interface is bound to a driver that uses the USB major number. * If this interface does not use the USB major, this field should * be unused. The driver should set this value in the probe() * function of the driver, after it has been assigned a minor * number from the USB core by calling usb_register_dev(). * @condition: binding state of the interface: not bound, binding * (in probe()), bound to a driver, or unbinding (in disconnect()) * @sysfs_files_created: sysfs attributes exist * @ep_devs_created: endpoint child pseudo-devices exist * @unregistering: flag set when the interface is being unregistered * @needs_remote_wakeup: flag set when the driver requires remote-wakeup * capability during autosuspend. * @needs_altsetting0: flag set when a set-interface request for altsetting 0 * has been deferred. * @needs_binding: flag set when the driver should be re-probed or unbound * following a reset or suspend operation it doesn't support. * @authorized: This allows to (de)authorize individual interfaces instead * a whole device in contrast to the device authorization. * @wireless_status: if the USB device uses a receiver/emitter combo, whether * the emitter is connected. * @wireless_status_work: Used for scheduling wireless status changes * from atomic context. * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. * @reset_ws: Used for scheduling resets from atomic context. * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. * * USB device drivers attach to interfaces on a physical device. Each * interface encapsulates a single high level function, such as feeding * an audio stream to a speaker or reporting a change in a volume control. * Many USB devices only have one interface. The protocol used to talk to * an interface's endpoints can be defined in a usb "class" specification, * or by a product's vendor. The (default) control endpoint is part of * every interface, but is never listed among the interface's descriptors. * * The driver that is bound to the interface can use standard driver model * calls such as dev_get_drvdata() on the dev member of this structure. * * Each interface may have alternate settings. The initial configuration * of a device sets altsetting 0, but the device driver can change * that setting using usb_set_interface(). Alternate settings are often * used to control the use of periodic endpoints, such as by having * different endpoints use different amounts of reserved USB bandwidth. * All standards-conformant USB devices that use isochronous endpoints * will use them in non-default settings. * * The USB specification says that alternate setting numbers must run from * 0 to one less than the total number of alternate settings. But some * devices manage to mess this up, and the structures aren't necessarily * stored in numerical order anyhow. Use usb_altnum_to_altsetting() to * look up an alternate setting in the altsetting array based on its number. */ struct usb_interface { /* array of alternate settings for this interface, * stored in no particular order */ struct usb_host_interface *altsetting; struct usb_host_interface *cur_altsetting; /* the currently * active alternate setting */ unsigned num_altsetting; /* number of alternate settings */ /* If there is an interface association descriptor then it will list * the associated interfaces */ struct usb_interface_assoc_descriptor *intf_assoc; int minor; /* minor number this interface is * bound to */ enum usb_interface_condition condition; /* state of binding */ unsigned sysfs_files_created:1; /* the sysfs attributes exist */ unsigned ep_devs_created:1; /* endpoint "devices" exist */ unsigned unregistering:1; /* unregistration is in progress */ unsigned needs_remote_wakeup:1; /* driver requires remote wakeup */ unsigned needs_altsetting0:1; /* switch to altsetting 0 is pending */ unsigned needs_binding:1; /* needs delayed unbind/rebind */ unsigned resetting_device:1; /* true: bandwidth alloc after reset */ unsigned authorized:1; /* used for interface authorization */ enum usb_wireless_status wireless_status; struct work_struct wireless_status_work; struct device dev; /* interface specific device info */ struct device *usb_dev; struct work_struct reset_ws; /* for resets in atomic context */ }; #define to_usb_interface(__dev) container_of_const(__dev, struct usb_interface, dev) static inline void *usb_get_intfdata(struct usb_interface *intf) { return dev_get_drvdata(&intf->dev); } /** * usb_set_intfdata() - associate driver-specific data with an interface * @intf: USB interface * @data: driver data * * Drivers can use this function in their probe() callbacks to associate * driver-specific data with an interface. * * Note that there is generally no need to clear the driver-data pointer even * if some drivers do so for historical or implementation-specific reasons. */ static inline void usb_set_intfdata(struct usb_interface *intf, void *data) { dev_set_drvdata(&intf->dev, data); } struct usb_interface *usb_get_intf(struct usb_interface *intf); void usb_put_intf(struct usb_interface *intf); /* Hard limit */ #define USB_MAXENDPOINTS 30 /* this maximum is arbitrary */ #define USB_MAXINTERFACES 32 #define USB_MAXIADS (USB_MAXINTERFACES/2) bool usb_check_bulk_endpoints( const struct usb_interface *intf, const u8 *ep_addrs); bool usb_check_int_endpoints( const struct usb_interface *intf, const u8 *ep_addrs); /* * USB Resume Timer: Every Host controller driver should drive the resume * signalling on the bus for the amount of time defined by this macro. * * That way we will have a 'stable' behavior among all HCDs supported by Linux. * * Note that the USB Specification states we should drive resume for *at least* * 20 ms, but it doesn't give an upper bound. This creates two possible * situations which we want to avoid: * * (a) sometimes an msleep(20) might expire slightly before 20 ms, which causes * us to fail USB Electrical Tests, thus failing Certification * * (b) Some (many) devices actually need more than 20 ms of resume signalling, * and while we can argue that's against the USB Specification, we don't have * control over which devices a certification laboratory will be using for * certification. If CertLab uses a device which was tested against Windows and * that happens to have relaxed resume signalling rules, we might fall into * situations where we fail interoperability and electrical tests. * * In order to avoid both conditions, we're using a 40 ms resume timeout, which * should cope with both LPJ calibration errors and devices not following every * detail of the USB Specification. */ #define USB_RESUME_TIMEOUT 40 /* ms */ /** * struct usb_interface_cache - long-term representation of a device interface * @num_altsetting: number of altsettings defined. * @ref: reference counter. * @altsetting: variable-length array of interface structures, one for * each alternate setting that may be selected. Each one includes a * set of endpoint configurations. They will be in no particular order. * * These structures persist for the lifetime of a usb_device, unlike * struct usb_interface (which persists only as long as its configuration * is installed). The altsetting arrays can be accessed through these * structures at any time, permitting comparison of configurations and * providing support for the /sys/kernel/debug/usb/devices pseudo-file. */ struct usb_interface_cache { unsigned num_altsetting; /* number of alternate settings */ struct kref ref; /* reference counter */ /* variable-length array of alternate settings for this interface, * stored in no particular order */ struct usb_host_interface altsetting[]; }; #define ref_to_usb_interface_cache(r) \ container_of(r, struct usb_interface_cache, ref) #define altsetting_to_usb_interface_cache(a) \ container_of(a, struct usb_interface_cache, altsetting[0]) /** * struct usb_host_config - representation of a device's configuration * @desc: the device's configuration descriptor. * @string: pointer to the cached version of the iConfiguration string, if * present for this configuration. * @intf_assoc: list of any interface association descriptors in this config * @interface: array of pointers to usb_interface structures, one for each * interface in the configuration. The number of interfaces is stored * in desc.bNumInterfaces. These pointers are valid only while the * configuration is active. * @intf_cache: array of pointers to usb_interface_cache structures, one * for each interface in the configuration. These structures exist * for the entire life of the device. * @extra: pointer to buffer containing all extra descriptors associated * with this configuration (those preceding the first interface * descriptor). * @extralen: length of the extra descriptors buffer. * * USB devices may have multiple configurations, but only one can be active * at any time. Each encapsulates a different operational environment; * for example, a dual-speed device would have separate configurations for * full-speed and high-speed operation. The number of configurations * available is stored in the device descriptor as bNumConfigurations. * * A configuration can contain multiple interfaces. Each corresponds to * a different function of the USB device, and all are available whenever * the configuration is active. The USB standard says that interfaces * are supposed to be numbered from 0 to desc.bNumInterfaces-1, but a lot * of devices get this wrong. In addition, the interface array is not * guaranteed to be sorted in numerical order. Use usb_ifnum_to_if() to * look up an interface entry based on its number. * * Device drivers should not attempt to activate configurations. The choice * of which configuration to install is a policy decision based on such * considerations as available power, functionality provided, and the user's * desires (expressed through userspace tools). However, drivers can call * usb_reset_configuration() to reinitialize the current configuration and * all its interfaces. */ struct usb_host_config { struct usb_config_descriptor desc; char *string; /* iConfiguration string, if present */ /* List of any Interface Association Descriptors in this * configuration. */ struct usb_interface_assoc_descriptor *intf_assoc[USB_MAXIADS]; /* the interfaces associated with this configuration, * stored in no particular order */ struct usb_interface *interface[USB_MAXINTERFACES]; /* Interface information available even when this is not the * active configuration */ struct usb_interface_cache *intf_cache[USB_MAXINTERFACES]; unsigned char *extra; /* Extra descriptors */ int extralen; }; /* USB2.0 and USB3.0 device BOS descriptor set */ struct usb_host_bos { struct usb_bos_descriptor *desc; struct usb_ext_cap_descriptor *ext_cap; struct usb_ss_cap_descriptor *ss_cap; struct usb_ssp_cap_descriptor *ssp_cap; struct usb_ss_container_id_descriptor *ss_id; struct usb_ptm_cap_descriptor *ptm_cap; }; int __usb_get_extra_descriptor(char *buffer, unsigned size, unsigned char type, void **ptr, size_t min); #define usb_get_extra_descriptor(ifpoint, type, ptr) \ __usb_get_extra_descriptor((ifpoint)->extra, \ (ifpoint)->extralen, \ type, (void **)ptr, sizeof(**(ptr))) /* ----------------------------------------------------------------------- */ /* * Allocated per bus (tree of devices) we have: */ struct usb_bus { struct device *controller; /* host side hardware */ struct device *sysdev; /* as seen from firmware or bus */ int busnum; /* Bus number (in order of reg) */ const char *bus_name; /* stable id (PCI slot_name etc) */ u8 uses_pio_for_control; /* * Does the host controller use PIO * for control transfers? */ u8 otg_port; /* 0, or number of OTG/HNP port */ unsigned is_b_host:1; /* true during some HNP roleswitches */ unsigned b_hnp_enable:1; /* OTG: did A-Host enable HNP? */ unsigned no_stop_on_short:1; /* * Quirk: some controllers don't stop * the ep queue on a short transfer * with the URB_SHORT_NOT_OK flag set. */ unsigned no_sg_constraint:1; /* no sg constraint */ unsigned sg_tablesize; /* 0 or largest number of sg list entries */ int devnum_next; /* Next open device number in * round-robin allocation */ struct mutex devnum_next_mutex; /* devnum_next mutex */ DECLARE_BITMAP(devmap, 128); /* USB device number allocation bitmap */ struct usb_device *root_hub; /* Root hub */ struct usb_bus *hs_companion; /* Companion EHCI bus, if any */ int bandwidth_allocated; /* on this bus: how much of the time * reserved for periodic (intr/iso) * requests is used, on average? * Units: microseconds/frame. * Limits: Full/low speed reserve 90%, * while high speed reserves 80%. */ int bandwidth_int_reqs; /* number of Interrupt requests */ int bandwidth_isoc_reqs; /* number of Isoc. requests */ unsigned resuming_ports; /* bit array: resuming root-hub ports */ #if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE) struct mon_bus *mon_bus; /* non-null when associated */ int monitored; /* non-zero when monitored */ #endif }; struct usb_dev_state; /* ----------------------------------------------------------------------- */ struct usb_tt; enum usb_link_tunnel_mode { USB_LINK_UNKNOWN = 0, USB_LINK_NATIVE, USB_LINK_TUNNELED, }; enum usb_port_connect_type { USB_PORT_CONNECT_TYPE_UNKNOWN = 0, USB_PORT_CONNECT_TYPE_HOT_PLUG, USB_PORT_CONNECT_TYPE_HARD_WIRED, USB_PORT_NOT_USED, }; /* * USB port quirks. */ /* For the given port, prefer the old (faster) enumeration scheme. */ #define USB_PORT_QUIRK_OLD_SCHEME BIT(0) /* Decrease TRSTRCY to 10ms during device enumeration. */ #define USB_PORT_QUIRK_FAST_ENUM BIT(1) /* * USB 2.0 Link Power Management (LPM) parameters. */ struct usb2_lpm_parameters { /* Best effort service latency indicate how long the host will drive * resume on an exit from L1. */ unsigned int besl; /* Timeout value in microseconds for the L1 inactivity (LPM) timer. * When the timer counts to zero, the parent hub will initiate a LPM * transition to L1. */ int timeout; }; /* * USB 3.0 Link Power Management (LPM) parameters. * * PEL and SEL are USB 3.0 Link PM latencies for device-initiated LPM exit. * MEL is the USB 3.0 Link PM latency for host-initiated LPM exit. * All three are stored in nanoseconds. */ struct usb3_lpm_parameters { /* * Maximum exit latency (MEL) for the host to send a packet to the * device (either a Ping for isoc endpoints, or a data packet for * interrupt endpoints), the hubs to decode the packet, and for all hubs * in the path to transition the links to U0. */ unsigned int mel; /* * Maximum exit latency for a device-initiated LPM transition to bring * all links into U0. Abbreviated as "PEL" in section 9.4.12 of the USB * 3.0 spec, with no explanation of what "P" stands for. "Path"? */ unsigned int pel; /* * The System Exit Latency (SEL) includes PEL, and three other * latencies. After a device initiates a U0 transition, it will take * some time from when the device sends the ERDY to when it will finally * receive the data packet. Basically, SEL should be the worse-case * latency from when a device starts initiating a U0 transition to when * it will get data. */ unsigned int sel; /* * The idle timeout value that is currently programmed into the parent * hub for this device. When the timer counts to zero, the parent hub * will initiate an LPM transition to either U1 or U2. */ int timeout; }; /** * struct usb_device - kernel's representation of a USB device * @devnum: device number; address on a USB bus * @devpath: device ID string for use in messages (e.g., /port/...) * @route: tree topology hex string for use with xHCI * @state: device state: configured, not attached, etc. * @speed: device speed: high/full/low (or error) * @rx_lanes: number of rx lanes in use, USB 3.2 adds dual-lane support * @tx_lanes: number of tx lanes in use, USB 3.2 adds dual-lane support * @ssp_rate: SuperSpeed Plus phy signaling rate and lane count * @tt: Transaction Translator info; used with low/full speed dev, highspeed hub * @ttport: device port on that tt hub * @toggle: one bit for each endpoint, with ([0] = IN, [1] = OUT) endpoints * @parent: our hub, unless we're the root * @bus: bus we're part of * @ep0: endpoint 0 data (default control pipe) * @dev: generic device interface * @descriptor: USB device descriptor * @bos: USB device BOS descriptor set * @config: all of the device's configs * @actconfig: the active configuration * @ep_in: array of IN endpoints * @ep_out: array of OUT endpoints * @rawdescriptors: raw descriptors for each config * @bus_mA: Current available from the bus * @portnum: parent port number (origin 1) * @level: number of USB hub ancestors * @devaddr: device address, XHCI: assigned by HW, others: same as devnum * @can_submit: URBs may be submitted * @persist_enabled: USB_PERSIST enabled for this device * @reset_in_progress: the device is being reset * @have_langid: whether string_langid is valid * @authorized: policy has said we can use it; * (user space) policy determines if we authorize this device to be * used or not. By default, wired USB devices are authorized. * WUSB devices are not, until we authorize them from user space. * FIXME -- complete doc * @authenticated: Crypto authentication passed * @tunnel_mode: Connection native or tunneled over USB4 * @lpm_capable: device supports LPM * @lpm_devinit_allow: Allow USB3 device initiated LPM, exit latency is in range * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM * @usb2_hw_lpm_besl_capable: device can perform USB2 hardware BESL LPM * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled * @usb2_hw_lpm_allowed: Userspace allows USB 2.0 LPM to be enabled * @usb3_lpm_u1_enabled: USB3 hardware U1 LPM enabled * @usb3_lpm_u2_enabled: USB3 hardware U2 LPM enabled * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) * @serial: iSerialNumber string, if present (static) * @filelist: usbfs files that are open to this device * @maxchild: number of ports if hub * @quirks: quirks of the whole device * @urbnum: number of URBs submitted for the whole device * @active_duration: total time device is not suspended * @connect_time: time device was first connected * @do_remote_wakeup: remote wakeup should be enabled * @reset_resume: needs reset instead of resume * @port_is_suspended: the upstream port is suspended (L2 or U3) * @slot_id: Slot ID assigned by xHCI * @l1_params: best effor service latency for USB2 L1 LPM state, and L1 timeout. * @u1_params: exit latencies for USB3 U1 LPM state, and hub-initiated timeout. * @u2_params: exit latencies for USB3 U2 LPM state, and hub-initiated timeout. * @lpm_disable_count: Ref count used by usb_disable_lpm() and usb_enable_lpm() * to keep track of the number of functions that require USB 3.0 Link Power * Management to be disabled for this usb_device. This count should only * be manipulated by those functions, with the bandwidth_mutex is held. * @hub_delay: cached value consisting of: * parent->hub_delay + wHubDelay + tTPTransmissionDelay (40ns) * Will be used as wValue for SetIsochDelay requests. * @use_generic_driver: ask driver core to reprobe using the generic driver. * * Notes: * Usbcore drivers should not set usbdev->state directly. Instead use * usb_set_device_state(). */ struct usb_device { int devnum; char devpath[16]; u32 route; enum usb_device_state state; enum usb_device_speed speed; unsigned int rx_lanes; unsigned int tx_lanes; enum usb_ssp_rate ssp_rate; struct usb_tt *tt; int ttport; unsigned int toggle[2]; struct usb_device *parent; struct usb_bus *bus; struct usb_host_endpoint ep0; struct device dev; struct usb_device_descriptor descriptor; struct usb_host_bos *bos; struct usb_host_config *config; struct usb_host_config *actconfig; struct usb_host_endpoint *ep_in[16]; struct usb_host_endpoint *ep_out[16]; char **rawdescriptors; unsigned short bus_mA; u8 portnum; u8 level; u8 devaddr; unsigned can_submit:1; unsigned persist_enabled:1; unsigned reset_in_progress:1; unsigned have_langid:1; unsigned authorized:1; unsigned authenticated:1; unsigned lpm_capable:1; unsigned lpm_devinit_allow:1; unsigned usb2_hw_lpm_capable:1; unsigned usb2_hw_lpm_besl_capable:1; unsigned usb2_hw_lpm_enabled:1; unsigned usb2_hw_lpm_allowed:1; unsigned usb3_lpm_u1_enabled:1; unsigned usb3_lpm_u2_enabled:1; int string_langid; /* static strings from the device */ char *product; char *manufacturer; char *serial; struct list_head filelist; int maxchild; u32 quirks; atomic_t urbnum; unsigned long active_duration; unsigned long connect_time; unsigned do_remote_wakeup:1; unsigned reset_resume:1; unsigned port_is_suspended:1; enum usb_link_tunnel_mode tunnel_mode; int slot_id; struct usb2_lpm_parameters l1_params; struct usb3_lpm_parameters u1_params; struct usb3_lpm_parameters u2_params; unsigned lpm_disable_count; u16 hub_delay; unsigned use_generic_driver:1; }; #define to_usb_device(__dev) container_of_const(__dev, struct usb_device, dev) static inline struct usb_device *__intf_to_usbdev(struct usb_interface *intf) { return to_usb_device(intf->dev.parent); } static inline const struct usb_device *__intf_to_usbdev_const(const struct usb_interface *intf) { return to_usb_device((const struct device *)intf->dev.parent); } #define interface_to_usbdev(intf) \ _Generic((intf), \ const struct usb_interface *: __intf_to_usbdev_const, \ struct usb_interface *: __intf_to_usbdev)(intf) extern struct usb_device *usb_get_dev(struct usb_device *dev); extern void usb_put_dev(struct usb_device *dev); extern struct usb_device *usb_hub_find_child(struct usb_device *hdev, int port1); /** * usb_hub_for_each_child - iterate over all child devices on the hub * @hdev: USB device belonging to the usb hub * @port1: portnum associated with child device * @child: child device pointer */ #define usb_hub_for_each_child(hdev, port1, child) \ for (port1 = 1, child = usb_hub_find_child(hdev, port1); \ port1 <= hdev->maxchild; \ child = usb_hub_find_child(hdev, ++port1)) \ if (!child) continue; else /* USB device locking */ #define usb_lock_device(udev) device_lock(&(udev)->dev) #define usb_unlock_device(udev) device_unlock(&(udev)->dev) #define usb_lock_device_interruptible(udev) device_lock_interruptible(&(udev)->dev) #define usb_trylock_device(udev) device_trylock(&(udev)->dev) extern int usb_lock_device_for_reset(struct usb_device *udev, const struct usb_interface *iface); /* USB port reset for device reinitialization */ extern int usb_reset_device(struct usb_device *dev); extern void usb_queue_reset_device(struct usb_interface *dev); extern struct device *usb_intf_get_dma_device(struct usb_interface *intf); #ifdef CONFIG_ACPI extern int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable); extern bool usb_acpi_power_manageable(struct usb_device *hdev, int index); extern int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index); #else static inline int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable) { return 0; } static inline bool usb_acpi_power_manageable(struct usb_device *hdev, int index) { return true; } static inline int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) { return 0; } #endif /* USB autosuspend and autoresume */ #ifdef CONFIG_PM extern void usb_enable_autosuspend(struct usb_device *udev); extern void usb_disable_autosuspend(struct usb_device *udev); extern int usb_autopm_get_interface(struct usb_interface *intf); extern void usb_autopm_put_interface(struct usb_interface *intf); extern int usb_autopm_get_interface_async(struct usb_interface *intf); extern void usb_autopm_put_interface_async(struct usb_interface *intf); extern void usb_autopm_get_interface_no_resume(struct usb_interface *intf); extern void usb_autopm_put_interface_no_suspend(struct usb_interface *intf); static inline void usb_mark_last_busy(struct usb_device *udev) { pm_runtime_mark_last_busy(&udev->dev); } #else static inline int usb_enable_autosuspend(struct usb_device *udev) { return 0; } static inline int usb_disable_autosuspend(struct usb_device *udev) { return 0; } static inline int usb_autopm_get_interface(struct usb_interface *intf) { return 0; } static inline int usb_autopm_get_interface_async(struct usb_interface *intf) { return 0; } static inline void usb_autopm_put_interface(struct usb_interface *intf) { } static inline void usb_autopm_put_interface_async(struct usb_interface *intf) { } static inline void usb_autopm_get_interface_no_resume( struct usb_interface *intf) { } static inline void usb_autopm_put_interface_no_suspend( struct usb_interface *intf) { } static inline void usb_mark_last_busy(struct usb_device *udev) { } #endif extern int usb_disable_lpm(struct usb_device *udev); extern void usb_enable_lpm(struct usb_device *udev); /* Same as above, but these functions lock/unlock the bandwidth_mutex. */ extern int usb_unlocked_disable_lpm(struct usb_device *udev); extern void usb_unlocked_enable_lpm(struct usb_device *udev); extern int usb_disable_ltm(struct usb_device *udev); extern void usb_enable_ltm(struct usb_device *udev); static inline bool usb_device_supports_ltm(struct usb_device *udev) { if (udev->speed < USB_SPEED_SUPER || !udev->bos || !udev->bos->ss_cap) return false; return udev->bos->ss_cap->bmAttributes & USB_LTM_SUPPORT; } static inline bool usb_device_no_sg_constraint(struct usb_device *udev) { return udev && udev->bus && udev->bus->no_sg_constraint; } /*-------------------------------------------------------------------------*/ /* for drivers using iso endpoints */ extern int usb_get_current_frame_number(struct usb_device *usb_dev); /* Sets up a group of bulk endpoints to support multiple stream IDs. */ extern int usb_alloc_streams(struct usb_interface *interface, struct usb_host_endpoint **eps, unsigned int num_eps, unsigned int num_streams, gfp_t mem_flags); /* Reverts a group of bulk endpoints back to not using stream IDs. */ extern int usb_free_streams(struct usb_interface *interface, struct usb_host_endpoint **eps, unsigned int num_eps, gfp_t mem_flags); /* used these for multi-interface device registration */ extern int usb_driver_claim_interface(struct usb_driver *driver, struct usb_interface *iface, void *data); /** * usb_interface_claimed - returns true iff an interface is claimed * @iface: the interface being checked * * Return: %true (nonzero) iff the interface is claimed, else %false * (zero). * * Note: * Callers must own the driver model's usb bus readlock. So driver * probe() entries don't need extra locking, but other call contexts * may need to explicitly claim that lock. * */ static inline int usb_interface_claimed(struct usb_interface *iface) { return (iface->dev.driver != NULL); } extern void usb_driver_release_interface(struct usb_driver *driver, struct usb_interface *iface); int usb_set_wireless_status(struct usb_interface *iface, enum usb_wireless_status status); const struct usb_device_id *usb_match_id(struct usb_interface *interface, const struct usb_device_id *id); extern int usb_match_one_id(struct usb_interface *interface, const struct usb_device_id *id); extern int usb_for_each_dev(void *data, int (*fn)(struct usb_device *, void *)); extern struct usb_interface *usb_find_interface(struct usb_driver *drv, int minor); extern struct usb_interface *usb_ifnum_to_if(const struct usb_device *dev, unsigned ifnum); extern struct usb_host_interface *usb_altnum_to_altsetting( const struct usb_interface *intf, unsigned int altnum); extern struct usb_host_interface *usb_find_alt_setting( struct usb_host_config *config, unsigned int iface_num, unsigned int alt_num); /* port claiming functions */ int usb_hub_claim_port(struct usb_device *hdev, unsigned port1, struct usb_dev_state *owner); int usb_hub_release_port(struct usb_device *hdev, unsigned port1, struct usb_dev_state *owner); /** * usb_make_path - returns stable device path in the usb tree * @dev: the device whose path is being constructed * @buf: where to put the string * @size: how big is "buf"? * * Return: Length of the string (> 0) or negative if size was too small. * * Note: * This identifier is intended to be "stable", reflecting physical paths in * hardware such as physical bus addresses for host controllers or ports on * USB hubs. That makes it stay the same until systems are physically * reconfigured, by re-cabling a tree of USB devices or by moving USB host * controllers. Adding and removing devices, including virtual root hubs * in host controller driver modules, does not change these path identifiers; * neither does rebooting or re-enumerating. These are more useful identifiers * than changeable ("unstable") ones like bus numbers or device addresses. * * With a partial exception for devices connected to USB 2.0 root hubs, these * identifiers are also predictable. So long as the device tree isn't changed, * plugging any USB device into a given hub port always gives it the same path. * Because of the use of "companion" controllers, devices connected to ports on * USB 2.0 root hubs (EHCI host controllers) will get one path ID if they are * high speed, and a different one if they are full or low speed. */ static inline int usb_make_path(struct usb_device *dev, char *buf, size_t size) { int actual; actual = snprintf(buf, size, "usb-%s-%s", dev->bus->bus_name, dev->devpath); return (actual >= (int)size) ? -1 : actual; } /*-------------------------------------------------------------------------*/ #define USB_DEVICE_ID_MATCH_DEVICE \ (USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_PRODUCT) #define USB_DEVICE_ID_MATCH_DEV_RANGE \ (USB_DEVICE_ID_MATCH_DEV_LO | USB_DEVICE_ID_MATCH_DEV_HI) #define USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION \ (USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_DEV_RANGE) #define USB_DEVICE_ID_MATCH_DEV_INFO \ (USB_DEVICE_ID_MATCH_DEV_CLASS | \ USB_DEVICE_ID_MATCH_DEV_SUBCLASS | \ USB_DEVICE_ID_MATCH_DEV_PROTOCOL) #define USB_DEVICE_ID_MATCH_INT_INFO \ (USB_DEVICE_ID_MATCH_INT_CLASS | \ USB_DEVICE_ID_MATCH_INT_SUBCLASS | \ USB_DEVICE_ID_MATCH_INT_PROTOCOL) /** * USB_DEVICE - macro used to describe a specific usb device * @vend: the 16 bit USB Vendor ID * @prod: the 16 bit USB Product ID * * This macro is used to create a struct usb_device_id that matches a * specific device. */ #define USB_DEVICE(vend, prod) \ .match_flags = USB_DEVICE_ID_MATCH_DEVICE, \ .idVendor = (vend), \ .idProduct = (prod) /** * USB_DEVICE_VER - describe a specific usb device with a version range * @vend: the 16 bit USB Vendor ID * @prod: the 16 bit USB Product ID * @lo: the bcdDevice_lo value * @hi: the bcdDevice_hi value * * This macro is used to create a struct usb_device_id that matches a * specific device, with a version range. */ #define USB_DEVICE_VER(vend, prod, lo, hi) \ .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, \ .idVendor = (vend), \ .idProduct = (prod), \ .bcdDevice_lo = (lo), \ .bcdDevice_hi = (hi) /** * USB_DEVICE_INTERFACE_CLASS - describe a usb device with a specific interface class * @vend: the 16 bit USB Vendor ID * @prod: the 16 bit USB Product ID * @cl: bInterfaceClass value * * This macro is used to create a struct usb_device_id that matches a * specific interface class of devices. */ #define USB_DEVICE_INTERFACE_CLASS(vend, prod, cl) \ .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ USB_DEVICE_ID_MATCH_INT_CLASS, \ .idVendor = (vend), \ .idProduct = (prod), \ .bInterfaceClass = (cl) /** * USB_DEVICE_INTERFACE_PROTOCOL - describe a usb device with a specific interface protocol * @vend: the 16 bit USB Vendor ID * @prod: the 16 bit USB Product ID * @pr: bInterfaceProtocol value * * This macro is used to create a struct usb_device_id that matches a * specific interface protocol of devices. */ #define USB_DEVICE_INTERFACE_PROTOCOL(vend, prod, pr) \ .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ USB_DEVICE_ID_MATCH_INT_PROTOCOL, \ .idVendor = (vend), \ .idProduct = (prod), \ .bInterfaceProtocol = (pr) /** * USB_DEVICE_INTERFACE_NUMBER - describe a usb device with a specific interface number * @vend: the 16 bit USB Vendor ID * @prod: the 16 bit USB Product ID * @num: bInterfaceNumber value * * This macro is used to create a struct usb_device_id that matches a * specific interface number of devices. */ #define USB_DEVICE_INTERFACE_NUMBER(vend, prod, num) \ .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \ USB_DEVICE_ID_MATCH_INT_NUMBER, \ .idVendor = (vend), \ .idProduct = (prod), \ .bInterfaceNumber = (num) /** * USB_DEVICE_INFO - macro used to describe a class of usb devices * @cl: bDeviceClass value * @sc: bDeviceSubClass value * @pr: bDeviceProtocol value * * This macro is used to create a struct usb_device_id that matches a * specific class of devices. */ #define USB_DEVICE_INFO(cl, sc, pr) \ .match_flags = USB_DEVICE_ID_MATCH_DEV_INFO, \ .bDeviceClass = (cl), \ .bDeviceSubClass = (sc), \ .bDeviceProtocol = (pr) /** * USB_INTERFACE_INFO - macro used to describe a class of usb interfaces * @cl: bInterfaceClass value * @sc: bInterfaceSubClass value * @pr: bInterfaceProtocol value * * This macro is used to create a struct usb_device_id that matches a * specific class of interfaces. */ #define USB_INTERFACE_INFO(cl, sc, pr) \ .match_flags = USB_DEVICE_ID_MATCH_INT_INFO, \ .bInterfaceClass = (cl), \ .bInterfaceSubClass = (sc), \ .bInterfaceProtocol = (pr) /** * USB_DEVICE_AND_INTERFACE_INFO - describe a specific usb device with a class of usb interfaces * @vend: the 16 bit USB Vendor ID * @prod: the 16 bit USB Product ID * @cl: bInterfaceClass value * @sc: bInterfaceSubClass value * @pr: bInterfaceProtocol value * * This macro is used to create a struct usb_device_id that matches a * specific device with a specific class of interfaces. * * This is especially useful when explicitly matching devices that have * vendor specific bDeviceClass values, but standards-compliant interfaces. */ #define USB_DEVICE_AND_INTERFACE_INFO(vend, prod, cl, sc, pr) \ .match_flags = USB_DEVICE_ID_MATCH_INT_INFO \ | USB_DEVICE_ID_MATCH_DEVICE, \ .idVendor = (vend), \ .idProduct = (prod), \ .bInterfaceClass = (cl), \ .bInterfaceSubClass = (sc), \ .bInterfaceProtocol = (pr) /** * USB_VENDOR_AND_INTERFACE_INFO - describe a specific usb vendor with a class of usb interfaces * @vend: the 16 bit USB Vendor ID * @cl: bInterfaceClass value * @sc: bInterfaceSubClass value * @pr: bInterfaceProtocol value * * This macro is used to create a struct usb_device_id that matches a * specific vendor with a specific class of interfaces. * * This is especially useful when explicitly matching devices that have * vendor specific bDeviceClass values, but standards-compliant interfaces. */ #define USB_VENDOR_AND_INTERFACE_INFO(vend, cl, sc, pr) \ .match_flags = USB_DEVICE_ID_MATCH_INT_INFO \ | USB_DEVICE_ID_MATCH_VENDOR, \ .idVendor = (vend), \ .bInterfaceClass = (cl), \ .bInterfaceSubClass = (sc), \ .bInterfaceProtocol = (pr) /* ----------------------------------------------------------------------- */ /* Stuff for dynamic usb ids */ extern struct mutex usb_dynids_lock; struct usb_dynids { struct list_head list; }; struct usb_dynid { struct list_head node; struct usb_device_id id; }; extern ssize_t usb_store_new_id(struct usb_dynids *dynids, const struct usb_device_id *id_table, struct device_driver *driver, const char *buf, size_t count); extern ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf); /** * struct usb_driver - identifies USB interface driver to usbcore * @name: The driver name should be unique among USB drivers, * and should normally be the same as the module name. * @probe: Called to see if the driver is willing to manage a particular * interface on a device. If it is, probe returns zero and uses * usb_set_intfdata() to associate driver-specific data with the * interface. It may also use usb_set_interface() to specify the * appropriate altsetting. If unwilling to manage the interface, * return -ENODEV, if genuine IO errors occurred, an appropriate * negative errno value. * @disconnect: Called when the interface is no longer accessible, usually * because its device has been (or is being) disconnected or the * driver module is being unloaded. * @unlocked_ioctl: Used for drivers that want to talk to userspace through * the "usbfs" filesystem. This lets devices provide ways to * expose information to user space regardless of where they * do (or don't) show up otherwise in the filesystem. * @suspend: Called when the device is going to be suspended by the * system either from system sleep or runtime suspend context. The * return value will be ignored in system sleep context, so do NOT * try to continue using the device if suspend fails in this case. * Instead, let the resume or reset-resume routine recover from * the failure. * @resume: Called when the device is being resumed by the system. * @reset_resume: Called when the suspended device has been reset instead * of being resumed. * @pre_reset: Called by usb_reset_device() when the device is about to be * reset. This routine must not return until the driver has no active * URBs for the device, and no more URBs may be submitted until the * post_reset method is called. * @post_reset: Called by usb_reset_device() after the device * has been reset * @shutdown: Called at shut-down time to quiesce the device. * @id_table: USB drivers use ID table to support hotplugging. * Export this with MODULE_DEVICE_TABLE(usb,...). This must be set * or your driver's probe function will never get called. * @dev_groups: Attributes attached to the device that will be created once it * is bound to the driver. * @dynids: used internally to hold the list of dynamically added device * ids for this driver. * @driver: The driver-model core driver structure. * @no_dynamic_id: if set to 1, the USB core will not allow dynamic ids to be * added to this driver by preventing the sysfs file from being created. * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend * for interfaces bound to this driver. * @soft_unbind: if set to 1, the USB core will not kill URBs and disable * endpoints before calling the driver's disconnect method. * @disable_hub_initiated_lpm: if set to 1, the USB core will not allow hubs * to initiate lower power link state transitions when an idle timeout * occurs. Device-initiated USB 3.0 link PM will still be allowed. * * USB interface drivers must provide a name, probe() and disconnect() * methods, and an id_table. Other driver fields are optional. * * The id_table is used in hotplugging. It holds a set of descriptors, * and specialized data may be associated with each entry. That table * is used by both user and kernel mode hotplugging support. * * The probe() and disconnect() methods are called in a context where * they can sleep, but they should avoid abusing the privilege. Most * work to connect to a device should be done when the device is opened, * and undone at the last close. The disconnect code needs to address * concurrency issues with respect to open() and close() methods, as * well as forcing all pending I/O requests to complete (by unlinking * them as necessary, and blocking until the unlinks complete). */ struct usb_driver { const char *name; int (*probe) (struct usb_interface *intf, const struct usb_device_id *id); void (*disconnect) (struct usb_interface *intf); int (*unlocked_ioctl) (struct usb_interface *intf, unsigned int code, void *buf); int (*suspend) (struct usb_interface *intf, pm_message_t message); int (*resume) (struct usb_interface *intf); int (*reset_resume)(struct usb_interface *intf); int (*pre_reset)(struct usb_interface *intf); int (*post_reset)(struct usb_interface *intf); void (*shutdown)(struct usb_interface *intf); const struct usb_device_id *id_table; const struct attribute_group **dev_groups; struct usb_dynids dynids; struct device_driver driver; unsigned int no_dynamic_id:1; unsigned int supports_autosuspend:1; unsigned int disable_hub_initiated_lpm:1; unsigned int soft_unbind:1; }; #define to_usb_driver(d) container_of_const(d, struct usb_driver, driver) /** * struct usb_device_driver - identifies USB device driver to usbcore * @name: The driver name should be unique among USB drivers, * and should normally be the same as the module name. * @match: If set, used for better device/driver matching. * @probe: Called to see if the driver is willing to manage a particular * device. If it is, probe returns zero and uses dev_set_drvdata() * to associate driver-specific data with the device. If unwilling * to manage the device, return a negative errno value. * @disconnect: Called when the device is no longer accessible, usually * because it has been (or is being) disconnected or the driver's * module is being unloaded. * @suspend: Called when the device is going to be suspended by the system. * @resume: Called when the device is being resumed by the system. * @choose_configuration: If non-NULL, called instead of the default * usb_choose_configuration(). If this returns an error then we'll go * on to call the normal usb_choose_configuration(). * @dev_groups: Attributes attached to the device that will be created once it * is bound to the driver. * @driver: The driver-model core driver structure. * @id_table: used with @match() to select better matching driver at * probe() time. * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend * for devices bound to this driver. * @generic_subclass: if set to 1, the generic USB driver's probe, disconnect, * resume and suspend functions will be called in addition to the driver's * own, so this part of the setup does not need to be replicated. * * USB drivers must provide all the fields listed above except driver, * match, and id_table. */ struct usb_device_driver { const char *name; bool (*match) (struct usb_device *udev); int (*probe) (struct usb_device *udev); void (*disconnect) (struct usb_device *udev); int (*suspend) (struct usb_device *udev, pm_message_t message); int (*resume) (struct usb_device *udev, pm_message_t message); int (*choose_configuration) (struct usb_device *udev); const struct attribute_group **dev_groups; struct device_driver driver; const struct usb_device_id *id_table; unsigned int supports_autosuspend:1; unsigned int generic_subclass:1; }; #define to_usb_device_driver(d) container_of_const(d, struct usb_device_driver, driver) /** * struct usb_class_driver - identifies a USB driver that wants to use the USB major number * @name: the usb class device name for this driver. Will show up in sysfs. * @devnode: Callback to provide a naming hint for a possible * device node to create. * @fops: pointer to the struct file_operations of this driver. * @minor_base: the start of the minor range for this driver. * * This structure is used for the usb_register_dev() and * usb_deregister_dev() functions, to consolidate a number of the * parameters used for them. */ struct usb_class_driver { char *name; char *(*devnode)(const struct device *dev, umode_t *mode); const struct file_operations *fops; int minor_base; }; /* * use these in module_init()/module_exit() * and don't forget MODULE_DEVICE_TABLE(usb, ...) */ extern int usb_register_driver(struct usb_driver *, struct module *, const char *); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define usb_register(driver) \ usb_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) extern void usb_deregister(struct usb_driver *); /** * module_usb_driver() - Helper macro for registering a USB driver * @__usb_driver: usb_driver struct * * Helper macro for USB drivers which do not do anything special in module * init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() */ #define module_usb_driver(__usb_driver) \ module_driver(__usb_driver, usb_register, \ usb_deregister) extern int usb_register_device_driver(struct usb_device_driver *, struct module *); extern void usb_deregister_device_driver(struct usb_device_driver *); extern int usb_register_dev(struct usb_interface *intf, struct usb_class_driver *class_driver); extern void usb_deregister_dev(struct usb_interface *intf, struct usb_class_driver *class_driver); extern int usb_disabled(void); /* ----------------------------------------------------------------------- */ /* * URB support, for asynchronous request completions */ /* * urb->transfer_flags: * * Note: URB_DIR_IN/OUT is automatically set in usb_submit_urb(). */ #define URB_SHORT_NOT_OK 0x0001 /* report short reads as errors */ #define URB_ISO_ASAP 0x0002 /* iso-only; use the first unexpired * slot in the schedule */ #define URB_NO_TRANSFER_DMA_MAP 0x0004 /* urb->transfer_dma valid on submit */ #define URB_ZERO_PACKET 0x0040 /* Finish bulk OUT with short packet */ #define URB_NO_INTERRUPT 0x0080 /* HINT: no non-error interrupt * needed */ #define URB_FREE_BUFFER 0x0100 /* Free transfer buffer with the URB */ /* The following flags are used internally by usbcore and HCDs */ #define URB_DIR_IN 0x0200 /* Transfer from device to host */ #define URB_DIR_OUT 0 #define URB_DIR_MASK URB_DIR_IN #define URB_DMA_MAP_SINGLE 0x00010000 /* Non-scatter-gather mapping */ #define URB_DMA_MAP_PAGE 0x00020000 /* HCD-unsupported S-G */ #define URB_DMA_MAP_SG 0x00040000 /* HCD-supported S-G */ #define URB_MAP_LOCAL 0x00080000 /* HCD-local-memory mapping */ #define URB_SETUP_MAP_SINGLE 0x00100000 /* Setup packet DMA mapped */ #define URB_SETUP_MAP_LOCAL 0x00200000 /* HCD-local setup packet */ #define URB_DMA_SG_COMBINED 0x00400000 /* S-G entries were combined */ #define URB_ALIGNED_TEMP_BUFFER 0x00800000 /* Temp buffer was alloc'd */ struct usb_iso_packet_descriptor { unsigned int offset; unsigned int length; /* expected length */ unsigned int actual_length; int status; }; struct urb; struct usb_anchor { struct list_head urb_list; wait_queue_head_t wait; spinlock_t lock; atomic_t suspend_wakeups; unsigned int poisoned:1; }; static inline void init_usb_anchor(struct usb_anchor *anchor) { memset(anchor, 0, sizeof(*anchor)); INIT_LIST_HEAD(&anchor->urb_list); init_waitqueue_head(&anchor->wait); spin_lock_init(&anchor->lock); } typedef void (*usb_complete_t)(struct urb *); /** * struct urb - USB Request Block * @urb_list: For use by current owner of the URB. * @anchor_list: membership in the list of an anchor * @anchor: to anchor URBs to a common mooring * @ep: Points to the endpoint's data structure. Will eventually * replace @pipe. * @pipe: Holds endpoint number, direction, type, and more. * Create these values with the eight macros available; * usb_{snd,rcv}TYPEpipe(dev,endpoint), where the TYPE is "ctrl" * (control), "bulk", "int" (interrupt), or "iso" (isochronous). * For example usb_sndbulkpipe() or usb_rcvintpipe(). Endpoint * numbers range from zero to fifteen. Note that "in" endpoint two * is a different endpoint (and pipe) from "out" endpoint two. * The current configuration controls the existence, type, and * maximum packet size of any given endpoint. * @stream_id: the endpoint's stream ID for bulk streams * @dev: Identifies the USB device to perform the request. * @status: This is read in non-iso completion functions to get the * status of the particular request. ISO requests only use it * to tell whether the URB was unlinked; detailed status for * each frame is in the fields of the iso_frame-desc. * @transfer_flags: A variety of flags may be used to affect how URB * submission, unlinking, or operation are handled. Different * kinds of URB can use different flags. * @transfer_buffer: This identifies the buffer to (or from) which the I/O * request will be performed unless URB_NO_TRANSFER_DMA_MAP is set * (however, do not leave garbage in transfer_buffer even then). * This buffer must be suitable for DMA; allocate it with * kmalloc() or equivalent. For transfers to "in" endpoints, contents * of this buffer will be modified. This buffer is used for the data * stage of control transfers. * @transfer_dma: When transfer_flags includes URB_NO_TRANSFER_DMA_MAP, * the device driver is saying that it provided this DMA address, * which the host controller driver should use in preference to the * transfer_buffer. * @sg: scatter gather buffer list, the buffer size of each element in * the list (except the last) must be divisible by the endpoint's * max packet size if no_sg_constraint isn't set in 'struct usb_bus' * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may * be broken up into chunks according to the current maximum packet * size for the endpoint, which is a function of the configuration * and is encoded in the pipe. When the length is zero, neither * transfer_buffer nor transfer_dma is used. * @actual_length: This is read in non-iso completion functions, and * it tells how many bytes (out of transfer_buffer_length) were * transferred. It will normally be the same as requested, unless * either an error was reported or a short read was performed. * The URB_SHORT_NOT_OK transfer flag may be used to make such * short reads be reported as errors. * @setup_packet: Only used for control transfers, this points to eight bytes * of setup data. Control transfers always start by sending this data * to the device. Then transfer_buffer is read or written, if needed. * @setup_dma: DMA pointer for the setup packet. The caller must not use * this field; setup_packet must point to a valid buffer. * @start_frame: Returns the initial frame for isochronous transfers. * @number_of_packets: Lists the number of ISO transfer buffers. * @interval: Specifies the polling interval for interrupt or isochronous * transfers. The units are frames (milliseconds) for full and low * speed devices, and microframes (1/8 millisecond) for highspeed * and SuperSpeed devices. * @error_count: Returns the number of ISO transfers that reported errors. * @context: For use in completion functions. This normally points to * request-specific driver context. * @complete: Completion handler. This URB is passed as the parameter to the * completion function. The completion function may then do what * it likes with the URB, including resubmitting or freeing it. * @iso_frame_desc: Used to provide arrays of ISO transfer buffers and to * collect the transfer status for each buffer. * * This structure identifies USB transfer requests. URBs must be allocated by * calling usb_alloc_urb() and freed with a call to usb_free_urb(). * Initialization may be done using various usb_fill_*_urb() functions. URBs * are submitted using usb_submit_urb(), and pending requests may be canceled * using usb_unlink_urb() or usb_kill_urb(). * * Data Transfer Buffers: * * Normally drivers provide I/O buffers allocated with kmalloc() or otherwise * taken from the general page pool. That is provided by transfer_buffer * (control requests also use setup_packet), and host controller drivers * perform a dma mapping (and unmapping) for each buffer transferred. Those * mapping operations can be expensive on some platforms (perhaps using a dma * bounce buffer or talking to an IOMMU), * although they're cheap on commodity x86 and ppc hardware. * * Alternatively, drivers may pass the URB_NO_TRANSFER_DMA_MAP transfer flag, * which tells the host controller driver that no such mapping is needed for * the transfer_buffer since * the device driver is DMA-aware. For example, a device driver might * allocate a DMA buffer with usb_alloc_coherent() or call usb_buffer_map(). * When this transfer flag is provided, host controller drivers will * attempt to use the dma address found in the transfer_dma * field rather than determining a dma address themselves. * * Note that transfer_buffer must still be set if the controller * does not support DMA (as indicated by hcd_uses_dma()) and when talking * to root hub. If you have to transfer between highmem zone and the device * on such controller, create a bounce buffer or bail out with an error. * If transfer_buffer cannot be set (is in highmem) and the controller is DMA * capable, assign NULL to it, so that usbmon knows not to use the value. * The setup_packet must always be set, so it cannot be located in highmem. * * Initialization: * * All URBs submitted must initialize the dev, pipe, transfer_flags (may be * zero), and complete fields. All URBs must also initialize * transfer_buffer and transfer_buffer_length. They may provide the * URB_SHORT_NOT_OK transfer flag, indicating that short reads are * to be treated as errors; that flag is invalid for write requests. * * Bulk URBs may * use the URB_ZERO_PACKET transfer flag, indicating that bulk OUT transfers * should always terminate with a short packet, even if it means adding an * extra zero length packet. * * Control URBs must provide a valid pointer in the setup_packet field. * Unlike the transfer_buffer, the setup_packet may not be mapped for DMA * beforehand. * * Interrupt URBs must provide an interval, saying how often (in milliseconds * or, for highspeed devices, 125 microsecond units) * to poll for transfers. After the URB has been submitted, the interval * field reflects how the transfer was actually scheduled. * The polling interval may be more frequent than requested. * For example, some controllers have a maximum interval of 32 milliseconds, * while others support intervals of up to 1024 milliseconds. * Isochronous URBs also have transfer intervals. (Note that for isochronous * endpoints, as well as high speed interrupt endpoints, the encoding of * the transfer interval in the endpoint descriptor is logarithmic. * Device drivers must convert that value to linear units themselves.) * * If an isochronous endpoint queue isn't already running, the host * controller will schedule a new URB to start as soon as bandwidth * utilization allows. If the queue is running then a new URB will be * scheduled to start in the first transfer slot following the end of the * preceding URB, if that slot has not already expired. If the slot has * expired (which can happen when IRQ delivery is delayed for a long time), * the scheduling behavior depends on the URB_ISO_ASAP flag. If the flag * is clear then the URB will be scheduled to start in the expired slot, * implying that some of its packets will not be transferred; if the flag * is set then the URB will be scheduled in the first unexpired slot, * breaking the queue's synchronization. Upon URB completion, the * start_frame field will be set to the (micro)frame number in which the * transfer was scheduled. Ranges for frame counter values are HC-specific * and can go from as low as 256 to as high as 65536 frames. * * Isochronous URBs have a different data transfer model, in part because * the quality of service is only "best effort". Callers provide specially * allocated URBs, with number_of_packets worth of iso_frame_desc structures * at the end. Each such packet is an individual ISO transfer. Isochronous * URBs are normally queued, submitted by drivers to arrange that * transfers are at least double buffered, and then explicitly resubmitted * in completion handlers, so * that data (such as audio or video) streams at as constant a rate as the * host controller scheduler can support. * * Completion Callbacks: * * The completion callback is made in_interrupt(), and one of the first * things that a completion handler should do is check the status field. * The status field is provided for all URBs. It is used to report * unlinked URBs, and status for all non-ISO transfers. It should not * be examined before the URB is returned to the completion handler. * * The context field is normally used to link URBs back to the relevant * driver or request state. * * When the completion callback is invoked for non-isochronous URBs, the * actual_length field tells how many bytes were transferred. This field * is updated even when the URB terminated with an error or was unlinked. * * ISO transfer status is reported in the status and actual_length fields * of the iso_frame_desc array, and the number of errors is reported in * error_count. Completion callbacks for ISO transfers will normally * (re)submit URBs to ensure a constant transfer rate. * * Note that even fields marked "public" should not be touched by the driver * when the urb is owned by the hcd, that is, since the call to * usb_submit_urb() till the entry into the completion routine. */ struct urb { /* private: usb core and host controller only fields in the urb */ struct kref kref; /* reference count of the URB */ int unlinked; /* unlink error code */ void *hcpriv; /* private data for host controller */ atomic_t use_count; /* concurrent submissions counter */ atomic_t reject; /* submissions will fail */ /* public: documented fields in the urb that can be used by drivers */ struct list_head urb_list; /* list head for use by the urb's * current owner */ struct list_head anchor_list; /* the URB may be anchored */ struct usb_anchor *anchor; struct usb_device *dev; /* (in) pointer to associated device */ struct usb_host_endpoint *ep; /* (internal) pointer to endpoint */ unsigned int pipe; /* (in) pipe information */ unsigned int stream_id; /* (in) stream ID */ int status; /* (return) non-ISO status */ unsigned int transfer_flags; /* (in) URB_SHORT_NOT_OK | ...*/ void *transfer_buffer; /* (in) associated data buffer */ dma_addr_t transfer_dma; /* (in) dma addr for transfer_buffer */ struct scatterlist *sg; /* (in) scatter gather buffer list */ int num_mapped_sgs; /* (internal) mapped sg entries */ int num_sgs; /* (in) number of entries in the sg list */ u32 transfer_buffer_length; /* (in) data buffer length */ u32 actual_length; /* (return) actual transfer length */ unsigned char *setup_packet; /* (in) setup packet (control only) */ dma_addr_t setup_dma; /* (in) dma addr for setup_packet */ int start_frame; /* (modify) start frame (ISO) */ int number_of_packets; /* (in) number of ISO packets */ int interval; /* (modify) transfer interval * (INT/ISO) */ int error_count; /* (return) number of ISO errors */ void *context; /* (in) context for completion */ usb_complete_t complete; /* (in) completion routine */ struct usb_iso_packet_descriptor iso_frame_desc[]; /* (in) ISO ONLY */ }; /* ----------------------------------------------------------------------- */ /** * usb_fill_control_urb - initializes a control urb * @urb: pointer to the urb to initialize. * @dev: pointer to the struct usb_device for this urb. * @pipe: the endpoint pipe * @setup_packet: pointer to the setup_packet buffer. The buffer must be * suitable for DMA. * @transfer_buffer: pointer to the transfer buffer. The buffer must be * suitable for DMA. * @buffer_length: length of the transfer buffer * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * * Initializes a control urb with the proper information needed to submit * it to a device. * * The transfer buffer and the setup_packet buffer will most likely be filled * or read via DMA. The simplest way to get a buffer that can be DMAed to is * allocating it via kmalloc() or equivalent, even for very small buffers. * If the buffers are embedded in a bigger structure, there is a risk that * the buffer itself, the previous fields and/or the next fields are corrupted * due to cache incoherencies; or slowed down if they are evicted from the * cache. For more information, check &struct urb. * */ static inline void usb_fill_control_urb(struct urb *urb, struct usb_device *dev, unsigned int pipe, unsigned char *setup_packet, void *transfer_buffer, int buffer_length, usb_complete_t complete_fn, void *context) { urb->dev = dev; urb->pipe = pipe; urb->setup_packet = setup_packet; urb->transfer_buffer = transfer_buffer; urb->transfer_buffer_length = buffer_length; urb->complete = complete_fn; urb->context = context; } /** * usb_fill_bulk_urb - macro to help initialize a bulk urb * @urb: pointer to the urb to initialize. * @dev: pointer to the struct usb_device for this urb. * @pipe: the endpoint pipe * @transfer_buffer: pointer to the transfer buffer. The buffer must be * suitable for DMA. * @buffer_length: length of the transfer buffer * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * * Initializes a bulk urb with the proper information needed to submit it * to a device. * * Refer to usb_fill_control_urb() for a description of the requirements for * transfer_buffer. */ static inline void usb_fill_bulk_urb(struct urb *urb, struct usb_device *dev, unsigned int pipe, void *transfer_buffer, int buffer_length, usb_complete_t complete_fn, void *context) { urb->dev = dev; urb->pipe = pipe; urb->transfer_buffer = transfer_buffer; urb->transfer_buffer_length = buffer_length; urb->complete = complete_fn; urb->context = context; } /** * usb_fill_int_urb - macro to help initialize a interrupt urb * @urb: pointer to the urb to initialize. * @dev: pointer to the struct usb_device for this urb. * @pipe: the endpoint pipe * @transfer_buffer: pointer to the transfer buffer. The buffer must be * suitable for DMA. * @buffer_length: length of the transfer buffer * @complete_fn: pointer to the usb_complete_t function * @context: what to set the urb context to. * @interval: what to set the urb interval to, encoded like * the endpoint descriptor's bInterval value. * * Initializes a interrupt urb with the proper information needed to submit * it to a device. * * Refer to usb_fill_control_urb() for a description of the requirements for * transfer_buffer. * * Note that High Speed and SuperSpeed(+) interrupt endpoints use a logarithmic * encoding of the endpoint interval, and express polling intervals in * microframes (eight per millisecond) rather than in frames (one per * millisecond). */ static inline void usb_fill_int_urb(struct urb *urb, struct usb_device *dev, unsigned int pipe, void *transfer_buffer, int buffer_length, usb_complete_t complete_fn, void *context, int interval) { urb->dev = dev; urb->pipe = pipe; urb->transfer_buffer = transfer_buffer; urb->transfer_buffer_length = buffer_length; urb->complete = complete_fn; urb->context = context; if (dev->speed == USB_SPEED_HIGH || dev->speed >= USB_SPEED_SUPER) { /* make sure interval is within allowed range */ interval = clamp(interval, 1, 16); urb->interval = 1 << (interval - 1); } else { urb->interval = interval; } urb->start_frame = -1; } extern void usb_init_urb(struct urb *urb); extern struct urb *usb_alloc_urb(int iso_packets, gfp_t mem_flags); extern void usb_free_urb(struct urb *urb); #define usb_put_urb usb_free_urb extern struct urb *usb_get_urb(struct urb *urb); extern int usb_submit_urb(struct urb *urb, gfp_t mem_flags); extern int usb_unlink_urb(struct urb *urb); extern void usb_kill_urb(struct urb *urb); extern void usb_poison_urb(struct urb *urb); extern void usb_unpoison_urb(struct urb *urb); extern void usb_block_urb(struct urb *urb); extern void usb_kill_anchored_urbs(struct usb_anchor *anchor); extern void usb_poison_anchored_urbs(struct usb_anchor *anchor); extern void usb_unpoison_anchored_urbs(struct usb_anchor *anchor); extern void usb_unlink_anchored_urbs(struct usb_anchor *anchor); extern void usb_anchor_suspend_wakeups(struct usb_anchor *anchor); extern void usb_anchor_resume_wakeups(struct usb_anchor *anchor); extern void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor); extern void usb_unanchor_urb(struct urb *urb); extern int usb_wait_anchor_empty_timeout(struct usb_anchor *anchor, unsigned int timeout); extern struct urb *usb_get_from_anchor(struct usb_anchor *anchor); extern void usb_scuttle_anchored_urbs(struct usb_anchor *anchor); extern int usb_anchor_empty(struct usb_anchor *anchor); #define usb_unblock_urb usb_unpoison_urb /** * usb_urb_dir_in - check if an URB describes an IN transfer * @urb: URB to be checked * * Return: 1 if @urb describes an IN transfer (device-to-host), * otherwise 0. */ static inline int usb_urb_dir_in(struct urb *urb) { return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_IN; } /** * usb_urb_dir_out - check if an URB describes an OUT transfer * @urb: URB to be checked * * Return: 1 if @urb describes an OUT transfer (host-to-device), * otherwise 0. */ static inline int usb_urb_dir_out(struct urb *urb) { return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_OUT; } int usb_pipe_type_check(struct usb_device *dev, unsigned int pipe); int usb_urb_ep_type_check(const struct urb *urb); void *usb_alloc_coherent(struct usb_device *dev, size_t size, gfp_t mem_flags, dma_addr_t *dma); void usb_free_coherent(struct usb_device *dev, size_t size, void *addr, dma_addr_t dma); /*-------------------------------------------------------------------* * SYNCHRONOUS CALL SUPPORT * *-------------------------------------------------------------------*/ extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout); extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout); extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout); /* wrappers around usb_control_msg() for the most common standard requests */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, __u8 requesttype, __u16 value, __u16 index, const void *data, __u16 size, int timeout, gfp_t memflags); int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout, gfp_t memflags); extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype, unsigned char descindex, void *buf, int size); extern int usb_get_status(struct usb_device *dev, int recip, int type, int target, void *data); static inline int usb_get_std_status(struct usb_device *dev, int recip, int target, void *data) { return usb_get_status(dev, recip, USB_STATUS_TYPE_STANDARD, target, data); } static inline int usb_get_ptm_status(struct usb_device *dev, void *data) { return usb_get_status(dev, USB_RECIP_DEVICE, USB_STATUS_TYPE_PTM, 0, data); } extern int usb_string(struct usb_device *dev, int index, char *buf, size_t size); extern char *usb_cache_string(struct usb_device *udev, int index); /* wrappers that also update important state inside usbcore */ extern int usb_clear_halt(struct usb_device *dev, int pipe); extern int usb_reset_configuration(struct usb_device *dev); extern int usb_set_interface(struct usb_device *dev, int ifnum, int alternate); extern void usb_reset_endpoint(struct usb_device *dev, unsigned int epaddr); /* this request isn't really synchronous, but it belongs with the others */ extern int usb_driver_set_configuration(struct usb_device *udev, int config); /* choose and set configuration for device */ extern int usb_choose_configuration(struct usb_device *udev); extern int usb_set_configuration(struct usb_device *dev, int configuration); /* * timeouts, in milliseconds, used for sending/receiving control messages * they typically complete within a few frames (msec) after they're issued * USB identifies 5 second timeouts, maybe more in a few cases, and a few * slow devices (like some MGE Ellipse UPSes) actually push that limit. */ #define USB_CTRL_GET_TIMEOUT 5000 #define USB_CTRL_SET_TIMEOUT 5000 /** * struct usb_sg_request - support for scatter/gather I/O * @status: zero indicates success, else negative errno * @bytes: counts bytes transferred. * * These requests are initialized using usb_sg_init(), and then are used * as request handles passed to usb_sg_wait() or usb_sg_cancel(). Most * members of the request object aren't for driver access. * * The status and bytecount values are valid only after usb_sg_wait() * returns. If the status is zero, then the bytecount matches the total * from the request. * * After an error completion, drivers may need to clear a halt condition * on the endpoint. */ struct usb_sg_request { int status; size_t bytes; /* private: * members below are private to usbcore, * and are not provided for driver access! */ spinlock_t lock; struct usb_device *dev; int pipe; int entries; struct urb **urbs; int count; struct completion complete; }; int usb_sg_init( struct usb_sg_request *io, struct usb_device *dev, unsigned pipe, unsigned period, struct scatterlist *sg, int nents, size_t length, gfp_t mem_flags ); void usb_sg_cancel(struct usb_sg_request *io); void usb_sg_wait(struct usb_sg_request *io); /* ----------------------------------------------------------------------- */ /* * For various legacy reasons, Linux has a small cookie that's paired with * a struct usb_device to identify an endpoint queue. Queue characteristics * are defined by the endpoint's descriptor. This cookie is called a "pipe", * an unsigned int encoded as: * * - direction: bit 7 (0 = Host-to-Device [Out], * 1 = Device-to-Host [In] ... * like endpoint bEndpointAddress) * - device address: bits 8-14 ... bit positions known to uhci-hcd * - endpoint: bits 15-18 ... bit positions known to uhci-hcd * - pipe type: bits 30-31 (00 = isochronous, 01 = interrupt, * 10 = control, 11 = bulk) * * Given the device address and endpoint descriptor, pipes are redundant. */ /* NOTE: these are not the standard USB_ENDPOINT_XFER_* values!! */ /* (yet ... they're the values used by usbfs) */ #define PIPE_ISOCHRONOUS 0 #define PIPE_INTERRUPT 1 #define PIPE_CONTROL 2 #define PIPE_BULK 3 #define usb_pipein(pipe) ((pipe) & USB_DIR_IN) #define usb_pipeout(pipe) (!usb_pipein(pipe)) #define usb_pipedevice(pipe) (((pipe) >> 8) & 0x7f) #define usb_pipeendpoint(pipe) (((pipe) >> 15) & 0xf) #define usb_pipetype(pipe) (((pipe) >> 30) & 3) #define usb_pipeisoc(pipe) (usb_pipetype((pipe)) == PIPE_ISOCHRONOUS) #define usb_pipeint(pipe) (usb_pipetype((pipe)) == PIPE_INTERRUPT) #define usb_pipecontrol(pipe) (usb_pipetype((pipe)) == PIPE_CONTROL) #define usb_pipebulk(pipe) (usb_pipetype((pipe)) == PIPE_BULK) static inline unsigned int __create_pipe(struct usb_device *dev, unsigned int endpoint) { return (dev->devnum << 8) | (endpoint << 15); } /* Create various pipes... */ #define usb_sndctrlpipe(dev, endpoint) \ ((PIPE_CONTROL << 30) | __create_pipe(dev, endpoint)) #define usb_rcvctrlpipe(dev, endpoint) \ ((PIPE_CONTROL << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN) #define usb_sndisocpipe(dev, endpoint) \ ((PIPE_ISOCHRONOUS << 30) | __create_pipe(dev, endpoint)) #define usb_rcvisocpipe(dev, endpoint) \ ((PIPE_ISOCHRONOUS << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN) #define usb_sndbulkpipe(dev, endpoint) \ ((PIPE_BULK << 30) | __create_pipe(dev, endpoint)) #define usb_rcvbulkpipe(dev, endpoint) \ ((PIPE_BULK << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN) #define usb_sndintpipe(dev, endpoint) \ ((PIPE_INTERRUPT << 30) | __create_pipe(dev, endpoint)) #define usb_rcvintpipe(dev, endpoint) \ ((PIPE_INTERRUPT << 30) | __create_pipe(dev, endpoint) | USB_DIR_IN) static inline struct usb_host_endpoint * usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) { struct usb_host_endpoint **eps; eps = usb_pipein(pipe) ? dev->ep_in : dev->ep_out; return eps[usb_pipeendpoint(pipe)]; } static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) { struct usb_host_endpoint *ep = usb_pipe_endpoint(udev, pipe); if (!ep) return 0; /* NOTE: only 0x07ff bits are for packet size... */ return usb_endpoint_maxp(&ep->desc); } /* translate USB error codes to codes user space understands */ static inline int usb_translate_errors(int error_code) { switch (error_code) { case 0: case -ENOMEM: case -ENODEV: case -EOPNOTSUPP: return error_code; default: return -EIO; } } /* Events from the usb core */ #define USB_DEVICE_ADD 0x0001 #define USB_DEVICE_REMOVE 0x0002 #define USB_BUS_ADD 0x0003 #define USB_BUS_REMOVE 0x0004 extern void usb_register_notify(struct notifier_block *nb); extern void usb_unregister_notify(struct notifier_block *nb); /* debugfs stuff */ extern struct dentry *usb_debug_root; /* LED triggers */ enum usb_led_event { USB_LED_EVENT_HOST = 0, USB_LED_EVENT_GADGET = 1, }; #ifdef CONFIG_USB_LED_TRIG extern void usb_led_activity(enum usb_led_event ev); #else static inline void usb_led_activity(enum usb_led_event ev) {} #endif #endif /* __KERNEL__ */ #endif |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 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_sb.h" #include "xfs_mount.h" #include "xfs_trans.h" #include "xfs_error.h" #include "xfs_alloc.h" #include "xfs_fsops.h" #include "xfs_trans_space.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_ag.h" #include "xfs_ag_resv.h" #include "xfs_trace.h" #include "xfs_rtalloc.h" #include "xfs_rtrmap_btree.h" #include "xfs_rtrefcount_btree.h" /* * Write new AG headers to disk. Non-transactional, but need to be * written and completed prior to the growfs transaction being logged. * To do this, we use a delayed write buffer list and wait for * submission and IO completion of the list as a whole. This allows the * IO subsystem to merge all the AG headers in a single AG into a single * IO and hide most of the latency of the IO from us. * * This also means that if we get an error whilst building the buffer * list to write, we can cancel the entire list without having written * anything. */ static int xfs_resizefs_init_new_ags( struct xfs_trans *tp, struct aghdr_init_data *id, xfs_agnumber_t oagcount, xfs_agnumber_t nagcount, xfs_rfsblock_t delta, struct xfs_perag *last_pag, bool *lastag_extended) { struct xfs_mount *mp = tp->t_mountp; xfs_rfsblock_t nb = mp->m_sb.sb_dblocks + delta; int error; *lastag_extended = false; INIT_LIST_HEAD(&id->buffer_list); for (id->agno = nagcount - 1; id->agno >= oagcount; id->agno--, delta -= id->agsize) { if (id->agno == nagcount - 1) id->agsize = nb - (id->agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks); else id->agsize = mp->m_sb.sb_agblocks; error = xfs_ag_init_headers(mp, id); if (error) { xfs_buf_delwri_cancel(&id->buffer_list); return error; } } error = xfs_buf_delwri_submit(&id->buffer_list); if (error) return error; if (delta) { *lastag_extended = true; error = xfs_ag_extend_space(last_pag, tp, delta); } return error; } /* * growfs operations */ static int xfs_growfs_data_private( struct xfs_mount *mp, /* mount point for filesystem */ struct xfs_growfs_data *in) /* growfs data input struct */ { xfs_agnumber_t oagcount = mp->m_sb.sb_agcount; struct xfs_buf *bp; int error; xfs_agnumber_t nagcount; xfs_agnumber_t nagimax = 0; xfs_rfsblock_t nb, nb_div, nb_mod; int64_t delta; bool lastag_extended = false; struct xfs_trans *tp; struct aghdr_init_data id = {}; struct xfs_perag *last_pag; nb = in->newblocks; error = xfs_sb_validate_fsb_count(&mp->m_sb, nb); if (error) return error; if (nb > mp->m_sb.sb_dblocks) { error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1), XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL); if (error) return error; xfs_buf_relse(bp); } /* Make sure the new fs size won't cause problems with the log. */ error = xfs_growfs_check_rtgeom(mp, nb, mp->m_sb.sb_rblocks, mp->m_sb.sb_rextsize); if (error) return error; nb_div = nb; nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS) nb_div++; else if (nb_mod) nb = nb_div * mp->m_sb.sb_agblocks; if (nb_div > XFS_MAX_AGNUMBER + 1) { nb_div = XFS_MAX_AGNUMBER + 1; nb = nb_div * mp->m_sb.sb_agblocks; } nagcount = nb_div; delta = nb - mp->m_sb.sb_dblocks; /* * Reject filesystems with a single AG because they are not * supported, and reject a shrink operation that would cause a * filesystem to become unsupported. */ if (delta < 0 && nagcount < 2) return -EINVAL; /* No work to do */ if (delta == 0) return 0; /* TODO: shrinking the entire AGs hasn't yet completed */ if (nagcount < oagcount) return -EINVAL; /* allocate the new per-ag structures */ error = xfs_initialize_perag(mp, oagcount, nagcount, nb, &nagimax); if (error) return error; if (delta > 0) error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata, XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp); else error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata, -delta, 0, 0, &tp); if (error) goto out_free_unused_perag; last_pag = xfs_perag_get(mp, oagcount - 1); if (delta > 0) { error = xfs_resizefs_init_new_ags(tp, &id, oagcount, nagcount, delta, last_pag, &lastag_extended); } else { xfs_warn_experimental(mp, XFS_EXPERIMENTAL_SHRINK); error = xfs_ag_shrink_space(last_pag, &tp, -delta); } xfs_perag_put(last_pag); if (error) goto out_trans_cancel; /* * Update changed superblock fields transactionally. These are not * seen by the rest of the world until the transaction commit applies * them atomically to the superblock. */ if (nagcount > oagcount) xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount); if (delta) xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS, delta); if (id.nfree) xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree); /* * Sync sb counters now to reflect the updated values. This is * particularly important for shrink because the write verifier * will fail if sb_fdblocks is ever larger than sb_dblocks. */ if (xfs_has_lazysbcount(mp)) xfs_log_sb(tp); xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) return error; /* New allocation groups fully initialized, so update mount struct */ if (nagimax) mp->m_maxagi = nagimax; xfs_set_low_space_thresholds(mp); mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); if (delta > 0) { /* * If we expanded the last AG, free the per-AG reservation * so we can reinitialize it with the new size. */ if (lastag_extended) { struct xfs_perag *pag; pag = xfs_perag_get(mp, id.agno); xfs_ag_resv_free(pag); xfs_perag_put(pag); } /* * Reserve AG metadata blocks. ENOSPC here does not mean there * was a growfs failure, just that there still isn't space for * new user data after the grow has been run. */ error = xfs_fs_reserve_ag_blocks(mp); if (error == -ENOSPC) error = 0; /* Compute new maxlevels for rt btrees. */ xfs_rtrmapbt_compute_maxlevels(mp); xfs_rtrefcountbt_compute_maxlevels(mp); } return error; out_trans_cancel: xfs_trans_cancel(tp); out_free_unused_perag: if (nagcount > oagcount) xfs_free_perag_range(mp, oagcount, nagcount); return error; } static int xfs_growfs_log_private( struct xfs_mount *mp, /* mount point for filesystem */ struct xfs_growfs_log *in) /* growfs log input struct */ { xfs_extlen_t nb; nb = in->newblocks; if (nb < XFS_MIN_LOG_BLOCKS || nb < XFS_B_TO_FSB(mp, XFS_MIN_LOG_BYTES)) return -EINVAL; if (nb == mp->m_sb.sb_logblocks && in->isint == (mp->m_sb.sb_logstart != 0)) return -EINVAL; /* * Moving the log is hard, need new interfaces to sync * the log first, hold off all activity while moving it. * Can have shorter or longer log in the same space, * or transform internal to external log or vice versa. */ return -ENOSYS; } static int xfs_growfs_imaxpct( struct xfs_mount *mp, __u32 imaxpct) { struct xfs_trans *tp; int dpct; int error; if (imaxpct > 100) return -EINVAL; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata, XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp); if (error) return error; dpct = imaxpct - mp->m_sb.sb_imax_pct; xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct); xfs_trans_set_sync(tp); return xfs_trans_commit(tp); } /* * protected versions of growfs function acquire and release locks on the mount * point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG, * XFS_IOC_FSGROWFSRT */ int xfs_growfs_data( struct xfs_mount *mp, struct xfs_growfs_data *in) { int error = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!mutex_trylock(&mp->m_growlock)) return -EWOULDBLOCK; /* update imaxpct separately to the physical grow of the filesystem */ if (in->imaxpct != mp->m_sb.sb_imax_pct) { error = xfs_growfs_imaxpct(mp, in->imaxpct); if (error) goto out_error; } if (in->newblocks != mp->m_sb.sb_dblocks) { error = xfs_growfs_data_private(mp, in); if (error) goto out_error; } /* Post growfs calculations needed to reflect new state in operations */ if (mp->m_sb.sb_imax_pct) { uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct; do_div(icount, 100); M_IGEO(mp)->maxicount = XFS_FSB_TO_INO(mp, icount); } else M_IGEO(mp)->maxicount = 0; /* Update secondary superblocks now the physical grow has completed */ error = xfs_update_secondary_sbs(mp); out_error: /* * Increment the generation unconditionally, the error could be from * updating the secondary superblocks, in which case the new size * is live already. */ mp->m_generation++; mutex_unlock(&mp->m_growlock); return error; } int xfs_growfs_log( xfs_mount_t *mp, struct xfs_growfs_log *in) { int error; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!mutex_trylock(&mp->m_growlock)) return -EWOULDBLOCK; error = xfs_growfs_log_private(mp, in); mutex_unlock(&mp->m_growlock); return error; } /* * Reserve the requested number of blocks if available. Otherwise return * as many as possible to satisfy the request. The actual number * reserved are returned in outval. */ int xfs_reserve_blocks( struct xfs_mount *mp, uint64_t request) { int64_t lcounter, delta; int64_t fdblks_delta = 0; int64_t free; int error = 0; /* * With per-cpu counters, this becomes an interesting problem. we need * to work out if we are freeing or allocation blocks first, then we can * do the modification as necessary. * * We do this under the m_sb_lock so that if we are near ENOSPC, we will * hold out any changes while we work out what to do. This means that * the amount of free space can change while we do this, so we need to * retry if we end up trying to reserve more space than is available. */ spin_lock(&mp->m_sb_lock); /* * If our previous reservation was larger than the current value, * then move any unused blocks back to the free pool. Modify the resblks * counters directly since we shouldn't have any problems unreserving * space. */ if (mp->m_resblks > request) { lcounter = mp->m_resblks_avail - request; if (lcounter > 0) { /* release unused blocks */ fdblks_delta = lcounter; mp->m_resblks_avail -= lcounter; } mp->m_resblks = request; if (fdblks_delta) { spin_unlock(&mp->m_sb_lock); xfs_add_fdblocks(mp, fdblks_delta); spin_lock(&mp->m_sb_lock); } goto out; } /* * If the request is larger than the current reservation, reserve the * blocks before we update the reserve counters. Sample m_fdblocks and * perform a partial reservation if the request exceeds free space. * * The code below estimates how many blocks it can request from * fdblocks to stash in the reserve pool. This is a classic TOCTOU * race since fdblocks updates are not always coordinated via * m_sb_lock. Set the reserve size even if there's not enough free * space to fill it because mod_fdblocks will refill an undersized * reserve when it can. */ free = percpu_counter_sum(&mp->m_fdblocks) - xfs_fdblocks_unavailable(mp); delta = request - mp->m_resblks; mp->m_resblks = request; if (delta > 0 && free > 0) { /* * We'll either succeed in getting space from the free block * count or we'll get an ENOSPC. Don't set the reserved flag * here - we don't want to reserve the extra reserve blocks * from the reserve. * * The desired reserve size can change after we drop the lock. * Use mod_fdblocks to put the space into the reserve or into * fdblocks as appropriate. */ fdblks_delta = min(free, delta); spin_unlock(&mp->m_sb_lock); error = xfs_dec_fdblocks(mp, fdblks_delta, 0); if (!error) xfs_add_fdblocks(mp, fdblks_delta); spin_lock(&mp->m_sb_lock); } out: spin_unlock(&mp->m_sb_lock); return error; } int xfs_fs_goingdown( xfs_mount_t *mp, uint32_t inflags) { switch (inflags) { case XFS_FSOP_GOING_FLAGS_DEFAULT: { if (!bdev_freeze(mp->m_super->s_bdev)) { xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT); bdev_thaw(mp->m_super->s_bdev); } break; } case XFS_FSOP_GOING_FLAGS_LOGFLUSH: xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT); break; case XFS_FSOP_GOING_FLAGS_NOLOGFLUSH: xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT | SHUTDOWN_LOG_IO_ERROR); break; default: return -EINVAL; } return 0; } /* * Force a shutdown of the filesystem instantly while keeping the filesystem * consistent. We don't do an unmount here; just shutdown the shop, make sure * that absolutely nothing persistent happens to this filesystem after this * point. * * The shutdown state change is atomic, resulting in the first and only the * first shutdown call processing the shutdown. This means we only shutdown the * log once as it requires, and we don't spam the logs when multiple concurrent * shutdowns race to set the shutdown flags. */ void xfs_do_force_shutdown( struct xfs_mount *mp, uint32_t flags, char *fname, int lnnum) { int tag; const char *why; if (xfs_set_shutdown(mp)) { xlog_shutdown_wait(mp->m_log); return; } if (mp->m_sb_bp) mp->m_sb_bp->b_flags |= XBF_DONE; if (flags & SHUTDOWN_FORCE_UMOUNT) xfs_alert(mp, "User initiated shutdown received."); if (xlog_force_shutdown(mp->m_log, flags)) { tag = XFS_PTAG_SHUTDOWN_LOGERROR; why = "Log I/O Error"; } else if (flags & SHUTDOWN_CORRUPT_INCORE) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of in-memory data"; } else if (flags & SHUTDOWN_CORRUPT_ONDISK) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of on-disk metadata"; } else if (flags & SHUTDOWN_DEVICE_REMOVED) { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Block device removal"; } else { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Metadata I/O Error"; } trace_xfs_force_shutdown(mp, tag, flags, fname, lnnum); xfs_alert_tag(mp, tag, "%s (0x%x) detected at %pS (%s:%d). Shutting down filesystem.", why, flags, __return_address, fname, lnnum); xfs_alert(mp, "Please unmount the filesystem and rectify the problem(s)"); if (xfs_error_level >= XFS_ERRLEVEL_HIGH) xfs_stack_trace(); } /* * Reserve free space for per-AG metadata. */ int xfs_fs_reserve_ag_blocks( struct xfs_mount *mp) { struct xfs_perag *pag = NULL; int error = 0; int err2; mp->m_finobt_nores = false; while ((pag = xfs_perag_next(mp, pag))) { err2 = xfs_ag_resv_init(pag, NULL); if (err2 && !error) error = err2; } if (error && error != -ENOSPC) { xfs_warn(mp, "Error %d reserving per-AG metadata reserve pool.", error); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } if (xfs_has_realtime(mp)) { err2 = xfs_rt_resv_init(mp); if (err2 && err2 != -ENOSPC) { xfs_warn(mp, "Error %d reserving realtime metadata reserve pool.", err2); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); } if (err2 && !error) error = err2; } return error; } /* * Free space reserved for per-AG metadata. */ void xfs_fs_unreserve_ag_blocks( struct xfs_mount *mp) { struct xfs_perag *pag = NULL; if (xfs_has_realtime(mp)) xfs_rt_resv_free(mp); while ((pag = xfs_perag_next(mp, pag))) xfs_ag_resv_free(pag); } |
| 1062 593 54 6 6 27 4092 2729 4156 14 150 1942 583 1 885 42 1637 3039 147 285 146 169 184 48 21 303 418 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/err.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/limits.h> #include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> struct list_lru; /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Three common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] * * xa_limit_16b - [0 - USHRT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) #define xa_limit_16b XA_LIMIT(0, USHRT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (IS_ENABLED(CONFIG_BASE_SMALL) ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; struct list_lru *xa_lru; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL, \ .xa_lru = NULL, \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline int xas_get_order(struct xa_state *xas) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_advance() - Skip over sibling entries. * @xas: XArray operation state. * @index: Index of last sibling entry. * * Move the operation state to refer to the last sibling entry. * This is useful for loops that normally want to see sibling * entries but sometimes want to skip them. Use xas_set() if you * want to move to an index which is not part of this entry. */ static inline void xas_advance(struct xa_state *xas, unsigned long index) { unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; xas->xa_index = index; xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page * cache and swap cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) { xas->xa_lru = lru; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */ |
| 5 3745 1 1619 3745 3 291 69 5 1613 1613 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0-only */ /* A pointer that can point to either kernel or userspace memory. */ #ifndef _LINUX_BPFPTR_H #define _LINUX_BPFPTR_H #include <linux/mm.h> #include <linux/sockptr.h> typedef sockptr_t bpfptr_t; static inline bool bpfptr_is_kernel(bpfptr_t bpfptr) { return bpfptr.is_kernel; } static inline bpfptr_t KERNEL_BPFPTR(void *p) { return (bpfptr_t) { .kernel = p, .is_kernel = true }; } static inline bpfptr_t USER_BPFPTR(void __user *p) { return (bpfptr_t) { .user = p }; } static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel) { if (is_kernel) return KERNEL_BPFPTR((void*) (uintptr_t) addr); else return USER_BPFPTR(u64_to_user_ptr(addr)); } static inline bool bpfptr_is_null(bpfptr_t bpfptr) { if (bpfptr_is_kernel(bpfptr)) return !bpfptr.kernel; return !bpfptr.user; } static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) { if (bpfptr_is_kernel(*bpfptr)) bpfptr->kernel += val; else bpfptr->user += val; } static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, size_t offset, size_t size) { if (!bpfptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); return copy_from_kernel_nofault(dst, src.kernel + offset, size); } static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) { return copy_from_bpfptr_offset(dst, src, 0, size); } static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, const void *src, size_t size) { return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len) { void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_bpfptr(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } #define kvmemdup_bpfptr(...) alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__)) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { if (bpfptr_is_kernel(src)) return strncpy_from_kernel_nofault(dst, src.kernel, count); return strncpy_from_user(dst, src.user, count); } #endif /* _LINUX_BPFPTR_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ASIX AX88179/178A USB 3.0/2.0 to Gigabit Ethernet Devices * * Copyright (C) 2011-2013 ASIX */ #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/mii.h> #include <linux/usb.h> #include <linux/crc32.h> #include <linux/usb/usbnet.h> #include <uapi/linux/mdio.h> #include <linux/mdio.h> #define AX88179_PHY_ID 0x03 #define AX_EEPROM_LEN 0x100 #define AX88179_EEPROM_MAGIC 0x17900b95 #define AX_MCAST_FLTSIZE 8 #define AX_MAX_MCAST 64 #define AX_INT_PPLS_LINK ((u32)BIT(16)) #define AX_RXHDR_L4_TYPE_MASK 0x1c #define AX_RXHDR_L4_TYPE_UDP 4 #define AX_RXHDR_L4_TYPE_TCP 16 #define AX_RXHDR_L3CSUM_ERR 2 #define AX_RXHDR_L4CSUM_ERR 1 #define AX_RXHDR_CRC_ERR ((u32)BIT(29)) #define AX_RXHDR_DROP_ERR ((u32)BIT(31)) #define AX_ACCESS_MAC 0x01 #define AX_ACCESS_PHY 0x02 #define AX_ACCESS_EEPROM 0x04 #define AX_ACCESS_EFUS 0x05 #define AX_RELOAD_EEPROM_EFUSE 0x06 #define AX_PAUSE_WATERLVL_HIGH 0x54 #define AX_PAUSE_WATERLVL_LOW 0x55 #define PHYSICAL_LINK_STATUS 0x02 #define AX_USB_SS 0x04 #define AX_USB_HS 0x02 #define GENERAL_STATUS 0x03 /* Check AX88179 version. UA1:Bit2 = 0, UA2:Bit2 = 1 */ #define AX_SECLD 0x04 #define AX_SROM_ADDR 0x07 #define AX_SROM_CMD 0x0a #define EEP_RD 0x04 #define EEP_BUSY 0x10 #define AX_SROM_DATA_LOW 0x08 #define AX_SROM_DATA_HIGH 0x09 #define AX_RX_CTL 0x0b #define AX_RX_CTL_DROPCRCERR 0x0100 #define AX_RX_CTL_IPE 0x0200 #define AX_RX_CTL_START 0x0080 #define AX_RX_CTL_AP 0x0020 #define AX_RX_CTL_AM 0x0010 #define AX_RX_CTL_AB 0x0008 #define AX_RX_CTL_AMALL 0x0002 #define AX_RX_CTL_PRO 0x0001 #define AX_RX_CTL_STOP 0x0000 #define AX_NODE_ID 0x10 #define AX_MULFLTARY 0x16 #define AX_MEDIUM_STATUS_MODE 0x22 #define AX_MEDIUM_GIGAMODE 0x01 #define AX_MEDIUM_FULL_DUPLEX 0x02 #define AX_MEDIUM_EN_125MHZ 0x08 #define AX_MEDIUM_RXFLOW_CTRLEN 0x10 #define AX_MEDIUM_TXFLOW_CTRLEN 0x20 #define AX_MEDIUM_RECEIVE_EN 0x100 #define AX_MEDIUM_PS 0x200 #define AX_MEDIUM_JUMBO_EN 0x8040 #define AX_MONITOR_MOD 0x24 #define AX_MONITOR_MODE_RWLC 0x02 #define AX_MONITOR_MODE_RWMP 0x04 #define AX_MONITOR_MODE_PMEPOL 0x20 #define AX_MONITOR_MODE_PMETYPE 0x40 #define AX_GPIO_CTRL 0x25 #define AX_GPIO_CTRL_GPIO3EN 0x80 #define AX_GPIO_CTRL_GPIO2EN 0x40 #define AX_GPIO_CTRL_GPIO1EN 0x20 #define AX_PHYPWR_RSTCTL 0x26 #define AX_PHYPWR_RSTCTL_BZ 0x0010 #define AX_PHYPWR_RSTCTL_IPRL 0x0020 #define AX_PHYPWR_RSTCTL_AT 0x1000 #define AX_RX_BULKIN_QCTRL 0x2e #define AX_CLK_SELECT 0x33 #define AX_CLK_SELECT_BCS 0x01 #define AX_CLK_SELECT_ACS 0x02 #define AX_CLK_SELECT_ULR 0x08 #define AX_RXCOE_CTL 0x34 #define AX_RXCOE_IP 0x01 #define AX_RXCOE_TCP 0x02 #define AX_RXCOE_UDP 0x04 #define AX_RXCOE_TCPV6 0x20 #define AX_RXCOE_UDPV6 0x40 #define AX_TXCOE_CTL 0x35 #define AX_TXCOE_IP 0x01 #define AX_TXCOE_TCP 0x02 #define AX_TXCOE_UDP 0x04 #define AX_TXCOE_TCPV6 0x20 #define AX_TXCOE_UDPV6 0x40 #define AX_LEDCTRL 0x73 #define GMII_PHY_PHYSR 0x11 #define GMII_PHY_PHYSR_SMASK 0xc000 #define GMII_PHY_PHYSR_GIGA 0x8000 #define GMII_PHY_PHYSR_100 0x4000 #define GMII_PHY_PHYSR_FULL 0x2000 #define GMII_PHY_PHYSR_LINK 0x400 #define GMII_LED_ACT 0x1a #define GMII_LED_ACTIVE_MASK 0xff8f #define GMII_LED0_ACTIVE BIT(4) #define GMII_LED1_ACTIVE BIT(5) #define GMII_LED2_ACTIVE BIT(6) #define GMII_LED_LINK 0x1c #define GMII_LED_LINK_MASK 0xf888 #define GMII_LED0_LINK_10 BIT(0) #define GMII_LED0_LINK_100 BIT(1) #define GMII_LED0_LINK_1000 BIT(2) #define GMII_LED1_LINK_10 BIT(4) #define GMII_LED1_LINK_100 BIT(5) #define GMII_LED1_LINK_1000 BIT(6) #define GMII_LED2_LINK_10 BIT(8) #define GMII_LED2_LINK_100 BIT(9) #define GMII_LED2_LINK_1000 BIT(10) #define LED0_ACTIVE BIT(0) #define LED0_LINK_10 BIT(1) #define LED0_LINK_100 BIT(2) #define LED0_LINK_1000 BIT(3) #define LED0_FD BIT(4) #define LED0_USB3_MASK 0x001f #define LED1_ACTIVE BIT(5) #define LED1_LINK_10 BIT(6) #define LED1_LINK_100 BIT(7) #define LED1_LINK_1000 BIT(8) #define LED1_FD BIT(9) #define LED1_USB3_MASK 0x03e0 #define LED2_ACTIVE BIT(10) #define LED2_LINK_1000 BIT(13) #define LED2_LINK_100 BIT(12) #define LED2_LINK_10 BIT(11) #define LED2_FD BIT(14) #define LED_VALID BIT(15) #define LED2_USB3_MASK 0x7c00 #define GMII_PHYPAGE 0x1e #define GMII_PHY_PAGE_SELECT 0x1f #define GMII_PHY_PGSEL_EXT 0x0007 #define GMII_PHY_PGSEL_PAGE0 0x0000 #define GMII_PHY_PGSEL_PAGE3 0x0003 #define GMII_PHY_PGSEL_PAGE5 0x0005 static int ax88179_reset(struct usbnet *dev); struct ax88179_data { u8 eee_enabled; u8 eee_active; u16 rxctl; u8 in_pm; u32 wol_supported; u32 wolopts; u8 disconnecting; }; struct ax88179_int_data { __le32 intdata1; __le32 intdata2; }; static const struct { unsigned char ctrl, timer_l, timer_h, size, ifg; } AX88179_BULKIN_SIZE[] = { {7, 0x4f, 0, 0x12, 0xff}, {7, 0x20, 3, 0x16, 0xff}, {7, 0xae, 7, 0x18, 0xff}, {7, 0xcc, 0x4c, 0x18, 8}, }; static void ax88179_set_pm_mode(struct usbnet *dev, bool pm_mode) { struct ax88179_data *ax179_data = dev->driver_priv; ax179_data->in_pm = pm_mode; } static int ax88179_in_pm(struct usbnet *dev) { struct ax88179_data *ax179_data = dev->driver_priv; return ax179_data->in_pm; } static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, u16 size, void *data) { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16); struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); if (!ax88179_in_pm(dev)) fn = usbnet_read_cmd; else fn = usbnet_read_cmd_nopm; ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n", index, ret); return ret; } static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, u16 size, const void *data) { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); if (!ax88179_in_pm(dev)) fn = usbnet_write_cmd; else fn = usbnet_write_cmd_nopm; ret = fn(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to write reg index 0x%04x: %d\n", index, ret); return ret; } static void ax88179_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value, u16 index, u16 size, void *data) { u16 buf; if (2 == size) { buf = *((u16 *)data); cpu_to_le16s(&buf); usbnet_write_cmd_async(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, &buf, size); } else { usbnet_write_cmd_async(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); } } static int ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, u16 size, void *data) { int ret; if (2 == size) { u16 buf = 0; ret = __ax88179_read_cmd(dev, cmd, value, index, size, &buf); le16_to_cpus(&buf); *((u16 *)data) = buf; } else if (4 == size) { u32 buf = 0; ret = __ax88179_read_cmd(dev, cmd, value, index, size, &buf); le32_to_cpus(&buf); *((u32 *)data) = buf; } else { ret = __ax88179_read_cmd(dev, cmd, value, index, size, data); } return ret; } static int ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, u16 size, const void *data) { int ret; if (2 == size) { u16 buf; buf = *((u16 *)data); cpu_to_le16s(&buf); ret = __ax88179_write_cmd(dev, cmd, value, index, size, &buf); } else { ret = __ax88179_write_cmd(dev, cmd, value, index, size, data); } return ret; } static void ax88179_status(struct usbnet *dev, struct urb *urb) { struct ax88179_int_data *event; u32 link; if (urb->actual_length < 8) return; event = urb->transfer_buffer; le32_to_cpus((void *)&event->intdata1); link = (((__force u32)event->intdata1) & AX_INT_PPLS_LINK) >> 16; if (netif_carrier_ok(dev->net) != link) { usbnet_link_change(dev, link, 1); if (!link) netdev_info(dev->net, "ax88179 - Link status is: 0\n"); } } static int ax88179_mdio_read(struct net_device *netdev, int phy_id, int loc) { struct usbnet *dev = netdev_priv(netdev); u16 res; ax88179_read_cmd(dev, AX_ACCESS_PHY, phy_id, (__u16)loc, 2, &res); return res; } static void ax88179_mdio_write(struct net_device *netdev, int phy_id, int loc, int val) { struct usbnet *dev = netdev_priv(netdev); u16 res = (u16) val; ax88179_write_cmd(dev, AX_ACCESS_PHY, phy_id, (__u16)loc, 2, &res); } static inline int ax88179_phy_mmd_indirect(struct usbnet *dev, u16 prtad, u16 devad) { u16 tmp16; int ret; tmp16 = devad; ret = ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_MMD_CTRL, 2, &tmp16); tmp16 = prtad; ret = ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_MMD_DATA, 2, &tmp16); tmp16 = devad | MII_MMD_CTRL_NOINCR; ret = ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_MMD_CTRL, 2, &tmp16); return ret; } static int ax88179_phy_read_mmd_indirect(struct usbnet *dev, u16 prtad, u16 devad) { int ret; u16 tmp16; ax88179_phy_mmd_indirect(dev, prtad, devad); ret = ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_MMD_DATA, 2, &tmp16); if (ret < 0) return ret; return tmp16; } static int ax88179_phy_write_mmd_indirect(struct usbnet *dev, u16 prtad, u16 devad, u16 data) { int ret; ax88179_phy_mmd_indirect(dev, prtad, devad); ret = ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_MMD_DATA, 2, &data); if (ret < 0) return ret; return 0; } static int ax88179_suspend(struct usb_interface *intf, pm_message_t message) { struct usbnet *dev = usb_get_intfdata(intf); struct ax88179_data *priv = dev->driver_priv; u16 tmp16; u8 tmp8; ax88179_set_pm_mode(dev, true); usbnet_suspend(intf, message); /* Enable WoL */ if (priv->wolopts) { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MONITOR_MOD, 1, 1, &tmp8); if (priv->wolopts & WAKE_PHY) tmp8 |= AX_MONITOR_MODE_RWLC; if (priv->wolopts & WAKE_MAGIC) tmp8 |= AX_MONITOR_MODE_RWMP; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MONITOR_MOD, 1, 1, &tmp8); } /* Disable RX path */ ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); tmp16 &= ~AX_MEDIUM_RECEIVE_EN; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); /* Force bulk-in zero length */ ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, &tmp16); tmp16 |= AX_PHYPWR_RSTCTL_BZ | AX_PHYPWR_RSTCTL_IPRL; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, &tmp16); /* change clock */ tmp8 = 0; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, &tmp8); /* Configure RX control register => stop operation */ tmp16 = AX_RX_CTL_STOP; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RX_CTL, 2, 2, &tmp16); ax88179_set_pm_mode(dev, false); return 0; } /* This function is used to enable the autodetach function. */ /* This function is determined by offset 0x43 of EEPROM */ static int ax88179_auto_detach(struct usbnet *dev) { u16 tmp16; u8 tmp8; if (ax88179_read_cmd(dev, AX_ACCESS_EEPROM, 0x43, 1, 2, &tmp16) < 0) return 0; if ((tmp16 == 0xFFFF) || (!(tmp16 & 0x0100))) return 0; /* Enable Auto Detach bit */ tmp8 = 0; ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, &tmp8); tmp8 |= AX_CLK_SELECT_ULR; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, &tmp8); ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, &tmp16); tmp16 |= AX_PHYPWR_RSTCTL_AT; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, &tmp16); return 0; } static int ax88179_resume(struct usb_interface *intf) { struct usbnet *dev = usb_get_intfdata(intf); ax88179_set_pm_mode(dev, true); usbnet_link_change(dev, 0, 0); ax88179_reset(dev); ax88179_set_pm_mode(dev, false); return usbnet_resume(intf); } static void ax88179_disconnect(struct usb_interface *intf) { struct usbnet *dev = usb_get_intfdata(intf); struct ax88179_data *ax179_data; if (!dev) return; ax179_data = dev->driver_priv; ax179_data->disconnecting = 1; usbnet_disconnect(intf); } static void ax88179_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { struct usbnet *dev = netdev_priv(net); struct ax88179_data *priv = dev->driver_priv; wolinfo->supported = priv->wol_supported; wolinfo->wolopts = priv->wolopts; } static int ax88179_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { struct usbnet *dev = netdev_priv(net); struct ax88179_data *priv = dev->driver_priv; if (wolinfo->wolopts & ~(priv->wol_supported)) return -EINVAL; priv->wolopts = wolinfo->wolopts; return 0; } static int ax88179_get_eeprom_len(struct net_device *net) { return AX_EEPROM_LEN; } static int ax88179_get_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom, u8 *data) { struct usbnet *dev = netdev_priv(net); u16 *eeprom_buff; int first_word, last_word; int i, ret; if (eeprom->len == 0) return -EINVAL; eeprom->magic = AX88179_EEPROM_MAGIC; first_word = eeprom->offset >> 1; last_word = (eeprom->offset + eeprom->len - 1) >> 1; eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16), GFP_KERNEL); if (!eeprom_buff) return -ENOMEM; /* ax88179/178A returns 2 bytes from eeprom on read */ for (i = first_word; i <= last_word; i++) { ret = __ax88179_read_cmd(dev, AX_ACCESS_EEPROM, i, 1, 2, &eeprom_buff[i - first_word]); if (ret < 0) { kfree(eeprom_buff); return -EIO; } } memcpy(data, (u8 *)eeprom_buff + (eeprom->offset & 1), eeprom->len); kfree(eeprom_buff); return 0; } static int ax88179_set_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom, u8 *data) { struct usbnet *dev = netdev_priv(net); u16 *eeprom_buff; int first_word; int last_word; int ret; int i; netdev_dbg(net, "write EEPROM len %d, offset %d, magic 0x%x\n", eeprom->len, eeprom->offset, eeprom->magic); if (eeprom->len == 0) return -EINVAL; if (eeprom->magic != AX88179_EEPROM_MAGIC) return -EINVAL; first_word = eeprom->offset >> 1; last_word = (eeprom->offset + eeprom->len - 1) >> 1; eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16), GFP_KERNEL); if (!eeprom_buff) return -ENOMEM; /* align data to 16 bit boundaries, read the missing data from the EEPROM */ if (eeprom->offset & 1) { ret = ax88179_read_cmd(dev, AX_ACCESS_EEPROM, first_word, 1, 2, &eeprom_buff[0]); if (ret < 0) { netdev_err(net, "Failed to read EEPROM at offset 0x%02x.\n", first_word); goto free; } } if ((eeprom->offset + eeprom->len) & 1) { ret = ax88179_read_cmd(dev, AX_ACCESS_EEPROM, last_word, 1, 2, &eeprom_buff[last_word - first_word]); if (ret < 0) { netdev_err(net, "Failed to read EEPROM at offset 0x%02x.\n", last_word); goto free; } } memcpy((u8 *)eeprom_buff + (eeprom->offset & 1), data, eeprom->len); for (i = first_word; i <= last_word; i++) { netdev_dbg(net, "write to EEPROM at offset 0x%02x, data 0x%04x\n", i, eeprom_buff[i - first_word]); ret = ax88179_write_cmd(dev, AX_ACCESS_EEPROM, i, 1, 2, &eeprom_buff[i - first_word]); if (ret < 0) { netdev_err(net, "Failed to write EEPROM at offset 0x%02x.\n", i); goto free; } msleep(20); } /* reload EEPROM data */ ret = ax88179_write_cmd(dev, AX_RELOAD_EEPROM_EFUSE, 0x0000, 0, 0, NULL); if (ret < 0) { netdev_err(net, "Failed to reload EEPROM data\n"); goto free; } ret = 0; free: kfree(eeprom_buff); return ret; } static int ax88179_get_link_ksettings(struct net_device *net, struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); mii_ethtool_get_link_ksettings(&dev->mii, cmd); return 0; } static int ax88179_set_link_ksettings(struct net_device *net, const struct ethtool_link_ksettings *cmd) { struct usbnet *dev = netdev_priv(net); return mii_ethtool_set_link_ksettings(&dev->mii, cmd); } static int ax88179_ethtool_get_eee(struct usbnet *dev, struct ethtool_keee *data) { int val; /* Get Supported EEE */ val = ax88179_phy_read_mmd_indirect(dev, MDIO_PCS_EEE_ABLE, MDIO_MMD_PCS); if (val < 0) return val; mii_eee_cap1_mod_linkmode_t(data->supported, val); /* Get advertisement EEE */ val = ax88179_phy_read_mmd_indirect(dev, MDIO_AN_EEE_ADV, MDIO_MMD_AN); if (val < 0) return val; mii_eee_cap1_mod_linkmode_t(data->advertised, val); /* Get LP advertisement EEE */ val = ax88179_phy_read_mmd_indirect(dev, MDIO_AN_EEE_LPABLE, MDIO_MMD_AN); if (val < 0) return val; mii_eee_cap1_mod_linkmode_t(data->lp_advertised, val); return 0; } static int ax88179_ethtool_set_eee(struct usbnet *dev, struct ethtool_keee *data) { u16 tmp16 = linkmode_to_mii_eee_cap1_t(data->advertised); return ax88179_phy_write_mmd_indirect(dev, MDIO_AN_EEE_ADV, MDIO_MMD_AN, tmp16); } static int ax88179_chk_eee(struct usbnet *dev) { struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; struct ax88179_data *priv = dev->driver_priv; mii_ethtool_gset(&dev->mii, &ecmd); if (ecmd.duplex & DUPLEX_FULL) { int eee_lp, eee_cap, eee_adv; u32 lp, cap, adv, supported = 0; eee_cap = ax88179_phy_read_mmd_indirect(dev, MDIO_PCS_EEE_ABLE, MDIO_MMD_PCS); if (eee_cap < 0) { priv->eee_active = 0; return false; } cap = mmd_eee_cap_to_ethtool_sup_t(eee_cap); if (!cap) { priv->eee_active = 0; return false; } eee_lp = ax88179_phy_read_mmd_indirect(dev, MDIO_AN_EEE_LPABLE, MDIO_MMD_AN); if (eee_lp < 0) { priv->eee_active = 0; return false; } eee_adv = ax88179_phy_read_mmd_indirect(dev, MDIO_AN_EEE_ADV, MDIO_MMD_AN); if (eee_adv < 0) { priv->eee_active = 0; return false; } adv = mmd_eee_adv_to_ethtool_adv_t(eee_adv); lp = mmd_eee_adv_to_ethtool_adv_t(eee_lp); supported = (ecmd.speed == SPEED_1000) ? SUPPORTED_1000baseT_Full : SUPPORTED_100baseT_Full; if (!(lp & adv & supported)) { priv->eee_active = 0; return false; } priv->eee_active = 1; return true; } priv->eee_active = 0; return false; } static void ax88179_disable_eee(struct usbnet *dev) { u16 tmp16; tmp16 = GMII_PHY_PGSEL_PAGE3; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PAGE_SELECT, 2, &tmp16); tmp16 = 0x3246; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_PHYADDR, 2, &tmp16); tmp16 = GMII_PHY_PGSEL_PAGE0; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PAGE_SELECT, 2, &tmp16); } static void ax88179_enable_eee(struct usbnet *dev) { u16 tmp16; tmp16 = GMII_PHY_PGSEL_PAGE3; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PAGE_SELECT, 2, &tmp16); tmp16 = 0x3247; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_PHYADDR, 2, &tmp16); tmp16 = GMII_PHY_PGSEL_PAGE5; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PAGE_SELECT, 2, &tmp16); tmp16 = 0x0680; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, MII_BMSR, 2, &tmp16); tmp16 = GMII_PHY_PGSEL_PAGE0; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PAGE_SELECT, 2, &tmp16); } static int ax88179_get_eee(struct net_device *net, struct ethtool_keee *edata) { struct usbnet *dev = netdev_priv(net); struct ax88179_data *priv = dev->driver_priv; edata->eee_enabled = priv->eee_enabled; edata->eee_active = priv->eee_active; return ax88179_ethtool_get_eee(dev, edata); } static int ax88179_set_eee(struct net_device *net, struct ethtool_keee *edata) { struct usbnet *dev = netdev_priv(net); struct ax88179_data *priv = dev->driver_priv; int ret; priv->eee_enabled = edata->eee_enabled; if (!priv->eee_enabled) { ax88179_disable_eee(dev); } else { priv->eee_enabled = ax88179_chk_eee(dev); if (!priv->eee_enabled) return -EOPNOTSUPP; ax88179_enable_eee(dev); } ret = ax88179_ethtool_set_eee(dev, edata); if (ret) return ret; mii_nway_restart(&dev->mii); usbnet_link_change(dev, 0, 0); return ret; } static int ax88179_ioctl(struct net_device *net, struct ifreq *rq, int cmd) { struct usbnet *dev = netdev_priv(net); return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); } static const struct ethtool_ops ax88179_ethtool_ops = { .get_link = ethtool_op_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_wol = ax88179_get_wol, .set_wol = ax88179_set_wol, .get_eeprom_len = ax88179_get_eeprom_len, .get_eeprom = ax88179_get_eeprom, .set_eeprom = ax88179_set_eeprom, .get_eee = ax88179_get_eee, .set_eee = ax88179_set_eee, .nway_reset = usbnet_nway_reset, .get_link_ksettings = ax88179_get_link_ksettings, .set_link_ksettings = ax88179_set_link_ksettings, .get_ts_info = ethtool_op_get_ts_info, }; static void ax88179_set_multicast(struct net_device *net) { struct usbnet *dev = netdev_priv(net); struct ax88179_data *data = dev->driver_priv; u8 *m_filter = ((u8 *)dev->data); data->rxctl = (AX_RX_CTL_START | AX_RX_CTL_AB | AX_RX_CTL_IPE); if (net->flags & IFF_PROMISC) { data->rxctl |= AX_RX_CTL_PRO; } else if (net->flags & IFF_ALLMULTI || netdev_mc_count(net) > AX_MAX_MCAST) { data->rxctl |= AX_RX_CTL_AMALL; } else if (netdev_mc_empty(net)) { /* just broadcast and directed */ } else { /* We use dev->data for our 8 byte filter buffer * to avoid allocating memory that is tricky to free later */ u32 crc_bits; struct netdev_hw_addr *ha; memset(m_filter, 0, AX_MCAST_FLTSIZE); netdev_for_each_mc_addr(ha, net) { crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26; *(m_filter + (crc_bits >> 3)) |= (1 << (crc_bits & 7)); } ax88179_write_cmd_async(dev, AX_ACCESS_MAC, AX_MULFLTARY, AX_MCAST_FLTSIZE, AX_MCAST_FLTSIZE, m_filter); data->rxctl |= AX_RX_CTL_AM; } ax88179_write_cmd_async(dev, AX_ACCESS_MAC, AX_RX_CTL, 2, 2, &data->rxctl); } static int ax88179_set_features(struct net_device *net, netdev_features_t features) { u8 tmp; struct usbnet *dev = netdev_priv(net); netdev_features_t changed = net->features ^ features; if (changed & NETIF_F_IP_CSUM) { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_TXCOE_CTL, 1, 1, &tmp); tmp ^= AX_TXCOE_TCP | AX_TXCOE_UDP; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_TXCOE_CTL, 1, 1, &tmp); } if (changed & NETIF_F_IPV6_CSUM) { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_TXCOE_CTL, 1, 1, &tmp); tmp ^= AX_TXCOE_TCPV6 | AX_TXCOE_UDPV6; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_TXCOE_CTL, 1, 1, &tmp); } if (changed & NETIF_F_RXCSUM) { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_RXCOE_CTL, 1, 1, &tmp); tmp ^= AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP | AX_RXCOE_TCPV6 | AX_RXCOE_UDPV6; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RXCOE_CTL, 1, 1, &tmp); } return 0; } static int ax88179_change_mtu(struct net_device *net, int new_mtu) { struct usbnet *dev = netdev_priv(net); u16 tmp16; WRITE_ONCE(net->mtu, new_mtu); dev->hard_mtu = net->mtu + net->hard_header_len; if (net->mtu > 1500) { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); tmp16 |= AX_MEDIUM_JUMBO_EN; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); } else { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); tmp16 &= ~AX_MEDIUM_JUMBO_EN; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); } /* max qlen depend on hard_mtu and rx_urb_size */ usbnet_update_max_qlen(dev); return 0; } static int ax88179_set_mac_addr(struct net_device *net, void *p) { struct usbnet *dev = netdev_priv(net); struct sockaddr *addr = p; int ret; if (netif_running(net)) return -EBUSY; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; eth_hw_addr_set(net, addr->sa_data); /* Set the MAC address */ ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, ETH_ALEN, net->dev_addr); if (ret < 0) return ret; return 0; } static const struct net_device_ops ax88179_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_get_stats64 = dev_get_tstats64, .ndo_change_mtu = ax88179_change_mtu, .ndo_set_mac_address = ax88179_set_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = ax88179_ioctl, .ndo_set_rx_mode = ax88179_set_multicast, .ndo_set_features = ax88179_set_features, }; static int ax88179_check_eeprom(struct usbnet *dev) { u8 i, buf, eeprom[20]; u16 csum, delay = HZ / 10; unsigned long jtimeout; /* Read EEPROM content */ for (i = 0; i < 6; i++) { buf = i; if (ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_SROM_ADDR, 1, 1, &buf) < 0) return -EINVAL; buf = EEP_RD; if (ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_SROM_CMD, 1, 1, &buf) < 0) return -EINVAL; jtimeout = jiffies + delay; do { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_SROM_CMD, 1, 1, &buf); if (time_after(jiffies, jtimeout)) return -EINVAL; } while (buf & EEP_BUSY); __ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_SROM_DATA_LOW, 2, 2, &eeprom[i * 2]); if ((i == 0) && (eeprom[0] == 0xFF)) return -EINVAL; } csum = eeprom[6] + eeprom[7] + eeprom[8] + eeprom[9]; csum = (csum >> 8) + (csum & 0xff); if ((csum + eeprom[10]) != 0xff) return -EINVAL; return 0; } static int ax88179_check_efuse(struct usbnet *dev, u16 *ledmode) { u8 i; u8 efuse[64]; u16 csum = 0; if (ax88179_read_cmd(dev, AX_ACCESS_EFUS, 0, 64, 64, efuse) < 0) return -EINVAL; if (*efuse == 0xFF) return -EINVAL; for (i = 0; i < 64; i++) csum = csum + efuse[i]; while (csum > 255) csum = (csum & 0x00FF) + ((csum >> 8) & 0x00FF); if (csum != 0xFF) return -EINVAL; *ledmode = (efuse[51] << 8) | efuse[52]; return 0; } static int ax88179_convert_old_led(struct usbnet *dev, u16 *ledvalue) { u16 led; /* Loaded the old eFuse LED Mode */ if (ax88179_read_cmd(dev, AX_ACCESS_EEPROM, 0x3C, 1, 2, &led) < 0) return -EINVAL; led >>= 8; switch (led) { case 0xFF: led = LED0_ACTIVE | LED1_LINK_10 | LED1_LINK_100 | LED1_LINK_1000 | LED2_ACTIVE | LED2_LINK_10 | LED2_LINK_100 | LED2_LINK_1000 | LED_VALID; break; case 0xFE: led = LED0_ACTIVE | LED1_LINK_1000 | LED2_LINK_100 | LED_VALID; break; case 0xFD: led = LED0_ACTIVE | LED1_LINK_1000 | LED2_LINK_100 | LED2_LINK_10 | LED_VALID; break; case 0xFC: led = LED0_ACTIVE | LED1_ACTIVE | LED1_LINK_1000 | LED2_ACTIVE | LED2_LINK_100 | LED2_LINK_10 | LED_VALID; break; default: led = LED0_ACTIVE | LED1_LINK_10 | LED1_LINK_100 | LED1_LINK_1000 | LED2_ACTIVE | LED2_LINK_10 | LED2_LINK_100 | LED2_LINK_1000 | LED_VALID; break; } *ledvalue = led; return 0; } static int ax88179_led_setting(struct usbnet *dev) { u8 ledfd, value = 0; u16 tmp, ledact, ledlink, ledvalue = 0, delay = HZ / 10; unsigned long jtimeout; /* Check AX88179 version. UA1 or UA2*/ ax88179_read_cmd(dev, AX_ACCESS_MAC, GENERAL_STATUS, 1, 1, &value); if (!(value & AX_SECLD)) { /* UA1 */ value = AX_GPIO_CTRL_GPIO3EN | AX_GPIO_CTRL_GPIO2EN | AX_GPIO_CTRL_GPIO1EN; if (ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_GPIO_CTRL, 1, 1, &value) < 0) return -EINVAL; } /* Check EEPROM */ if (!ax88179_check_eeprom(dev)) { value = 0x42; if (ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_SROM_ADDR, 1, 1, &value) < 0) return -EINVAL; value = EEP_RD; if (ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_SROM_CMD, 1, 1, &value) < 0) return -EINVAL; jtimeout = jiffies + delay; do { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_SROM_CMD, 1, 1, &value); if (time_after(jiffies, jtimeout)) return -EINVAL; } while (value & EEP_BUSY); ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_SROM_DATA_HIGH, 1, 1, &value); ledvalue = (value << 8); ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_SROM_DATA_LOW, 1, 1, &value); ledvalue |= value; /* load internal ROM for defaule setting */ if ((ledvalue == 0xFFFF) || ((ledvalue & LED_VALID) == 0)) ax88179_convert_old_led(dev, &ledvalue); } else if (!ax88179_check_efuse(dev, &ledvalue)) { if ((ledvalue == 0xFFFF) || ((ledvalue & LED_VALID) == 0)) ax88179_convert_old_led(dev, &ledvalue); } else { ax88179_convert_old_led(dev, &ledvalue); } tmp = GMII_PHY_PGSEL_EXT; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PAGE_SELECT, 2, &tmp); tmp = 0x2c; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHYPAGE, 2, &tmp); ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_LED_ACT, 2, &ledact); ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_LED_LINK, 2, &ledlink); ledact &= GMII_LED_ACTIVE_MASK; ledlink &= GMII_LED_LINK_MASK; if (ledvalue & LED0_ACTIVE) ledact |= GMII_LED0_ACTIVE; if (ledvalue & LED1_ACTIVE) ledact |= GMII_LED1_ACTIVE; if (ledvalue & LED2_ACTIVE) ledact |= GMII_LED2_ACTIVE; if (ledvalue & LED0_LINK_10) ledlink |= GMII_LED0_LINK_10; if (ledvalue & LED1_LINK_10) ledlink |= GMII_LED1_LINK_10; if (ledvalue & LED2_LINK_10) ledlink |= GMII_LED2_LINK_10; if (ledvalue & LED0_LINK_100) ledlink |= GMII_LED0_LINK_100; if (ledvalue & LED1_LINK_100) ledlink |= GMII_LED1_LINK_100; if (ledvalue & LED2_LINK_100) ledlink |= GMII_LED2_LINK_100; if (ledvalue & LED0_LINK_1000) ledlink |= GMII_LED0_LINK_1000; if (ledvalue & LED1_LINK_1000) ledlink |= GMII_LED1_LINK_1000; if (ledvalue & LED2_LINK_1000) ledlink |= GMII_LED2_LINK_1000; tmp = ledact; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_LED_ACT, 2, &tmp); tmp = ledlink; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_LED_LINK, 2, &tmp); tmp = GMII_PHY_PGSEL_PAGE0; ax88179_write_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PAGE_SELECT, 2, &tmp); /* LED full duplex setting */ ledfd = 0; if (ledvalue & LED0_FD) ledfd |= 0x01; else if ((ledvalue & LED0_USB3_MASK) == 0) ledfd |= 0x02; if (ledvalue & LED1_FD) ledfd |= 0x04; else if ((ledvalue & LED1_USB3_MASK) == 0) ledfd |= 0x08; if (ledvalue & LED2_FD) ledfd |= 0x10; else if ((ledvalue & LED2_USB3_MASK) == 0) ledfd |= 0x20; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_LEDCTRL, 1, 1, &ledfd); return 0; } static void ax88179_get_mac_addr(struct usbnet *dev) { u8 mac[ETH_ALEN]; memset(mac, 0, sizeof(mac)); /* Maybe the boot loader passed the MAC address via device tree */ if (!eth_platform_get_mac_address(&dev->udev->dev, mac)) { netif_dbg(dev, ifup, dev->net, "MAC address read from device tree"); } else { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, ETH_ALEN, mac); netif_dbg(dev, ifup, dev->net, "MAC address read from ASIX chip"); } if (is_valid_ether_addr(mac)) { eth_hw_addr_set(dev->net, mac); if (!is_local_ether_addr(mac)) dev->net->addr_assign_type = NET_ADDR_PERM; } else { netdev_info(dev->net, "invalid MAC address, using random\n"); } ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, ETH_ALEN, dev->net->dev_addr); } static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) { struct ax88179_data *ax179_data; int ret; ret = usbnet_get_endpoints(dev, intf); if (ret < 0) return ret; ax179_data = kzalloc(sizeof(*ax179_data), GFP_KERNEL); if (!ax179_data) return -ENOMEM; dev->driver_priv = ax179_data; dev->net->netdev_ops = &ax88179_netdev_ops; dev->net->ethtool_ops = &ax88179_ethtool_ops; dev->net->needed_headroom = 8; dev->net->max_mtu = 4088; /* Initialize MII structure */ dev->mii.dev = dev->net; dev->mii.mdio_read = ax88179_mdio_read; dev->mii.mdio_write = ax88179_mdio_write; dev->mii.phy_id_mask = 0xff; dev->mii.reg_num_mask = 0xff; dev->mii.phy_id = 0x03; dev->mii.supports_gmii = 1; dev->net->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO; dev->net->hw_features |= dev->net->features; netif_set_tso_max_size(dev->net, 16384); ax88179_reset(dev); return 0; } static void ax88179_unbind(struct usbnet *dev, struct usb_interface *intf) { struct ax88179_data *ax179_data = dev->driver_priv; u16 tmp16; /* Configure RX control register => stop operation */ tmp16 = AX_RX_CTL_STOP; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RX_CTL, 2, 2, &tmp16); tmp16 = 0; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, &tmp16); /* Power down ethernet PHY */ tmp16 = 0; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, &tmp16); kfree(ax179_data); } static void ax88179_rx_checksum(struct sk_buff *skb, u32 *pkt_hdr) { skb->ip_summed = CHECKSUM_NONE; /* checksum error bit is set */ if ((*pkt_hdr & AX_RXHDR_L3CSUM_ERR) || (*pkt_hdr & AX_RXHDR_L4CSUM_ERR)) return; /* It must be a TCP or UDP packet with a valid checksum */ if (((*pkt_hdr & AX_RXHDR_L4_TYPE_MASK) == AX_RXHDR_L4_TYPE_TCP) || ((*pkt_hdr & AX_RXHDR_L4_TYPE_MASK) == AX_RXHDR_L4_TYPE_UDP)) skb->ip_summed = CHECKSUM_UNNECESSARY; } static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { struct sk_buff *ax_skb; int pkt_cnt; u32 rx_hdr; u16 hdr_off; u32 *pkt_hdr; /* At the end of the SKB, there's a header telling us how many packets * are bundled into this buffer and where we can find an array of * per-packet metadata (which contains elements encoded into u16). */ /* SKB contents for current firmware: * <packet 1> <padding> * ... * <packet N> <padding> * <per-packet metadata entry 1> <dummy header> * ... * <per-packet metadata entry N> <dummy header> * <padding2> <rx_hdr> * * where: * <packet N> contains pkt_len bytes: * 2 bytes of IP alignment pseudo header * packet received * <per-packet metadata entry N> contains 4 bytes: * pkt_len and fields AX_RXHDR_* * <padding> 0-7 bytes to terminate at * 8 bytes boundary (64-bit). * <padding2> 4 bytes to make rx_hdr terminate at * 8 bytes boundary (64-bit) * <dummy-header> contains 4 bytes: * pkt_len=0 and AX_RXHDR_DROP_ERR * <rx-hdr> contains 4 bytes: * pkt_cnt and hdr_off (offset of * <per-packet metadata entry 1>) * * pkt_cnt is number of entrys in the per-packet metadata. * In current firmware there is 2 entrys per packet. * The first points to the packet and the * second is a dummy header. * This was done probably to align fields in 64-bit and * maintain compatibility with old firmware. * This code assumes that <dummy header> and <padding2> are * optional. */ if (skb->len < 4) return 0; skb_trim(skb, skb->len - 4); rx_hdr = get_unaligned_le32(skb_tail_pointer(skb)); pkt_cnt = (u16)rx_hdr; hdr_off = (u16)(rx_hdr >> 16); if (pkt_cnt == 0) return 0; /* Make sure that the bounds of the metadata array are inside the SKB * (and in front of the counter at the end). */ if (pkt_cnt * 4 + hdr_off > skb->len) return 0; pkt_hdr = (u32 *)(skb->data + hdr_off); /* Packets must not overlap the metadata array */ skb_trim(skb, hdr_off); for (; pkt_cnt > 0; pkt_cnt--, pkt_hdr++) { u16 pkt_len_plus_padd; u16 pkt_len; le32_to_cpus(pkt_hdr); pkt_len = (*pkt_hdr >> 16) & 0x1fff; pkt_len_plus_padd = (pkt_len + 7) & 0xfff8; /* Skip dummy header used for alignment */ if (pkt_len == 0) continue; if (pkt_len_plus_padd > skb->len) return 0; /* Check CRC or runt packet */ if ((*pkt_hdr & (AX_RXHDR_CRC_ERR | AX_RXHDR_DROP_ERR)) || pkt_len < 2 + ETH_HLEN) { dev->net->stats.rx_errors++; skb_pull(skb, pkt_len_plus_padd); continue; } /* last packet */ if (pkt_len_plus_padd == skb->len) { skb_trim(skb, pkt_len); /* Skip IP alignment pseudo header */ skb_pull(skb, 2); ax88179_rx_checksum(skb, pkt_hdr); return 1; } ax_skb = netdev_alloc_skb_ip_align(dev->net, pkt_len); if (!ax_skb) return 0; skb_put(ax_skb, pkt_len); memcpy(ax_skb->data, skb->data + 2, pkt_len); ax88179_rx_checksum(ax_skb, pkt_hdr); usbnet_skb_return(dev, ax_skb); skb_pull(skb, pkt_len_plus_padd); } return 0; } static struct sk_buff * ax88179_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) { u32 tx_hdr1, tx_hdr2; int frame_size = dev->maxpacket; int headroom; void *ptr; tx_hdr1 = skb->len; tx_hdr2 = skb_shinfo(skb)->gso_size; /* Set TSO mss */ if (((skb->len + 8) % frame_size) == 0) tx_hdr2 |= 0x80008000; /* Enable padding */ headroom = skb_headroom(skb) - 8; if ((dev->net->features & NETIF_F_SG) && skb_linearize(skb)) return NULL; if ((skb_header_cloned(skb) || headroom < 0) && pskb_expand_head(skb, headroom < 0 ? 8 : 0, 0, GFP_ATOMIC)) { dev_kfree_skb_any(skb); return NULL; } ptr = skb_push(skb, 8); put_unaligned_le32(tx_hdr1, ptr); put_unaligned_le32(tx_hdr2, ptr + 4); usbnet_set_skb_tx_stats(skb, (skb_shinfo(skb)->gso_segs ?: 1), 0); return skb; } static int ax88179_link_reset(struct usbnet *dev) { struct ax88179_data *ax179_data = dev->driver_priv; u8 tmp[5], link_sts; u16 mode, tmp16, delay = HZ / 10; u32 tmp32 = 0x40000000; unsigned long jtimeout; jtimeout = jiffies + delay; while (tmp32 & 0x40000000) { mode = 0; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RX_CTL, 2, 2, &mode); ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RX_CTL, 2, 2, &ax179_data->rxctl); /*link up, check the usb device control TX FIFO full or empty*/ ax88179_read_cmd(dev, 0x81, 0x8c, 0, 4, &tmp32); if (time_after(jiffies, jtimeout)) return 0; } mode = AX_MEDIUM_RECEIVE_EN | AX_MEDIUM_TXFLOW_CTRLEN | AX_MEDIUM_RXFLOW_CTRLEN; ax88179_read_cmd(dev, AX_ACCESS_MAC, PHYSICAL_LINK_STATUS, 1, 1, &link_sts); ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PHYSR, 2, &tmp16); if (!(tmp16 & GMII_PHY_PHYSR_LINK)) { netdev_info(dev->net, "ax88179 - Link status is: 0\n"); return 0; } else if (GMII_PHY_PHYSR_GIGA == (tmp16 & GMII_PHY_PHYSR_SMASK)) { mode |= AX_MEDIUM_GIGAMODE | AX_MEDIUM_EN_125MHZ; if (dev->net->mtu > 1500) mode |= AX_MEDIUM_JUMBO_EN; if (link_sts & AX_USB_SS) memcpy(tmp, &AX88179_BULKIN_SIZE[0], 5); else if (link_sts & AX_USB_HS) memcpy(tmp, &AX88179_BULKIN_SIZE[1], 5); else memcpy(tmp, &AX88179_BULKIN_SIZE[3], 5); } else if (GMII_PHY_PHYSR_100 == (tmp16 & GMII_PHY_PHYSR_SMASK)) { mode |= AX_MEDIUM_PS; if (link_sts & (AX_USB_SS | AX_USB_HS)) memcpy(tmp, &AX88179_BULKIN_SIZE[2], 5); else memcpy(tmp, &AX88179_BULKIN_SIZE[3], 5); } else { memcpy(tmp, &AX88179_BULKIN_SIZE[3], 5); } /* RX bulk configuration */ ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RX_BULKIN_QCTRL, 5, 5, tmp); dev->rx_urb_size = (1024 * (tmp[3] + 2)); if (tmp16 & GMII_PHY_PHYSR_FULL) mode |= AX_MEDIUM_FULL_DUPLEX; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &mode); ax179_data->eee_enabled = ax88179_chk_eee(dev); netif_carrier_on(dev->net); netdev_info(dev->net, "ax88179 - Link status is: 1\n"); return 0; } static int ax88179_reset(struct usbnet *dev) { u8 buf[5]; u16 *tmp16; u8 *tmp; struct ax88179_data *ax179_data = dev->driver_priv; struct ethtool_keee eee_data; tmp16 = (u16 *)buf; tmp = (u8 *)buf; /* Power up ethernet PHY */ *tmp16 = 0; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, tmp16); *tmp16 = AX_PHYPWR_RSTCTL_IPRL; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, tmp16); msleep(500); *tmp = AX_CLK_SELECT_ACS | AX_CLK_SELECT_BCS; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, tmp); msleep(200); /* Ethernet PHY Auto Detach*/ ax88179_auto_detach(dev); /* Read MAC address from DTB or asix chip */ ax88179_get_mac_addr(dev); memcpy(dev->net->perm_addr, dev->net->dev_addr, ETH_ALEN); /* RX bulk configuration */ memcpy(tmp, &AX88179_BULKIN_SIZE[0], 5); ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RX_BULKIN_QCTRL, 5, 5, tmp); dev->rx_urb_size = 1024 * 20; *tmp = 0x34; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PAUSE_WATERLVL_LOW, 1, 1, tmp); *tmp = 0x52; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PAUSE_WATERLVL_HIGH, 1, 1, tmp); /* Enable checksum offload */ *tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP | AX_RXCOE_TCPV6 | AX_RXCOE_UDPV6; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RXCOE_CTL, 1, 1, tmp); *tmp = AX_TXCOE_IP | AX_TXCOE_TCP | AX_TXCOE_UDP | AX_TXCOE_TCPV6 | AX_TXCOE_UDPV6; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_TXCOE_CTL, 1, 1, tmp); /* Configure RX control register => start operation */ *tmp16 = AX_RX_CTL_DROPCRCERR | AX_RX_CTL_IPE | AX_RX_CTL_START | AX_RX_CTL_AP | AX_RX_CTL_AMALL | AX_RX_CTL_AB; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_RX_CTL, 2, 2, tmp16); *tmp = AX_MONITOR_MODE_PMETYPE | AX_MONITOR_MODE_PMEPOL | AX_MONITOR_MODE_RWMP; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MONITOR_MOD, 1, 1, tmp); /* Configure default medium type => giga */ *tmp16 = AX_MEDIUM_RECEIVE_EN | AX_MEDIUM_TXFLOW_CTRLEN | AX_MEDIUM_RXFLOW_CTRLEN | AX_MEDIUM_FULL_DUPLEX | AX_MEDIUM_GIGAMODE; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, tmp16); /* Check if WoL is supported */ ax179_data->wol_supported = 0; if (ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MONITOR_MOD, 1, 1, &tmp) > 0) ax179_data->wol_supported = WAKE_MAGIC | WAKE_PHY; ax88179_led_setting(dev); ax179_data->eee_enabled = 0; ax179_data->eee_active = 0; ax88179_disable_eee(dev); ax88179_ethtool_get_eee(dev, &eee_data); linkmode_zero(eee_data.advertised); ax88179_ethtool_set_eee(dev, &eee_data); /* Restart autoneg */ mii_nway_restart(&dev->mii); usbnet_link_change(dev, 0, 0); return 0; } static int ax88179_net_reset(struct usbnet *dev) { u16 tmp16; ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PHYSR, 2, &tmp16); if (tmp16) { ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); if (!(tmp16 & AX_MEDIUM_RECEIVE_EN)) { tmp16 |= AX_MEDIUM_RECEIVE_EN; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); } } else { ax88179_reset(dev); } return 0; } static int ax88179_stop(struct usbnet *dev) { u16 tmp16; ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); tmp16 &= ~AX_MEDIUM_RECEIVE_EN; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, &tmp16); return 0; } static const struct driver_info ax88179_info = { .description = "ASIX AX88179 USB 3.0 Gigabit Ethernet", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info ax88178a_info = { .description = "ASIX AX88178A USB 2.0 Gigabit Ethernet", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info cypress_GX3_info = { .description = "Cypress GX3 SuperSpeed to Gigabit Ethernet Controller", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info dlink_dub1312_info = { .description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info sitecom_info = { .description = "Sitecom USB 3.0 to Gigabit Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info samsung_info = { .description = "Samsung USB Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info lenovo_info = { .description = "Lenovo OneLinkDock Gigabit LAN", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info belkin_info = { .description = "Belkin USB Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info toshiba_info = { .description = "Toshiba USB Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info mct_info = { .description = "MCT USB 3.0 Gigabit Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info at_umc2000_info = { .description = "AT-UMC2000 USB 3.0/USB 3.1 Gen 1 to Gigabit Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info at_umc200_info = { .description = "AT-UMC200 USB 3.0/USB 3.1 Gen 1 to Fast Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct driver_info at_umc2000sp_info = { .description = "AT-UMC2000/SP USB 3.0/USB 3.1 Gen 1 to Gigabit Ethernet Adapter", .bind = ax88179_bind, .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_net_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, }; static const struct usb_device_id products[] = { { /* ASIX AX88179 10/100/1000 */ USB_DEVICE_AND_INTERFACE_INFO(0x0b95, 0x1790, 0xff, 0xff, 0), .driver_info = (unsigned long)&ax88179_info, }, { /* ASIX AX88178A 10/100/1000 */ USB_DEVICE_AND_INTERFACE_INFO(0x0b95, 0x178a, 0xff, 0xff, 0), .driver_info = (unsigned long)&ax88178a_info, }, { /* Cypress GX3 SuperSpeed to Gigabit Ethernet Bridge Controller */ USB_DEVICE_AND_INTERFACE_INFO(0x04b4, 0x3610, 0xff, 0xff, 0), .driver_info = (unsigned long)&cypress_GX3_info, }, { /* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x4a00, 0xff, 0xff, 0), .driver_info = (unsigned long)&dlink_dub1312_info, }, { /* Sitecom USB 3.0 to Gigabit Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x0df6, 0x0072, 0xff, 0xff, 0), .driver_info = (unsigned long)&sitecom_info, }, { /* Samsung USB Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x04e8, 0xa100, 0xff, 0xff, 0), .driver_info = (unsigned long)&samsung_info, }, { /* Lenovo OneLinkDock Gigabit LAN */ USB_DEVICE_AND_INTERFACE_INFO(0x17ef, 0x304b, 0xff, 0xff, 0), .driver_info = (unsigned long)&lenovo_info, }, { /* Belkin B2B128 USB 3.0 Hub + Gigabit Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x050d, 0x0128, 0xff, 0xff, 0), .driver_info = (unsigned long)&belkin_info, }, { /* Toshiba USB 3.0 GBit Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x0930, 0x0a13, 0xff, 0xff, 0), .driver_info = (unsigned long)&toshiba_info, }, { /* Magic Control Technology U3-A9003 USB 3.0 Gigabit Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x0711, 0x0179, 0xff, 0xff, 0), .driver_info = (unsigned long)&mct_info, }, { /* Allied Telesis AT-UMC2000 USB 3.0/USB 3.1 Gen 1 to Gigabit Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x07c9, 0x000e, 0xff, 0xff, 0), .driver_info = (unsigned long)&at_umc2000_info, }, { /* Allied Telesis AT-UMC200 USB 3.0/USB 3.1 Gen 1 to Fast Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x07c9, 0x000f, 0xff, 0xff, 0), .driver_info = (unsigned long)&at_umc200_info, }, { /* Allied Telesis AT-UMC2000/SP USB 3.0/USB 3.1 Gen 1 to Gigabit Ethernet Adapter */ USB_DEVICE_AND_INTERFACE_INFO(0x07c9, 0x0010, 0xff, 0xff, 0), .driver_info = (unsigned long)&at_umc2000sp_info, }, { }, }; MODULE_DEVICE_TABLE(usb, products); static struct usb_driver ax88179_178a_driver = { .name = "ax88179_178a", .id_table = products, .probe = usbnet_probe, .suspend = ax88179_suspend, .resume = ax88179_resume, .reset_resume = ax88179_resume, .disconnect = ax88179_disconnect, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; module_usb_driver(ax88179_178a_driver); MODULE_DESCRIPTION("ASIX AX88179/178A based USB 3.0/2.0 Gigabit Ethernet Devices"); MODULE_LICENSE("GPL"); |
| 10 10 10 1 1 1 1 24 24 8 12 1 1 6 3 3 1 2 2 1 1 1 3 6 2 6 6 6 5 1 1 1 1 25 25 1 1 11 2 13 21 18 5 17 2 3 13 2 7 20 2 20 1 14 7 5 16 3 5 18 70 1 1 1 1 1 25 1 7 4 7 1 28 1 1 7 5 2 5 2 6 1 5 2 6 1 6 7 7 7 7 2 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 | // SPDX-License-Identifier: GPL-2.0-only /* * cec-api.c - HDMI Consumer Electronics Control framework - API * * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #include <linux/errno.h> #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/ktime.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/types.h> #include <linux/uaccess.h> #include <linux/version.h> #include <media/cec-pin.h> #include "cec-priv.h" #include "cec-pin-priv.h" static inline struct cec_devnode *cec_devnode_data(struct file *filp) { struct cec_fh *fh = filp->private_data; return &fh->adap->devnode; } /* CEC file operations */ static __poll_t cec_poll(struct file *filp, struct poll_table_struct *poll) { struct cec_fh *fh = filp->private_data; struct cec_adapter *adap = fh->adap; __poll_t res = 0; poll_wait(filp, &fh->wait, poll); if (!cec_is_registered(adap)) return EPOLLERR | EPOLLHUP | EPOLLPRI; mutex_lock(&adap->lock); if (adap->is_configured && adap->transmit_queue_sz < CEC_MAX_MSG_TX_QUEUE_SZ) res |= EPOLLOUT | EPOLLWRNORM; if (fh->queued_msgs) res |= EPOLLIN | EPOLLRDNORM; if (fh->total_queued_events) res |= EPOLLPRI; mutex_unlock(&adap->lock); return res; } static bool cec_is_busy(const struct cec_adapter *adap, const struct cec_fh *fh) { bool valid_initiator = adap->cec_initiator && adap->cec_initiator == fh; bool valid_follower = adap->cec_follower && adap->cec_follower == fh; /* * Exclusive initiators and followers can always access the CEC adapter */ if (valid_initiator || valid_follower) return false; /* * All others can only access the CEC adapter if there is no * exclusive initiator and they are in INITIATOR mode. */ return adap->cec_initiator || fh->mode_initiator == CEC_MODE_NO_INITIATOR; } static long cec_adap_g_caps(struct cec_adapter *adap, struct cec_caps __user *parg) { struct cec_caps caps = {}; strscpy(caps.driver, adap->devnode.dev.parent->driver->name, sizeof(caps.driver)); strscpy(caps.name, adap->name, sizeof(caps.name)); caps.available_log_addrs = adap->available_log_addrs; caps.capabilities = adap->capabilities; caps.version = LINUX_VERSION_CODE; if (copy_to_user(parg, &caps, sizeof(caps))) return -EFAULT; return 0; } static long cec_adap_g_phys_addr(struct cec_adapter *adap, __u16 __user *parg) { u16 phys_addr; mutex_lock(&adap->lock); phys_addr = adap->phys_addr; mutex_unlock(&adap->lock); if (copy_to_user(parg, &phys_addr, sizeof(phys_addr))) return -EFAULT; return 0; } static int cec_validate_phys_addr(u16 phys_addr) { int i; if (phys_addr == CEC_PHYS_ADDR_INVALID) return 0; for (i = 0; i < 16; i += 4) if (phys_addr & (0xf << i)) break; if (i == 16) return 0; for (i += 4; i < 16; i += 4) if ((phys_addr & (0xf << i)) == 0) return -EINVAL; return 0; } static long cec_adap_s_phys_addr(struct cec_adapter *adap, struct cec_fh *fh, bool block, __u16 __user *parg) { u16 phys_addr; long err; if (!(adap->capabilities & CEC_CAP_PHYS_ADDR)) return -ENOTTY; if (copy_from_user(&phys_addr, parg, sizeof(phys_addr))) return -EFAULT; err = cec_validate_phys_addr(phys_addr); if (err) return err; mutex_lock(&adap->lock); if (cec_is_busy(adap, fh)) err = -EBUSY; else __cec_s_phys_addr(adap, phys_addr, block); mutex_unlock(&adap->lock); return err; } static long cec_adap_g_log_addrs(struct cec_adapter *adap, struct cec_log_addrs __user *parg) { struct cec_log_addrs log_addrs; mutex_lock(&adap->lock); /* * We use memcpy here instead of assignment since there is a * hole at the end of struct cec_log_addrs that an assignment * might ignore. So when we do copy_to_user() we could leak * one byte of memory. */ memcpy(&log_addrs, &adap->log_addrs, sizeof(log_addrs)); if (!adap->is_configured) memset(log_addrs.log_addr, CEC_LOG_ADDR_INVALID, sizeof(log_addrs.log_addr)); mutex_unlock(&adap->lock); if (copy_to_user(parg, &log_addrs, sizeof(log_addrs))) return -EFAULT; return 0; } static long cec_adap_s_log_addrs(struct cec_adapter *adap, struct cec_fh *fh, bool block, struct cec_log_addrs __user *parg) { struct cec_log_addrs log_addrs; long err = -EBUSY; if (!(adap->capabilities & CEC_CAP_LOG_ADDRS)) return -ENOTTY; if (copy_from_user(&log_addrs, parg, sizeof(log_addrs))) return -EFAULT; log_addrs.flags &= CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK | CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU | CEC_LOG_ADDRS_FL_CDC_ONLY; mutex_lock(&adap->lock); if (!adap->is_claiming_log_addrs && !adap->is_configuring && (!log_addrs.num_log_addrs || !adap->is_configured) && !cec_is_busy(adap, fh)) { err = __cec_s_log_addrs(adap, &log_addrs, block); if (!err) log_addrs = adap->log_addrs; } mutex_unlock(&adap->lock); if (err) return err; if (copy_to_user(parg, &log_addrs, sizeof(log_addrs))) return -EFAULT; return 0; } static long cec_adap_g_connector_info(struct cec_adapter *adap, struct cec_log_addrs __user *parg) { int ret = 0; if (!(adap->capabilities & CEC_CAP_CONNECTOR_INFO)) return -ENOTTY; mutex_lock(&adap->lock); if (copy_to_user(parg, &adap->conn_info, sizeof(adap->conn_info))) ret = -EFAULT; mutex_unlock(&adap->lock); return ret; } static long cec_transmit(struct cec_adapter *adap, struct cec_fh *fh, bool block, struct cec_msg __user *parg) { struct cec_msg msg = {}; long err = 0; if (!(adap->capabilities & CEC_CAP_TRANSMIT)) return -ENOTTY; if (copy_from_user(&msg, parg, sizeof(msg))) return -EFAULT; mutex_lock(&adap->lock); if (adap->log_addrs.num_log_addrs == 0) err = -EPERM; else if (adap->is_configuring) err = -ENONET; else if (cec_is_busy(adap, fh)) err = -EBUSY; else err = cec_transmit_msg_fh(adap, &msg, fh, block); mutex_unlock(&adap->lock); if (err) return err; if (copy_to_user(parg, &msg, sizeof(msg))) return -EFAULT; return 0; } /* Called by CEC_RECEIVE: wait for a message to arrive */ static int cec_receive_msg(struct cec_fh *fh, struct cec_msg *msg, bool block) { u32 timeout = msg->timeout; int res; do { mutex_lock(&fh->lock); /* Are there received messages queued up? */ if (fh->queued_msgs) { /* Yes, return the first one */ struct cec_msg_entry *entry = list_first_entry(&fh->msgs, struct cec_msg_entry, list); list_del(&entry->list); *msg = entry->msg; kfree(entry); fh->queued_msgs--; mutex_unlock(&fh->lock); /* restore original timeout value */ msg->timeout = timeout; return 0; } /* No, return EAGAIN in non-blocking mode or wait */ mutex_unlock(&fh->lock); /* Return when in non-blocking mode */ if (!block) return -EAGAIN; if (msg->timeout) { /* The user specified a timeout */ res = wait_event_interruptible_timeout(fh->wait, fh->queued_msgs, msecs_to_jiffies(msg->timeout)); if (res == 0) res = -ETIMEDOUT; else if (res > 0) res = 0; } else { /* Wait indefinitely */ res = wait_event_interruptible(fh->wait, fh->queued_msgs); } /* Exit on error, otherwise loop to get the new message */ } while (!res); return res; } static long cec_receive(struct cec_adapter *adap, struct cec_fh *fh, bool block, struct cec_msg __user *parg) { struct cec_msg msg = {}; long err; if (copy_from_user(&msg, parg, sizeof(msg))) return -EFAULT; err = cec_receive_msg(fh, &msg, block); if (err) return err; msg.flags = 0; if (copy_to_user(parg, &msg, sizeof(msg))) return -EFAULT; return 0; } static long cec_dqevent(struct cec_adapter *adap, struct cec_fh *fh, bool block, struct cec_event __user *parg) { struct cec_event_entry *ev = NULL; u64 ts = ~0ULL; unsigned int i; unsigned int ev_idx; long err = 0; mutex_lock(&fh->lock); while (!fh->total_queued_events && block) { mutex_unlock(&fh->lock); err = wait_event_interruptible(fh->wait, fh->total_queued_events); if (err) return err; mutex_lock(&fh->lock); } /* Find the oldest event */ for (i = 0; i < CEC_NUM_EVENTS; i++) { struct cec_event_entry *entry = list_first_entry_or_null(&fh->events[i], struct cec_event_entry, list); if (entry && entry->ev.ts <= ts) { ev = entry; ev_idx = i; ts = ev->ev.ts; } } if (!ev) { err = -EAGAIN; goto unlock; } list_del(&ev->list); if (copy_to_user(parg, &ev->ev, sizeof(ev->ev))) err = -EFAULT; if (ev_idx >= CEC_NUM_CORE_EVENTS) kfree(ev); fh->queued_events[ev_idx]--; fh->total_queued_events--; unlock: mutex_unlock(&fh->lock); return err; } static long cec_g_mode(struct cec_adapter *adap, struct cec_fh *fh, u32 __user *parg) { u32 mode = fh->mode_initiator | fh->mode_follower; if (copy_to_user(parg, &mode, sizeof(mode))) return -EFAULT; return 0; } static long cec_s_mode(struct cec_adapter *adap, struct cec_fh *fh, u32 __user *parg) { u32 mode; u8 mode_initiator; u8 mode_follower; bool send_pin_event = false; long err = 0; if (copy_from_user(&mode, parg, sizeof(mode))) return -EFAULT; if (mode & ~(CEC_MODE_INITIATOR_MSK | CEC_MODE_FOLLOWER_MSK)) { dprintk(1, "%s: invalid mode bits set\n", __func__); return -EINVAL; } mode_initiator = mode & CEC_MODE_INITIATOR_MSK; mode_follower = mode & CEC_MODE_FOLLOWER_MSK; if (mode_initiator > CEC_MODE_EXCL_INITIATOR || mode_follower > CEC_MODE_MONITOR_ALL) { dprintk(1, "%s: unknown mode\n", __func__); return -EINVAL; } if (mode_follower == CEC_MODE_MONITOR_ALL && !(adap->capabilities & CEC_CAP_MONITOR_ALL)) { dprintk(1, "%s: MONITOR_ALL not supported\n", __func__); return -EINVAL; } if (mode_follower == CEC_MODE_MONITOR_PIN && !(adap->capabilities & CEC_CAP_MONITOR_PIN)) { dprintk(1, "%s: MONITOR_PIN not supported\n", __func__); return -EINVAL; } /* Follower modes should always be able to send CEC messages */ if ((mode_initiator == CEC_MODE_NO_INITIATOR || !(adap->capabilities & CEC_CAP_TRANSMIT)) && mode_follower >= CEC_MODE_FOLLOWER && mode_follower <= CEC_MODE_EXCL_FOLLOWER_PASSTHRU) { dprintk(1, "%s: cannot transmit\n", __func__); return -EINVAL; } /* Monitor modes require CEC_MODE_NO_INITIATOR */ if (mode_initiator && mode_follower >= CEC_MODE_MONITOR_PIN) { dprintk(1, "%s: monitor modes require NO_INITIATOR\n", __func__); return -EINVAL; } /* Monitor modes require CAP_NET_ADMIN */ if (mode_follower >= CEC_MODE_MONITOR_PIN && !capable(CAP_NET_ADMIN)) return -EPERM; mutex_lock(&adap->lock); /* * You can't become exclusive follower if someone else already * has that job. */ if ((mode_follower == CEC_MODE_EXCL_FOLLOWER || mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) && adap->cec_follower && adap->cec_follower != fh) err = -EBUSY; /* * You can't become exclusive initiator if someone else already * has that job. */ if (mode_initiator == CEC_MODE_EXCL_INITIATOR && adap->cec_initiator && adap->cec_initiator != fh) err = -EBUSY; if (!err) { bool old_mon_all = fh->mode_follower == CEC_MODE_MONITOR_ALL; bool new_mon_all = mode_follower == CEC_MODE_MONITOR_ALL; if (old_mon_all != new_mon_all) { if (new_mon_all) err = cec_monitor_all_cnt_inc(adap); else cec_monitor_all_cnt_dec(adap); } } if (!err) { bool old_mon_pin = fh->mode_follower == CEC_MODE_MONITOR_PIN; bool new_mon_pin = mode_follower == CEC_MODE_MONITOR_PIN; if (old_mon_pin != new_mon_pin) { send_pin_event = new_mon_pin; if (new_mon_pin) err = cec_monitor_pin_cnt_inc(adap); else cec_monitor_pin_cnt_dec(adap); } } if (err) { mutex_unlock(&adap->lock); return err; } if (fh->mode_follower == CEC_MODE_FOLLOWER) adap->follower_cnt--; if (mode_follower == CEC_MODE_FOLLOWER) adap->follower_cnt++; if (send_pin_event) { struct cec_event ev = { .flags = CEC_EVENT_FL_INITIAL_STATE, }; ev.event = adap->cec_pin_is_high ? CEC_EVENT_PIN_CEC_HIGH : CEC_EVENT_PIN_CEC_LOW; cec_queue_event_fh(fh, &ev, 0); } if (mode_follower == CEC_MODE_EXCL_FOLLOWER || mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU) { adap->passthrough = mode_follower == CEC_MODE_EXCL_FOLLOWER_PASSTHRU; adap->cec_follower = fh; } else if (adap->cec_follower == fh) { adap->passthrough = false; adap->cec_follower = NULL; } if (mode_initiator == CEC_MODE_EXCL_INITIATOR) adap->cec_initiator = fh; else if (adap->cec_initiator == fh) adap->cec_initiator = NULL; fh->mode_initiator = mode_initiator; fh->mode_follower = mode_follower; mutex_unlock(&adap->lock); return 0; } static long cec_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct cec_fh *fh = filp->private_data; struct cec_adapter *adap = fh->adap; bool block = !(filp->f_flags & O_NONBLOCK); void __user *parg = (void __user *)arg; if (!cec_is_registered(adap)) return -ENODEV; switch (cmd) { case CEC_ADAP_G_CAPS: return cec_adap_g_caps(adap, parg); case CEC_ADAP_G_PHYS_ADDR: return cec_adap_g_phys_addr(adap, parg); case CEC_ADAP_S_PHYS_ADDR: return cec_adap_s_phys_addr(adap, fh, block, parg); case CEC_ADAP_G_LOG_ADDRS: return cec_adap_g_log_addrs(adap, parg); case CEC_ADAP_S_LOG_ADDRS: return cec_adap_s_log_addrs(adap, fh, block, parg); case CEC_ADAP_G_CONNECTOR_INFO: return cec_adap_g_connector_info(adap, parg); case CEC_TRANSMIT: return cec_transmit(adap, fh, block, parg); case CEC_RECEIVE: return cec_receive(adap, fh, block, parg); case CEC_DQEVENT: return cec_dqevent(adap, fh, block, parg); case CEC_G_MODE: return cec_g_mode(adap, fh, parg); case CEC_S_MODE: return cec_s_mode(adap, fh, parg); default: return -ENOTTY; } } static int cec_open(struct inode *inode, struct file *filp) { struct cec_devnode *devnode = container_of(inode->i_cdev, struct cec_devnode, cdev); struct cec_adapter *adap = to_cec_adapter(devnode); struct cec_fh *fh = kzalloc(sizeof(*fh), GFP_KERNEL); /* * Initial events that are automatically sent when the cec device is * opened. */ struct cec_event ev = { .event = CEC_EVENT_STATE_CHANGE, .flags = CEC_EVENT_FL_INITIAL_STATE, }; unsigned int i; int err; if (!fh) return -ENOMEM; INIT_LIST_HEAD(&fh->msgs); INIT_LIST_HEAD(&fh->xfer_list); for (i = 0; i < CEC_NUM_EVENTS; i++) INIT_LIST_HEAD(&fh->events[i]); mutex_init(&fh->lock); init_waitqueue_head(&fh->wait); fh->mode_initiator = CEC_MODE_INITIATOR; fh->adap = adap; err = cec_get_device(adap); if (err) { kfree(fh); return err; } filp->private_data = fh; /* Queue up initial state events */ ev.state_change.phys_addr = adap->phys_addr; ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; ev.state_change.have_conn_info = adap->conn_info.type != CEC_CONNECTOR_TYPE_NO_CONNECTOR; cec_queue_event_fh(fh, &ev, 0); #ifdef CONFIG_CEC_PIN if (adap->pin && adap->pin->ops->read_hpd && !adap->devnode.unregistered) { err = adap->pin->ops->read_hpd(adap); if (err >= 0) { ev.event = err ? CEC_EVENT_PIN_HPD_HIGH : CEC_EVENT_PIN_HPD_LOW; cec_queue_event_fh(fh, &ev, 0); } } if (adap->pin && adap->pin->ops->read_5v && !adap->devnode.unregistered) { err = adap->pin->ops->read_5v(adap); if (err >= 0) { ev.event = err ? CEC_EVENT_PIN_5V_HIGH : CEC_EVENT_PIN_5V_LOW; cec_queue_event_fh(fh, &ev, 0); } } #endif mutex_lock(&devnode->lock); mutex_lock(&devnode->lock_fhs); list_add(&fh->list, &devnode->fhs); mutex_unlock(&devnode->lock_fhs); mutex_unlock(&devnode->lock); return 0; } /* Override for the release function */ static int cec_release(struct inode *inode, struct file *filp) { struct cec_devnode *devnode = cec_devnode_data(filp); struct cec_adapter *adap = to_cec_adapter(devnode); struct cec_fh *fh = filp->private_data; unsigned int i; mutex_lock(&adap->lock); if (adap->cec_initiator == fh) adap->cec_initiator = NULL; if (adap->cec_follower == fh) { adap->cec_follower = NULL; adap->passthrough = false; } if (fh->mode_follower == CEC_MODE_FOLLOWER) adap->follower_cnt--; if (fh->mode_follower == CEC_MODE_MONITOR_PIN) cec_monitor_pin_cnt_dec(adap); if (fh->mode_follower == CEC_MODE_MONITOR_ALL) cec_monitor_all_cnt_dec(adap); mutex_unlock(&adap->lock); mutex_lock(&devnode->lock); mutex_lock(&devnode->lock_fhs); list_del(&fh->list); mutex_unlock(&devnode->lock_fhs); mutex_unlock(&devnode->lock); /* Unhook pending transmits from this filehandle. */ mutex_lock(&adap->lock); while (!list_empty(&fh->xfer_list)) { struct cec_data *data = list_first_entry(&fh->xfer_list, struct cec_data, xfer_list); data->blocking = false; data->fh = NULL; list_del_init(&data->xfer_list); } mutex_unlock(&adap->lock); mutex_lock(&fh->lock); while (!list_empty(&fh->msgs)) { struct cec_msg_entry *entry = list_first_entry(&fh->msgs, struct cec_msg_entry, list); list_del(&entry->list); kfree(entry); } for (i = CEC_NUM_CORE_EVENTS; i < CEC_NUM_EVENTS; i++) { while (!list_empty(&fh->events[i])) { struct cec_event_entry *entry = list_first_entry(&fh->events[i], struct cec_event_entry, list); list_del(&entry->list); kfree(entry); } } mutex_unlock(&fh->lock); kfree(fh); cec_put_device(adap); filp->private_data = NULL; return 0; } const struct file_operations cec_devnode_fops = { .owner = THIS_MODULE, .open = cec_open, .unlocked_ioctl = cec_ioctl, .compat_ioctl = cec_ioctl, .release = cec_release, .poll = cec_poll, }; |
| 18 18 18 18 10 10 10 10 10 12 12 12 12 15 10 10 10 10 15 10 12 12 12 12 6 6 6 6 6 6 6 6 6 6 6 15 15 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "send.h" #include "main.h" #include <linux/atomic.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/workqueue.h> #include "distributed-arp-table.h" #include "fragmentation.h" #include "gateway_client.h" #include "hard-interface.h" #include "log.h" #include "network-coding.h" #include "originator.h" #include "routing.h" #include "soft-interface.h" #include "translation-table.h" static void batadv_send_outstanding_bcast_packet(struct work_struct *work); /** * batadv_send_skb_packet() - send an already prepared packet * @skb: the packet to send * @hard_iface: the interface to use to send the broadcast packet * @dst_addr: the payload destination * * Send out an already prepared packet to the given neighbor or broadcast it * using the specified interface. Either hard_iface or neigh_node must be not * NULL. * If neigh_node is NULL, then the packet is broadcasted using hard_iface, * otherwise it is sent as unicast to the given neighbor. * * Regardless of the return value, the skb is consumed. * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, const u8 *dst_addr) { struct batadv_priv *bat_priv; struct ethhdr *ethhdr; int ret; bat_priv = netdev_priv(hard_iface->soft_iface); if (hard_iface->if_status != BATADV_IF_ACTIVE) goto send_skb_err; if (unlikely(!hard_iface->net_dev)) goto send_skb_err; if (!(hard_iface->net_dev->flags & IFF_UP)) { pr_warn("Interface %s is not up - can't send packet via that interface!\n", hard_iface->net_dev->name); goto send_skb_err; } /* push to the ethernet header. */ if (batadv_skb_head_push(skb, ETH_HLEN) < 0) goto send_skb_err; skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr); ether_addr_copy(ethhdr->h_dest, dst_addr); ethhdr->h_proto = htons(ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); skb->protocol = htons(ETH_P_BATMAN); skb->dev = hard_iface->net_dev; /* Save a clone of the skb to use when decoding coded packets */ batadv_nc_skb_store_for_decoding(bat_priv, skb); /* dev_queue_xmit() returns a negative result on error. However on * congestion and traffic shaping, it drops and returns NET_XMIT_DROP * (which is > 0). This will not be treated as an error. */ ret = dev_queue_xmit(skb); return net_xmit_eval(ret); send_skb_err: kfree_skb(skb); return NET_XMIT_DROP; } /** * batadv_send_broadcast_skb() - Send broadcast packet via hard interface * @skb: packet to be transmitted (with batadv header and no outer eth header) * @hard_iface: outgoing interface * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_broadcast_skb(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { return batadv_send_skb_packet(skb, hard_iface, batadv_broadcast_addr); } /** * batadv_send_unicast_skb() - Send unicast packet to neighbor * @skb: packet to be transmitted (with batadv header and no outer eth header) * @neigh: neighbor which is used as next hop to destination * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_unicast_skb(struct sk_buff *skb, struct batadv_neigh_node *neigh) { #ifdef CONFIG_BATMAN_ADV_BATMAN_V struct batadv_hardif_neigh_node *hardif_neigh; #endif int ret; ret = batadv_send_skb_packet(skb, neigh->if_incoming, neigh->addr); #ifdef CONFIG_BATMAN_ADV_BATMAN_V hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr); if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; batadv_hardif_neigh_put(hardif_neigh); #endif return ret; } /** * batadv_send_skb_to_orig() - Lookup next-hop and transmit skb. * @skb: Packet to be transmitted. * @orig_node: Final destination of the packet. * @recv_if: Interface used when receiving the packet (can be NULL). * * Looks up the best next-hop towards the passed originator and passes the * skb on for preparation of MAC header. If the packet originated from this * host, NULL can be passed as recv_if and no interface alternating is * attempted. * * Return: negative errno code on a failure, -EINPROGRESS if the skb is * buffered for later transmit or the NET_XMIT status returned by the * lower routine if the packet has been passed down. */ int batadv_send_skb_to_orig(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = orig_node->bat_priv; struct batadv_neigh_node *neigh_node; int ret; /* batadv_find_router() increases neigh_nodes refcount if found. */ neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); if (!neigh_node) { ret = -EINVAL; goto free_skb; } /* Check if the skb is too large to send in one piece and fragment * it if needed. */ if (atomic_read(&bat_priv->fragmentation) && skb->len > neigh_node->if_incoming->net_dev->mtu) { /* Fragment and send packet. */ ret = batadv_frag_send_packet(skb, orig_node, neigh_node); /* skb was consumed */ skb = NULL; goto put_neigh_node; } /* try to network code the packet, if it is received on an interface * (i.e. being forwarded). If the packet originates from this node or if * network coding fails, then send the packet as usual. */ if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) ret = -EINPROGRESS; else ret = batadv_send_unicast_skb(skb, neigh_node); /* skb was consumed */ skb = NULL; put_neigh_node: batadv_neigh_node_put(neigh_node); free_skb: kfree_skb(skb); return ret; } /** * batadv_send_skb_push_fill_unicast() - extend the buffer and initialize the * common fields for unicast packets * @skb: the skb carrying the unicast header to initialize * @hdr_size: amount of bytes to push at the beginning of the skb * @orig_node: the destination node * * Return: false if the buffer extension was not possible or true otherwise. */ static bool batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node) { struct batadv_unicast_packet *unicast_packet; u8 ttvn = (u8)atomic_read(&orig_node->last_ttvn); if (batadv_skb_head_push(skb, hdr_size) < 0) return false; unicast_packet = (struct batadv_unicast_packet *)skb->data; unicast_packet->version = BATADV_COMPAT_VERSION; /* batman packet type: unicast */ unicast_packet->packet_type = BATADV_UNICAST; /* set unicast ttl */ unicast_packet->ttl = BATADV_TTL; /* copy the destination for faster routing */ ether_addr_copy(unicast_packet->dest, orig_node->orig); /* set the destination tt version number */ unicast_packet->ttvn = ttvn; return true; } /** * batadv_send_skb_prepare_unicast() - encapsulate an skb with a unicast header * @skb: the skb containing the payload to encapsulate * @orig_node: the destination node * * Return: false if the payload could not be encapsulated or true otherwise. */ static bool batadv_send_skb_prepare_unicast(struct sk_buff *skb, struct batadv_orig_node *orig_node) { size_t uni_size = sizeof(struct batadv_unicast_packet); return batadv_send_skb_push_fill_unicast(skb, uni_size, orig_node); } /** * batadv_send_skb_prepare_unicast_4addr() - encapsulate an skb with a * unicast 4addr header * @bat_priv: the bat priv with all the soft interface information * @skb: the skb containing the payload to encapsulate * @orig: the destination node * @packet_subtype: the unicast 4addr packet subtype to use * * Return: false if the payload could not be encapsulated or true otherwise. */ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig, int packet_subtype) { struct batadv_hard_iface *primary_if; struct batadv_unicast_4addr_packet *uc_4addr_packet; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* Pull the header space and fill the unicast_packet substructure. * We can do that because the first member of the uc_4addr_packet * is of type struct unicast_packet */ if (!batadv_send_skb_push_fill_unicast(skb, sizeof(*uc_4addr_packet), orig)) goto out; uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR; ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr); uc_4addr_packet->subtype = packet_subtype; uc_4addr_packet->reserved = 0; ret = true; out: batadv_hardif_put(primary_if); return ret; } /** * batadv_send_skb_unicast() - encapsulate and send an skb via unicast * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @orig_node: the originator to send the packet to * @vid: the vid to be used to search the translation table * * Wrap the given skb into a batman-adv unicast or unicast-4addr header * depending on whether BATADV_UNICAST or BATADV_UNICAST_4ADDR was supplied * as packet_type. Then send this frame to the given orig_node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_unicast_packet *unicast_packet; struct ethhdr *ethhdr; int ret = NET_XMIT_DROP; if (!orig_node) goto out; switch (packet_type) { case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It * should never be invoked with any other packet type */ goto out; } /* skb->data might have been reallocated by * batadv_send_skb_prepare_unicast{,_4addr}() */ ethhdr = eth_hdr(skb); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route * for this client. The destination will receive this packet and will * try to reroute it because the ttvn contained in the header is less * than the current one */ if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) unicast_packet->ttvn = unicast_packet->ttvn - 1; ret = batadv_send_skb_to_orig(skb, orig_node, NULL); /* skb was consumed */ skb = NULL; out: kfree_skb(skb); return ret; } /** * batadv_send_skb_via_tt_generic() - send an skb via TT lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet * header via the translation table. Wrap the given skb into a batman-adv * unicast or unicast-4addr header depending on whether BATADV_UNICAST or * BATADV_UNICAST_4ADDR was supplied as packet_type. Then send this frame * to the according destination node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, u8 *dst_hint, unsigned short vid) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; u8 *src, *dst; int ret; src = ethhdr->h_source; dst = ethhdr->h_dest; /* if we got an hint! let's send the packet to this client (if any) */ if (dst_hint) { src = NULL; dst = dst_hint; } orig_node = batadv_transtable_search(bat_priv, src, dst, vid); ret = batadv_send_skb_unicast(bat_priv, skb, packet_type, packet_subtype, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_send_skb_via_gw() - send an skb via gateway lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @vid: the vid to be used to search the translation table * * Look up the currently selected gateway. Wrap the given skb into a batman-adv * unicast header and send this frame to this gateway node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret; orig_node = batadv_gw_get_selected_orig(bat_priv); ret = batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, BATADV_P_DATA, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. */ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet, bool dropped) { if (dropped) kfree_skb(forw_packet->skb); else consume_skb(forw_packet->skb); batadv_hardif_put(forw_packet->if_incoming); batadv_hardif_put(forw_packet->if_outgoing); if (forw_packet->queue_left) atomic_inc(forw_packet->queue_left); kfree(forw_packet); } /** * batadv_forw_packet_alloc() - allocate a forwarding packet * @if_incoming: The (optional) if_incoming to be grabbed * @if_outgoing: The (optional) if_outgoing to be grabbed * @queue_left: The (optional) queue counter to decrease * @bat_priv: The bat_priv for the mesh of this forw_packet * @skb: The raw packet this forwarding packet shall contain * * Allocates a forwarding packet and tries to get a reference to the * (optional) if_incoming, if_outgoing and queue_left. If queue_left * is NULL then bat_priv is optional, too. * * Return: An allocated forwarding packet on success, NULL otherwise. */ struct batadv_forw_packet * batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing, atomic_t *queue_left, struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_forw_packet *forw_packet; const char *qname; if (queue_left && !batadv_atomic_dec_not_zero(queue_left)) { qname = "unknown"; if (queue_left == &bat_priv->bcast_queue_left) qname = "bcast"; if (queue_left == &bat_priv->batman_queue_left) qname = "batman"; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s queue is full\n", qname); return NULL; } forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); if (!forw_packet) goto err; if (if_incoming) kref_get(&if_incoming->refcount); if (if_outgoing) kref_get(&if_outgoing->refcount); INIT_HLIST_NODE(&forw_packet->list); INIT_HLIST_NODE(&forw_packet->cleanup_list); forw_packet->skb = skb; forw_packet->queue_left = queue_left; forw_packet->if_incoming = if_incoming; forw_packet->if_outgoing = if_outgoing; forw_packet->num_packets = 0; return forw_packet; err: if (queue_left) atomic_inc(queue_left); return NULL; } /** * batadv_forw_packet_was_stolen() - check whether someone stole this packet * @forw_packet: the forwarding packet to check * * This function checks whether the given forwarding packet was claimed by * someone else for free(). * * Return: True if someone stole it, false otherwise. */ static bool batadv_forw_packet_was_stolen(struct batadv_forw_packet *forw_packet) { return !hlist_unhashed(&forw_packet->cleanup_list); } /** * batadv_forw_packet_steal() - claim a forw_packet for free() * @forw_packet: the forwarding packet to steal * @lock: a key to the store to steal from (e.g. forw_{bat,bcast}_list_lock) * * This function tries to steal a specific forw_packet from global * visibility for the purpose of getting it for free(). That means * the caller is *not* allowed to requeue it afterwards. * * Return: True if stealing was successful. False if someone else stole it * before us. */ bool batadv_forw_packet_steal(struct batadv_forw_packet *forw_packet, spinlock_t *lock) { /* did purging routine steal it earlier? */ spin_lock_bh(lock); if (batadv_forw_packet_was_stolen(forw_packet)) { spin_unlock_bh(lock); return false; } hlist_del_init(&forw_packet->list); /* Just to spot misuse of this function */ hlist_add_fake(&forw_packet->cleanup_list); spin_unlock_bh(lock); return true; } /** * batadv_forw_packet_list_steal() - claim a list of forward packets for free() * @forw_list: the to be stolen forward packets * @cleanup_list: a backup pointer, to be able to dispose the packet later * @hard_iface: the interface to steal forward packets from * * This function claims responsibility to free any forw_packet queued on the * given hard_iface. If hard_iface is NULL forwarding packets on all hard * interfaces will be claimed. * * The packets are being moved from the forw_list to the cleanup_list. This * makes it possible for already running threads to notice the claim. */ static void batadv_forw_packet_list_steal(struct hlist_head *forw_list, struct hlist_head *cleanup_list, const struct batadv_hard_iface *hard_iface) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, forw_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if (hard_iface && forw_packet->if_incoming != hard_iface && forw_packet->if_outgoing != hard_iface) continue; hlist_del(&forw_packet->list); hlist_add_head(&forw_packet->cleanup_list, cleanup_list); } } /** * batadv_forw_packet_list_free() - free a list of forward packets * @head: a list of to be freed forw_packets * * This function cancels the scheduling of any packet in the provided list, * waits for any possibly running packet forwarding thread to finish and * finally, safely frees this forward packet. * * This function might sleep. */ static void batadv_forw_packet_list_free(struct hlist_head *head) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, head, cleanup_list) { cancel_delayed_work_sync(&forw_packet->delayed_work); hlist_del(&forw_packet->cleanup_list); batadv_forw_packet_free(forw_packet, true); } } /** * batadv_forw_packet_queue() - try to queue a forwarding packet * @forw_packet: the forwarding packet to queue * @lock: a key to the store (e.g. forw_{bat,bcast}_list_lock) * @head: the shelve to queue it on (e.g. forw_{bat,bcast}_list) * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a forwarding packet. Requeuing * is prevented if the according interface is shutting down * (e.g. if batadv_forw_packet_list_steal() was called for this * packet earlier). * * Calling batadv_forw_packet_queue() after a call to * batadv_forw_packet_steal() is forbidden! * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_queue(struct batadv_forw_packet *forw_packet, spinlock_t *lock, struct hlist_head *head, unsigned long send_time) { spin_lock_bh(lock); /* did purging routine steal it from us? */ if (batadv_forw_packet_was_stolen(forw_packet)) { /* If you got it for free() without trouble, then * don't get back into the queue after stealing... */ WARN_ONCE(hlist_fake(&forw_packet->cleanup_list), "Requeuing after batadv_forw_packet_steal() not allowed!\n"); spin_unlock_bh(lock); return; } hlist_del_init(&forw_packet->list); hlist_add_head(&forw_packet->list, head); queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time - jiffies); spin_unlock_bh(lock); } /** * batadv_forw_packet_bcast_queue() - try to queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a broadcast packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_bcast_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bcast_list_lock, &bat_priv->forw_bcast_list, send_time); } /** * batadv_forw_packet_ogmv1_queue() - try to queue an OGMv1 packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue an OGMv1 packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bat_list_lock, &bat_priv->forw_bat_list, send_time); } /** * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to queue on * * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { struct batadv_forw_packet *forw_packet; unsigned long send_time = jiffies; struct sk_buff *newskb; newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) goto err; forw_packet = batadv_forw_packet_alloc(if_in, if_out, &bat_priv->bcast_queue_left, bat_priv, newskb); if (!forw_packet) goto err_packet_free; forw_packet->own = own_packet; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); send_time += delay ? delay : msecs_to_jiffies(5); batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return NETDEV_TX_OK; err_packet_free: kfree_skb(newskb); err: return NETDEV_TX_BUSY; } /** * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to forward to * * Transmits a broadcast packet on the specified interface either immediately * or if a delay is given after that. Furthermore, queues additional * retransmissions if this interface is a wireless one. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { unsigned int num_bcasts = if_out->num_bcasts; struct sk_buff *newskb; int ret = NETDEV_TX_OK; if (!delay) { newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) return NETDEV_TX_BUSY; batadv_send_broadcast_skb(newskb, if_out); num_bcasts--; } /* delayed broadcast or rebroadcasts? */ if (num_bcasts >= 1) { BATADV_SKB_CB(skb)->num_bcasts = num_bcasts; ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay, own_packet, if_in, if_out); } return ret; } /** * batadv_send_no_broadcast() - check whether (re)broadcast is necessary * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to check * @own_packet: true if it is a self-generated broadcast packet * @if_out: the outgoing interface checked and considered for (re)broadcast * * Return: False if a packet needs to be (re)broadcasted on the given interface, * true otherwise. */ static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, struct sk_buff *skb, bool own_packet, struct batadv_hard_iface *if_out) { struct batadv_hardif_neigh_node *neigh_node = NULL; struct batadv_bcast_packet *bcast_packet; u8 *orig_neigh; u8 *neigh_addr; char *type; int ret; if (!own_packet) { neigh_addr = eth_hdr(skb)->h_source; neigh_node = batadv_hardif_neigh_get(if_out, neigh_addr); } bcast_packet = (struct batadv_bcast_packet *)skb->data; orig_neigh = neigh_node ? neigh_node->orig : NULL; ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, orig_neigh); batadv_hardif_neigh_put(neigh_node); /* ok, may broadcast */ if (!ret) return false; /* no broadcast */ switch (ret) { case BATADV_HARDIF_BCAST_NORECIPIENT: type = "no neighbor"; break; case BATADV_HARDIF_BCAST_DUPFWD: type = "single neighbor is source"; break; case BATADV_HARDIF_BCAST_DUPORIG: type = "single neighbor is originator"; break; default: type = "unknown"; } batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", bcast_packet->orig, if_out->net_dev->name, type); return true; } /** * __batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the given skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if; int ret = NETDEV_TX_OK; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return NETDEV_TX_BUSY; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != bat_priv->soft_iface) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; if (batadv_send_no_broadcast(bat_priv, skb, own_packet, hard_iface)) { batadv_hardif_put(hard_iface); continue; } ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay, own_packet, primary_if, hard_iface); batadv_hardif_put(hard_iface); if (ret == NETDEV_TX_BUSY) break; } rcu_read_unlock(); batadv_hardif_put(primary_if); return ret; } /** * batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); } /** * batadv_send_bcast_packet() - send and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Consumes the provided skb. */ void batadv_send_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); consume_skb(skb); } /** * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary * @forw_packet: the forwarding packet to check * * Checks whether a given packet has any (re)transmissions left on the provided * interface. * * hard_iface may be NULL: In that case the number of transmissions this skb had * so far is compared with the maximum amount of retransmissions independent of * any interface instead. * * Return: True if (re)transmissions are left, false otherwise. */ static bool batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet) { return BATADV_SKB_CB(forw_packet->skb)->num_bcasts; } /** * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a * packet * @forw_packet: the packet to decrease the counter for */ static void batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet) { BATADV_SKB_CB(forw_packet->skb)->num_bcasts--; } /** * batadv_forw_packet_is_rebroadcast() - check packet for previous transmissions * @forw_packet: the packet to check * * Return: True if this packet was transmitted before, false otherwise. */ bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet) { unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts; return num_bcasts != forw_packet->if_outgoing->num_bcasts; } /** * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet * @work: work queue item * * Transmits a queued broadcast packet and if necessary reschedules it. */ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { unsigned long send_time = jiffies + msecs_to_jiffies(5); struct batadv_forw_packet *forw_packet; struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct sk_buff *skb1; bool dropped = false; delayed_work = to_delayed_work(work); forw_packet = container_of(delayed_work, struct batadv_forw_packet, delayed_work); bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) { dropped = true; goto out; } if (batadv_dat_drop_broadcast_packet(bat_priv, forw_packet)) { dropped = true; goto out; } /* send a copy of the saved skb */ skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); if (!skb1) goto out; batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing); batadv_forw_packet_bcasts_dec(forw_packet); if (batadv_forw_packet_bcasts_left(forw_packet)) { batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return; } out: /* do we get something for free()? */ if (batadv_forw_packet_steal(forw_packet, &bat_priv->forw_bcast_list_lock)) batadv_forw_packet_free(forw_packet, dropped); } /** * batadv_purge_outstanding_packets() - stop/purge scheduled bcast/OGMv1 packets * @bat_priv: the bat priv with all the soft interface information * @hard_iface: the hard interface to cancel and purge bcast/ogm packets on * * This method cancels and purges any broadcast and OGMv1 packet on the given * hard_iface. If hard_iface is NULL, broadcast and OGMv1 packets on all hard * interfaces will be canceled and purged. * * This function might sleep. */ void batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface) { struct hlist_head head = HLIST_HEAD_INIT; if (hard_iface) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s(): %s\n", __func__, hard_iface->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s()\n", __func__); /* claim bcast list for free() */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bcast_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bcast_list_lock); /* claim batman packet list for free() */ spin_lock_bh(&bat_priv->forw_bat_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bat_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bat_list_lock); /* then cancel or wait for packet workers to finish and free */ batadv_forw_packet_list_free(&head); } |
| 1 1 14 14 14 68 68 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2018 - 2021, 2023 - 2024 Intel Corporation */ #include <net/cfg80211.h> #include "core.h" #include "nl80211.h" #include "rdev-ops.h" static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, struct nlattr *ftmreq, struct cfg80211_pmsr_request_peer *out, struct genl_info *info) { const struct cfg80211_pmsr_capabilities *capa = rdev->wiphy.pmsr_capa; struct nlattr *tb[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1]; u32 preamble = NL80211_PREAMBLE_DMG; /* only optional in DMG */ /* validate existing data */ if (!(rdev->wiphy.pmsr_capa->ftm.bandwidths & BIT(out->chandef.width))) { NL_SET_ERR_MSG(info->extack, "FTM: unsupported bandwidth"); return -EINVAL; } /* no validation needed - was already done via nested policy */ nla_parse_nested_deprecated(tb, NL80211_PMSR_FTM_REQ_ATTR_MAX, ftmreq, NULL, NULL); if (tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE]) preamble = nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE]); /* set up values - struct is 0-initialized */ out->ftm.requested = true; switch (out->chandef.chan->band) { case NL80211_BAND_60GHZ: /* optional */ break; default: if (!tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE]) { NL_SET_ERR_MSG(info->extack, "FTM: must specify preamble"); return -EINVAL; } } if (!(capa->ftm.preambles & BIT(preamble))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE], "FTM: invalid preamble"); return -EINVAL; } out->ftm.preamble = preamble; out->ftm.burst_period = 0; if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]) out->ftm.burst_period = nla_get_u16(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD]); out->ftm.asap = !!tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP]; if (out->ftm.asap && !capa->ftm.asap) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_ASAP], "FTM: ASAP mode not supported"); return -EINVAL; } if (!out->ftm.asap && !capa->ftm.non_asap) { NL_SET_ERR_MSG(info->extack, "FTM: non-ASAP mode not supported"); return -EINVAL; } out->ftm.num_bursts_exp = 0; if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]) out->ftm.num_bursts_exp = nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP]); if (capa->ftm.max_bursts_exponent >= 0 && out->ftm.num_bursts_exp > capa->ftm.max_bursts_exponent) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_BURSTS_EXP], "FTM: max NUM_BURSTS_EXP must be set lower than the device limit"); return -EINVAL; } out->ftm.burst_duration = 15; if (tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]) out->ftm.burst_duration = nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION]); out->ftm.ftms_per_burst = 0; if (tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]) out->ftm.ftms_per_burst = nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST]); if (capa->ftm.max_ftms_per_burst && (out->ftm.ftms_per_burst > capa->ftm.max_ftms_per_burst || out->ftm.ftms_per_burst == 0)) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST], "FTM: FTMs per burst must be set lower than the device limit but non-zero"); return -EINVAL; } out->ftm.ftmr_retries = 3; if (tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]) out->ftm.ftmr_retries = nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES]); out->ftm.request_lci = !!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI]; if (out->ftm.request_lci && !capa->ftm.request_lci) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI], "FTM: LCI request not supported"); } out->ftm.request_civicloc = !!tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC]; if (out->ftm.request_civicloc && !capa->ftm.request_civicloc) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC], "FTM: civic location request not supported"); } out->ftm.trigger_based = !!tb[NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED]; if (out->ftm.trigger_based && !capa->ftm.trigger_based) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED], "FTM: trigger based ranging is not supported"); return -EINVAL; } out->ftm.non_trigger_based = !!tb[NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED]; if (out->ftm.non_trigger_based && !capa->ftm.non_trigger_based) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED], "FTM: trigger based ranging is not supported"); return -EINVAL; } if (out->ftm.trigger_based && out->ftm.non_trigger_based) { NL_SET_ERR_MSG(info->extack, "FTM: can't set both trigger based and non trigger based"); return -EINVAL; } if (out->ftm.ftms_per_burst > 31 && !out->ftm.non_trigger_based && !out->ftm.trigger_based) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST], "FTM: FTMs per burst must be set lower than 31"); return -ERANGE; } if ((out->ftm.trigger_based || out->ftm.non_trigger_based) && out->ftm.preamble != NL80211_PREAMBLE_HE) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE], "FTM: non EDCA based ranging must use HE preamble"); return -EINVAL; } out->ftm.lmr_feedback = !!tb[NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK]; if (!out->ftm.trigger_based && !out->ftm.non_trigger_based && out->ftm.lmr_feedback) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK], "FTM: LMR feedback set for EDCA based ranging"); return -EINVAL; } if (tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR]) { if (!out->ftm.non_trigger_based && !out->ftm.trigger_based) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR], "FTM: BSS color set for EDCA based ranging"); return -EINVAL; } out->ftm.bss_color = nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR]); } return 0; } static int pmsr_parse_peer(struct cfg80211_registered_device *rdev, struct nlattr *peer, struct cfg80211_pmsr_request_peer *out, struct genl_info *info) { struct nlattr *tb[NL80211_PMSR_PEER_ATTR_MAX + 1]; struct nlattr *req[NL80211_PMSR_REQ_ATTR_MAX + 1]; struct nlattr *treq; int err, rem; /* no validation needed - was already done via nested policy */ nla_parse_nested_deprecated(tb, NL80211_PMSR_PEER_ATTR_MAX, peer, NULL, NULL); if (!tb[NL80211_PMSR_PEER_ATTR_ADDR] || !tb[NL80211_PMSR_PEER_ATTR_CHAN] || !tb[NL80211_PMSR_PEER_ATTR_REQ]) { NL_SET_ERR_MSG_ATTR(info->extack, peer, "insufficient peer data"); return -EINVAL; } memcpy(out->addr, nla_data(tb[NL80211_PMSR_PEER_ATTR_ADDR]), ETH_ALEN); /* reuse info->attrs */ memset(info->attrs, 0, sizeof(*info->attrs) * (NL80211_ATTR_MAX + 1)); err = nla_parse_nested_deprecated(info->attrs, NL80211_ATTR_MAX, tb[NL80211_PMSR_PEER_ATTR_CHAN], NULL, info->extack); if (err) return err; err = nl80211_parse_chandef(rdev, info, &out->chandef); if (err) return err; /* no validation needed - was already done via nested policy */ nla_parse_nested_deprecated(req, NL80211_PMSR_REQ_ATTR_MAX, tb[NL80211_PMSR_PEER_ATTR_REQ], NULL, NULL); if (!req[NL80211_PMSR_REQ_ATTR_DATA]) { NL_SET_ERR_MSG_ATTR(info->extack, tb[NL80211_PMSR_PEER_ATTR_REQ], "missing request type/data"); return -EINVAL; } if (req[NL80211_PMSR_REQ_ATTR_GET_AP_TSF]) out->report_ap_tsf = true; if (out->report_ap_tsf && !rdev->wiphy.pmsr_capa->report_ap_tsf) { NL_SET_ERR_MSG_ATTR(info->extack, req[NL80211_PMSR_REQ_ATTR_GET_AP_TSF], "reporting AP TSF is not supported"); return -EINVAL; } nla_for_each_nested(treq, req[NL80211_PMSR_REQ_ATTR_DATA], rem) { switch (nla_type(treq)) { case NL80211_PMSR_TYPE_FTM: err = pmsr_parse_ftm(rdev, treq, out, info); break; default: NL_SET_ERR_MSG_ATTR(info->extack, treq, "unsupported measurement type"); err = -EINVAL; } } if (err) return err; return 0; } int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) { struct nlattr *reqattr = info->attrs[NL80211_ATTR_PEER_MEASUREMENTS]; struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct wireless_dev *wdev = info->user_ptr[1]; struct cfg80211_pmsr_request *req; struct nlattr *peers, *peer; int count, rem, err, idx; if (!rdev->wiphy.pmsr_capa) return -EOPNOTSUPP; if (!reqattr) return -EINVAL; peers = nla_find(nla_data(reqattr), nla_len(reqattr), NL80211_PMSR_ATTR_PEERS); if (!peers) return -EINVAL; count = 0; nla_for_each_nested(peer, peers, rem) { count++; if (count > rdev->wiphy.pmsr_capa->max_peers) { NL_SET_ERR_MSG_ATTR(info->extack, peer, "Too many peers used"); return -EINVAL; } } req = kzalloc(struct_size(req, peers, count), GFP_KERNEL); if (!req) return -ENOMEM; req->n_peers = count; if (info->attrs[NL80211_ATTR_TIMEOUT]) req->timeout = nla_get_u32(info->attrs[NL80211_ATTR_TIMEOUT]); if (info->attrs[NL80211_ATTR_MAC]) { if (!rdev->wiphy.pmsr_capa->randomize_mac_addr) { NL_SET_ERR_MSG_ATTR(info->extack, info->attrs[NL80211_ATTR_MAC], "device cannot randomize MAC address"); err = -EINVAL; goto out_err; } err = nl80211_parse_random_mac(info->attrs, req->mac_addr, req->mac_addr_mask); if (err) goto out_err; } else { memcpy(req->mac_addr, wdev_address(wdev), ETH_ALEN); eth_broadcast_addr(req->mac_addr_mask); } idx = 0; nla_for_each_nested(peer, peers, rem) { /* NB: this reuses info->attrs, but we no longer need it */ err = pmsr_parse_peer(rdev, peer, &req->peers[idx], info); if (err) goto out_err; idx++; } req->cookie = cfg80211_assign_cookie(rdev); req->nl_portid = info->snd_portid; err = rdev_start_pmsr(rdev, wdev, req); if (err) goto out_err; list_add_tail(&req->list, &wdev->pmsr_list); nl_set_extack_cookie_u64(info->extack, req->cookie); return 0; out_err: kfree(req); return err; } void cfg80211_pmsr_complete(struct wireless_dev *wdev, struct cfg80211_pmsr_request *req, gfp_t gfp) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmsr_request *tmp, *prev, *to_free = NULL; struct sk_buff *msg; void *hdr; trace_cfg80211_pmsr_complete(wdev->wiphy, wdev, req->cookie); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) goto free_request; hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PEER_MEASUREMENT_COMPLETE); if (!hdr) goto free_msg; if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD)) goto free_msg; if (nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, req->cookie, NL80211_ATTR_PAD)) goto free_msg; genlmsg_end(msg, hdr); genlmsg_unicast(wiphy_net(wdev->wiphy), msg, req->nl_portid); goto free_request; free_msg: nlmsg_free(msg); free_request: spin_lock_bh(&wdev->pmsr_lock); /* * cfg80211_pmsr_process_abort() may have already moved this request * to the free list, and will free it later. In this case, don't free * it here. */ list_for_each_entry_safe(tmp, prev, &wdev->pmsr_list, list) { if (tmp == req) { list_del(&req->list); to_free = req; break; } } spin_unlock_bh(&wdev->pmsr_lock); kfree(to_free); } EXPORT_SYMBOL_GPL(cfg80211_pmsr_complete); static int nl80211_pmsr_send_ftm_res(struct sk_buff *msg, struct cfg80211_pmsr_result *res) { if (res->status == NL80211_PMSR_STATUS_FAILURE) { if (nla_put_u32(msg, NL80211_PMSR_FTM_RESP_ATTR_FAIL_REASON, res->ftm.failure_reason)) goto error; if (res->ftm.failure_reason == NL80211_PMSR_FTM_FAILURE_PEER_BUSY && res->ftm.busy_retry_time && nla_put_u32(msg, NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME, res->ftm.busy_retry_time)) goto error; return 0; } #define PUT(tp, attr, val) \ do { \ if (nla_put_##tp(msg, \ NL80211_PMSR_FTM_RESP_ATTR_##attr, \ res->ftm.val)) \ goto error; \ } while (0) #define PUTOPT(tp, attr, val) \ do { \ if (res->ftm.val##_valid) \ PUT(tp, attr, val); \ } while (0) #define PUT_U64(attr, val) \ do { \ if (nla_put_u64_64bit(msg, \ NL80211_PMSR_FTM_RESP_ATTR_##attr,\ res->ftm.val, \ NL80211_PMSR_FTM_RESP_ATTR_PAD)) \ goto error; \ } while (0) #define PUTOPT_U64(attr, val) \ do { \ if (res->ftm.val##_valid) \ PUT_U64(attr, val); \ } while (0) if (res->ftm.burst_index >= 0) PUT(u32, BURST_INDEX, burst_index); PUTOPT(u32, NUM_FTMR_ATTEMPTS, num_ftmr_attempts); PUTOPT(u32, NUM_FTMR_SUCCESSES, num_ftmr_successes); PUT(u8, NUM_BURSTS_EXP, num_bursts_exp); PUT(u8, BURST_DURATION, burst_duration); PUT(u8, FTMS_PER_BURST, ftms_per_burst); PUTOPT(s32, RSSI_AVG, rssi_avg); PUTOPT(s32, RSSI_SPREAD, rssi_spread); if (res->ftm.tx_rate_valid && !nl80211_put_sta_rate(msg, &res->ftm.tx_rate, NL80211_PMSR_FTM_RESP_ATTR_TX_RATE)) goto error; if (res->ftm.rx_rate_valid && !nl80211_put_sta_rate(msg, &res->ftm.rx_rate, NL80211_PMSR_FTM_RESP_ATTR_RX_RATE)) goto error; PUTOPT_U64(RTT_AVG, rtt_avg); PUTOPT_U64(RTT_VARIANCE, rtt_variance); PUTOPT_U64(RTT_SPREAD, rtt_spread); PUTOPT_U64(DIST_AVG, dist_avg); PUTOPT_U64(DIST_VARIANCE, dist_variance); PUTOPT_U64(DIST_SPREAD, dist_spread); if (res->ftm.lci && res->ftm.lci_len && nla_put(msg, NL80211_PMSR_FTM_RESP_ATTR_LCI, res->ftm.lci_len, res->ftm.lci)) goto error; if (res->ftm.civicloc && res->ftm.civicloc_len && nla_put(msg, NL80211_PMSR_FTM_RESP_ATTR_CIVICLOC, res->ftm.civicloc_len, res->ftm.civicloc)) goto error; #undef PUT #undef PUTOPT #undef PUT_U64 #undef PUTOPT_U64 return 0; error: return -ENOSPC; } static int nl80211_pmsr_send_result(struct sk_buff *msg, struct cfg80211_pmsr_result *res) { struct nlattr *pmsr, *peers, *peer, *resp, *data, *typedata; pmsr = nla_nest_start_noflag(msg, NL80211_ATTR_PEER_MEASUREMENTS); if (!pmsr) goto error; peers = nla_nest_start_noflag(msg, NL80211_PMSR_ATTR_PEERS); if (!peers) goto error; peer = nla_nest_start_noflag(msg, 1); if (!peer) goto error; if (nla_put(msg, NL80211_PMSR_PEER_ATTR_ADDR, ETH_ALEN, res->addr)) goto error; resp = nla_nest_start_noflag(msg, NL80211_PMSR_PEER_ATTR_RESP); if (!resp) goto error; if (nla_put_u32(msg, NL80211_PMSR_RESP_ATTR_STATUS, res->status) || nla_put_u64_64bit(msg, NL80211_PMSR_RESP_ATTR_HOST_TIME, res->host_time, NL80211_PMSR_RESP_ATTR_PAD)) goto error; if (res->ap_tsf_valid && nla_put_u64_64bit(msg, NL80211_PMSR_RESP_ATTR_AP_TSF, res->ap_tsf, NL80211_PMSR_RESP_ATTR_PAD)) goto error; if (res->final && nla_put_flag(msg, NL80211_PMSR_RESP_ATTR_FINAL)) goto error; data = nla_nest_start_noflag(msg, NL80211_PMSR_RESP_ATTR_DATA); if (!data) goto error; typedata = nla_nest_start_noflag(msg, res->type); if (!typedata) goto error; switch (res->type) { case NL80211_PMSR_TYPE_FTM: if (nl80211_pmsr_send_ftm_res(msg, res)) goto error; break; default: WARN_ON(1); } nla_nest_end(msg, typedata); nla_nest_end(msg, data); nla_nest_end(msg, resp); nla_nest_end(msg, peer); nla_nest_end(msg, peers); nla_nest_end(msg, pmsr); return 0; error: return -ENOSPC; } void cfg80211_pmsr_report(struct wireless_dev *wdev, struct cfg80211_pmsr_request *req, struct cfg80211_pmsr_result *result, gfp_t gfp) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct sk_buff *msg; void *hdr; int err; trace_cfg80211_pmsr_report(wdev->wiphy, wdev, req->cookie, result->addr); /* * Currently, only variable items are LCI and civic location, * both of which are reasonably short so we don't need to * worry about them here for the allocation. */ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!msg) return; hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PEER_MEASUREMENT_RESULT); if (!hdr) goto free; if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD)) goto free; if (nla_put_u64_64bit(msg, NL80211_ATTR_COOKIE, req->cookie, NL80211_ATTR_PAD)) goto free; err = nl80211_pmsr_send_result(msg, result); if (err) { pr_err_ratelimited("peer measurement result: message didn't fit!"); goto free; } genlmsg_end(msg, hdr); genlmsg_unicast(wiphy_net(wdev->wiphy), msg, req->nl_portid); return; free: nlmsg_free(msg); } EXPORT_SYMBOL_GPL(cfg80211_pmsr_report); static void cfg80211_pmsr_process_abort(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmsr_request *req, *tmp; LIST_HEAD(free_list); lockdep_assert_wiphy(wdev->wiphy); spin_lock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &wdev->pmsr_list, list) { if (req->nl_portid) continue; list_move_tail(&req->list, &free_list); } spin_unlock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &free_list, list) { rdev_abort_pmsr(rdev, wdev, req); kfree(req); } } void cfg80211_pmsr_free_wk(struct work_struct *work) { struct wireless_dev *wdev = container_of(work, struct wireless_dev, pmsr_free_wk); guard(wiphy)(wdev->wiphy); cfg80211_pmsr_process_abort(wdev); } void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) { struct cfg80211_pmsr_request *req; bool found = false; spin_lock_bh(&wdev->pmsr_lock); list_for_each_entry(req, &wdev->pmsr_list, list) { found = true; req->nl_portid = 0; } spin_unlock_bh(&wdev->pmsr_lock); if (found) cfg80211_pmsr_process_abort(wdev); WARN_ON(!list_empty(&wdev->pmsr_list)); } void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid) { struct cfg80211_pmsr_request *req; spin_lock_bh(&wdev->pmsr_lock); list_for_each_entry(req, &wdev->pmsr_list, list) { if (req->nl_portid == portid) { req->nl_portid = 0; schedule_work(&wdev->pmsr_free_wk); } } spin_unlock_bh(&wdev->pmsr_lock); } |
| 54 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 7 2 4 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/compaction.c * * Memory compaction for the reduction of external fragmentation. Note that * this heavily depends upon page migration to do all the real heavy * lifting * * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie> */ #include <linux/cpu.h> #include <linux/swap.h> #include <linux/migrate.h> #include <linux/compaction.h> #include <linux/mm_inline.h> #include <linux/sched/signal.h> #include <linux/backing-dev.h> #include <linux/sysctl.h> #include <linux/sysfs.h> #include <linux/page-isolation.h> #include <linux/kasan.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/page_owner.h> #include <linux/psi.h> #include <linux/cpuset.h> #include "internal.h" #ifdef CONFIG_COMPACTION /* * Fragmentation score check interval for proactive compaction purposes. */ #define HPAGE_FRAG_CHECK_INTERVAL_MSEC (500) static inline void count_compact_event(enum vm_event_item item) { count_vm_event(item); } static inline void count_compact_events(enum vm_event_item item, long delta) { count_vm_events(item, delta); } /* * order == -1 is expected when compacting proactively via * 1. /proc/sys/vm/compact_memory * 2. /sys/devices/system/node/nodex/compact * 3. /proc/sys/vm/compaction_proactiveness */ static inline bool is_via_compact_memory(int order) { return order == -1; } #else #define count_compact_event(item) do { } while (0) #define count_compact_events(item, delta) do { } while (0) static inline bool is_via_compact_memory(int order) { return false; } #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA #define CREATE_TRACE_POINTS #include <trace/events/compaction.h> #define block_start_pfn(pfn, order) round_down(pfn, 1UL << (order)) #define block_end_pfn(pfn, order) ALIGN((pfn) + 1, 1UL << (order)) /* * Page order with-respect-to which proactive compaction * calculates external fragmentation, which is used as * the "fragmentation score" of a node/zone. */ #if defined CONFIG_TRANSPARENT_HUGEPAGE #define COMPACTION_HPAGE_ORDER HPAGE_PMD_ORDER #elif defined CONFIG_HUGETLBFS #define COMPACTION_HPAGE_ORDER HUGETLB_PAGE_ORDER #else #define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT) #endif static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags) { post_alloc_hook(page, order, __GFP_MOVABLE); set_page_refcounted(page); return page; } #define mark_allocated(...) alloc_hooks(mark_allocated_noprof(__VA_ARGS__)) static unsigned long release_free_list(struct list_head *freepages) { int order; unsigned long high_pfn = 0; for (order = 0; order < NR_PAGE_ORDERS; order++) { struct page *page, *next; list_for_each_entry_safe(page, next, &freepages[order], lru) { unsigned long pfn = page_to_pfn(page); list_del(&page->lru); /* * Convert free pages into post allocation pages, so * that we can free them via __free_page. */ mark_allocated(page, order, __GFP_MOVABLE); __free_pages(page, order); if (pfn > high_pfn) high_pfn = pfn; } } return high_pfn; } #ifdef CONFIG_COMPACTION bool PageMovable(struct page *page) { const struct movable_operations *mops; VM_BUG_ON_PAGE(!PageLocked(page), page); if (!__PageMovable(page)) return false; mops = page_movable_ops(page); if (mops) return true; return false; } void __SetPageMovable(struct page *page, const struct movable_operations *mops) { VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE((unsigned long)mops & PAGE_MAPPING_MOVABLE, page); page->mapping = (void *)((unsigned long)mops | PAGE_MAPPING_MOVABLE); } EXPORT_SYMBOL(__SetPageMovable); void __ClearPageMovable(struct page *page) { VM_BUG_ON_PAGE(!PageMovable(page), page); /* * This page still has the type of a movable page, but it's * actually not movable any more. */ page->mapping = (void *)PAGE_MAPPING_MOVABLE; } EXPORT_SYMBOL(__ClearPageMovable); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 /* * Compaction is deferred when compaction fails to result in a page * allocation success. 1 << compact_defer_shift, compactions are skipped up * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT */ static void defer_compaction(struct zone *zone, int order) { zone->compact_considered = 0; zone->compact_defer_shift++; if (order < zone->compact_order_failed) zone->compact_order_failed = order; if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; trace_mm_compaction_defer_compaction(zone, order); } /* Returns true if compaction should be skipped this time */ static bool compaction_deferred(struct zone *zone, int order) { unsigned long defer_limit = 1UL << zone->compact_defer_shift; if (order < zone->compact_order_failed) return false; /* Avoid possible overflow */ if (++zone->compact_considered >= defer_limit) { zone->compact_considered = defer_limit; return false; } trace_mm_compaction_deferred(zone, order); return true; } /* * Update defer tracking counters after successful compaction of given order, * which means an allocation either succeeded (alloc_success == true) or is * expected to succeed. */ void compaction_defer_reset(struct zone *zone, int order, bool alloc_success) { if (alloc_success) { zone->compact_considered = 0; zone->compact_defer_shift = 0; } if (order >= zone->compact_order_failed) zone->compact_order_failed = order + 1; trace_mm_compaction_defer_reset(zone, order); } /* Returns true if restarting compaction after many failures */ static bool compaction_restarting(struct zone *zone, int order) { if (order < zone->compact_order_failed) return false; return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && zone->compact_considered >= 1UL << zone->compact_defer_shift; } /* Returns true if the pageblock should be scanned for pages to isolate. */ static inline bool isolation_suitable(struct compact_control *cc, struct page *page) { if (cc->ignore_skip_hint) return true; return !get_pageblock_skip(page); } static void reset_cached_positions(struct zone *zone) { zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; zone->compact_cached_free_pfn = pageblock_start_pfn(zone_end_pfn(zone) - 1); } #ifdef CONFIG_SPARSEMEM /* * If the PFN falls into an offline section, return the start PFN of the * next online section. If the PFN falls into an online section or if * there is no next online section, return 0. */ static unsigned long skip_offline_sections(unsigned long start_pfn) { unsigned long start_nr = pfn_to_section_nr(start_pfn); if (online_section_nr(start_nr)) return 0; while (++start_nr <= __highest_present_section_nr) { if (online_section_nr(start_nr)) return section_nr_to_pfn(start_nr); } return 0; } /* * If the PFN falls into an offline section, return the end PFN of the * next online section in reverse. If the PFN falls into an online section * or if there is no next online section in reverse, return 0. */ static unsigned long skip_offline_sections_reverse(unsigned long start_pfn) { unsigned long start_nr = pfn_to_section_nr(start_pfn); if (!start_nr || online_section_nr(start_nr)) return 0; while (start_nr-- > 0) { if (online_section_nr(start_nr)) return section_nr_to_pfn(start_nr) + PAGES_PER_SECTION; } return 0; } #else static unsigned long skip_offline_sections(unsigned long start_pfn) { return 0; } static unsigned long skip_offline_sections_reverse(unsigned long start_pfn) { return 0; } #endif /* * Compound pages of >= pageblock_order should consistently be skipped until * released. It is always pointless to compact pages of such order (if they are * migratable), and the pageblocks they occupy cannot contain any free pages. */ static bool pageblock_skip_persistent(struct page *page) { if (!PageCompound(page)) return false; page = compound_head(page); if (compound_order(page) >= pageblock_order) return true; return false; } static bool __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, bool check_target) { struct page *page = pfn_to_online_page(pfn); struct page *block_page; struct page *end_page; unsigned long block_pfn; if (!page) return false; if (zone != page_zone(page)) return false; if (pageblock_skip_persistent(page)) return false; /* * If skip is already cleared do no further checking once the * restart points have been set. */ if (check_source && check_target && !get_pageblock_skip(page)) return true; /* * If clearing skip for the target scanner, do not select a * non-movable pageblock as the starting point. */ if (!check_source && check_target && get_pageblock_migratetype(page) != MIGRATE_MOVABLE) return false; /* Ensure the start of the pageblock or zone is online and valid */ block_pfn = pageblock_start_pfn(pfn); block_pfn = max(block_pfn, zone->zone_start_pfn); block_page = pfn_to_online_page(block_pfn); if (block_page) { page = block_page; pfn = block_pfn; } /* Ensure the end of the pageblock or zone is online and valid */ block_pfn = pageblock_end_pfn(pfn) - 1; block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); end_page = pfn_to_online_page(block_pfn); if (!end_page) return false; /* * Only clear the hint if a sample indicates there is either a * free page or an LRU page in the block. One or other condition * is necessary for the block to be a migration source/target. */ do { if (check_source && PageLRU(page)) { clear_pageblock_skip(page); return true; } if (check_target && PageBuddy(page)) { clear_pageblock_skip(page); return true; } page += (1 << PAGE_ALLOC_COSTLY_ORDER); } while (page <= end_page); return false; } /* * This function is called to clear all cached information on pageblocks that * should be skipped for page isolation when the migrate and free page scanner * meet. */ static void __reset_isolation_suitable(struct zone *zone) { unsigned long migrate_pfn = zone->zone_start_pfn; unsigned long free_pfn = zone_end_pfn(zone) - 1; unsigned long reset_migrate = free_pfn; unsigned long reset_free = migrate_pfn; bool source_set = false; bool free_set = false; /* Only flush if a full compaction finished recently */ if (!zone->compact_blockskip_flush) return; zone->compact_blockskip_flush = false; /* * Walk the zone and update pageblock skip information. Source looks * for PageLRU while target looks for PageBuddy. When the scanner * is found, both PageBuddy and PageLRU are checked as the pageblock * is suitable as both source and target. */ for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages, free_pfn -= pageblock_nr_pages) { cond_resched(); /* Update the migrate PFN */ if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) && migrate_pfn < reset_migrate) { source_set = true; reset_migrate = migrate_pfn; zone->compact_init_migrate_pfn = reset_migrate; zone->compact_cached_migrate_pfn[0] = reset_migrate; zone->compact_cached_migrate_pfn[1] = reset_migrate; } /* Update the free PFN */ if (__reset_isolation_pfn(zone, free_pfn, free_set, true) && free_pfn > reset_free) { free_set = true; reset_free = free_pfn; zone->compact_init_free_pfn = reset_free; zone->compact_cached_free_pfn = reset_free; } } /* Leave no distance if no suitable block was reset */ if (reset_migrate >= reset_free) { zone->compact_cached_migrate_pfn[0] = migrate_pfn; zone->compact_cached_migrate_pfn[1] = migrate_pfn; zone->compact_cached_free_pfn = free_pfn; } } void reset_isolation_suitable(pg_data_t *pgdat) { int zoneid; for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { struct zone *zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; __reset_isolation_suitable(zone); } } /* * Sets the pageblock skip bit if it was clear. Note that this is a hint as * locks are not required for read/writers. Returns true if it was already set. */ static bool test_and_set_skip(struct compact_control *cc, struct page *page) { bool skip; /* Do not update if skip hint is being ignored */ if (cc->ignore_skip_hint) return false; skip = get_pageblock_skip(page); if (!skip && !cc->no_set_skip_hint) set_pageblock_skip(page); return skip; } static void update_cached_migrate(struct compact_control *cc, unsigned long pfn) { struct zone *zone = cc->zone; /* Set for isolation rather than compaction */ if (cc->no_set_skip_hint) return; pfn = pageblock_end_pfn(pfn); /* Update where async and sync compaction should restart */ if (pfn > zone->compact_cached_migrate_pfn[0]) zone->compact_cached_migrate_pfn[0] = pfn; if (cc->mode != MIGRATE_ASYNC && pfn > zone->compact_cached_migrate_pfn[1]) zone->compact_cached_migrate_pfn[1] = pfn; } /* * If no pages were isolated then mark this pageblock to be skipped in the * future. The information is later cleared by __reset_isolation_suitable(). */ static void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long pfn) { struct zone *zone = cc->zone; if (cc->no_set_skip_hint) return; set_pageblock_skip(page); if (pfn < zone->compact_cached_free_pfn) zone->compact_cached_free_pfn = pfn; } #else static inline bool isolation_suitable(struct compact_control *cc, struct page *page) { return true; } static inline bool pageblock_skip_persistent(struct page *page) { return false; } static inline void update_pageblock_skip(struct compact_control *cc, struct page *page, unsigned long pfn) { } static void update_cached_migrate(struct compact_control *cc, unsigned long pfn) { } static bool test_and_set_skip(struct compact_control *cc, struct page *page) { return false; } #endif /* CONFIG_COMPACTION */ /* * Compaction requires the taking of some coarse locks that are potentially * very heavily contended. For async compaction, trylock and record if the * lock is contended. The lock will still be acquired but compaction will * abort when the current block is finished regardless of success rate. * Sync compaction acquires the lock. * * Always returns true which makes it easier to track lock state in callers. */ static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags, struct compact_control *cc) __acquires(lock) { /* Track if the lock is contended in async mode */ if (cc->mode == MIGRATE_ASYNC && !cc->contended) { if (spin_trylock_irqsave(lock, *flags)) return true; cc->contended = true; } spin_lock_irqsave(lock, *flags); return true; } /* * Compaction requires the taking of some coarse locks that are potentially * very heavily contended. The lock should be periodically unlocked to avoid * having disabled IRQs for a long time, even when there is nobody waiting on * the lock. It might also be that allowing the IRQs will result in * need_resched() becoming true. If scheduling is needed, compaction schedules. * Either compaction type will also abort if a fatal signal is pending. * In either case if the lock was locked, it is dropped and not regained. * * Returns true if compaction should abort due to fatal signal pending. * Returns false when compaction can continue. */ static bool compact_unlock_should_abort(spinlock_t *lock, unsigned long flags, bool *locked, struct compact_control *cc) { if (*locked) { spin_unlock_irqrestore(lock, flags); *locked = false; } if (fatal_signal_pending(current)) { cc->contended = true; return true; } cond_resched(); return false; } /* * Isolate free pages onto a private freelist. If @strict is true, will abort * returning 0 on any invalid PFNs or non-free pages inside of the pageblock * (even though it may still end up isolating some pages). */ static unsigned long isolate_freepages_block(struct compact_control *cc, unsigned long *start_pfn, unsigned long end_pfn, struct list_head *freelist, unsigned int stride, bool strict) { int nr_scanned = 0, total_isolated = 0; struct page *page; unsigned long flags = 0; bool locked = false; unsigned long blockpfn = *start_pfn; unsigned int order; /* Strict mode is for isolation, speed is secondary */ if (strict) stride = 1; page = pfn_to_page(blockpfn); /* Isolate free pages. */ for (; blockpfn < end_pfn; blockpfn += stride, page += stride) { int isolated; /* * Periodically drop the lock (if held) regardless of its * contention, to give chance to IRQs. Abort if fatal signal * pending. */ if (!(blockpfn % COMPACT_CLUSTER_MAX) && compact_unlock_should_abort(&cc->zone->lock, flags, &locked, cc)) break; nr_scanned++; /* * For compound pages such as THP and hugetlbfs, we can save * potentially a lot of iterations if we skip them at once. * The check is racy, but we can consider only valid values * and the only danger is skipping too much. */ if (PageCompound(page)) { const unsigned int order = compound_order(page); if ((order <= MAX_PAGE_ORDER) && (blockpfn + (1UL << order) <= end_pfn)) { blockpfn += (1UL << order) - 1; page += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } goto isolate_fail; } if (!PageBuddy(page)) goto isolate_fail; /* If we already hold the lock, we can skip some rechecking. */ if (!locked) { locked = compact_lock_irqsave(&cc->zone->lock, &flags, cc); /* Recheck this is a buddy page under lock */ if (!PageBuddy(page)) goto isolate_fail; } /* Found a free page, will break it into order-0 pages */ order = buddy_order(page); isolated = __isolate_free_page(page, order); if (!isolated) break; set_page_private(page, order); nr_scanned += isolated - 1; total_isolated += isolated; cc->nr_freepages += isolated; list_add_tail(&page->lru, &freelist[order]); if (!strict && cc->nr_migratepages <= cc->nr_freepages) { blockpfn += isolated; break; } /* Advance to the end of split page */ blockpfn += isolated - 1; page += isolated - 1; continue; isolate_fail: if (strict) break; } if (locked) spin_unlock_irqrestore(&cc->zone->lock, flags); /* * Be careful to not go outside of the pageblock. */ if (unlikely(blockpfn > end_pfn)) blockpfn = end_pfn; trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn, nr_scanned, total_isolated); /* Record how far we have got within the block */ *start_pfn = blockpfn; /* * If strict isolation is requested by CMA then check that all the * pages requested were isolated. If there were any failures, 0 is * returned and CMA will fail. */ if (strict && blockpfn < end_pfn) total_isolated = 0; cc->total_free_scanned += nr_scanned; if (total_isolated) count_compact_events(COMPACTISOLATED, total_isolated); return total_isolated; } /** * isolate_freepages_range() - isolate free pages. * @cc: Compaction control structure. * @start_pfn: The first PFN to start isolating. * @end_pfn: The one-past-last PFN. * * Non-free pages, invalid PFNs, or zone boundaries within the * [start_pfn, end_pfn) range are considered errors, cause function to * undo its actions and return zero. cc->freepages[] are empty. * * Otherwise, function returns one-past-the-last PFN of isolated page * (which may be greater then end_pfn if end fell in a middle of * a free page). cc->freepages[] contain free pages isolated. */ unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long isolated, pfn, block_start_pfn, block_end_pfn; int order; for (order = 0; order < NR_PAGE_ORDERS; order++) INIT_LIST_HEAD(&cc->freepages[order]); pfn = start_pfn; block_start_pfn = pageblock_start_pfn(pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = pageblock_end_pfn(pfn); for (; pfn < end_pfn; pfn += isolated, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { /* Protect pfn from changing by isolate_freepages_block */ unsigned long isolate_start_pfn = pfn; /* * pfn could pass the block_end_pfn if isolated freepage * is more than pageblock order. In this case, we adjust * scanning range to right one. */ if (pfn >= block_end_pfn) { block_start_pfn = pageblock_start_pfn(pfn); block_end_pfn = pageblock_end_pfn(pfn); } block_end_pfn = min(block_end_pfn, end_pfn); if (!pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone)) break; isolated = isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, cc->freepages, 0, true); /* * In strict mode, isolate_freepages_block() returns 0 if * there are any holes in the block (ie. invalid PFNs or * non-free pages). */ if (!isolated) break; /* * If we managed to isolate pages, it is always (1 << n) * * pageblock_nr_pages for some non-negative n. (Max order * page may span two pageblocks). */ } if (pfn < end_pfn) { /* Loop terminated early, cleanup. */ release_free_list(cc->freepages); return 0; } /* We don't use freelists for anything. */ return pfn; } /* Similar to reclaim, but different enough that they don't share logic */ static bool too_many_isolated(struct compact_control *cc) { pg_data_t *pgdat = cc->zone->zone_pgdat; bool too_many; unsigned long active, inactive, isolated; inactive = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_ANON); active = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_FILE) + node_page_state(pgdat, NR_ISOLATED_ANON); /* * Allow GFP_NOFS to isolate past the limit set for regular * compaction runs. This prevents an ABBA deadlock when other * compactors have already isolated to the limit, but are * blocked on filesystem locks held by the GFP_NOFS thread. */ if (cc->gfp_mask & __GFP_FS) { inactive >>= 3; active >>= 3; } too_many = isolated > (inactive + active) / 2; if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /** * skip_isolation_on_order() - determine when to skip folio isolation based on * folio order and compaction target order * @order: to-be-isolated folio order * @target_order: compaction target order * * This avoids unnecessary folio isolations during compaction. */ static bool skip_isolation_on_order(int order, int target_order) { /* * Unless we are performing global compaction (i.e., * is_via_compact_memory), skip any folios that are larger than the * target order: we wouldn't be here if we'd have a free folio with * the desired target_order, so migrating this folio would likely fail * later. */ if (!is_via_compact_memory(target_order) && order >= target_order) return true; /* * We limit memory compaction to pageblocks and won't try * creating free blocks of memory that are larger than that. */ return order >= pageblock_order; } /** * isolate_migratepages_block() - isolate all migrate-able pages within * a single pageblock * @cc: Compaction control structure. * @low_pfn: The first PFN to isolate * @end_pfn: The one-past-the-last PFN to isolate, within same pageblock * @mode: Isolation mode to be used. * * Isolate all pages that can be migrated from the range specified by * [low_pfn, end_pfn). The range is expected to be within same pageblock. * Returns errno, like -EAGAIN or -EINTR in case e.g signal pending or congestion, * -ENOMEM in case we could not allocate a page, or 0. * cc->migrate_pfn will contain the next pfn to scan. * * The pages are isolated on cc->migratepages list (not required to be empty), * and cc->nr_migratepages is updated accordingly. */ static int isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn, isolate_mode_t mode) { pg_data_t *pgdat = cc->zone->zone_pgdat; unsigned long nr_scanned = 0, nr_isolated = 0; struct lruvec *lruvec; unsigned long flags = 0; struct lruvec *locked = NULL; struct folio *folio = NULL; struct page *page = NULL, *valid_page = NULL; struct address_space *mapping; unsigned long start_pfn = low_pfn; bool skip_on_failure = false; unsigned long next_skip_pfn = 0; bool skip_updated = false; int ret = 0; cc->migrate_pfn = low_pfn; /* * Ensure that there are not too many pages isolated from the LRU * list by either parallel reclaimers or compaction. If there are, * delay for some time until fewer pages are isolated */ while (unlikely(too_many_isolated(cc))) { /* stop isolation if there are still pages not migrated */ if (cc->nr_migratepages) return -EAGAIN; /* async migration should just abort */ if (cc->mode == MIGRATE_ASYNC) return -EAGAIN; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); if (fatal_signal_pending(current)) return -EINTR; } cond_resched(); if (cc->direct_compaction && (cc->mode == MIGRATE_ASYNC)) { skip_on_failure = true; next_skip_pfn = block_end_pfn(low_pfn, cc->order); } /* Time to isolate some pages for migration */ for (; low_pfn < end_pfn; low_pfn++) { bool is_dirty, is_unevictable; if (skip_on_failure && low_pfn >= next_skip_pfn) { /* * We have isolated all migration candidates in the * previous order-aligned block, and did not skip it due * to failure. We should migrate the pages now and * hopefully succeed compaction. */ if (nr_isolated) break; /* * We failed to isolate in the previous order-aligned * block. Set the new boundary to the end of the * current block. Note we can't simply increase * next_skip_pfn by 1 << order, as low_pfn might have * been incremented by a higher number due to skipping * a compound or a high-order buddy page in the * previous loop iteration. */ next_skip_pfn = block_end_pfn(low_pfn, cc->order); } /* * Periodically drop the lock (if held) regardless of its * contention, to give chance to IRQs. Abort completely if * a fatal signal is pending. */ if (!(low_pfn % COMPACT_CLUSTER_MAX)) { if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } if (fatal_signal_pending(current)) { cc->contended = true; ret = -EINTR; goto fatal_pending; } cond_resched(); } nr_scanned++; page = pfn_to_page(low_pfn); /* * Check if the pageblock has already been marked skipped. * Only the first PFN is checked as the caller isolates * COMPACT_CLUSTER_MAX at a time so the second call must * not falsely conclude that the block should be skipped. */ if (!valid_page && (pageblock_aligned(low_pfn) || low_pfn == cc->zone->zone_start_pfn)) { if (!isolation_suitable(cc, page)) { low_pfn = end_pfn; folio = NULL; goto isolate_abort; } valid_page = page; } if (PageHuge(page)) { /* * skip hugetlbfs if we are not compacting for pages * bigger than its order. THPs and other compound pages * are handled below. */ if (!cc->alloc_contig) { const unsigned int order = compound_order(page); if (order <= MAX_PAGE_ORDER) { low_pfn += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } goto isolate_fail; } /* for alloc_contig case */ if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } ret = isolate_or_dissolve_huge_page(page, &cc->migratepages); /* * Fail isolation in case isolate_or_dissolve_huge_page() * reports an error. In case of -ENOMEM, abort right away. */ if (ret < 0) { /* Do not report -EBUSY down the chain */ if (ret == -EBUSY) ret = 0; low_pfn += compound_nr(page) - 1; nr_scanned += compound_nr(page) - 1; goto isolate_fail; } if (PageHuge(page)) { /* * Hugepage was successfully isolated and placed * on the cc->migratepages list. */ folio = page_folio(page); low_pfn += folio_nr_pages(folio) - 1; goto isolate_success_no_list; } /* * Ok, the hugepage was dissolved. Now these pages are * Buddy and cannot be re-allocated because they are * isolated. Fall-through as the check below handles * Buddy pages. */ } /* * Skip if free. We read page order here without zone lock * which is generally unsafe, but the race window is small and * the worst thing that can happen is that we skip some * potential isolation targets. */ if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); /* * Without lock, we cannot be sure that what we got is * a valid page order. Consider only values in the * valid order range to prevent low_pfn overflow. */ if (freepage_order > 0 && freepage_order <= MAX_PAGE_ORDER) { low_pfn += (1UL << freepage_order) - 1; nr_scanned += (1UL << freepage_order) - 1; } continue; } /* * Regardless of being on LRU, compound pages such as THP * (hugetlbfs is handled above) are not to be compacted unless * we are attempting an allocation larger than the compound * page size. We can potentially save a lot of iterations if we * skip them at once. The check is racy, but we can consider * only valid values and the only danger is skipping too much. */ if (PageCompound(page) && !cc->alloc_contig) { const unsigned int order = compound_order(page); /* Skip based on page order and compaction target order. */ if (skip_isolation_on_order(order, cc->order)) { if (order <= MAX_PAGE_ORDER) { low_pfn += (1UL << order) - 1; nr_scanned += (1UL << order) - 1; } goto isolate_fail; } } /* * Check may be lockless but that's ok as we recheck later. * It's possible to migrate LRU and non-lru movable pages. * Skip any other type of page */ if (!PageLRU(page)) { /* * __PageMovable can return false positive so we need * to verify it under page_lock. */ if (unlikely(__PageMovable(page)) && !PageIsolated(page)) { if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } if (isolate_movable_page(page, mode)) { folio = page_folio(page); goto isolate_success; } } goto isolate_fail; } /* * Be careful not to clear PageLRU until after we're * sure the page is not being freed elsewhere -- the * page release code relies on it. */ folio = folio_get_nontail_page(page); if (unlikely(!folio)) goto isolate_fail; /* * Migration will fail if an anonymous page is pinned in memory, * so avoid taking lru_lock and isolating it unnecessarily in an * admittedly racy check. */ mapping = folio_mapping(folio); if (!mapping && (folio_ref_count(folio) - 1) > folio_mapcount(folio)) goto isolate_fail_put; /* * Only allow to migrate anonymous pages in GFP_NOFS context * because those do not depend on fs locks. */ if (!(cc->gfp_mask & __GFP_FS) && mapping) goto isolate_fail_put; /* Only take pages on LRU: a check now makes later tests safe */ if (!folio_test_lru(folio)) goto isolate_fail_put; is_unevictable = folio_test_unevictable(folio); /* Compaction might skip unevictable pages but CMA takes them */ if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable) goto isolate_fail_put; /* * To minimise LRU disruption, the caller can indicate with * ISOLATE_ASYNC_MIGRATE that it only wants to isolate pages * it will be able to migrate without blocking - clean pages * for the most part. PageWriteback would require blocking. */ if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio)) goto isolate_fail_put; is_dirty = folio_test_dirty(folio); if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) || (mapping && is_unevictable)) { bool migrate_dirty = true; bool is_inaccessible; /* * Only folios without mappings or that have * a ->migrate_folio callback are possible to migrate * without blocking. * * Folios from inaccessible mappings are not migratable. * * However, we can be racing with truncation, which can * free the mapping that we need to check. Truncation * holds the folio lock until after the folio is removed * from the page so holding it ourselves is sufficient. * * To avoid locking the folio just to check inaccessible, * assume every inaccessible folio is also unevictable, * which is a cheaper test. If our assumption goes * wrong, it's not a correctness bug, just potentially * wasted cycles. */ if (!folio_trylock(folio)) goto isolate_fail_put; mapping = folio_mapping(folio); if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) { migrate_dirty = !mapping || mapping->a_ops->migrate_folio; } is_inaccessible = mapping && mapping_inaccessible(mapping); folio_unlock(folio); if (!migrate_dirty || is_inaccessible) goto isolate_fail_put; } /* Try isolate the folio */ if (!folio_test_clear_lru(folio)) goto isolate_fail_put; lruvec = folio_lruvec(folio); /* If we already hold the lock, we can skip some rechecking */ if (lruvec != locked) { if (locked) unlock_page_lruvec_irqrestore(locked, flags); compact_lock_irqsave(&lruvec->lru_lock, &flags, cc); locked = lruvec; lruvec_memcg_debug(lruvec, folio); /* * Try get exclusive access under lock. If marked for * skip, the scan is aborted unless the current context * is a rescan to reach the end of the pageblock. */ if (!skip_updated && valid_page) { skip_updated = true; if (test_and_set_skip(cc, valid_page) && !cc->finish_pageblock) { low_pfn = end_pfn; goto isolate_abort; } } /* * Check LRU folio order under the lock */ if (unlikely(skip_isolation_on_order(folio_order(folio), cc->order) && !cc->alloc_contig)) { low_pfn += folio_nr_pages(folio) - 1; nr_scanned += folio_nr_pages(folio) - 1; folio_set_lru(folio); goto isolate_fail_put; } } /* The folio is taken off the LRU */ if (folio_test_large(folio)) low_pfn += folio_nr_pages(folio) - 1; /* Successfully isolated */ lruvec_del_folio(lruvec, folio); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); isolate_success: list_add(&folio->lru, &cc->migratepages); isolate_success_no_list: cc->nr_migratepages += folio_nr_pages(folio); nr_isolated += folio_nr_pages(folio); nr_scanned += folio_nr_pages(folio) - 1; /* * Avoid isolating too much unless this block is being * fully scanned (e.g. dirty/writeback pages, parallel allocation) * or a lock is contended. For contention, isolate quickly to * potentially remove one source of contention. */ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX && !cc->finish_pageblock && !cc->contended) { ++low_pfn; break; } continue; isolate_fail_put: /* Avoid potential deadlock in freeing page under lru_lock */ if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } folio_put(folio); isolate_fail: if (!skip_on_failure && ret != -ENOMEM) continue; /* * We have isolated some pages, but then failed. Release them * instead of migrating, as we cannot form the cc->order buddy * page anyway. */ if (nr_isolated) { if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; } putback_movable_pages(&cc->migratepages); cc->nr_migratepages = 0; nr_isolated = 0; } if (low_pfn < next_skip_pfn) { low_pfn = next_skip_pfn - 1; /* * The check near the loop beginning would have updated * next_skip_pfn too, but this is a bit simpler. */ next_skip_pfn += 1UL << cc->order; } if (ret == -ENOMEM) break; } /* * The PageBuddy() check could have potentially brought us outside * the range to be scanned. */ if (unlikely(low_pfn > end_pfn)) low_pfn = end_pfn; folio = NULL; isolate_abort: if (locked) unlock_page_lruvec_irqrestore(locked, flags); if (folio) { folio_set_lru(folio); folio_put(folio); } /* * Update the cached scanner pfn once the pageblock has been scanned. * Pages will either be migrated in which case there is no point * scanning in the near future or migration failed in which case the * failure reason may persist. The block is marked for skipping if * there were no pages isolated in the block or if the block is * rescanned twice in a row. */ if (low_pfn == end_pfn && (!nr_isolated || cc->finish_pageblock)) { if (!cc->no_set_skip_hint && valid_page && !skip_updated) set_pageblock_skip(valid_page); update_cached_migrate(cc, low_pfn); } trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, nr_scanned, nr_isolated); fatal_pending: cc->total_migrate_scanned += nr_scanned; if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); cc->migrate_pfn = low_pfn; return ret; } /** * isolate_migratepages_range() - isolate migrate-able pages in a PFN range * @cc: Compaction control structure. * @start_pfn: The first PFN to start isolating. * @end_pfn: The one-past-last PFN. * * Returns -EAGAIN when contented, -EINTR in case of a signal pending, -ENOMEM * in case we could not allocate a page, or 0. */ int isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn, block_start_pfn, block_end_pfn; int ret = 0; /* Scan block by block. First and last block may be incomplete */ pfn = start_pfn; block_start_pfn = pageblock_start_pfn(pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = pageblock_end_pfn(pfn); for (; pfn < end_pfn; pfn = block_end_pfn, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { block_end_pfn = min(block_end_pfn, end_pfn); if (!pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone)) continue; ret = isolate_migratepages_block(cc, pfn, block_end_pfn, ISOLATE_UNEVICTABLE); if (ret) break; if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) break; } return ret; } #endif /* CONFIG_COMPACTION || CONFIG_CMA */ #ifdef CONFIG_COMPACTION static bool suitable_migration_source(struct compact_control *cc, struct page *page) { int block_mt; if (pageblock_skip_persistent(page)) return false; if ((cc->mode != MIGRATE_ASYNC) || !cc->direct_compaction) return true; block_mt = get_pageblock_migratetype(page); if (cc->migratetype == MIGRATE_MOVABLE) return is_migrate_movable(block_mt); else return block_mt == cc->migratetype; } /* Returns true if the page is within a block suitable for migration to */ static bool suitable_migration_target(struct compact_control *cc, struct page *page) { /* If the page is a large free page, then disallow migration */ if (PageBuddy(page)) { int order = cc->order > 0 ? cc->order : pageblock_order; /* * We are checking page_order without zone->lock taken. But * the only small danger is that we skip a potentially suitable * pageblock, so it's not worth to check order for valid range. */ if (buddy_order_unsafe(page) >= order) return false; } if (cc->ignore_block_suitable) return true; /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ if (is_migrate_movable(get_pageblock_migratetype(page))) return true; /* Otherwise skip the block */ return false; } static inline unsigned int freelist_scan_limit(struct compact_control *cc) { unsigned short shift = BITS_PER_LONG - 1; return (COMPACT_CLUSTER_MAX >> min(shift, cc->fast_search_fail)) + 1; } /* * Test whether the free scanner has reached the same or lower pageblock than * the migration scanner, and compaction should thus terminate. */ static inline bool compact_scanners_met(struct compact_control *cc) { return (cc->free_pfn >> pageblock_order) <= (cc->migrate_pfn >> pageblock_order); } /* * Used when scanning for a suitable migration target which scans freelists * in reverse. Reorders the list such as the unscanned pages are scanned * first on the next iteration of the free scanner */ static void move_freelist_head(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); if (!list_is_first(&freepage->buddy_list, freelist)) { list_cut_before(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } /* * Similar to move_freelist_head except used by the migration scanner * when scanning forward. It's possible for these list operations to * move against each other if they search the free list exactly in * lockstep. */ static void move_freelist_tail(struct list_head *freelist, struct page *freepage) { LIST_HEAD(sublist); if (!list_is_last(&freepage->buddy_list, freelist)) { list_cut_position(&sublist, freelist, &freepage->buddy_list); list_splice_tail(&sublist, freelist); } } static void fast_isolate_around(struct compact_control *cc, unsigned long pfn) { unsigned long start_pfn, end_pfn; struct page *page; /* Do not search around if there are enough pages already */ if (cc->nr_freepages >= cc->nr_migratepages) return; /* Minimise scanning during async compaction */ if (cc->direct_compaction && cc->mode == MIGRATE_ASYNC) return; /* Pageblock boundaries */ start_pfn = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn); end_pfn = min(pageblock_end_pfn(pfn), zone_end_pfn(cc->zone)); page = pageblock_pfn_to_page(start_pfn, end_pfn, cc->zone); if (!page) return; isolate_freepages_block(cc, &start_pfn, end_pfn, cc->freepages, 1, false); /* Skip this pageblock in the future as it's full or nearly full */ if (start_pfn == end_pfn && !cc->no_set_skip_hint) set_pageblock_skip(page); } /* Search orders in round-robin fashion */ static int next_search_order(struct compact_control *cc, int order) { order--; if (order < 0) order = cc->order - 1; /* Search wrapped around? */ if (order == cc->search_order) { cc->search_order--; if (cc->search_order < 0) cc->search_order = cc->order - 1; return -1; } return order; } static void fast_isolate_freepages(struct compact_control *cc) { unsigned int limit = max(1U, freelist_scan_limit(cc) >> 1); unsigned int nr_scanned = 0, total_isolated = 0; unsigned long low_pfn, min_pfn, highest = 0; unsigned long nr_isolated = 0; unsigned long distance; struct page *page = NULL; bool scan_start = false; int order; /* Full compaction passes in a negative order */ if (cc->order <= 0) return; /* * If starting the scan, use a deeper search and use the highest * PFN found if a suitable one is not found. */ if (cc->free_pfn >= cc->zone->compact_init_free_pfn) { limit = pageblock_nr_pages >> 1; scan_start = true; } /* * Preferred point is in the top quarter of the scan space but take * a pfn from the top half if the search is problematic. */ distance = (cc->free_pfn - cc->migrate_pfn); low_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 2)); min_pfn = pageblock_start_pfn(cc->free_pfn - (distance >> 1)); if (WARN_ON_ONCE(min_pfn > low_pfn)) low_pfn = min_pfn; /* * Search starts from the last successful isolation order or the next * order to search after a previous failure */ cc->search_order = min_t(unsigned int, cc->order - 1, cc->search_order); for (order = cc->search_order; !page && order >= 0; order = next_search_order(cc, order)) { struct free_area *area = &cc->zone->free_area[order]; struct list_head *freelist; struct page *freepage; unsigned long flags; unsigned int order_scanned = 0; unsigned long high_pfn = 0; if (!area->nr_free) continue; spin_lock_irqsave(&cc->zone->lock, flags); freelist = &area->free_list[MIGRATE_MOVABLE]; list_for_each_entry_reverse(freepage, freelist, buddy_list) { unsigned long pfn; order_scanned++; nr_scanned++; pfn = page_to_pfn(freepage); if (pfn >= highest) highest = max(pageblock_start_pfn(pfn), cc->zone->zone_start_pfn); if (pfn >= low_pfn) { cc->fast_search_fail = 0; cc->search_order = order; page = freepage; break; } if (pfn >= min_pfn && pfn > high_pfn) { high_pfn = pfn; /* Shorten the scan if a candidate is found */ limit >>= 1; } if (order_scanned >= limit) break; } /* Use a maximum candidate pfn if a preferred one was not found */ if (!page && high_pfn) { page = pfn_to_page(high_pfn); /* Update freepage for the list reorder below */ freepage = page; } /* Reorder to so a future search skips recent pages */ move_freelist_head(freelist, freepage); /* Isolate the page if available */ if (page) { if (__isolate_free_page(page, order)) { set_page_private(page, order); nr_isolated = 1 << order; nr_scanned += nr_isolated - 1; total_isolated += nr_isolated; cc->nr_freepages += nr_isolated; list_add_tail(&page->lru, &cc->freepages[order]); count_compact_events(COMPACTISOLATED, nr_isolated); } else { /* If isolation fails, abort the search */ order = cc->search_order + 1; page = NULL; } } spin_unlock_irqrestore(&cc->zone->lock, flags); /* Skip fast search if enough freepages isolated */ if (cc->nr_freepages >= cc->nr_migratepages) break; /* * Smaller scan on next order so the total scan is related * to freelist_scan_limit. */ if (order_scanned >= limit) limit = max(1U, limit >> 1); } trace_mm_compaction_fast_isolate_freepages(min_pfn, cc->free_pfn, nr_scanned, total_isolated); if (!page) { cc->fast_search_fail++; if (scan_start) { /* * Use the highest PFN found above min. If one was * not found, be pessimistic for direct compaction * and use the min mark. */ if (highest >= min_pfn) { page = pfn_to_page(highest); cc->free_pfn = highest; } else { if (cc->direct_compaction && pfn_valid(min_pfn)) { page = pageblock_pfn_to_page(min_pfn, min(pageblock_end_pfn(min_pfn), zone_end_pfn(cc->zone)), cc->zone); if (page && !suitable_migration_target(cc, page)) page = NULL; cc->free_pfn = min_pfn; } } } } if (highest && highest >= cc->zone->compact_cached_free_pfn) { highest -= pageblock_nr_pages; cc->zone->compact_cached_free_pfn = highest; } cc->total_free_scanned += nr_scanned; if (!page) return; low_pfn = page_to_pfn(page); fast_isolate_around(cc, low_pfn); } /* * Based on information in the current compact_control, find blocks * suitable for isolating free pages from and then isolate them. */ static void isolate_freepages(struct compact_control *cc) { struct zone *zone = cc->zone; struct page *page; unsigned long block_start_pfn; /* start of current pageblock */ unsigned long isolate_start_pfn; /* exact pfn we start at */ unsigned long block_end_pfn; /* end of current pageblock */ unsigned long low_pfn; /* lowest pfn scanner is able to scan */ unsigned int stride; /* Try a small search of the free lists for a candidate */ fast_isolate_freepages(cc); if (cc->nr_freepages) return; /* * Initialise the free scanner. The starting point is where we last * successfully isolated from, zone-cached value, or the end of the * zone when isolating for the first time. For looping we also need * this pfn aligned down to the pageblock boundary, because we do * block_start_pfn -= pageblock_nr_pages in the for loop. * For ending point, take care when isolating in last pageblock of a * zone which ends in the middle of a pageblock. * The low boundary is the end of the pageblock the migration scanner * is using. */ isolate_start_pfn = cc->free_pfn; block_start_pfn = pageblock_start_pfn(isolate_start_pfn); block_end_pfn = min(block_start_pfn + pageblock_nr_pages, zone_end_pfn(zone)); low_pfn = pageblock_end_pfn(cc->migrate_pfn); stride = cc->mode == MIGRATE_ASYNC ? COMPACT_CLUSTER_MAX : 1; /* * Isolate free pages until enough are available to migrate the * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ for (; block_start_pfn >= low_pfn; block_end_pfn = block_start_pfn, block_start_pfn -= pageblock_nr_pages, isolate_start_pfn = block_start_pfn) { unsigned long nr_isolated; /* * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check resched. */ if (!(block_start_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) cond_resched(); page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone); if (!page) { unsigned long next_pfn; next_pfn = skip_offline_sections_reverse(block_start_pfn); if (next_pfn) block_start_pfn = max(next_pfn, low_pfn); continue; } /* Check the block is suitable for migration */ if (!suitable_migration_target(cc, page)) continue; /* If isolation recently failed, do not retry */ if (!isolation_suitable(cc, page)) continue; /* Found a block suitable for isolating free pages from. */ nr_isolated = isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, cc->freepages, stride, false); /* Update the skip hint if the full pageblock was scanned */ if (isolate_start_pfn == block_end_pfn) update_pageblock_skip(cc, page, block_start_pfn - pageblock_nr_pages); /* Are enough freepages isolated? */ if (cc->nr_freepages >= cc->nr_migratepages) { if (isolate_start_pfn >= block_end_pfn) { /* * Restart at previous pageblock if more * freepages can be isolated next time. */ isolate_start_pfn = block_start_pfn - pageblock_nr_pages; } break; } else if (isolate_start_pfn < block_end_pfn) { /* * If isolation failed early, do not continue * needlessly. */ break; } /* Adjust stride depending on isolation */ if (nr_isolated) { stride = 1; continue; } stride = min_t(unsigned int, COMPACT_CLUSTER_MAX, stride << 1); } /* * Record where the free scanner will restart next time. Either we * broke from the loop and set isolate_start_pfn based on the last * call to isolate_freepages_block(), or we met the migration scanner * and the loop terminated due to isolate_start_pfn < low_pfn */ cc->free_pfn = isolate_start_pfn; } /* * This is a migrate-callback that "allocates" freepages by taking pages * from the isolated freelists in the block we are migrating to. */ static struct folio *compaction_alloc_noprof(struct folio *src, unsigned long data) { struct compact_control *cc = (struct compact_control *)data; struct folio *dst; int order = folio_order(src); bool has_isolated_pages = false; int start_order; struct page *freepage; unsigned long size; again: for (start_order = order; start_order < NR_PAGE_ORDERS; start_order++) if (!list_empty(&cc->freepages[start_order])) break; /* no free pages in the list */ if (start_order == NR_PAGE_ORDERS) { if (has_isolated_pages) return NULL; isolate_freepages(cc); has_isolated_pages = true; goto again; } freepage = list_first_entry(&cc->freepages[start_order], struct page, lru); size = 1 << start_order; list_del(&freepage->lru); while (start_order > order) { start_order--; size >>= 1; list_add(&freepage[size].lru, &cc->freepages[start_order]); set_page_private(&freepage[size], start_order); } dst = (struct folio *)freepage; post_alloc_hook(&dst->page, order, __GFP_MOVABLE); set_page_refcounted(&dst->page); if (order) prep_compound_page(&dst->page, order); cc->nr_freepages -= 1 << order; cc->nr_migratepages -= 1 << order; return page_rmappable_folio(&dst->page); } static struct folio *compaction_alloc(struct folio *src, unsigned long data) { return alloc_hooks(compaction_alloc_noprof(src, data)); } /* * This is a migrate-callback that "frees" freepages back to the isolated * freelist. All pages on the freelist are from the same zone, so there is no * special handling needed for NUMA. */ static void compaction_free(struct folio *dst, unsigned long data) { struct compact_control *cc = (struct compact_control *)data; int order = folio_order(dst); struct page *page = &dst->page; if (folio_put_testzero(dst)) { free_pages_prepare(page, order); list_add(&dst->lru, &cc->freepages[order]); cc->nr_freepages += 1 << order; } cc->nr_migratepages += 1 << order; /* * someone else has referenced the page, we cannot take it back to our * free list. */ } /* possible outcome of isolate_migratepages */ typedef enum { ISOLATE_ABORT, /* Abort compaction now */ ISOLATE_NONE, /* No pages isolated, continue scanning */ ISOLATE_SUCCESS, /* Pages isolated, migrate */ } isolate_migrate_t; /* * Allow userspace to control policy on scanning the unevictable LRU for * compactable pages. */ static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT; /* * Tunable for proactive compaction. It determines how * aggressively the kernel should compact memory in the * background. It takes values in the range [0, 100]. */ static unsigned int __read_mostly sysctl_compaction_proactiveness = 20; static int sysctl_extfrag_threshold = 500; static int __read_mostly sysctl_compact_memory; static inline void update_fast_start_pfn(struct compact_control *cc, unsigned long pfn) { if (cc->fast_start_pfn == ULONG_MAX) return; if (!cc->fast_start_pfn) cc->fast_start_pfn = pfn; cc->fast_start_pfn = min(cc->fast_start_pfn, pfn); } static inline unsigned long reinit_migrate_pfn(struct compact_control *cc) { if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX) return cc->migrate_pfn; cc->migrate_pfn = cc->fast_start_pfn; cc->fast_start_pfn = ULONG_MAX; return cc->migrate_pfn; } /* * Briefly search the free lists for a migration source that already has * some free pages to reduce the number of pages that need migration * before a pageblock is free. */ static unsigned long fast_find_migrateblock(struct compact_control *cc) { unsigned int limit = freelist_scan_limit(cc); unsigned int nr_scanned = 0; unsigned long distance; unsigned long pfn = cc->migrate_pfn; unsigned long high_pfn; int order; bool found_block = false; /* Skip hints are relied on to avoid repeats on the fast search */ if (cc->ignore_skip_hint) return pfn; /* * If the pageblock should be finished then do not select a different * pageblock. */ if (cc->finish_pageblock) return pfn; /* * If the migrate_pfn is not at the start of a zone or the start * of a pageblock then assume this is a continuation of a previous * scan restarted due to COMPACT_CLUSTER_MAX. */ if (pfn != cc->zone->zone_start_pfn && pfn != pageblock_start_pfn(pfn)) return pfn; /* * For smaller orders, just linearly scan as the number of pages * to migrate should be relatively small and does not necessarily * justify freeing up a large block for a small allocation. */ if (cc->order <= PAGE_ALLOC_COSTLY_ORDER) return pfn; /* * Only allow kcompactd and direct requests for movable pages to * quickly clear out a MOVABLE pageblock for allocation. This * reduces the risk that a large movable pageblock is freed for * an unmovable/reclaimable small allocation. */ if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE) return pfn; /* * When starting the migration scanner, pick any pageblock within the * first half of the search space. Otherwise try and pick a pageblock * within the first eighth to reduce the chances that a migration * target later becomes a source. */ distance = (cc->free_pfn - cc->migrate_pfn) >> 1; if (cc->migrate_pfn != cc->zone->zone_start_pfn) distance >>= 2; high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance); for (order = cc->order - 1; order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit; order--) { struct free_area *area = &cc->zone->free_area[order]; struct list_head *freelist; unsigned long flags; struct page *freepage; if (!area->nr_free) continue; spin_lock_irqsave(&cc->zone->lock, flags); freelist = &area->free_list[MIGRATE_MOVABLE]; list_for_each_entry(freepage, freelist, buddy_list) { unsigned long free_pfn; if (nr_scanned++ >= limit) { move_freelist_tail(freelist, freepage); break; } free_pfn = page_to_pfn(freepage); if (free_pfn < high_pfn) { /* * Avoid if skipped recently. Ideally it would * move to the tail but even safe iteration of * the list assumes an entry is deleted, not * reordered. */ if (get_pageblock_skip(freepage)) continue; /* Reorder to so a future search skips recent pages */ move_freelist_tail(freelist, freepage); update_fast_start_pfn(cc, free_pfn); pfn = pageblock_start_pfn(free_pfn); if (pfn < cc->zone->zone_start_pfn) pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; break; } } spin_unlock_irqrestore(&cc->zone->lock, flags); } cc->total_migrate_scanned += nr_scanned; /* * If fast scanning failed then use a cached entry for a page block * that had free pages as the basis for starting a linear scan. */ if (!found_block) { cc->fast_search_fail++; pfn = reinit_migrate_pfn(cc); } return pfn; } /* * Isolate all pages that can be migrated from the first suitable block, * starting at the block pointed to by the migrate scanner pfn within * compact_control. */ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) { unsigned long block_start_pfn; unsigned long block_end_pfn; unsigned long low_pfn; struct page *page; const isolate_mode_t isolate_mode = (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) | (cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0); bool fast_find_block; /* * Start at where we last stopped, or beginning of the zone as * initialized by compact_zone(). The first failure will use * the lowest PFN as the starting point for linear scanning. */ low_pfn = fast_find_migrateblock(cc); block_start_pfn = pageblock_start_pfn(low_pfn); if (block_start_pfn < cc->zone->zone_start_pfn) block_start_pfn = cc->zone->zone_start_pfn; /* * fast_find_migrateblock() has already ensured the pageblock is not * set with a skipped flag, so to avoid the isolation_suitable check * below again, check whether the fast search was successful. */ fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail; /* Only scan within a pageblock boundary */ block_end_pfn = pageblock_end_pfn(low_pfn); /* * Iterate over whole pageblocks until we find the first suitable. * Do not cross the free scanner. */ for (; block_end_pfn <= cc->free_pfn; fast_find_block = false, cc->migrate_pfn = low_pfn = block_end_pfn, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { /* * This can potentially iterate a massively long zone with * many pageblocks unsuitable, so periodically check if we * need to schedule. */ if (!(low_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) cond_resched(); page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, cc->zone); if (!page) { unsigned long next_pfn; next_pfn = skip_offline_sections(block_start_pfn); if (next_pfn) block_end_pfn = min(next_pfn, cc->free_pfn); continue; } /* * If isolation recently failed, do not retry. Only check the * pageblock once. COMPACT_CLUSTER_MAX causes a pageblock * to be visited multiple times. Assume skip was checked * before making it "skip" so other compaction instances do * not scan the same block. */ if ((pageblock_aligned(low_pfn) || low_pfn == cc->zone->zone_start_pfn) && !fast_find_block && !isolation_suitable(cc, page)) continue; /* * For async direct compaction, only scan the pageblocks of the * same migratetype without huge pages. Async direct compaction * is optimistic to see if the minimum amount of work satisfies * the allocation. The cached PFN is updated as it's possible * that all remaining blocks between source and target are * unsuitable and the compaction scanners fail to meet. */ if (!suitable_migration_source(cc, page)) { update_cached_migrate(cc, block_end_pfn); continue; } /* Perform the isolation */ if (isolate_migratepages_block(cc, low_pfn, block_end_pfn, isolate_mode)) return ISOLATE_ABORT; /* * Either we isolated something and proceed with migration. Or * we failed and compact_zone should decide if we should * continue or not. */ break; } return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } /* * Determine whether kswapd is (or recently was!) running on this node. * * pgdat_kswapd_lock() pins pgdat->kswapd, so a concurrent kswapd_stop() can't * zero it. */ static bool kswapd_is_running(pg_data_t *pgdat) { bool running; pgdat_kswapd_lock(pgdat); running = pgdat->kswapd && task_is_running(pgdat->kswapd); pgdat_kswapd_unlock(pgdat); return running; } /* * A zone's fragmentation score is the external fragmentation wrt to the * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100]. */ static unsigned int fragmentation_score_zone(struct zone *zone) { return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER); } /* * A weighted zone's fragmentation score is the external fragmentation * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It * returns a value in the range [0, 100]. * * The scaling factor ensures that proactive compaction focuses on larger * zones like ZONE_NORMAL, rather than smaller, specialized zones like * ZONE_DMA32. For smaller zones, the score value remains close to zero, * and thus never exceeds the high threshold for proactive compaction. */ static unsigned int fragmentation_score_zone_weighted(struct zone *zone) { unsigned long score; score = zone->present_pages * fragmentation_score_zone(zone); return div64_ul(score, zone->zone_pgdat->node_present_pages + 1); } /* * The per-node proactive (background) compaction process is started by its * corresponding kcompactd thread when the node's fragmentation score * exceeds the high threshold. The compaction process remains active till * the node's score falls below the low threshold, or one of the back-off * conditions is met. */ static unsigned int fragmentation_score_node(pg_data_t *pgdat) { unsigned int score = 0; int zoneid; for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { struct zone *zone; zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; score += fragmentation_score_zone_weighted(zone); } return score; } static unsigned int fragmentation_score_wmark(bool low) { unsigned int wmark_low; /* * Cap the low watermark to avoid excessive compaction * activity in case a user sets the proactiveness tunable * close to 100 (maximum). */ wmark_low = max(100U - sysctl_compaction_proactiveness, 5U); return low ? wmark_low : min(wmark_low + 10, 100U); } static bool should_proactive_compact_node(pg_data_t *pgdat) { int wmark_high; if (!sysctl_compaction_proactiveness || kswapd_is_running(pgdat)) return false; wmark_high = fragmentation_score_wmark(false); return fragmentation_score_node(pgdat) > wmark_high; } static enum compact_result __compact_finished(struct compact_control *cc) { unsigned int order; const int migratetype = cc->migratetype; int ret; /* Compaction run completes if the migrate and free scanner meet */ if (compact_scanners_met(cc)) { /* Let the next compaction start anew. */ reset_cached_positions(cc->zone); /* * Mark that the PG_migrate_skip information should be cleared * by kswapd when it goes to sleep. kcompactd does not set the * flag itself as the decision to be clear should be directly * based on an allocation request. */ if (cc->direct_compaction) cc->zone->compact_blockskip_flush = true; if (cc->whole_zone) return COMPACT_COMPLETE; else return COMPACT_PARTIAL_SKIPPED; } if (cc->proactive_compaction) { int score, wmark_low; pg_data_t *pgdat; pgdat = cc->zone->zone_pgdat; if (kswapd_is_running(pgdat)) return COMPACT_PARTIAL_SKIPPED; score = fragmentation_score_zone(cc->zone); wmark_low = fragmentation_score_wmark(true); if (score > wmark_low) ret = COMPACT_CONTINUE; else ret = COMPACT_SUCCESS; goto out; } if (is_via_compact_memory(cc->order)) return COMPACT_CONTINUE; /* * Always finish scanning a pageblock to reduce the possibility of * fallbacks in the future. This is particularly important when * migration source is unmovable/reclaimable but it's not worth * special casing. */ if (!pageblock_aligned(cc->migrate_pfn)) return COMPACT_CONTINUE; /* Direct compactor: Is a suitable page free? */ ret = COMPACT_NO_SUITABLE_PAGE; for (order = cc->order; order < NR_PAGE_ORDERS; order++) { struct free_area *area = &cc->zone->free_area[order]; bool can_steal; /* Job done if page is free of the right migratetype */ if (!free_area_empty(area, migratetype)) return COMPACT_SUCCESS; #ifdef CONFIG_CMA /* MIGRATE_MOVABLE can fallback on MIGRATE_CMA */ if (migratetype == MIGRATE_MOVABLE && !free_area_empty(area, MIGRATE_CMA)) return COMPACT_SUCCESS; #endif /* * Job done if allocation would steal freepages from * other migratetype buddy lists. */ if (find_suitable_fallback(area, order, migratetype, true, &can_steal) != -1) /* * Movable pages are OK in any pageblock. If we are * stealing for a non-movable allocation, make sure * we finish compacting the current pageblock first * (which is assured by the above migrate_pfn align * check) so it is as free as possible and we won't * have to steal another one soon. */ return COMPACT_SUCCESS; } out: if (cc->contended || fatal_signal_pending(current)) ret = COMPACT_CONTENDED; return ret; } static enum compact_result compact_finished(struct compact_control *cc) { int ret; ret = __compact_finished(cc); trace_mm_compaction_finished(cc->zone, cc->order, ret); if (ret == COMPACT_NO_SUITABLE_PAGE) ret = COMPACT_CONTINUE; return ret; } static bool __compaction_suitable(struct zone *zone, int order, int highest_zoneidx, unsigned long wmark_target) { unsigned long watermark; /* * Watermarks for order-0 must be met for compaction to be able to * isolate free pages for migration targets. This means that the * watermark and alloc_flags have to match, or be more pessimistic than * the check in __isolate_free_page(). We don't use the direct * compactor's alloc_flags, as they are not relevant for freepage * isolation. We however do use the direct compactor's highest_zoneidx * to skip over zones where lowmem reserves would prevent allocation * even if compaction succeeds. * For costly orders, we require low watermark instead of min for * compaction to proceed to increase its chances. * ALLOC_CMA is used, as pages in CMA pageblocks are considered * suitable migration targets */ watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ? low_wmark_pages(zone) : min_wmark_pages(zone); watermark += compact_gap(order); return __zone_watermark_ok(zone, 0, watermark, highest_zoneidx, ALLOC_CMA, wmark_target); } /* * compaction_suitable: Is this suitable to run compaction on this zone now? */ bool compaction_suitable(struct zone *zone, int order, int highest_zoneidx) { enum compact_result compact_result; bool suitable; suitable = __compaction_suitable(zone, order, highest_zoneidx, zone_page_state(zone, NR_FREE_PAGES)); /* * fragmentation index determines if allocation failures are due to * low memory or external fragmentation * * index of -1000 would imply allocations might succeed depending on * watermarks, but we already failed the high-order watermark check * index towards 0 implies failure is due to lack of memory * index towards 1000 implies failure is due to fragmentation * * Only compact if a failure would be due to fragmentation. Also * ignore fragindex for non-costly orders where the alternative to * a successful reclaim/compaction is OOM. Fragindex and the * vm.extfrag_threshold sysctl is meant as a heuristic to prevent * excessive compaction for costly orders, but it should not be at the * expense of system stability. */ if (suitable) { compact_result = COMPACT_CONTINUE; if (order > PAGE_ALLOC_COSTLY_ORDER) { int fragindex = fragmentation_index(zone, order); if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) { suitable = false; compact_result = COMPACT_NOT_SUITABLE_ZONE; } } } else { compact_result = COMPACT_SKIPPED; } trace_mm_compaction_suitable(zone, order, compact_result); return suitable; } bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags) { struct zone *zone; struct zoneref *z; /* * Make sure at least one zone would pass __compaction_suitable if we continue * retrying the reclaim. */ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->highest_zoneidx, ac->nodemask) { unsigned long available; /* * Do not consider all the reclaimable memory because we do not * want to trash just for a single high order allocation which * is even not guaranteed to appear even if __compaction_suitable * is happy about the watermark check. */ available = zone_reclaimable_pages(zone) / order; available += zone_page_state_snapshot(zone, NR_FREE_PAGES); if (__compaction_suitable(zone, order, ac->highest_zoneidx, available)) return true; } return false; } /* * Should we do compaction for target allocation order. * Return COMPACT_SUCCESS if allocation for target order can be already * satisfied * Return COMPACT_SKIPPED if compaction for target order is likely to fail * Return COMPACT_CONTINUE if compaction for target order should be ran */ static enum compact_result compaction_suit_allocation_order(struct zone *zone, unsigned int order, int highest_zoneidx, unsigned int alloc_flags, bool async) { unsigned long watermark; watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); if (zone_watermark_ok(zone, order, watermark, highest_zoneidx, alloc_flags)) return COMPACT_SUCCESS; /* * For unmovable allocations (without ALLOC_CMA), check if there is enough * free memory in the non-CMA pageblocks. Otherwise compaction could form * the high-order page in CMA pageblocks, which would not help the * allocation to succeed. However, limit the check to costly order async * compaction (such as opportunistic THP attempts) because there is the * possibility that compaction would migrate pages from non-CMA to CMA * pageblock. */ if (order > PAGE_ALLOC_COSTLY_ORDER && async && !(alloc_flags & ALLOC_CMA)) { watermark = low_wmark_pages(zone) + compact_gap(order); if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx, 0, zone_page_state(zone, NR_FREE_PAGES))) return COMPACT_SKIPPED; } if (!compaction_suitable(zone, order, highest_zoneidx)) return COMPACT_SKIPPED; return COMPACT_CONTINUE; } static enum compact_result compact_zone(struct compact_control *cc, struct capture_control *capc) { enum compact_result ret; unsigned long start_pfn = cc->zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(cc->zone); unsigned long last_migrated_pfn; const bool sync = cc->mode != MIGRATE_ASYNC; bool update_cached; unsigned int nr_succeeded = 0, nr_migratepages; int order; /* * These counters track activities during zone compaction. Initialize * them before compacting a new zone. */ cc->total_migrate_scanned = 0; cc->total_free_scanned = 0; cc->nr_migratepages = 0; cc->nr_freepages = 0; for (order = 0; order < NR_PAGE_ORDERS; order++) INIT_LIST_HEAD(&cc->freepages[order]); INIT_LIST_HEAD(&cc->migratepages); cc->migratetype = gfp_migratetype(cc->gfp_mask); if (!is_via_compact_memory(cc->order)) { ret = compaction_suit_allocation_order(cc->zone, cc->order, cc->highest_zoneidx, cc->alloc_flags, cc->mode == MIGRATE_ASYNC); if (ret != COMPACT_CONTINUE) return ret; } /* * Clear pageblock skip if there were failures recently and compaction * is about to be retried after being deferred. */ if (compaction_restarting(cc->zone, cc->order)) __reset_isolation_suitable(cc->zone); /* * Setup to move all movable pages to the end of the zone. Used cached * information on where the scanners should start (unless we explicitly * want to compact the whole zone), but check that it is initialised * by ensuring the values are within zone boundaries. */ cc->fast_start_pfn = 0; if (cc->whole_zone) { cc->migrate_pfn = start_pfn; cc->free_pfn = pageblock_start_pfn(end_pfn - 1); } else { cc->migrate_pfn = cc->zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = cc->zone->compact_cached_free_pfn; if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { cc->free_pfn = pageblock_start_pfn(end_pfn - 1); cc->zone->compact_cached_free_pfn = cc->free_pfn; } if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { cc->migrate_pfn = start_pfn; cc->zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; cc->zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } if (cc->migrate_pfn <= cc->zone->compact_init_migrate_pfn) cc->whole_zone = true; } last_migrated_pfn = 0; /* * Migrate has separate cached PFNs for ASYNC and SYNC* migration on * the basis that some migrations will fail in ASYNC mode. However, * if the cached PFNs match and pageblocks are skipped due to having * no isolation candidates, then the sync state does not matter. * Until a pageblock with isolation candidates is found, keep the * cached PFNs in sync to avoid revisiting the same blocks. */ update_cached = !sync && cc->zone->compact_cached_migrate_pfn[0] == cc->zone->compact_cached_migrate_pfn[1]; trace_mm_compaction_begin(cc, start_pfn, end_pfn, sync); /* lru_add_drain_all could be expensive with involving other CPUs */ lru_add_drain(); while ((ret = compact_finished(cc)) == COMPACT_CONTINUE) { int err; unsigned long iteration_start_pfn = cc->migrate_pfn; /* * Avoid multiple rescans of the same pageblock which can * happen if a page cannot be isolated (dirty/writeback in * async mode) or if the migrated pages are being allocated * before the pageblock is cleared. The first rescan will * capture the entire pageblock for migration. If it fails, * it'll be marked skip and scanning will proceed as normal. */ cc->finish_pageblock = false; if (pageblock_start_pfn(last_migrated_pfn) == pageblock_start_pfn(iteration_start_pfn)) { cc->finish_pageblock = true; } rescan: switch (isolate_migratepages(cc)) { case ISOLATE_ABORT: ret = COMPACT_CONTENDED; putback_movable_pages(&cc->migratepages); cc->nr_migratepages = 0; goto out; case ISOLATE_NONE: if (update_cached) { cc->zone->compact_cached_migrate_pfn[1] = cc->zone->compact_cached_migrate_pfn[0]; } /* * We haven't isolated and migrated anything, but * there might still be unflushed migrations from * previous cc->order aligned block. */ goto check_drain; case ISOLATE_SUCCESS: update_cached = false; last_migrated_pfn = max(cc->zone->zone_start_pfn, pageblock_start_pfn(cc->migrate_pfn - 1)); } /* * Record the number of pages to migrate since the * compaction_alloc/free() will update cc->nr_migratepages * properly. */ nr_migratepages = cc->nr_migratepages; err = migrate_pages(&cc->migratepages, compaction_alloc, compaction_free, (unsigned long)cc, cc->mode, MR_COMPACTION, &nr_succeeded); trace_mm_compaction_migratepages(nr_migratepages, nr_succeeded); /* All pages were either migrated or will be released */ cc->nr_migratepages = 0; if (err) { putback_movable_pages(&cc->migratepages); /* * migrate_pages() may return -ENOMEM when scanners meet * and we want compact_finished() to detect it */ if (err == -ENOMEM && !compact_scanners_met(cc)) { ret = COMPACT_CONTENDED; goto out; } /* * If an ASYNC or SYNC_LIGHT fails to migrate a page * within the pageblock_order-aligned block and * fast_find_migrateblock may be used then scan the * remainder of the pageblock. This will mark the * pageblock "skip" to avoid rescanning in the near * future. This will isolate more pages than necessary * for the request but avoid loops due to * fast_find_migrateblock revisiting blocks that were * recently partially scanned. */ if (!pageblock_aligned(cc->migrate_pfn) && !cc->ignore_skip_hint && !cc->finish_pageblock && (cc->mode < MIGRATE_SYNC)) { cc->finish_pageblock = true; /* * Draining pcplists does not help THP if * any page failed to migrate. Even after * drain, the pageblock will not be free. */ if (cc->order == COMPACTION_HPAGE_ORDER) last_migrated_pfn = 0; goto rescan; } } /* Stop if a page has been captured */ if (capc && capc->page) { ret = COMPACT_SUCCESS; break; } check_drain: /* * Has the migration scanner moved away from the previous * cc->order aligned block where we migrated from? If yes, * flush the pages that were freed, so that they can merge and * compact_finished() can detect immediately if allocation * would succeed. */ if (cc->order > 0 && last_migrated_pfn) { unsigned long current_block_start = block_start_pfn(cc->migrate_pfn, cc->order); if (last_migrated_pfn < current_block_start) { lru_add_drain_cpu_zone(cc->zone); /* No more flushing until we migrate again */ last_migrated_pfn = 0; } } } out: /* * Release free pages and update where the free scanner should restart, * so we don't leave any returned pages behind in the next attempt. */ if (cc->nr_freepages > 0) { unsigned long free_pfn = release_free_list(cc->freepages); cc->nr_freepages = 0; VM_BUG_ON(free_pfn == 0); /* The cached pfn is always the first in a pageblock */ free_pfn = pageblock_start_pfn(free_pfn); /* * Only go back, not forward. The cached pfn might have been * already reset to zone end in compact_finished() */ if (free_pfn > cc->zone->compact_cached_free_pfn) cc->zone->compact_cached_free_pfn = free_pfn; } count_compact_events(COMPACTMIGRATE_SCANNED, cc->total_migrate_scanned); count_compact_events(COMPACTFREE_SCANNED, cc->total_free_scanned); trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret); VM_BUG_ON(!list_empty(&cc->migratepages)); return ret; } static enum compact_result compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, enum compact_priority prio, unsigned int alloc_flags, int highest_zoneidx, struct page **capture) { enum compact_result ret; struct compact_control cc = { .order = order, .search_order = order, .gfp_mask = gfp_mask, .zone = zone, .mode = (prio == COMPACT_PRIO_ASYNC) ? MIGRATE_ASYNC : MIGRATE_SYNC_LIGHT, .alloc_flags = alloc_flags, .highest_zoneidx = highest_zoneidx, .direct_compaction = true, .whole_zone = (prio == MIN_COMPACT_PRIORITY), .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) }; struct capture_control capc = { .cc = &cc, .page = NULL, }; /* * Make sure the structs are really initialized before we expose the * capture control, in case we are interrupted and the interrupt handler * frees a page. */ barrier(); WRITE_ONCE(current->capture_control, &capc); ret = compact_zone(&cc, &capc); /* * Make sure we hide capture control first before we read the captured * page pointer, otherwise an interrupt could free and capture a page * and we would leak it. */ WRITE_ONCE(current->capture_control, NULL); *capture = READ_ONCE(capc.page); /* * Technically, it is also possible that compaction is skipped but * the page is still captured out of luck(IRQ came and freed the page). * Returning COMPACT_SUCCESS in such cases helps in properly accounting * the COMPACT[STALL|FAIL] when compaction is skipped. */ if (*capture) ret = COMPACT_SUCCESS; return ret; } /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @gfp_mask: The GFP mask of the current allocation * @order: The order of the current allocation * @alloc_flags: The allocation flags of the current allocation * @ac: The context of current allocation * @prio: Determines how hard direct compaction should try to succeed * @capture: Pointer to free page created by compaction will be stored here * * This is the main entry point for direct page compaction. */ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **capture) { struct zoneref *z; struct zone *zone; enum compact_result rc = COMPACT_SKIPPED; if (!gfp_compaction_allowed(gfp_mask)) return COMPACT_SKIPPED; trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio); /* Compact each zone in the list */ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->highest_zoneidx, ac->nodemask) { enum compact_result status; if (cpusets_enabled() && (alloc_flags & ALLOC_CPUSET) && !__cpuset_zone_allowed(zone, gfp_mask)) continue; if (prio > MIN_COMPACT_PRIORITY && compaction_deferred(zone, order)) { rc = max_t(enum compact_result, COMPACT_DEFERRED, rc); continue; } status = compact_zone_order(zone, order, gfp_mask, prio, alloc_flags, ac->highest_zoneidx, capture); rc = max(status, rc); /* The allocation should succeed, stop compacting */ if (status == COMPACT_SUCCESS) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller * will repeat this with true if allocation indeed * succeeds in this zone. */ compaction_defer_reset(zone, order, false); break; } if (prio != COMPACT_PRIO_ASYNC && (status == COMPACT_COMPLETE || status == COMPACT_PARTIAL_SKIPPED)) /* * We think that allocation won't succeed in this zone * so we defer compaction there. If it ends up * succeeding after all, it will be reset. */ defer_compaction(zone, order); /* * We might have stopped compacting due to need_resched() in * async compaction, or due to a fatal signal detected. In that * case do not try further zones */ if ((prio == COMPACT_PRIO_ASYNC && need_resched()) || fatal_signal_pending(current)) break; } return rc; } /* * compact_node() - compact all zones within a node * @pgdat: The node page data * @proactive: Whether the compaction is proactive * * For proactive compaction, compact till each zone's fragmentation score * reaches within proactive compaction thresholds (as determined by the * proactiveness tunable), it is possible that the function returns before * reaching score targets due to various back-off conditions, such as, * contention on per-node or per-zone locks. */ static int compact_node(pg_data_t *pgdat, bool proactive) { int zoneid; struct zone *zone; struct compact_control cc = { .order = -1, .mode = proactive ? MIGRATE_SYNC_LIGHT : MIGRATE_SYNC, .ignore_skip_hint = true, .whole_zone = true, .gfp_mask = GFP_KERNEL, .proactive_compaction = proactive, }; for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; if (fatal_signal_pending(current)) return -EINTR; cc.zone = zone; compact_zone(&cc, NULL); if (proactive) { count_compact_events(KCOMPACTD_MIGRATE_SCANNED, cc.total_migrate_scanned); count_compact_events(KCOMPACTD_FREE_SCANNED, cc.total_free_scanned); } } return 0; } /* Compact all zones of all nodes in the system */ static int compact_nodes(void) { int ret, nid; /* Flush pending updates to the LRU lists */ lru_add_drain_all(); for_each_online_node(nid) { ret = compact_node(NODE_DATA(nid), false); if (ret) return ret; } return 0; } static int compaction_proactiveness_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc, nid; rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; if (write && sysctl_compaction_proactiveness) { for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); if (pgdat->proactive_compact_trigger) continue; pgdat->proactive_compact_trigger = true; trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, -1, pgdat->nr_zones - 1); wake_up_interruptible(&pgdat->kcompactd_wait); } } return 0; } /* * This is the entry point for compacting all nodes via * /proc/sys/vm/compact_memory */ static int sysctl_compaction_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, length, ppos); if (ret) return ret; if (sysctl_compact_memory != 1) return -EINVAL; if (write) ret = compact_nodes(); return ret; } #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) static ssize_t compact_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int nid = dev->id; if (nid >= 0 && nid < nr_node_ids && node_online(nid)) { /* Flush pending updates to the LRU lists */ lru_add_drain_all(); compact_node(NODE_DATA(nid), false); } return count; } static DEVICE_ATTR_WO(compact); int compaction_register_node(struct node *node) { return device_create_file(&node->dev, &dev_attr_compact); } void compaction_unregister_node(struct node *node) { device_remove_file(&node->dev, &dev_attr_compact); } #endif /* CONFIG_SYSFS && CONFIG_NUMA */ static inline bool kcompactd_work_requested(pg_data_t *pgdat) { return pgdat->kcompactd_max_order > 0 || kthread_should_stop() || pgdat->proactive_compact_trigger; } static bool kcompactd_node_suitable(pg_data_t *pgdat) { int zoneid; struct zone *zone; enum zone_type highest_zoneidx = pgdat->kcompactd_highest_zoneidx; enum compact_result ret; for (zoneid = 0; zoneid <= highest_zoneidx; zoneid++) { zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; ret = compaction_suit_allocation_order(zone, pgdat->kcompactd_max_order, highest_zoneidx, ALLOC_WMARK_MIN, false); if (ret == COMPACT_CONTINUE) return true; } return false; } static void kcompactd_do_work(pg_data_t *pgdat) { /* * With no special task, compact all zones so that a page of requested * order is allocatable. */ int zoneid; struct zone *zone; struct compact_control cc = { .order = pgdat->kcompactd_max_order, .search_order = pgdat->kcompactd_max_order, .highest_zoneidx = pgdat->kcompactd_highest_zoneidx, .mode = MIGRATE_SYNC_LIGHT, .ignore_skip_hint = false, .gfp_mask = GFP_KERNEL, }; enum compact_result ret; trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order, cc.highest_zoneidx); count_compact_event(KCOMPACTD_WAKE); for (zoneid = 0; zoneid <= cc.highest_zoneidx; zoneid++) { int status; zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; if (compaction_deferred(zone, cc.order)) continue; ret = compaction_suit_allocation_order(zone, cc.order, zoneid, ALLOC_WMARK_MIN, false); if (ret != COMPACT_CONTINUE) continue; if (kthread_should_stop()) return; cc.zone = zone; status = compact_zone(&cc, NULL); if (status == COMPACT_SUCCESS) { compaction_defer_reset(zone, cc.order, false); } else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) { /* * Buddy pages may become stranded on pcps that could * otherwise coalesce on the zone's free area for * order >= cc.order. This is ratelimited by the * upcoming deferral. */ drain_all_pages(zone); /* * We use sync migration mode here, so we defer like * sync direct compaction does. */ defer_compaction(zone, cc.order); } count_compact_events(KCOMPACTD_MIGRATE_SCANNED, cc.total_migrate_scanned); count_compact_events(KCOMPACTD_FREE_SCANNED, cc.total_free_scanned); } /* * Regardless of success, we are done until woken up next. But remember * the requested order/highest_zoneidx in case it was higher/tighter * than our current ones */ if (pgdat->kcompactd_max_order <= cc.order) pgdat->kcompactd_max_order = 0; if (pgdat->kcompactd_highest_zoneidx >= cc.highest_zoneidx) pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; } void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx) { if (!order) return; if (pgdat->kcompactd_max_order < order) pgdat->kcompactd_max_order = order; if (pgdat->kcompactd_highest_zoneidx > highest_zoneidx) pgdat->kcompactd_highest_zoneidx = highest_zoneidx; /* * Pairs with implicit barrier in wait_event_freezable() * such that wakeups are not missed. */ if (!wq_has_sleeper(&pgdat->kcompactd_wait)) return; if (!kcompactd_node_suitable(pgdat)) return; trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order, highest_zoneidx); wake_up_interruptible(&pgdat->kcompactd_wait); } /* * The background compaction daemon, started as a kernel thread * from the init process. */ static int kcompactd(void *p) { pg_data_t *pgdat = (pg_data_t *)p; long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC); long timeout = default_timeout; set_freezable(); pgdat->kcompactd_max_order = 0; pgdat->kcompactd_highest_zoneidx = pgdat->nr_zones - 1; while (!kthread_should_stop()) { unsigned long pflags; /* * Avoid the unnecessary wakeup for proactive compaction * when it is disabled. */ if (!sysctl_compaction_proactiveness) timeout = MAX_SCHEDULE_TIMEOUT; trace_mm_compaction_kcompactd_sleep(pgdat->node_id); if (wait_event_freezable_timeout(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat), timeout) && !pgdat->proactive_compact_trigger) { psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); psi_memstall_leave(&pflags); /* * Reset the timeout value. The defer timeout from * proactive compaction is lost here but that is fine * as the condition of the zone changing substantionally * then carrying on with the previous defer interval is * not useful. */ timeout = default_timeout; continue; } /* * Start the proactive work with default timeout. Based * on the fragmentation score, this timeout is updated. */ timeout = default_timeout; if (should_proactive_compact_node(pgdat)) { unsigned int prev_score, score; prev_score = fragmentation_score_node(pgdat); compact_node(pgdat, true); score = fragmentation_score_node(pgdat); /* * Defer proactive compaction if the fragmentation * score did not go down i.e. no progress made. */ if (unlikely(score >= prev_score)) timeout = default_timeout << COMPACT_MAX_DEFER_SHIFT; } if (unlikely(pgdat->proactive_compact_trigger)) pgdat->proactive_compact_trigger = false; } return 0; } /* * This kcompactd start function will be called by init and node-hot-add. * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added. */ void __meminit kcompactd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); if (pgdat->kcompactd) return; pgdat->kcompactd = kthread_create_on_node(kcompactd, pgdat, nid, "kcompactd%d", nid); if (IS_ERR(pgdat->kcompactd)) { pr_err("Failed to start kcompactd on node %d\n", nid); pgdat->kcompactd = NULL; } else { wake_up_process(pgdat->kcompactd); } } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void __meminit kcompactd_stop(int nid) { struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd; if (kcompactd) { kthread_stop(kcompactd); NODE_DATA(nid)->kcompactd = NULL; } } static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, old; if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) return proc_dointvec_minmax(table, write, buffer, lenp, ppos); old = *(int *)table->data; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret) return ret; if (old != *(int *)table->data) pr_warn_once("sysctl attribute %s changed by %s[%d]\n", table->procname, current->comm, task_pid_nr(current)); return ret; } static const struct ctl_table vm_compaction[] = { { .procname = "compact_memory", .data = &sysctl_compact_memory, .maxlen = sizeof(int), .mode = 0200, .proc_handler = sysctl_compaction_handler, }, { .procname = "compaction_proactiveness", .data = &sysctl_compaction_proactiveness, .maxlen = sizeof(sysctl_compaction_proactiveness), .mode = 0644, .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "extfrag_threshold", .data = &sysctl_extfrag_threshold, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_THOUSAND, }, { .procname = "compact_unevictable_allowed", .data = &sysctl_compact_unevictable_allowed, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_warn_RT_change, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static int __init kcompactd_init(void) { int nid; for_each_node_state(nid, N_MEMORY) kcompactd_run(nid); register_sysctl_init("vm", vm_compaction); return 0; } subsys_initcall(kcompactd_init) #endif /* CONFIG_COMPACTION */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" struct eee_req_info { struct ethnl_req_info base; }; struct eee_reply_data { struct ethnl_reply_data base; struct ethtool_keee eee; }; #define EEE_REPDATA(__reply_base) \ container_of(__reply_base, struct eee_reply_data, base) const struct nla_policy ethnl_eee_get_policy[] = { [ETHTOOL_A_EEE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int eee_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct eee_reply_data *data = EEE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; struct ethtool_keee *eee = &data->eee; int ret; if (!dev->ethtool_ops->get_eee) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = dev->ethtool_ops->get_eee(dev, eee); ethnl_ops_complete(dev); return ret; } static int eee_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct eee_reply_data *data = EEE_REPDATA(reply_base); const struct ethtool_keee *eee = &data->eee; int len = 0; int ret; /* MODES_OURS */ ret = ethnl_bitset_size(eee->advertised, eee->supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; /* MODES_PEERS */ ret = ethnl_bitset_size(eee->lp_advertised, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; len += nla_total_size(sizeof(u8)) + /* _EEE_ACTIVE */ nla_total_size(sizeof(u8)) + /* _EEE_ENABLED */ nla_total_size(sizeof(u8)) + /* _EEE_TX_LPI_ENABLED */ nla_total_size(sizeof(u32)); /* _EEE_TX_LPI_TIMER */ return len; } static int eee_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct eee_reply_data *data = EEE_REPDATA(reply_base); const struct ethtool_keee *eee = &data->eee; int ret; ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_OURS, eee->advertised, eee->supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_PEER, eee->lp_advertised, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; if (nla_put_u8(skb, ETHTOOL_A_EEE_ACTIVE, eee->eee_active) || nla_put_u8(skb, ETHTOOL_A_EEE_ENABLED, eee->eee_enabled) || nla_put_u8(skb, ETHTOOL_A_EEE_TX_LPI_ENABLED, eee->tx_lpi_enabled) || nla_put_u32(skb, ETHTOOL_A_EEE_TX_LPI_TIMER, eee->tx_lpi_timer)) return -EMSGSIZE; return 0; } /* EEE_SET */ const struct nla_policy ethnl_eee_set_policy[] = { [ETHTOOL_A_EEE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_EEE_MODES_OURS] = { .type = NLA_NESTED }, [ETHTOOL_A_EEE_ENABLED] = { .type = NLA_U8 }, [ETHTOOL_A_EEE_TX_LPI_ENABLED] = { .type = NLA_U8 }, [ETHTOOL_A_EEE_TX_LPI_TIMER] = { .type = NLA_U32 }, }; static int ethnl_set_eee_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_eee && ops->set_eee ? 1 : -EOPNOTSUPP; } static int ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) { struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; struct ethtool_keee eee = {}; bool mod = false; int ret; ret = dev->ethtool_ops->get_eee(dev, &eee); if (ret < 0) return ret; ret = ethnl_update_bitset(eee.advertised, __ETHTOOL_LINK_MODE_MASK_NBITS, tb[ETHTOOL_A_EEE_MODES_OURS], link_mode_names, info->extack, &mod); if (ret < 0) return ret; ethnl_update_bool(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); ethnl_update_bool(&eee.tx_lpi_enabled, tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], &mod); ethnl_update_u32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER], &mod); if (!mod) return 0; ret = dev->ethtool_ops->set_eee(dev, &eee); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_eee_request_ops = { .request_cmd = ETHTOOL_MSG_EEE_GET, .reply_cmd = ETHTOOL_MSG_EEE_GET_REPLY, .hdr_attr = ETHTOOL_A_EEE_HEADER, .req_info_size = sizeof(struct eee_req_info), .reply_data_size = sizeof(struct eee_reply_data), .prepare_data = eee_prepare_data, .reply_size = eee_reply_size, .fill_reply = eee_fill_reply, .set_validate = ethnl_set_eee_validate, .set = ethnl_set_eee, .set_ntf_cmd = ETHTOOL_MSG_EEE_NTF, }; |
| 783 6 4 770 766 10 3 10 4 8 767 769 757 766 576 578 576 74 75 4 47 24 47 18 9 10 10 6 8 2 56 14 42 1 1 4 36 36 13 21 21 17 4 3 3 2 2 1 28 12 15 15 6 6 1 97 86 10 4 41 97 91 97 1 1 89 1 7 3 1 96 81 87 87 87 87 86 87 87 87 87 87 87 87 87 87 87 87 87 87 86 86 11 87 126 1 1 124 124 125 125 89 125 35 124 125 125 121 175 75 2 58 15 61 12 11 62 29 44 70 3 44 30 54 19 66 7 65 8 16 4 18 2 8 12 16 4 16 4 15 4 16 4 16 4 77 20 57 1 61 14 4 13 4 2 1 2 11 3 32 3 20 2 3 1 3 1 2 12 10 3 2 2 1 8 9 1 2 67 2 94 94 61 1 1 59 1 1 60 57 1 1 54 55 62 1 63 62 56 64 65 38 38 80 80 2 1 1 35 80 35 80 75 80 1 1 1 80 80 92 92 1 1 92 79 1 80 80 77 1 86 1 1 85 85 1 44 1 43 1 43 43 43 1 43 43 42 89 2 86 88 87 86 86 85 83 83 83 82 81 81 81 80 79 80 1 78 2 79 78 1 75 75 74 1 1 73 72 1 73 1 71 2 70 69 1 68 68 34 34 34 34 34 34 34 34 34 1 1 34 2 33 33 97 35 42 98 87 1 46 46 46 1 46 46 46 46 45 46 45 2 98 97 86 10 87 18 85 16 95 10 87 2 53 10 98 79 96 26 11 56 56 55 55 53 54 54 54 64 64 65 64 65 2 9 55 56 1 54 55 44 11 5 1 1 1 40 1 39 39 1 38 38 38 1 38 1 38 38 1 38 38 38 37 37 1 37 37 1 36 1 1 34 34 34 34 3 33 33 33 87 23 10 10 3 8 5 5 4 1 98 89 2 11 96 95 37 95 87 87 94 7 1 1 8 34 153 3 146 3 7 16 5 13 3 4 86 28 1 2 16 12 22 7 4 4 118 128 1 24 16 89 38 35 8 8 34 3 3 3 3 3 54 2 5 48 2 5 4 48 14 34 1 34 13 1 1 1 15 13 2 13 2 13 1 1 12 1 1 12 1 13 11 1 1 12 6 2 6 2 7 1 7 1 7 1 8 7 1 7 1 6 2 50 18 18 18 18 18 69 69 69 69 4 64 4 63 59 18 23 15 4 65 69 10 8 1 1 8 8 2 8 8 1 8 8 1 1 8 8 1 75 1 9 73 2 2 64 5 3 3 4 3 2 2 62 1 50 8 42 48 2 7 41 5 41 1 3 39 36 4 40 10 34 1 2 29 24 26 8 7 1 6 22 22 8 9 6 13 2 1 16 16 32 32 32 6 1 5 2 1 1 21 8 16 8 8 8 5 3 3 6 6 6 14 14 5 2 7 3 3 3 1 1 1 36 36 5 3 25 3 1 24 21 6 1 4 3 18 18 4 11 3 6 4 8 8 4 8 8 1 1 12 9 9 13 5 11 59 59 2 12 13 3 3 3 3 2 1 3 1 1 78 79 43 43 43 43 3 2 16 1 2 2 47 20 20 42 24 28 27 37 4 35 4 32 2 31 4 24 6 13 15 14 1 13 2 5 12 6 5 1 4 4 3 1 1 20 20 20 19 1 19 1 20 19 1 1 2 1 1 17 18 1 18 12 3 3 2 3 2 3 2 3 2 12 12 12 12 12 12 12 12 12 2 2 2 1 5 2 12 10 2 12 12 12 12 25 25 25 3 2 20 2 2 16 18 2 16 1 16 16 15 1 14 2 1 11 1 1 12 12 12 12 12 12 12 10 2 12 12 20 1 1 1 1 1 1 46 6 34 6 4 3 1 1 1 1 1 2 2 60 60 59 60 60 58 60 60 60 59 60 60 60 60 60 59 60 1 60 59 60 60 60 60 60 59 59 59 59 60 60 60 60 60 60 60 60 60 60 60 59 60 60 60 60 60 59 60 59 6 5 1 1 1 2 1 1 1 17 1 1 12 3 1 1 2 10 1 9 3 1 4 1 2 2 2 2 31 30 1 16 35 5 1 4 3 5 42 3 42 2 27 2 28 1 28 1 29 29 28 45 35 32 3 33 2 31 4 33 1 2 33 30 2 31 2 31 2 3 27 3 25 3 1 27 2 28 2 30 1 30 29 29 1 27 21 1 1 1 18 16 17 15 2 1 16 11 6 16 1 16 1 17 17 16 17 15 2 15 2 16 1 16 16 3 1 11 1 12 1 3 1 3 3 1 3 8 8 6 2 1 7 5 2 3 3 4 4 6 5 1 2 1 1 3 1 1 1 2 1 1 2 1 1 3 2 1 8 8 6 2 6 2 7 1 8 6 2 6 2 6 2 5 1 5 1 11 4 5 3 5 1 1 2 1 1 30 2 28 28 28 27 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 25 1 2 27 27 27 27 27 27 27 27 27 2 3 2 4 1 5 4 5 4 1 1 1 5 5 5 5 5 6 3 3 1 4 4 4 1 1 1 1 1 1 1 1 17 1 2 8 6 10 6 14 13 13 1 10 10 10 2 2 42 12 41 41 41 11 31 19 9 5 11 1 10 1 9 1 8 1 7 1 6 1 5 1 2 3 2 3 2 45 1 13 13 32 30 11 9 36 4 33 7 38 2 7 3 3 4 31 31 31 31 31 3 31 34 29 5 31 3 34 34 25 7 3 28 3 7 2 21 1 24 2 24 2 1 1 1 1 1 1 1 1 1 1 1 1 1 53 45 1 1 5 2 5 17 17 3 2 17 2 1 14 5 2 7 5 2 2 2 2 2 2 2 2 2 2 2 2 2 5 2 1 3 1 2 2 8 7 1 1 12 1 1 1 2 1 2 3 1 1 2 2 3 2 1 64 2 3 60 57 4 4 55 2 7 1 58 1 59 2 55 1 3 2 54 2 1 52 1 53 1 1 1 4 4 1 1 2 1 3 3 1 1 1 6 6 6 3 40 2 37 1 1 4 33 4 34 1 5 2 28 2 26 25 1 26 26 7 17 1 6 1 1 5 3 1 1 1 3 2 1 1 1 54 3 6 46 48 11 37 22 3 18 1 20 2 2 20 21 18 3 21 3 17 1 18 1 17 1 17 1 17 1 16 1 15 1 17 16 17 17 17 16 17 15 1 15 14 1 2 2 2 1 4 1 1 2 3 1 1 6 1 3 1 1 2 2 2 2 2 2 4 7 3 4 2 1 2 2 2 4 2 1 1 6 2 1 1 1 1 1 1 4 2 2 12 12 2 2 5 3 3 3 1 3 42 42 27 15 11 1 3 8 10 10 62 1 61 55 6 60 47 6 8 53 53 4 5 44 16 4 35 3 1 2 2 2 1 1 1 1 1 1 1 1 1 1 1 5 3 4 2 1 1 1 1 1 15 1 1 2 7 2 2 3 2 1 1 89 59 3 29 57 55 1 56 2 7 51 3 7 26 46 1 11 15 5 14 10 1 10 1 1 1 1 1 1 1 1 1 8 1 2 3 2 2 1 1 1 2 1 1 1 1 3 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 11 1 2 8 5 2 2 2 2 1 1 10 4 2 2 19 17 2 6 1 1 3 2 4 4 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 8 2 1 3 1 5 5 5 1 4 1 1 1 1 1 1 1 1 1 13 1 1 11 2 11 2 10 1 8 2 8 2 7 3 1 8 18 19 1 18 18 4 1 15 4 1 1 1 1 1 1 1 2 1 1 1 1 1 1 902 55 5 841 47 745 750 766 892 2 127 767 95 823 53 891 143 152 598 126 820 95 757 144 3 3 3 60 60 43 2 40 43 43 42 43 43 43 43 43 41 5 4 5 1 1 2 2 2 2 58 58 58 1 1 1 1 1 1 1 4 2 2 4 4 4 4 2 2 9 9 9 9 9 9 8 1 1 1 1 2 2 2 132 65 68 68 68 1 68 68 1 1 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 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 32 |