| 3 5 3 1 1 5 2 20 20 3 15 2 2 1 7 2 1 1 1 1 1 1 1 1 2 2 14 4 5 6 7 3 10 10 4 5 9 3 4 2 4 2 2 4 11 4 3 1 3 3 1 1 4 11 2 9 8 1 4 1 1 2 1 5 48 32 16 4 4 4 4 4 2 2 2 2 13 2 17 17 49 48 48 49 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/fs_context.c * * Copyright (C) 1992 Rick Sladkey * Conversion to new mount api Copyright (C) David Howells * * NFS mount handling. * * Split from fs/nfs/super.c by David Howells <dhowells@redhat.com> */ #include <linux/compat.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <net/handshake.h> #include "nfs.h" #include "internal.h" #include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_MOUNT #if IS_ENABLED(CONFIG_NFS_V3) #define NFS_DEFAULT_VERSION 3 #else #define NFS_DEFAULT_VERSION 2 #endif #define NFS_MAX_CONNECTIONS 16 enum nfs_param { Opt_ac, Opt_acdirmax, Opt_acdirmin, Opt_acl, Opt_acregmax, Opt_acregmin, Opt_actimeo, Opt_addr, Opt_bg, Opt_bsize, Opt_clientaddr, Opt_cto, Opt_alignwrite, Opt_fatal_neterrors, Opt_fg, Opt_fscache, Opt_fscache_flag, Opt_hard, Opt_intr, Opt_local_lock, Opt_lock, Opt_lookupcache, Opt_migration, Opt_minorversion, Opt_mountaddr, Opt_mounthost, Opt_mountport, Opt_mountproto, Opt_mountvers, Opt_namelen, Opt_nconnect, Opt_max_connect, Opt_port, Opt_posix, Opt_proto, Opt_rdirplus, Opt_rdirplus_none, Opt_rdirplus_force, Opt_rdma, Opt_resvport, Opt_retrans, Opt_retry, Opt_rsize, Opt_sec, Opt_sharecache, Opt_sloppy, Opt_soft, Opt_softerr, Opt_softreval, Opt_source, Opt_tcp, Opt_timeo, Opt_trunkdiscovery, Opt_udp, Opt_v, Opt_vers, Opt_wsize, Opt_write, Opt_xprtsec, Opt_cert_serial, Opt_privkey_serial, }; enum { Opt_fatal_neterrors_default, Opt_fatal_neterrors_enetunreach, Opt_fatal_neterrors_none, }; static const struct constant_table nfs_param_enums_fatal_neterrors[] = { { "default", Opt_fatal_neterrors_default }, { "ENETDOWN:ENETUNREACH", Opt_fatal_neterrors_enetunreach }, { "ENETUNREACH:ENETDOWN", Opt_fatal_neterrors_enetunreach }, { "none", Opt_fatal_neterrors_none }, {} }; enum { Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_none, Opt_local_lock_posix, }; static const struct constant_table nfs_param_enums_local_lock[] = { { "all", Opt_local_lock_all }, { "flock", Opt_local_lock_flock }, { "posix", Opt_local_lock_posix }, { "none", Opt_local_lock_none }, {} }; enum { Opt_lookupcache_all, Opt_lookupcache_none, Opt_lookupcache_positive, }; static const struct constant_table nfs_param_enums_lookupcache[] = { { "all", Opt_lookupcache_all }, { "none", Opt_lookupcache_none }, { "pos", Opt_lookupcache_positive }, { "positive", Opt_lookupcache_positive }, {} }; enum { Opt_write_lazy, Opt_write_eager, Opt_write_wait, }; static const struct constant_table nfs_param_enums_write[] = { { "lazy", Opt_write_lazy }, { "eager", Opt_write_eager }, { "wait", Opt_write_wait }, {} }; static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_flag_no("ac", Opt_ac), fsparam_u32 ("acdirmax", Opt_acdirmax), fsparam_u32 ("acdirmin", Opt_acdirmin), fsparam_flag_no("acl", Opt_acl), fsparam_u32 ("acregmax", Opt_acregmax), fsparam_u32 ("acregmin", Opt_acregmin), fsparam_u32 ("actimeo", Opt_actimeo), fsparam_string("addr", Opt_addr), fsparam_flag ("bg", Opt_bg), fsparam_u32 ("bsize", Opt_bsize), fsparam_string("clientaddr", Opt_clientaddr), fsparam_flag_no("cto", Opt_cto), fsparam_flag_no("alignwrite", Opt_alignwrite), fsparam_enum("fatal_neterrors", Opt_fatal_neterrors, nfs_param_enums_fatal_neterrors), fsparam_flag ("fg", Opt_fg), fsparam_flag_no("fsc", Opt_fscache_flag), fsparam_string("fsc", Opt_fscache), fsparam_flag ("hard", Opt_hard), __fsparam(NULL, "intr", Opt_intr, fs_param_neg_with_no|fs_param_deprecated, NULL), fsparam_enum ("local_lock", Opt_local_lock, nfs_param_enums_local_lock), fsparam_flag_no("lock", Opt_lock), fsparam_enum ("lookupcache", Opt_lookupcache, nfs_param_enums_lookupcache), fsparam_flag_no("migration", Opt_migration), fsparam_u32 ("minorversion", Opt_minorversion), fsparam_string("mountaddr", Opt_mountaddr), fsparam_string("mounthost", Opt_mounthost), fsparam_u32 ("mountport", Opt_mountport), fsparam_string("mountproto", Opt_mountproto), fsparam_u32 ("mountvers", Opt_mountvers), fsparam_u32 ("namlen", Opt_namelen), fsparam_u32 ("nconnect", Opt_nconnect), fsparam_u32 ("max_connect", Opt_max_connect), fsparam_string("nfsvers", Opt_vers), fsparam_u32 ("port", Opt_port), fsparam_flag_no("posix", Opt_posix), fsparam_string("proto", Opt_proto), fsparam_flag_no("rdirplus", Opt_rdirplus), // rdirplus|nordirplus fsparam_string("rdirplus", Opt_rdirplus), // rdirplus=... fsparam_flag ("rdma", Opt_rdma), fsparam_flag_no("resvport", Opt_resvport), fsparam_u32 ("retrans", Opt_retrans), fsparam_string("retry", Opt_retry), fsparam_u32 ("rsize", Opt_rsize), fsparam_string("sec", Opt_sec), fsparam_flag_no("sharecache", Opt_sharecache), fsparam_flag ("sloppy", Opt_sloppy), fsparam_flag ("soft", Opt_soft), fsparam_flag ("softerr", Opt_softerr), fsparam_flag ("softreval", Opt_softreval), fsparam_string("source", Opt_source), fsparam_flag ("tcp", Opt_tcp), fsparam_u32 ("timeo", Opt_timeo), fsparam_flag_no("trunkdiscovery", Opt_trunkdiscovery), fsparam_flag ("udp", Opt_udp), fsparam_flag ("v2", Opt_v), fsparam_flag ("v3", Opt_v), fsparam_flag ("v4", Opt_v), fsparam_flag ("v4.0", Opt_v), fsparam_flag ("v4.1", Opt_v), fsparam_flag ("v4.2", Opt_v), fsparam_string("vers", Opt_vers), fsparam_enum ("write", Opt_write, nfs_param_enums_write), fsparam_u32 ("wsize", Opt_wsize), fsparam_string("xprtsec", Opt_xprtsec), fsparam_s32("cert_serial", Opt_cert_serial), fsparam_s32("privkey_serial", Opt_privkey_serial), {} }; enum { Opt_vers_2, Opt_vers_3, Opt_vers_4, Opt_vers_4_0, Opt_vers_4_1, Opt_vers_4_2, }; static const struct constant_table nfs_vers_tokens[] = { { "2", Opt_vers_2 }, { "3", Opt_vers_3 }, { "4", Opt_vers_4 }, { "4.0", Opt_vers_4_0 }, { "4.1", Opt_vers_4_1 }, { "4.2", Opt_vers_4_2 }, {} }; enum { Opt_xprt_rdma, Opt_xprt_rdma6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_udp, Opt_xprt_udp6, nr__Opt_xprt }; static const struct constant_table nfs_xprt_protocol_tokens[] = { { "rdma", Opt_xprt_rdma }, { "rdma6", Opt_xprt_rdma6 }, { "tcp", Opt_xprt_tcp }, { "tcp6", Opt_xprt_tcp6 }, { "udp", Opt_xprt_udp }, { "udp6", Opt_xprt_udp6 }, {} }; enum { Opt_sec_krb5, Opt_sec_krb5i, Opt_sec_krb5p, Opt_sec_lkey, Opt_sec_lkeyi, Opt_sec_lkeyp, Opt_sec_none, Opt_sec_spkm, Opt_sec_spkmi, Opt_sec_spkmp, Opt_sec_sys, nr__Opt_sec }; static const struct constant_table nfs_secflavor_tokens[] = { { "krb5", Opt_sec_krb5 }, { "krb5i", Opt_sec_krb5i }, { "krb5p", Opt_sec_krb5p }, { "lkey", Opt_sec_lkey }, { "lkeyi", Opt_sec_lkeyi }, { "lkeyp", Opt_sec_lkeyp }, { "none", Opt_sec_none }, { "null", Opt_sec_none }, { "spkm3", Opt_sec_spkm }, { "spkm3i", Opt_sec_spkmi }, { "spkm3p", Opt_sec_spkmp }, { "sys", Opt_sec_sys }, {} }; enum { Opt_xprtsec_none, Opt_xprtsec_tls, Opt_xprtsec_mtls, nr__Opt_xprtsec }; static const struct constant_table nfs_xprtsec_policies[] = { { "none", Opt_xprtsec_none }, { "tls", Opt_xprtsec_tls }, { "mtls", Opt_xprtsec_mtls }, {} }; static const struct constant_table nfs_rdirplus_tokens[] = { { "none", Opt_rdirplus_none }, { "force", Opt_rdirplus_force }, {} }; /* * Sanity-check a server address provided by the mount command. * * Address family must be initialized, and address must not be * the ANY address for that family. */ static int nfs_verify_server_address(struct sockaddr_storage *addr) { switch (addr->ss_family) { case AF_INET: { struct sockaddr_in *sa = (struct sockaddr_in *)addr; return sa->sin_addr.s_addr != htonl(INADDR_ANY); } case AF_INET6: { struct in6_addr *sa = &((struct sockaddr_in6 *)addr)->sin6_addr; return !ipv6_addr_any(sa); } } return 0; } #ifdef CONFIG_NFS_DISABLE_UDP_SUPPORT static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx) { return true; } #else static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx) { if (ctx->version == 4) return true; return false; } #endif /* * Sanity check the NFS transport protocol. */ static int nfs_validate_transport_protocol(struct fs_context *fc, struct nfs_fs_context *ctx) { switch (ctx->nfs_server.protocol) { case XPRT_TRANSPORT_UDP: if (nfs_server_transport_udp_invalid(ctx)) goto out_invalid_transport_udp; break; case XPRT_TRANSPORT_TCP: case XPRT_TRANSPORT_RDMA: break; default: ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; } if (ctx->xprtsec.policy != RPC_XPRTSEC_NONE) switch (ctx->nfs_server.protocol) { case XPRT_TRANSPORT_TCP: ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP_TLS; break; default: goto out_invalid_xprtsec_policy; } return 0; out_invalid_transport_udp: return nfs_invalf(fc, "NFS: Unsupported transport protocol udp"); out_invalid_xprtsec_policy: return nfs_invalf(fc, "NFS: Transport does not support xprtsec"); } /* * For text based NFSv2/v3 mounts, the mount protocol transport default * settings should depend upon the specified NFS transport. */ static void nfs_set_mount_transport_protocol(struct nfs_fs_context *ctx) { if (ctx->mount_server.protocol == XPRT_TRANSPORT_UDP || ctx->mount_server.protocol == XPRT_TRANSPORT_TCP) return; switch (ctx->nfs_server.protocol) { case XPRT_TRANSPORT_UDP: ctx->mount_server.protocol = XPRT_TRANSPORT_UDP; break; case XPRT_TRANSPORT_TCP: case XPRT_TRANSPORT_RDMA: ctx->mount_server.protocol = XPRT_TRANSPORT_TCP; } } /* * Add 'flavor' to 'auth_info' if not already present. * Returns true if 'flavor' ends up in the list, false otherwise */ static int nfs_auth_info_add(struct fs_context *fc, struct nfs_auth_info *auth_info, rpc_authflavor_t flavor) { unsigned int i; unsigned int max_flavor_len = ARRAY_SIZE(auth_info->flavors); /* make sure this flavor isn't already in the list */ for (i = 0; i < auth_info->flavor_len; i++) { if (flavor == auth_info->flavors[i]) return 0; } if (auth_info->flavor_len + 1 >= max_flavor_len) return nfs_invalf(fc, "NFS: too many sec= flavors"); auth_info->flavors[auth_info->flavor_len++] = flavor; return 0; } /* * Parse the value of the 'sec=' option. */ static int nfs_parse_security_flavors(struct fs_context *fc, struct fs_parameter *param) { struct nfs_fs_context *ctx = nfs_fc2context(fc); rpc_authflavor_t pseudoflavor; char *string = param->string, *p; int ret; trace_nfs_mount_assign(param->key, string); while ((p = strsep(&string, ":")) != NULL) { if (!*p) continue; switch (lookup_constant(nfs_secflavor_tokens, p, -1)) { case Opt_sec_none: pseudoflavor = RPC_AUTH_NULL; break; case Opt_sec_sys: pseudoflavor = RPC_AUTH_UNIX; break; case Opt_sec_krb5: pseudoflavor = RPC_AUTH_GSS_KRB5; break; case Opt_sec_krb5i: pseudoflavor = RPC_AUTH_GSS_KRB5I; break; case Opt_sec_krb5p: pseudoflavor = RPC_AUTH_GSS_KRB5P; break; case Opt_sec_lkey: pseudoflavor = RPC_AUTH_GSS_LKEY; break; case Opt_sec_lkeyi: pseudoflavor = RPC_AUTH_GSS_LKEYI; break; case Opt_sec_lkeyp: pseudoflavor = RPC_AUTH_GSS_LKEYP; break; case Opt_sec_spkm: pseudoflavor = RPC_AUTH_GSS_SPKM; break; case Opt_sec_spkmi: pseudoflavor = RPC_AUTH_GSS_SPKMI; break; case Opt_sec_spkmp: pseudoflavor = RPC_AUTH_GSS_SPKMP; break; default: return nfs_invalf(fc, "NFS: sec=%s option not recognized", p); } ret = nfs_auth_info_add(fc, &ctx->auth_info, pseudoflavor); if (ret < 0) return ret; } return 0; } static int nfs_parse_xprtsec_policy(struct fs_context *fc, struct fs_parameter *param) { struct nfs_fs_context *ctx = nfs_fc2context(fc); trace_nfs_mount_assign(param->key, param->string); switch (lookup_constant(nfs_xprtsec_policies, param->string, -1)) { case Opt_xprtsec_none: ctx->xprtsec.policy = RPC_XPRTSEC_NONE; break; case Opt_xprtsec_tls: ctx->xprtsec.policy = RPC_XPRTSEC_TLS_ANON; break; case Opt_xprtsec_mtls: ctx->xprtsec.policy = RPC_XPRTSEC_TLS_X509; break; default: return nfs_invalf(fc, "NFS: Unrecognized transport security policy"); } return 0; } static int nfs_parse_version_string(struct fs_context *fc, const char *string) { struct nfs_fs_context *ctx = nfs_fc2context(fc); ctx->flags &= ~NFS_MOUNT_VER3; switch (lookup_constant(nfs_vers_tokens, string, -1)) { case Opt_vers_2: ctx->version = 2; break; case Opt_vers_3: ctx->flags |= NFS_MOUNT_VER3; ctx->version = 3; break; case Opt_vers_4: /* Backward compatibility option. In future, * the mount program should always supply * a NFSv4 minor version number. */ ctx->version = 4; break; case Opt_vers_4_0: ctx->version = 4; ctx->minorversion = 0; break; case Opt_vers_4_1: ctx->version = 4; ctx->minorversion = 1; break; case Opt_vers_4_2: ctx->version = 4; ctx->minorversion = 2; break; default: return nfs_invalf(fc, "NFS: Unsupported NFS version"); } return 0; } #ifdef CONFIG_KEYS static int nfs_tls_key_verify(key_serial_t key_id) { struct key *key = key_lookup(key_id); int error = 0; if (IS_ERR(key)) { pr_err("key id %08x not found\n", key_id); return PTR_ERR(key); } if (test_bit(KEY_FLAG_REVOKED, &key->flags) || test_bit(KEY_FLAG_INVALIDATED, &key->flags)) { pr_err("key id %08x revoked\n", key_id); error = -EKEYREVOKED; } key_put(key); return error; } #else static inline int nfs_tls_key_verify(key_serial_t key_id) { return -ENOENT; } #endif /* CONFIG_KEYS */ /* * Parse a single mount parameter. */ static int nfs_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; struct nfs_fs_context *ctx = nfs_fc2context(fc); unsigned short protofamily, mountfamily; unsigned int len; int ret, opt; trace_nfs_mount_option(param); opt = fs_parse(fc, nfs_fs_parameters, param, &result); if (opt < 0) return (opt == -ENOPARAM && ctx->sloppy) ? 1 : opt; if (fc->security) ctx->has_sec_mnt_opts = 1; switch (opt) { case Opt_source: if (fc->source) return nfs_invalf(fc, "NFS: Multiple sources not supported"); fc->source = param->string; param->string = NULL; break; /* * boolean options: foo/nofoo */ case Opt_soft: ctx->flags |= NFS_MOUNT_SOFT; ctx->flags &= ~NFS_MOUNT_SOFTERR; break; case Opt_softerr: ctx->flags |= NFS_MOUNT_SOFTERR | NFS_MOUNT_SOFTREVAL; ctx->flags &= ~NFS_MOUNT_SOFT; break; case Opt_hard: ctx->flags &= ~(NFS_MOUNT_SOFT | NFS_MOUNT_SOFTERR | NFS_MOUNT_SOFTREVAL); break; case Opt_softreval: if (result.negated) ctx->flags &= ~NFS_MOUNT_SOFTREVAL; else ctx->flags |= NFS_MOUNT_SOFTREVAL; break; case Opt_posix: if (result.negated) ctx->flags &= ~NFS_MOUNT_POSIX; else ctx->flags |= NFS_MOUNT_POSIX; break; case Opt_cto: if (result.negated) ctx->flags |= NFS_MOUNT_NOCTO; else ctx->flags &= ~NFS_MOUNT_NOCTO; break; case Opt_trunkdiscovery: if (result.negated) ctx->flags &= ~NFS_MOUNT_TRUNK_DISCOVERY; else ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY; break; case Opt_alignwrite: if (result.negated) ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE; else ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE; break; case Opt_ac: if (result.negated) ctx->flags |= NFS_MOUNT_NOAC; else ctx->flags &= ~NFS_MOUNT_NOAC; break; case Opt_lock: if (result.negated) { ctx->lock_status = NFS_LOCK_NOLOCK; ctx->flags |= NFS_MOUNT_NONLM; ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } else { ctx->lock_status = NFS_LOCK_LOCK; ctx->flags &= ~NFS_MOUNT_NONLM; ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } break; case Opt_udp: ctx->flags &= ~NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_tcp: case Opt_rdma: ctx->flags |= NFS_MOUNT_TCP; /* for side protocols */ ret = xprt_find_transport_ident(param->key); if (ret < 0) goto out_bad_transport; ctx->nfs_server.protocol = ret; break; case Opt_acl: if (result.negated) ctx->flags |= NFS_MOUNT_NOACL; else ctx->flags &= ~NFS_MOUNT_NOACL; break; case Opt_rdirplus: if (result.negated) { ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS; ctx->flags |= NFS_MOUNT_NORDIRPLUS; } else if (!param->string) { ctx->flags &= ~(NFS_MOUNT_NORDIRPLUS | NFS_MOUNT_FORCE_RDIRPLUS); } else { switch (lookup_constant(nfs_rdirplus_tokens, param->string, -1)) { case Opt_rdirplus_none: ctx->flags &= ~NFS_MOUNT_FORCE_RDIRPLUS; ctx->flags |= NFS_MOUNT_NORDIRPLUS; break; case Opt_rdirplus_force: ctx->flags &= ~NFS_MOUNT_NORDIRPLUS; ctx->flags |= NFS_MOUNT_FORCE_RDIRPLUS; break; default: goto out_invalid_value; } } break; case Opt_sharecache: if (result.negated) ctx->flags |= NFS_MOUNT_UNSHARED; else ctx->flags &= ~NFS_MOUNT_UNSHARED; break; case Opt_resvport: if (result.negated) ctx->flags |= NFS_MOUNT_NORESVPORT; else ctx->flags &= ~NFS_MOUNT_NORESVPORT; break; case Opt_fscache_flag: if (result.negated) ctx->options &= ~NFS_OPTION_FSCACHE; else ctx->options |= NFS_OPTION_FSCACHE; kfree(ctx->fscache_uniq); ctx->fscache_uniq = NULL; break; case Opt_fscache: trace_nfs_mount_assign(param->key, param->string); ctx->options |= NFS_OPTION_FSCACHE; kfree(ctx->fscache_uniq); ctx->fscache_uniq = param->string; param->string = NULL; break; case Opt_migration: if (result.negated) ctx->options &= ~NFS_OPTION_MIGRATION; else ctx->options |= NFS_OPTION_MIGRATION; break; /* * options that take numeric values */ case Opt_port: if (result.uint_32 > USHRT_MAX) goto out_of_bounds; ctx->nfs_server.port = result.uint_32; break; case Opt_rsize: ctx->rsize = result.uint_32; break; case Opt_wsize: ctx->wsize = result.uint_32; break; case Opt_bsize: ctx->bsize = result.uint_32; break; case Opt_timeo: if (result.uint_32 < 1 || result.uint_32 > INT_MAX) goto out_of_bounds; ctx->timeo = result.uint_32; break; case Opt_retrans: if (result.uint_32 > INT_MAX) goto out_of_bounds; ctx->retrans = result.uint_32; break; case Opt_acregmin: ctx->acregmin = result.uint_32; break; case Opt_acregmax: ctx->acregmax = result.uint_32; break; case Opt_acdirmin: ctx->acdirmin = result.uint_32; break; case Opt_acdirmax: ctx->acdirmax = result.uint_32; break; case Opt_actimeo: ctx->acregmin = result.uint_32; ctx->acregmax = result.uint_32; ctx->acdirmin = result.uint_32; ctx->acdirmax = result.uint_32; break; case Opt_namelen: ctx->namlen = result.uint_32; break; case Opt_mountport: if (result.uint_32 > USHRT_MAX) goto out_of_bounds; ctx->mount_server.port = result.uint_32; break; case Opt_mountvers: if (result.uint_32 < NFS_MNT_VERSION || result.uint_32 > NFS_MNT3_VERSION) goto out_of_bounds; ctx->mount_server.version = result.uint_32; break; case Opt_minorversion: if (result.uint_32 < NFS4_MIN_MINOR_VERSION || result.uint_32 > NFS4_MAX_MINOR_VERSION) goto out_of_bounds; ctx->minorversion = result.uint_32; break; /* * options that take text values */ case Opt_v: ret = nfs_parse_version_string(fc, param->key + 1); if (ret < 0) return ret; break; case Opt_vers: if (!param->string) goto out_invalid_value; trace_nfs_mount_assign(param->key, param->string); ret = nfs_parse_version_string(fc, param->string); if (ret < 0) return ret; break; case Opt_sec: ret = nfs_parse_security_flavors(fc, param); if (ret < 0) return ret; break; case Opt_xprtsec: ret = nfs_parse_xprtsec_policy(fc, param); if (ret < 0) return ret; break; case Opt_cert_serial: ret = nfs_tls_key_verify(result.int_32); if (ret < 0) return ret; ctx->xprtsec.cert_serial = result.int_32; break; case Opt_privkey_serial: ret = nfs_tls_key_verify(result.int_32); if (ret < 0) return ret; ctx->xprtsec.privkey_serial = result.int_32; break; case Opt_proto: if (!param->string) goto out_invalid_value; trace_nfs_mount_assign(param->key, param->string); protofamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: protofamily = AF_INET6; fallthrough; case Opt_xprt_udp: ctx->flags &= ~NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_xprt_tcp6: protofamily = AF_INET6; fallthrough; case Opt_xprt_tcp: ctx->flags |= NFS_MOUNT_TCP; ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; break; case Opt_xprt_rdma6: protofamily = AF_INET6; fallthrough; case Opt_xprt_rdma: /* vector side protocols to TCP */ ctx->flags |= NFS_MOUNT_TCP; ret = xprt_find_transport_ident(param->string); if (ret < 0) goto out_bad_transport; ctx->nfs_server.protocol = ret; break; default: goto out_bad_transport; } ctx->protofamily = protofamily; break; case Opt_mountproto: if (!param->string) goto out_invalid_value; trace_nfs_mount_assign(param->key, param->string); mountfamily = AF_INET; switch (lookup_constant(nfs_xprt_protocol_tokens, param->string, -1)) { case Opt_xprt_udp6: mountfamily = AF_INET6; fallthrough; case Opt_xprt_udp: ctx->mount_server.protocol = XPRT_TRANSPORT_UDP; break; case Opt_xprt_tcp6: mountfamily = AF_INET6; fallthrough; case Opt_xprt_tcp: ctx->mount_server.protocol = XPRT_TRANSPORT_TCP; break; case Opt_xprt_rdma: /* not used for side protocols */ default: goto out_bad_transport; } ctx->mountfamily = mountfamily; break; case Opt_addr: trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->nfs_server.address, sizeof(ctx->nfs_server._address)); if (len == 0) goto out_invalid_address; ctx->nfs_server.addrlen = len; break; case Opt_clientaddr: trace_nfs_mount_assign(param->key, param->string); kfree(ctx->client_address); ctx->client_address = param->string; param->string = NULL; break; case Opt_mounthost: trace_nfs_mount_assign(param->key, param->string); kfree(ctx->mount_server.hostname); ctx->mount_server.hostname = param->string; param->string = NULL; break; case Opt_mountaddr: trace_nfs_mount_assign(param->key, param->string); len = rpc_pton(fc->net_ns, param->string, param->size, &ctx->mount_server.address, sizeof(ctx->mount_server._address)); if (len == 0) goto out_invalid_address; ctx->mount_server.addrlen = len; break; case Opt_nconnect: trace_nfs_mount_assign(param->key, param->string); if (result.uint_32 < 1 || result.uint_32 > NFS_MAX_CONNECTIONS) goto out_of_bounds; ctx->nfs_server.nconnect = result.uint_32; break; case Opt_max_connect: trace_nfs_mount_assign(param->key, param->string); if (result.uint_32 < 1 || result.uint_32 > NFS_MAX_TRANSPORTS) goto out_of_bounds; ctx->nfs_server.max_connect = result.uint_32; break; case Opt_fatal_neterrors: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_fatal_neterrors_default: if (fc->net_ns != &init_net) ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL; else ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL; break; case Opt_fatal_neterrors_enetunreach: ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL; break; case Opt_fatal_neterrors_none: ctx->flags &= ~NFS_MOUNT_NETUNREACH_FATAL; break; default: goto out_invalid_value; } break; case Opt_lookupcache: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_lookupcache_all: ctx->flags &= ~(NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE); break; case Opt_lookupcache_positive: ctx->flags &= ~NFS_MOUNT_LOOKUP_CACHE_NONE; ctx->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG; break; case Opt_lookupcache_none: ctx->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE; break; default: goto out_invalid_value; } break; case Opt_local_lock: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_local_lock_all: ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); break; case Opt_local_lock_flock: ctx->flags |= NFS_MOUNT_LOCAL_FLOCK; break; case Opt_local_lock_posix: ctx->flags |= NFS_MOUNT_LOCAL_FCNTL; break; case Opt_local_lock_none: ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); break; default: goto out_invalid_value; } break; case Opt_write: trace_nfs_mount_assign(param->key, param->string); switch (result.uint_32) { case Opt_write_lazy: ctx->flags &= ~(NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT); break; case Opt_write_eager: ctx->flags |= NFS_MOUNT_WRITE_EAGER; ctx->flags &= ~NFS_MOUNT_WRITE_WAIT; break; case Opt_write_wait: ctx->flags |= NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT; break; default: goto out_invalid_value; } break; /* * Special options */ case Opt_sloppy: ctx->sloppy = true; break; } return 0; out_invalid_value: return nfs_invalf(fc, "NFS: Bad mount option value specified"); out_invalid_address: return nfs_invalf(fc, "NFS: Bad IP address specified"); out_of_bounds: return nfs_invalf(fc, "NFS: Value for '%s' out of range", param->key); out_bad_transport: return nfs_invalf(fc, "NFS: Unrecognized transport protocol"); } /* * Split fc->source into "hostname:export_path". * * The leftmost colon demarks the split between the server's hostname * and the export path. If the hostname starts with a left square * bracket, then it may contain colons. * * Note: caller frees hostname and export path, even on error. */ static int nfs_parse_source(struct fs_context *fc, size_t maxnamlen, size_t maxpathlen) { struct nfs_fs_context *ctx = nfs_fc2context(fc); const char *dev_name = fc->source; size_t len; const char *end; if (unlikely(!dev_name || !*dev_name)) return -EINVAL; /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { end = strchr(++dev_name, ']'); if (end == NULL || end[1] != ':') goto out_bad_devname; len = end - dev_name; end++; } else { const char *comma; end = strchr(dev_name, ':'); if (end == NULL) goto out_bad_devname; len = end - dev_name; /* kill possible hostname list: not supported */ comma = memchr(dev_name, ',', len); if (comma) len = comma - dev_name; } if (len > maxnamlen) goto out_hostname; kfree(ctx->nfs_server.hostname); /* N.B. caller will free nfs_server.hostname in all cases */ ctx->nfs_server.hostname = kmemdup_nul(dev_name, len, GFP_KERNEL); if (!ctx->nfs_server.hostname) goto out_nomem; len = strlen(++end); if (len > maxpathlen) goto out_path; ctx->nfs_server.export_path = kmemdup_nul(end, len, GFP_KERNEL); if (!ctx->nfs_server.export_path) goto out_nomem; trace_nfs_mount_path(ctx->nfs_server.export_path); return 0; out_bad_devname: return nfs_invalf(fc, "NFS: device name not in host:path format"); out_nomem: nfs_errorf(fc, "NFS: not enough memory to parse device name"); return -ENOMEM; out_hostname: nfs_errorf(fc, "NFS: server hostname too long"); return -ENAMETOOLONG; out_path: nfs_errorf(fc, "NFS: export pathname too long"); return -ENAMETOOLONG; } static inline bool is_remount_fc(struct fs_context *fc) { return fc->root != NULL; } /* * Parse monolithic NFS2/NFS3 mount data * - fills in the mount root filehandle * * For option strings, user space handles the following behaviors: * * + DNS: mapping server host name to IP address ("addr=" option) * * + failure mode: how to behave if a mount request can't be handled * immediately ("fg/bg" option) * * + retry: how often to retry a mount request ("retry=" option) * * + breaking back: trying proto=udp after proto=tcp, v2 after v3, * mountproto=tcp after mountproto=udp, and so on */ static int nfs23_parse_monolithic(struct fs_context *fc, struct nfs_mount_data *data) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_fh *mntfh = ctx->mntfh; struct sockaddr_storage *sap = &ctx->nfs_server._address; int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; int ret; if (data == NULL) goto out_no_data; ctx->version = NFS_DEFAULT_VERSION; switch (data->version) { case 1: data->namlen = 0; fallthrough; case 2: data->bsize = 0; fallthrough; case 3: if (data->flags & NFS_MOUNT_VER3) goto out_no_v3; data->root.size = NFS2_FHSIZE; memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); /* Turn off security negotiation */ extra_flags |= NFS_MOUNT_SECFLAVOUR; fallthrough; case 4: if (data->flags & NFS_MOUNT_SECFLAVOUR) goto out_no_sec; fallthrough; case 5: memset(data->context, 0, sizeof(data->context)); fallthrough; case 6: if (data->flags & NFS_MOUNT_VER3) { if (data->root.size > NFS3_FHSIZE || data->root.size == 0) goto out_invalid_fh; mntfh->size = data->root.size; ctx->version = 3; } else { mntfh->size = NFS2_FHSIZE; ctx->version = 2; } memcpy(mntfh->data, data->root.data, mntfh->size); if (mntfh->size < sizeof(mntfh->data)) memset(mntfh->data + mntfh->size, 0, sizeof(mntfh->data) - mntfh->size); /* * for proto == XPRT_TRANSPORT_UDP, which is what uses * to_exponential, implying shift: limit the shift value * to BITS_PER_LONG (majortimeo is unsigned long) */ if (!(data->flags & NFS_MOUNT_TCP)) /* this will be UDP */ if (data->retrans >= 64) /* shift value is too large */ goto out_invalid_data; /* * Translate to nfs_fs_context, which nfs_fill_super * can deal with. */ ctx->flags = data->flags & NFS_MOUNT_FLAGMASK; ctx->flags |= extra_flags; ctx->rsize = data->rsize; ctx->wsize = data->wsize; ctx->timeo = data->timeo; ctx->retrans = data->retrans; ctx->acregmin = data->acregmin; ctx->acregmax = data->acregmax; ctx->acdirmin = data->acdirmin; ctx->acdirmax = data->acdirmax; ctx->need_mount = false; if (!is_remount_fc(fc)) { memcpy(sap, &data->addr, sizeof(data->addr)); ctx->nfs_server.addrlen = sizeof(data->addr); ctx->nfs_server.port = ntohs(data->addr.sin_port); } if (sap->ss_family != AF_INET || !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) ctx->nfs_server.protocol = XPRT_TRANSPORT_UDP; /* N.B. caller will free nfs_server.hostname in all cases */ ctx->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL); if (!ctx->nfs_server.hostname) goto out_nomem; ctx->namlen = data->namlen; ctx->bsize = data->bsize; if (data->flags & NFS_MOUNT_SECFLAVOUR) ctx->selected_flavor = data->pseudoflavor; else ctx->selected_flavor = RPC_AUTH_UNIX; if (!(data->flags & NFS_MOUNT_NONLM)) ctx->flags &= ~(NFS_MOUNT_LOCAL_FLOCK| NFS_MOUNT_LOCAL_FCNTL); else ctx->flags |= (NFS_MOUNT_LOCAL_FLOCK| NFS_MOUNT_LOCAL_FCNTL); /* * The legacy version 6 binary mount data from userspace has a * field used only to transport selinux information into the * kernel. To continue to support that functionality we * have a touch of selinux knowledge here in the NFS code. The * userspace code converted context=blah to just blah so we are * converting back to the full string selinux understands. */ if (data->context[0]){ #ifdef CONFIG_SECURITY_SELINUX int ret; data->context[NFS_MAX_CONTEXT_LEN] = '\0'; ret = vfs_parse_fs_string(fc, "context", data->context); if (ret < 0) return ret; #else return -EINVAL; #endif } break; default: goto generic; } ret = nfs_validate_transport_protocol(fc, ctx); if (ret) return ret; ctx->skip_reconfig_option_check = true; return 0; generic: return generic_parse_monolithic(fc, data); out_no_data: if (is_remount_fc(fc)) { ctx->skip_reconfig_option_check = true; return 0; } return nfs_invalf(fc, "NFS: mount program didn't pass any mount data"); out_no_v3: return nfs_invalf(fc, "NFS: nfs_mount_data version does not support v3"); out_no_sec: return nfs_invalf(fc, "NFS: nfs_mount_data version supports only AUTH_SYS"); out_nomem: return -ENOMEM; out_no_address: return nfs_invalf(fc, "NFS: mount program didn't pass remote address"); out_invalid_fh: return nfs_invalf(fc, "NFS: invalid root filehandle"); out_invalid_data: return nfs_invalf(fc, "NFS: invalid binary mount data"); } #if IS_ENABLED(CONFIG_NFS_V4) struct compat_nfs_string { compat_uint_t len; compat_uptr_t data; }; static inline void compat_nfs_string(struct nfs_string *dst, struct compat_nfs_string *src) { dst->data = compat_ptr(src->data); dst->len = src->len; } struct compat_nfs4_mount_data_v1 { compat_int_t version; compat_int_t flags; compat_int_t rsize; compat_int_t wsize; compat_int_t timeo; compat_int_t retrans; compat_int_t acregmin; compat_int_t acregmax; compat_int_t acdirmin; compat_int_t acdirmax; struct compat_nfs_string client_addr; struct compat_nfs_string mnt_path; struct compat_nfs_string hostname; compat_uint_t host_addrlen; compat_uptr_t host_addr; compat_int_t proto; compat_int_t auth_flavourlen; compat_uptr_t auth_flavours; }; static void nfs4_compat_mount_data_conv(struct nfs4_mount_data *data) { struct compat_nfs4_mount_data_v1 *compat = (struct compat_nfs4_mount_data_v1 *)data; /* copy the fields backwards */ data->auth_flavours = compat_ptr(compat->auth_flavours); data->auth_flavourlen = compat->auth_flavourlen; data->proto = compat->proto; data->host_addr = compat_ptr(compat->host_addr); data->host_addrlen = compat->host_addrlen; compat_nfs_string(&data->hostname, &compat->hostname); compat_nfs_string(&data->mnt_path, &compat->mnt_path); compat_nfs_string(&data->client_addr, &compat->client_addr); data->acdirmax = compat->acdirmax; data->acdirmin = compat->acdirmin; data->acregmax = compat->acregmax; data->acregmin = compat->acregmin; data->retrans = compat->retrans; data->timeo = compat->timeo; data->wsize = compat->wsize; data->rsize = compat->rsize; data->flags = compat->flags; data->version = compat->version; } /* * Validate NFSv4 mount options */ static int nfs4_parse_monolithic(struct fs_context *fc, struct nfs4_mount_data *data) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct sockaddr_storage *sap = &ctx->nfs_server._address; int ret; char *c; if (!data) { if (is_remount_fc(fc)) goto done; return nfs_invalf(fc, "NFS4: mount program didn't pass any mount data"); } ctx->version = 4; if (data->version != 1) return generic_parse_monolithic(fc, data); if (in_compat_syscall()) nfs4_compat_mount_data_conv(data); if (data->host_addrlen > sizeof(ctx->nfs_server.address)) goto out_no_address; if (data->host_addrlen == 0) goto out_no_address; ctx->nfs_server.addrlen = data->host_addrlen; if (copy_from_user(sap, data->host_addr, data->host_addrlen)) return -EFAULT; if (!nfs_verify_server_address(sap)) goto out_no_address; ctx->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); if (data->auth_flavourlen) { rpc_authflavor_t pseudoflavor; if (data->auth_flavourlen > 1) goto out_inval_auth; if (copy_from_user(&pseudoflavor, data->auth_flavours, sizeof(pseudoflavor))) return -EFAULT; ctx->selected_flavor = pseudoflavor; } else { ctx->selected_flavor = RPC_AUTH_UNIX; } c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); if (IS_ERR(c)) return PTR_ERR(c); ctx->nfs_server.hostname = c; c = strndup_user(data->mnt_path.data, NFS4_MAXPATHLEN); if (IS_ERR(c)) return PTR_ERR(c); ctx->nfs_server.export_path = c; trace_nfs_mount_path(c); c = strndup_user(data->client_addr.data, 16); if (IS_ERR(c)) return PTR_ERR(c); ctx->client_address = c; /* * Translate to nfs_fs_context, which nfs_fill_super * can deal with. */ ctx->flags = data->flags & NFS4_MOUNT_FLAGMASK; ctx->rsize = data->rsize; ctx->wsize = data->wsize; ctx->timeo = data->timeo; ctx->retrans = data->retrans; ctx->acregmin = data->acregmin; ctx->acregmax = data->acregmax; ctx->acdirmin = data->acdirmin; ctx->acdirmax = data->acdirmax; ctx->nfs_server.protocol = data->proto; ret = nfs_validate_transport_protocol(fc, ctx); if (ret) return ret; done: ctx->skip_reconfig_option_check = true; return 0; out_inval_auth: return nfs_invalf(fc, "NFS4: Invalid number of RPC auth flavours %d", data->auth_flavourlen); out_no_address: return nfs_invalf(fc, "NFS4: mount program didn't pass remote address"); } #endif /* * Parse a monolithic block of data from sys_mount(). */ static int nfs_fs_context_parse_monolithic(struct fs_context *fc, void *data) { if (fc->fs_type == &nfs_fs_type) return nfs23_parse_monolithic(fc, data); #if IS_ENABLED(CONFIG_NFS_V4) if (fc->fs_type == &nfs4_fs_type) return nfs4_parse_monolithic(fc, data); #endif return nfs_invalf(fc, "NFS: Unsupported monolithic data version"); } /* * Validate the preparsed information in the config. */ static int nfs_fs_context_validate(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_subversion *nfs_mod; struct sockaddr_storage *sap = &ctx->nfs_server._address; int max_namelen = PAGE_SIZE; int max_pathlen = NFS_MAXPATHLEN; int port = 0; int ret; if (!fc->source) goto out_no_device_name; /* Check for sanity first. */ if (ctx->minorversion && ctx->version != 4) goto out_minorversion_mismatch; if (ctx->options & NFS_OPTION_MIGRATION && (ctx->version != 4 || ctx->minorversion != 0)) goto out_migration_misuse; /* Verify that any proto=/mountproto= options match the address * families in the addr=/mountaddr= options. */ if (ctx->protofamily != AF_UNSPEC && ctx->protofamily != ctx->nfs_server.address.sa_family) goto out_proto_mismatch; if (ctx->mountfamily != AF_UNSPEC) { if (ctx->mount_server.addrlen) { if (ctx->mountfamily != ctx->mount_server.address.sa_family) goto out_mountproto_mismatch; } else { if (ctx->mountfamily != ctx->nfs_server.address.sa_family) goto out_mountproto_mismatch; } } if (!nfs_verify_server_address(sap)) goto out_no_address; ret = nfs_validate_transport_protocol(fc, ctx); if (ret) return ret; if (ctx->version == 4) { if (IS_ENABLED(CONFIG_NFS_V4)) { if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA) port = NFS_RDMA_PORT; else port = NFS_PORT; max_namelen = NFS4_MAXNAMLEN; max_pathlen = NFS4_MAXPATHLEN; ctx->flags &= ~(NFS_MOUNT_NONLM | NFS_MOUNT_NOACL | NFS_MOUNT_VER3 | NFS_MOUNT_LOCAL_FLOCK | NFS_MOUNT_LOCAL_FCNTL); } else { goto out_v4_not_compiled; } } else { nfs_set_mount_transport_protocol(ctx); if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA) port = NFS_RDMA_PORT; } nfs_set_port(sap, &ctx->nfs_server.port, port); ret = nfs_parse_source(fc, max_namelen, max_pathlen); if (ret < 0) return ret; /* Load the NFS protocol module if we haven't done so yet */ if (!ctx->nfs_mod) { nfs_mod = find_nfs_version(ctx->version); if (IS_ERR(nfs_mod)) { ret = PTR_ERR(nfs_mod); goto out_version_unavailable; } ctx->nfs_mod = nfs_mod; } /* Ensure the filesystem context has the correct fs_type */ if (fc->fs_type != ctx->nfs_mod->nfs_fs) { module_put(fc->fs_type->owner); __module_get(ctx->nfs_mod->nfs_fs->owner); fc->fs_type = ctx->nfs_mod->nfs_fs; } return 0; out_no_device_name: return nfs_invalf(fc, "NFS: Device name not specified"); out_v4_not_compiled: nfs_errorf(fc, "NFS: NFSv4 is not compiled into kernel"); return -EPROTONOSUPPORT; out_no_address: return nfs_invalf(fc, "NFS: mount program didn't pass remote address"); out_mountproto_mismatch: return nfs_invalf(fc, "NFS: Mount server address does not match mountproto= option"); out_proto_mismatch: return nfs_invalf(fc, "NFS: Server address does not match proto= option"); out_minorversion_mismatch: return nfs_invalf(fc, "NFS: Mount option vers=%u does not support minorversion=%u", ctx->version, ctx->minorversion); out_migration_misuse: return nfs_invalf(fc, "NFS: 'Migration' not supported for this NFS version"); out_version_unavailable: nfs_errorf(fc, "NFS: Version unavailable"); return ret; } /* * Create an NFS superblock by the appropriate method. */ static int nfs_get_tree(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); int err = nfs_fs_context_validate(fc); if (err) return err; if (!ctx->internal) return ctx->nfs_mod->rpc_ops->try_get_tree(fc); else return nfs_get_tree_common(fc); } /* * Handle duplication of a configuration. The caller copied *src into *sc, but * it can't deal with resource pointers in the filesystem context, so we have * to do that. We need to clear pointers, copy data or get extra refs as * appropriate. */ static int nfs_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { struct nfs_fs_context *src = nfs_fc2context(src_fc), *ctx; ctx = kmemdup(src, sizeof(struct nfs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->mntfh = nfs_alloc_fhandle(); if (!ctx->mntfh) { kfree(ctx); return -ENOMEM; } nfs_copy_fh(ctx->mntfh, src->mntfh); get_nfs_version(ctx->nfs_mod); ctx->client_address = NULL; ctx->mount_server.hostname = NULL; ctx->nfs_server.export_path = NULL; ctx->nfs_server.hostname = NULL; ctx->fscache_uniq = NULL; ctx->clone_data.fattr = NULL; fc->fs_private = ctx; return 0; } static void nfs_fs_context_free(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); if (ctx) { if (ctx->server) nfs_free_server(ctx->server); if (ctx->nfs_mod) put_nfs_version(ctx->nfs_mod); kfree(ctx->client_address); kfree(ctx->mount_server.hostname); kfree(ctx->nfs_server.export_path); kfree(ctx->nfs_server.hostname); kfree(ctx->fscache_uniq); nfs_free_fhandle(ctx->mntfh); nfs_free_fattr(ctx->clone_data.fattr); kfree(ctx); } } static const struct fs_context_operations nfs_fs_context_ops = { .free = nfs_fs_context_free, .dup = nfs_fs_context_dup, .parse_param = nfs_fs_context_parse_param, .parse_monolithic = nfs_fs_context_parse_monolithic, .get_tree = nfs_get_tree, .reconfigure = nfs_reconfigure, }; /* * Prepare superblock configuration. We use the namespaces attached to the * context. This may be the current process's namespaces, or it may be a * container's namespaces. */ static int nfs_init_fs_context(struct fs_context *fc) { struct nfs_fs_context *ctx; ctx = kzalloc_obj(struct nfs_fs_context); if (unlikely(!ctx)) return -ENOMEM; ctx->mntfh = nfs_alloc_fhandle(); if (unlikely(!ctx->mntfh)) { kfree(ctx); return -ENOMEM; } ctx->protofamily = AF_UNSPEC; ctx->mountfamily = AF_UNSPEC; ctx->mount_server.port = NFS_UNSPEC_PORT; if (fc->root) { /* reconfigure, start with the current config */ struct nfs_server *nfss = fc->root->d_sb->s_fs_info; struct net *net = nfss->nfs_client->cl_net; ctx->flags = nfss->flags; ctx->rsize = nfss->rsize; ctx->wsize = nfss->wsize; ctx->retrans = nfss->client->cl_timeout->to_retries; ctx->selected_flavor = nfss->client->cl_auth->au_flavor; ctx->acregmin = nfss->acregmin / HZ; ctx->acregmax = nfss->acregmax / HZ; ctx->acdirmin = nfss->acdirmin / HZ; ctx->acdirmax = nfss->acdirmax / HZ; ctx->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ; ctx->nfs_server.port = nfss->port; ctx->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; ctx->version = nfss->nfs_client->rpc_ops->version; ctx->minorversion = nfss->nfs_client->cl_minorversion; memcpy(&ctx->nfs_server._address, &nfss->nfs_client->cl_addr, ctx->nfs_server.addrlen); if (fc->net_ns != net) { put_net(fc->net_ns); fc->net_ns = get_net(net); } ctx->nfs_mod = nfss->nfs_client->cl_nfs_mod; get_nfs_version(ctx->nfs_mod); } else { /* defaults */ ctx->timeo = NFS_UNSPEC_TIMEO; ctx->retrans = NFS_UNSPEC_RETRANS; ctx->acregmin = NFS_DEF_ACREGMIN; ctx->acregmax = NFS_DEF_ACREGMAX; ctx->acdirmin = NFS_DEF_ACDIRMIN; ctx->acdirmax = NFS_DEF_ACDIRMAX; ctx->nfs_server.port = NFS_UNSPEC_PORT; ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP; ctx->selected_flavor = RPC_AUTH_MAXFLAVOR; ctx->minorversion = 0; ctx->need_mount = true; ctx->xprtsec.policy = RPC_XPRTSEC_NONE; ctx->xprtsec.cert_serial = TLS_NO_CERT; ctx->xprtsec.privkey_serial = TLS_NO_PRIVKEY; if (fc->net_ns != &init_net) ctx->flags |= NFS_MOUNT_NETUNREACH_FATAL; fc->s_iflags |= SB_I_STABLE_WRITES; } fc->fs_private = ctx; fc->ops = &nfs_fs_context_ops; return 0; } struct file_system_type nfs_fs_type = { .owner = THIS_MODULE, .name = "nfs", .init_fs_context = nfs_init_fs_context, .parameters = nfs_fs_parameters, .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE | FS_BINARY_MOUNTDATA | FS_USERNS_DELEGATABLE, }; MODULE_ALIAS_FS("nfs"); EXPORT_SYMBOL_GPL(nfs_fs_type); #if IS_ENABLED(CONFIG_NFS_V4) struct file_system_type nfs4_fs_type = { .owner = THIS_MODULE, .name = "nfs4", .init_fs_context = nfs_init_fs_context, .parameters = nfs_fs_parameters, .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE | FS_BINARY_MOUNTDATA | FS_USERNS_DELEGATABLE, }; MODULE_ALIAS_FS("nfs4"); MODULE_ALIAS("nfs4"); EXPORT_SYMBOL_GPL(nfs4_fs_type); #endif /* CONFIG_NFS_V4 */ |
| 8 8 34 34 34 34 34 8 8 8 7 7 3 3 3 3 3 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Authors: Bernard Metzler <bmt@zurich.ibm.com> */ /* Copyright (c) 2008-2019, IBM Corporation */ #include <linux/errno.h> #include <linux/types.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/xarray.h> #include <net/addrconf.h> #include <rdma/iw_cm.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> #include <rdma/uverbs_ioctl.h> #include "siw.h" #include "siw_verbs.h" #include "siw_mem.h" static int siw_qp_state_to_ib_qp_state[SIW_QP_STATE_COUNT] = { [SIW_QP_STATE_IDLE] = IB_QPS_INIT, [SIW_QP_STATE_RTR] = IB_QPS_RTR, [SIW_QP_STATE_RTS] = IB_QPS_RTS, [SIW_QP_STATE_CLOSING] = IB_QPS_SQD, [SIW_QP_STATE_TERMINATE] = IB_QPS_SQE, [SIW_QP_STATE_ERROR] = IB_QPS_ERR }; static int ib_qp_state_to_siw_qp_state[IB_QPS_ERR + 1] = { [IB_QPS_RESET] = SIW_QP_STATE_IDLE, [IB_QPS_INIT] = SIW_QP_STATE_IDLE, [IB_QPS_RTR] = SIW_QP_STATE_RTR, [IB_QPS_RTS] = SIW_QP_STATE_RTS, [IB_QPS_SQD] = SIW_QP_STATE_CLOSING, [IB_QPS_SQE] = SIW_QP_STATE_TERMINATE, [IB_QPS_ERR] = SIW_QP_STATE_ERROR }; static char ib_qp_state_to_string[IB_QPS_ERR + 1][sizeof("RESET")] = { [IB_QPS_RESET] = "RESET", [IB_QPS_INIT] = "INIT", [IB_QPS_RTR] = "RTR", [IB_QPS_RTS] = "RTS", [IB_QPS_SQD] = "SQD", [IB_QPS_SQE] = "SQE", [IB_QPS_ERR] = "ERR" }; void siw_mmap_free(struct rdma_user_mmap_entry *rdma_entry) { struct siw_user_mmap_entry *entry = to_siw_mmap_entry(rdma_entry); kfree(entry); } int siw_mmap(struct ib_ucontext *ctx, struct vm_area_struct *vma) { struct siw_ucontext *uctx = to_siw_ctx(ctx); size_t size = vma->vm_end - vma->vm_start; struct rdma_user_mmap_entry *rdma_entry; struct siw_user_mmap_entry *entry; int rv = -EINVAL; /* * Must be page aligned */ if (vma->vm_start & (PAGE_SIZE - 1)) { pr_warn("siw: mmap not page aligned\n"); return -EINVAL; } rdma_entry = rdma_user_mmap_entry_get(&uctx->base_ucontext, vma); if (!rdma_entry) { siw_dbg(&uctx->sdev->base_dev, "mmap lookup failed: %lu, %#zx\n", vma->vm_pgoff, size); return -EINVAL; } entry = to_siw_mmap_entry(rdma_entry); rv = remap_vmalloc_range(vma, entry->address, 0); if (rv) pr_warn("remap_vmalloc_range failed: %lu, %zu\n", vma->vm_pgoff, size); rdma_user_mmap_entry_put(rdma_entry); return rv; } int siw_alloc_ucontext(struct ib_ucontext *base_ctx, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(base_ctx->device); struct siw_ucontext *ctx = to_siw_ctx(base_ctx); struct siw_uresp_alloc_ctx uresp = {}; int rv; if (atomic_inc_return(&sdev->num_ctx) > SIW_MAX_CONTEXT) { rv = -ENOMEM; goto err_out; } ctx->sdev = sdev; uresp.dev_id = sdev->vendor_part_id; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; siw_dbg(base_ctx->device, "success. now %d context(s)\n", atomic_read(&sdev->num_ctx)); return 0; err_out: atomic_dec(&sdev->num_ctx); siw_dbg(base_ctx->device, "failure %d. now %d context(s)\n", rv, atomic_read(&sdev->num_ctx)); return rv; } void siw_dealloc_ucontext(struct ib_ucontext *base_ctx) { struct siw_ucontext *uctx = to_siw_ctx(base_ctx); atomic_dec(&uctx->sdev->num_ctx); } int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(base_dev); if (udata->inlen || udata->outlen) return -EINVAL; memset(attr, 0, sizeof(*attr)); /* Revisit atomic caps if RFC 7306 gets supported */ attr->atomic_cap = 0; attr->device_cap_flags = IB_DEVICE_MEM_MGT_EXTENSIONS; attr->kernel_cap_flags = IBK_ALLOW_USER_UNREG; attr->max_cq = sdev->attrs.max_cq; attr->max_cqe = sdev->attrs.max_cqe; attr->max_fast_reg_page_list_len = SIW_MAX_SGE_PBL; attr->max_mr = sdev->attrs.max_mr; attr->max_mw = sdev->attrs.max_mw; attr->max_mr_size = ~0ull; attr->max_pd = sdev->attrs.max_pd; attr->max_qp = sdev->attrs.max_qp; attr->max_qp_init_rd_atom = sdev->attrs.max_ird; attr->max_qp_rd_atom = sdev->attrs.max_ord; attr->max_qp_wr = sdev->attrs.max_qp_wr; attr->max_recv_sge = sdev->attrs.max_sge; attr->max_res_rd_atom = sdev->attrs.max_qp * sdev->attrs.max_ird; attr->max_send_sge = sdev->attrs.max_sge; attr->max_sge_rd = sdev->attrs.max_sge_rd; attr->max_srq = sdev->attrs.max_srq; attr->max_srq_sge = sdev->attrs.max_srq_sge; attr->max_srq_wr = sdev->attrs.max_srq_wr; attr->page_size_cap = PAGE_SIZE; attr->vendor_id = SIW_VENDOR_ID; attr->vendor_part_id = sdev->vendor_part_id; addrconf_addr_eui48((u8 *)&attr->sys_image_guid, sdev->raw_gid); return 0; } int siw_query_port(struct ib_device *base_dev, u32 port, struct ib_port_attr *attr) { struct net_device *ndev; int rv; memset(attr, 0, sizeof(*attr)); rv = ib_get_eth_speed(base_dev, port, &attr->active_speed, &attr->active_width); if (rv) return rv; ndev = ib_device_get_netdev(base_dev, SIW_PORT); if (!ndev) return -ENODEV; attr->gid_tbl_len = 1; attr->max_msg_sz = -1; attr->max_mtu = ib_mtu_int_to_enum(ndev->max_mtu); attr->active_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); attr->state = ib_get_curr_port_state(ndev); attr->phys_state = attr->state == IB_PORT_ACTIVE ? IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED; attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_DEVICE_MGMT_SUP; /* * All zero * * attr->lid = 0; * attr->bad_pkey_cntr = 0; * attr->qkey_viol_cntr = 0; * attr->sm_lid = 0; * attr->lmc = 0; * attr->max_vl_num = 0; * attr->sm_sl = 0; * attr->subnet_timeout = 0; * attr->init_type_repy = 0; */ dev_put(ndev); return rv; } int siw_get_port_immutable(struct ib_device *base_dev, u32 port, struct ib_port_immutable *port_immutable) { struct ib_port_attr attr; int rv = siw_query_port(base_dev, port, &attr); if (rv) return rv; port_immutable->gid_tbl_len = attr.gid_tbl_len; port_immutable->core_cap_flags = RDMA_CORE_PORT_IWARP; return 0; } int siw_query_gid(struct ib_device *base_dev, u32 port, int idx, union ib_gid *gid) { struct siw_device *sdev = to_siw_dev(base_dev); /* subnet_prefix == interface_id == 0; */ memset(gid, 0, sizeof(*gid)); memcpy(gid->raw, sdev->raw_gid, ETH_ALEN); return 0; } int siw_alloc_pd(struct ib_pd *pd, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(pd->device); if (atomic_inc_return(&sdev->num_pd) > SIW_MAX_PD) { atomic_dec(&sdev->num_pd); return -ENOMEM; } siw_dbg_pd(pd, "now %d PD's(s)\n", atomic_read(&sdev->num_pd)); return 0; } int siw_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata) { struct siw_device *sdev = to_siw_dev(pd->device); siw_dbg_pd(pd, "free PD\n"); atomic_dec(&sdev->num_pd); return 0; } void siw_qp_get_ref(struct ib_qp *base_qp) { siw_qp_get(to_siw_qp(base_qp)); } void siw_qp_put_ref(struct ib_qp *base_qp) { siw_qp_put(to_siw_qp(base_qp)); } static struct rdma_user_mmap_entry * siw_mmap_entry_insert(struct siw_ucontext *uctx, void *address, size_t length, u64 *offset) { struct siw_user_mmap_entry *entry = kzalloc_obj(*entry); int rv; *offset = SIW_INVAL_UOBJ_KEY; if (!entry) return NULL; entry->address = address; rv = rdma_user_mmap_entry_insert(&uctx->base_ucontext, &entry->rdma_entry, length); if (rv) { kfree(entry); return NULL; } *offset = rdma_user_mmap_get_offset(&entry->rdma_entry); return &entry->rdma_entry; } /* * siw_create_qp() * * Create QP of requested size on given device. * * @qp: Queue pait * @attrs: Initial QP attributes. * @udata: used to provide QP ID, SQ and RQ size back to user. */ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, struct ib_udata *udata) { struct ib_pd *pd = ibqp->pd; struct siw_qp *qp = to_siw_qp(ibqp); struct ib_device *base_dev = pd->device; struct siw_device *sdev = to_siw_dev(base_dev); struct siw_ucontext *uctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); unsigned long flags; int num_sqe, num_rqe, rv = 0; size_t length; siw_dbg(base_dev, "create new QP\n"); if (attrs->create_flags) return -EOPNOTSUPP; if (atomic_inc_return(&sdev->num_qp) > SIW_MAX_QP) { siw_dbg(base_dev, "too many QP's\n"); rv = -ENOMEM; goto err_atomic; } if (attrs->qp_type != IB_QPT_RC) { siw_dbg(base_dev, "only RC QP's supported\n"); rv = -EOPNOTSUPP; goto err_atomic; } if ((attrs->cap.max_send_wr > SIW_MAX_QP_WR) || (attrs->cap.max_recv_wr > SIW_MAX_QP_WR) || (attrs->cap.max_send_sge > SIW_MAX_SGE) || (attrs->cap.max_recv_sge > SIW_MAX_SGE)) { siw_dbg(base_dev, "QP size error\n"); rv = -EINVAL; goto err_atomic; } if (attrs->cap.max_inline_data > SIW_MAX_INLINE) { siw_dbg(base_dev, "max inline send: %d > %d\n", attrs->cap.max_inline_data, (int)SIW_MAX_INLINE); rv = -EINVAL; goto err_atomic; } /* * NOTE: we don't allow for a QP unable to hold any SQ WQE */ if (attrs->cap.max_send_wr == 0) { siw_dbg(base_dev, "QP must have send queue\n"); rv = -EINVAL; goto err_atomic; } if (!attrs->send_cq || (!attrs->recv_cq && !attrs->srq)) { siw_dbg(base_dev, "send CQ or receive CQ invalid\n"); rv = -EINVAL; goto err_atomic; } init_rwsem(&qp->state_lock); spin_lock_init(&qp->sq_lock); spin_lock_init(&qp->rq_lock); spin_lock_init(&qp->orq_lock); rv = siw_qp_add(sdev, qp); if (rv) goto err_atomic; /* All queue indices are derived from modulo operations * on a free running 'get' (consumer) and 'put' (producer) * unsigned counter. Having queue sizes at power of two * avoids handling counter wrap around. */ num_sqe = roundup_pow_of_two(attrs->cap.max_send_wr); num_rqe = attrs->cap.max_recv_wr; if (num_rqe) num_rqe = roundup_pow_of_two(num_rqe); if (udata) qp->sendq = vmalloc_user(num_sqe * sizeof(struct siw_sqe)); else qp->sendq = vcalloc(num_sqe, sizeof(struct siw_sqe)); if (qp->sendq == NULL) { rv = -ENOMEM; goto err_out_xa; } if (attrs->sq_sig_type != IB_SIGNAL_REQ_WR) { if (attrs->sq_sig_type == IB_SIGNAL_ALL_WR) qp->attrs.flags |= SIW_SIGNAL_ALL_WR; else { rv = -EINVAL; goto err_out_xa; } } qp->pd = pd; qp->scq = to_siw_cq(attrs->send_cq); qp->rcq = to_siw_cq(attrs->recv_cq); if (attrs->srq) { /* * SRQ support. * Verbs 6.3.7: ignore RQ size, if SRQ present * Verbs 6.3.5: do not check PD of SRQ against PD of QP */ qp->srq = to_siw_srq(attrs->srq); qp->attrs.rq_size = 0; siw_dbg(base_dev, "QP [%u]: SRQ attached\n", qp->base_qp.qp_num); } else if (num_rqe) { if (udata) qp->recvq = vmalloc_user(num_rqe * sizeof(struct siw_rqe)); else qp->recvq = vcalloc(num_rqe, sizeof(struct siw_rqe)); if (qp->recvq == NULL) { rv = -ENOMEM; goto err_out_xa; } qp->attrs.rq_size = num_rqe; } qp->attrs.sq_size = num_sqe; qp->attrs.sq_max_sges = attrs->cap.max_send_sge; qp->attrs.rq_max_sges = attrs->cap.max_recv_sge; /* Make those two tunables fixed for now. */ qp->tx_ctx.gso_seg_limit = 1; qp->tx_ctx.zcopy_tx = zcopy_tx; qp->attrs.state = SIW_QP_STATE_IDLE; if (udata) { struct siw_uresp_create_qp uresp = {}; uresp.num_sqe = num_sqe; uresp.num_rqe = num_rqe; uresp.qp_id = qp_id(qp); if (qp->sendq) { length = num_sqe * sizeof(struct siw_sqe); qp->sq_entry = siw_mmap_entry_insert(uctx, qp->sendq, length, &uresp.sq_key); if (!qp->sq_entry) { rv = -ENOMEM; goto err_out_xa; } } if (qp->recvq) { length = num_rqe * sizeof(struct siw_rqe); qp->rq_entry = siw_mmap_entry_insert(uctx, qp->recvq, length, &uresp.rq_key); if (!qp->rq_entry) { uresp.sq_key = SIW_INVAL_UOBJ_KEY; rv = -ENOMEM; goto err_out_xa; } } if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out_xa; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out_xa; } qp->tx_cpu = siw_get_tx_cpu(sdev); if (qp->tx_cpu < 0) { rv = -EINVAL; goto err_out_xa; } INIT_LIST_HEAD(&qp->devq); spin_lock_irqsave(&sdev->lock, flags); list_add_tail(&qp->devq, &sdev->qp_list); spin_unlock_irqrestore(&sdev->lock, flags); init_completion(&qp->qp_free); return 0; err_out_xa: xa_erase(&sdev->qp_xa, qp_id(qp)); if (uctx) { rdma_user_mmap_entry_remove(qp->sq_entry); rdma_user_mmap_entry_remove(qp->rq_entry); } vfree(qp->sendq); vfree(qp->recvq); err_atomic: atomic_dec(&sdev->num_qp); return rv; } /* * Minimum siw_query_qp() verb interface. * * @qp_attr_mask is not used but all available information is provided */ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) { struct siw_qp *qp; struct net_device *ndev; if (base_qp && qp_attr && qp_init_attr) qp = to_siw_qp(base_qp); else return -EINVAL; ndev = ib_device_get_netdev(base_qp->device, SIW_PORT); if (!ndev) return -ENODEV; qp_attr->qp_state = siw_qp_state_to_ib_qp_state[qp->attrs.state]; qp_attr->cap.max_inline_data = SIW_MAX_INLINE; qp_attr->cap.max_send_wr = qp->attrs.sq_size; qp_attr->cap.max_send_sge = qp->attrs.sq_max_sges; qp_attr->cap.max_recv_wr = qp->attrs.rq_size; qp_attr->cap.max_recv_sge = qp->attrs.rq_max_sges; qp_attr->path_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); qp_attr->max_rd_atomic = qp->attrs.irq_size; qp_attr->max_dest_rd_atomic = qp->attrs.orq_size; qp_attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; qp_init_attr->qp_type = base_qp->qp_type; qp_init_attr->send_cq = base_qp->send_cq; qp_init_attr->recv_cq = base_qp->recv_cq; qp_init_attr->srq = base_qp->srq; qp_init_attr->cap = qp_attr->cap; dev_put(ndev); return 0; } int siw_verbs_modify_qp(struct ib_qp *base_qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { struct siw_qp_attrs new_attrs; enum siw_qp_attr_mask siw_attr_mask = 0; struct siw_qp *qp = to_siw_qp(base_qp); int rv = 0; if (!attr_mask) return 0; if (attr_mask & ~IB_QP_ATTR_STANDARD_BITS) return -EOPNOTSUPP; memset(&new_attrs, 0, sizeof(new_attrs)); if (attr_mask & IB_QP_ACCESS_FLAGS) { siw_attr_mask = SIW_QP_ATTR_ACCESS_FLAGS; if (attr->qp_access_flags & IB_ACCESS_REMOTE_READ) new_attrs.flags |= SIW_RDMA_READ_ENABLED; if (attr->qp_access_flags & IB_ACCESS_REMOTE_WRITE) new_attrs.flags |= SIW_RDMA_WRITE_ENABLED; if (attr->qp_access_flags & IB_ACCESS_MW_BIND) new_attrs.flags |= SIW_RDMA_BIND_ENABLED; } if (attr_mask & IB_QP_STATE) { siw_dbg_qp(qp, "desired IB QP state: %s\n", ib_qp_state_to_string[attr->qp_state]); new_attrs.state = ib_qp_state_to_siw_qp_state[attr->qp_state]; if (new_attrs.state > SIW_QP_STATE_RTS) qp->tx_ctx.tx_suspend = 1; siw_attr_mask |= SIW_QP_ATTR_STATE; } if (!siw_attr_mask) goto out; down_write(&qp->state_lock); rv = siw_qp_modify(qp, &new_attrs, siw_attr_mask); up_write(&qp->state_lock); out: return rv; } int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata) { struct siw_qp *qp = to_siw_qp(base_qp); struct siw_ucontext *uctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); struct siw_qp_attrs qp_attrs; siw_dbg_qp(qp, "state %d\n", qp->attrs.state); /* * Mark QP as in process of destruction to prevent from * any async callbacks to RDMA core */ qp->attrs.flags |= SIW_QP_IN_DESTROY; qp->rx_stream.rx_suspend = 1; if (uctx) { rdma_user_mmap_entry_remove(qp->sq_entry); rdma_user_mmap_entry_remove(qp->rq_entry); } down_write(&qp->state_lock); qp_attrs.state = SIW_QP_STATE_ERROR; siw_qp_modify(qp, &qp_attrs, SIW_QP_ATTR_STATE); if (qp->cep) { siw_cep_put(qp->cep); qp->cep = NULL; } up_write(&qp->state_lock); qp->scq = qp->rcq = NULL; siw_qp_put(qp); wait_for_completion(&qp->qp_free); return 0; } /* * siw_copy_inline_sgl() * * Prepare sgl of inlined data for sending. For userland callers * function checks if given buffer addresses and len's are within * process context bounds. * Data from all provided sge's are copied together into the wqe, * referenced by a single sge. */ static int siw_copy_inline_sgl(const struct ib_send_wr *core_wr, struct siw_sqe *sqe) { struct ib_sge *core_sge = core_wr->sg_list; void *kbuf = &sqe->sge[1]; int num_sge = core_wr->num_sge, bytes = 0; sqe->sge[0].laddr = (uintptr_t)kbuf; sqe->sge[0].lkey = 0; while (num_sge--) { if (!core_sge->length) { core_sge++; continue; } bytes += core_sge->length; if (bytes > SIW_MAX_INLINE) { bytes = -EINVAL; break; } memcpy(kbuf, ib_virt_dma_to_ptr(core_sge->addr), core_sge->length); kbuf += core_sge->length; core_sge++; } sqe->sge[0].length = max(bytes, 0); sqe->num_sge = bytes > 0 ? 1 : 0; return bytes; } /* Complete SQ WR's without processing */ static int siw_sq_flush_wr(struct siw_qp *qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { int rv = 0; while (wr) { struct siw_sqe sqe = {}; switch (wr->opcode) { case IB_WR_RDMA_WRITE: sqe.opcode = SIW_OP_WRITE; break; case IB_WR_RDMA_READ: sqe.opcode = SIW_OP_READ; break; case IB_WR_RDMA_READ_WITH_INV: sqe.opcode = SIW_OP_READ_LOCAL_INV; break; case IB_WR_SEND: sqe.opcode = SIW_OP_SEND; break; case IB_WR_SEND_WITH_IMM: sqe.opcode = SIW_OP_SEND_WITH_IMM; break; case IB_WR_SEND_WITH_INV: sqe.opcode = SIW_OP_SEND_REMOTE_INV; break; case IB_WR_LOCAL_INV: sqe.opcode = SIW_OP_INVAL_STAG; break; case IB_WR_REG_MR: sqe.opcode = SIW_OP_REG_MR; break; default: rv = -EINVAL; break; } if (!rv) { sqe.id = wr->wr_id; rv = siw_sqe_complete(qp, &sqe, 0, SIW_WC_WR_FLUSH_ERR); } if (rv) { if (bad_wr) *bad_wr = wr; break; } wr = wr->next; } return rv; } /* Complete RQ WR's without processing */ static int siw_rq_flush_wr(struct siw_qp *qp, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { struct siw_rqe rqe = {}; int rv = 0; while (wr) { rqe.id = wr->wr_id; rv = siw_rqe_complete(qp, &rqe, 0, 0, SIW_WC_WR_FLUSH_ERR); if (rv) { if (bad_wr) *bad_wr = wr; break; } wr = wr->next; } return rv; } /* * siw_post_send() * * Post a list of S-WR's to a SQ. * * @base_qp: Base QP contained in siw QP * @wr: Null terminated list of user WR's * @bad_wr: Points to failing WR in case of synchronous failure. */ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { struct siw_qp *qp = to_siw_qp(base_qp); struct siw_wqe *wqe = tx_wqe(qp); unsigned long flags; int rv = 0, imm_err = 0; if (wr && !rdma_is_kernel_res(&qp->base_qp.res)) { siw_dbg_qp(qp, "wr must be empty for user mapped sq\n"); *bad_wr = wr; return -EINVAL; } /* * Try to acquire QP state lock. Must be non-blocking * to accommodate kernel clients needs. */ if (!down_read_trylock(&qp->state_lock)) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * ERROR state is final, so we can be sure * this state will not change as long as the QP * exists. * * This handles an ib_drain_sq() call with * a concurrent request to set the QP state * to ERROR. */ rv = siw_sq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP locked, state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } return rv; } if (unlikely(qp->attrs.state != SIW_QP_STATE_RTS)) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * Immediately flush this WR to CQ, if QP * is in ERROR state. SQ is guaranteed to * be empty, so WR complets in-order. * * Typically triggered by ib_drain_sq(). */ rv = siw_sq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP out of state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } up_read(&qp->state_lock); return rv; } spin_lock_irqsave(&qp->sq_lock, flags); while (wr) { u32 idx = qp->sq_put % qp->attrs.sq_size; struct siw_sqe *sqe = &qp->sendq[idx]; if (sqe->flags) { siw_dbg_qp(qp, "sq full\n"); rv = -ENOMEM; break; } if (wr->num_sge > qp->attrs.sq_max_sges) { siw_dbg_qp(qp, "too many sge's: %d\n", wr->num_sge); rv = -EINVAL; break; } sqe->id = wr->wr_id; if ((wr->send_flags & IB_SEND_SIGNALED) || (qp->attrs.flags & SIW_SIGNAL_ALL_WR)) sqe->flags |= SIW_WQE_SIGNALLED; if (wr->send_flags & IB_SEND_FENCE) sqe->flags |= SIW_WQE_READ_FENCE; switch (wr->opcode) { case IB_WR_SEND: case IB_WR_SEND_WITH_INV: if (wr->send_flags & IB_SEND_SOLICITED) sqe->flags |= SIW_WQE_SOLICITED; if (!(wr->send_flags & IB_SEND_INLINE)) { siw_copy_sgl(wr->sg_list, sqe->sge, wr->num_sge); sqe->num_sge = wr->num_sge; } else { rv = siw_copy_inline_sgl(wr, sqe); if (rv <= 0) { rv = -EINVAL; break; } sqe->flags |= SIW_WQE_INLINE; sqe->num_sge = 1; } if (wr->opcode == IB_WR_SEND) sqe->opcode = SIW_OP_SEND; else { sqe->opcode = SIW_OP_SEND_REMOTE_INV; sqe->rkey = wr->ex.invalidate_rkey; } break; case IB_WR_RDMA_READ_WITH_INV: case IB_WR_RDMA_READ: /* * iWarp restricts RREAD sink to SGL containing * 1 SGE only. we could relax to SGL with multiple * elements referring the SAME ltag or even sending * a private per-rreq tag referring to a checked * local sgl with MULTIPLE ltag's. */ if (unlikely(wr->num_sge != 1)) { rv = -EINVAL; break; } siw_copy_sgl(wr->sg_list, &sqe->sge[0], 1); /* * NOTE: zero length RREAD is allowed! */ sqe->raddr = rdma_wr(wr)->remote_addr; sqe->rkey = rdma_wr(wr)->rkey; sqe->num_sge = 1; if (wr->opcode == IB_WR_RDMA_READ) sqe->opcode = SIW_OP_READ; else sqe->opcode = SIW_OP_READ_LOCAL_INV; break; case IB_WR_RDMA_WRITE: if (!(wr->send_flags & IB_SEND_INLINE)) { siw_copy_sgl(wr->sg_list, &sqe->sge[0], wr->num_sge); sqe->num_sge = wr->num_sge; } else { rv = siw_copy_inline_sgl(wr, sqe); if (unlikely(rv < 0)) { rv = -EINVAL; break; } sqe->flags |= SIW_WQE_INLINE; sqe->num_sge = 1; } sqe->raddr = rdma_wr(wr)->remote_addr; sqe->rkey = rdma_wr(wr)->rkey; sqe->opcode = SIW_OP_WRITE; break; case IB_WR_REG_MR: sqe->base_mr = (uintptr_t)reg_wr(wr)->mr; sqe->rkey = reg_wr(wr)->key; sqe->access = reg_wr(wr)->access & IWARP_ACCESS_MASK; sqe->opcode = SIW_OP_REG_MR; break; case IB_WR_LOCAL_INV: sqe->rkey = wr->ex.invalidate_rkey; sqe->opcode = SIW_OP_INVAL_STAG; break; default: siw_dbg_qp(qp, "ib wr type %d unsupported\n", wr->opcode); rv = -EINVAL; break; } siw_dbg_qp(qp, "opcode %d, flags 0x%x, wr_id 0x%p\n", sqe->opcode, sqe->flags, (void *)(uintptr_t)sqe->id); if (unlikely(rv < 0)) break; /* make SQE only valid after completely written */ smp_wmb(); sqe->flags |= SIW_WQE_VALID; qp->sq_put++; wr = wr->next; } /* * Send directly if SQ processing is not in progress. * Eventual immediate errors (rv < 0) do not affect the involved * RI resources (Verbs, 8.3.1) and thus do not prevent from SQ * processing, if new work is already pending. But rv and pointer * to failed work request must be passed to caller. */ if (unlikely(rv < 0)) { /* * Immediate error */ siw_dbg_qp(qp, "Immediate error %d\n", rv); imm_err = rv; *bad_wr = wr; } if (wqe->wr_status != SIW_WR_IDLE) { spin_unlock_irqrestore(&qp->sq_lock, flags); goto skip_direct_sending; } rv = siw_activate_tx(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); if (rv <= 0) goto skip_direct_sending; if (rdma_is_kernel_res(&qp->base_qp.res)) { rv = siw_sq_start(qp); } else { qp->tx_ctx.in_syscall = 1; if (siw_qp_sq_process(qp) != 0 && !(qp->tx_ctx.tx_suspend)) siw_qp_cm_drop(qp, 0); qp->tx_ctx.in_syscall = 0; } skip_direct_sending: up_read(&qp->state_lock); if (unlikely(imm_err)) return imm_err; return (rv >= 0) ? 0 : rv; } /* * siw_post_receive() * * Post a list of R-WR's to a RQ. * * @base_qp: Base QP contained in siw QP * @wr: Null terminated list of user WR's * @bad_wr: Points to failing WR in case of synchronous failure. */ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { struct siw_qp *qp = to_siw_qp(base_qp); unsigned long flags; int rv = 0; if (qp->srq || qp->attrs.rq_size == 0) { *bad_wr = wr; return -EINVAL; } if (!rdma_is_kernel_res(&qp->base_qp.res)) { siw_dbg_qp(qp, "no kernel post_recv for user mapped rq\n"); *bad_wr = wr; return -EINVAL; } /* * Try to acquire QP state lock. Must be non-blocking * to accommodate kernel clients needs. */ if (!down_read_trylock(&qp->state_lock)) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * ERROR state is final, so we can be sure * this state will not change as long as the QP * exists. * * This handles an ib_drain_rq() call with * a concurrent request to set the QP state * to ERROR. */ rv = siw_rq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP locked, state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } return rv; } if (qp->attrs.state > SIW_QP_STATE_RTS) { if (qp->attrs.state == SIW_QP_STATE_ERROR) { /* * Immediately flush this WR to CQ, if QP * is in ERROR state. RQ is guaranteed to * be empty, so WR complets in-order. * * Typically triggered by ib_drain_rq(). */ rv = siw_rq_flush_wr(qp, wr, bad_wr); } else { siw_dbg_qp(qp, "QP out of state %d\n", qp->attrs.state); *bad_wr = wr; rv = -ENOTCONN; } up_read(&qp->state_lock); return rv; } /* * Serialize potentially multiple producers. * Not needed for single threaded consumer side. */ spin_lock_irqsave(&qp->rq_lock, flags); while (wr) { u32 idx = qp->rq_put % qp->attrs.rq_size; struct siw_rqe *rqe = &qp->recvq[idx]; if (rqe->flags) { siw_dbg_qp(qp, "RQ full\n"); rv = -ENOMEM; break; } if (wr->num_sge > qp->attrs.rq_max_sges) { siw_dbg_qp(qp, "too many sge's: %d\n", wr->num_sge); rv = -EINVAL; break; } rqe->id = wr->wr_id; rqe->num_sge = wr->num_sge; siw_copy_sgl(wr->sg_list, rqe->sge, wr->num_sge); /* make sure RQE is completely written before valid */ smp_wmb(); rqe->flags = SIW_WQE_VALID; qp->rq_put++; wr = wr->next; } spin_unlock_irqrestore(&qp->rq_lock, flags); up_read(&qp->state_lock); if (rv < 0) { siw_dbg_qp(qp, "error %d\n", rv); *bad_wr = wr; } return rv; } int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata) { struct siw_cq *cq = to_siw_cq(base_cq); struct siw_device *sdev = to_siw_dev(base_cq->device); struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); siw_dbg_cq(cq, "free CQ resources\n"); siw_cq_flush(cq); if (ctx) rdma_user_mmap_entry_remove(cq->cq_entry); atomic_dec(&sdev->num_cq); vfree(cq->queue); return 0; } /* * siw_create_cq() * * Populate CQ of requested size * * @base_cq: CQ as allocated by RDMA midlayer * @attr: Initial CQ attributes * @attrs: uverbs bundle */ int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr, struct uverbs_attr_bundle *attrs) { struct ib_udata *udata = &attrs->driver_udata; struct siw_device *sdev = to_siw_dev(base_cq->device); struct siw_cq *cq = to_siw_cq(base_cq); int rv, size = attr->cqe; if (attr->flags) return -EOPNOTSUPP; if (atomic_inc_return(&sdev->num_cq) > SIW_MAX_CQ) { siw_dbg(base_cq->device, "too many CQ's\n"); rv = -ENOMEM; goto err_out; } if (size < 1 || size > sdev->attrs.max_cqe) { siw_dbg(base_cq->device, "CQ size error: %d\n", size); rv = -EINVAL; goto err_out; } size = roundup_pow_of_two(size); cq->base_cq.cqe = size; cq->num_cqe = size; if (udata) cq->queue = vmalloc_user(size * sizeof(struct siw_cqe) + sizeof(struct siw_cq_ctrl)); else cq->queue = vzalloc(size * sizeof(struct siw_cqe) + sizeof(struct siw_cq_ctrl)); if (cq->queue == NULL) { rv = -ENOMEM; goto err_out; } get_random_bytes(&cq->id, 4); siw_dbg(base_cq->device, "new CQ [%u]\n", cq->id); spin_lock_init(&cq->lock); cq->notify = (struct siw_cq_ctrl *)&cq->queue[size]; if (udata) { struct siw_uresp_create_cq uresp = {}; struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); size_t length = size * sizeof(struct siw_cqe) + sizeof(struct siw_cq_ctrl); cq->cq_entry = siw_mmap_entry_insert(ctx, cq->queue, length, &uresp.cq_key); if (!cq->cq_entry) { rv = -ENOMEM; goto err_out; } uresp.cq_id = cq->id; uresp.num_cqe = size; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; } return 0; err_out: siw_dbg(base_cq->device, "CQ creation failed: %d", rv); if (cq->queue) { struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); if (ctx) rdma_user_mmap_entry_remove(cq->cq_entry); vfree(cq->queue); } atomic_dec(&sdev->num_cq); return rv; } /* * siw_poll_cq() * * Reap CQ entries if available and copy work completion status into * array of WC's provided by caller. Returns number of reaped CQE's. * * @base_cq: Base CQ contained in siw CQ. * @num_cqe: Maximum number of CQE's to reap. * @wc: Array of work completions to be filled by siw. */ int siw_poll_cq(struct ib_cq *base_cq, int num_cqe, struct ib_wc *wc) { struct siw_cq *cq = to_siw_cq(base_cq); int i; for (i = 0; i < num_cqe; i++) { if (!siw_reap_cqe(cq, wc)) break; wc++; } return i; } /* * siw_req_notify_cq() * * Request notification for new CQE's added to that CQ. * Defined flags: * o SIW_CQ_NOTIFY_SOLICITED lets siw trigger a notification * event if a WQE with notification flag set enters the CQ * o SIW_CQ_NOTIFY_NEXT_COMP lets siw trigger a notification * event if a WQE enters the CQ. * o IB_CQ_REPORT_MISSED_EVENTS: return value will provide the * number of not reaped CQE's regardless of its notification * type and current or new CQ notification settings. * * @base_cq: Base CQ contained in siw CQ. * @flags: Requested notification flags. */ int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags) { struct siw_cq *cq = to_siw_cq(base_cq); siw_dbg_cq(cq, "flags: 0x%02x\n", flags); if ((flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED) /* * Enable CQ event for next solicited completion. * and make it visible to all associated producers. */ smp_store_mb(cq->notify->flags, SIW_NOTIFY_SOLICITED); else /* * Enable CQ event for any signalled completion. * and make it visible to all associated producers. */ smp_store_mb(cq->notify->flags, SIW_NOTIFY_ALL); if (flags & IB_CQ_REPORT_MISSED_EVENTS) return cq->cq_put - cq->cq_get; return 0; } /* * siw_dereg_mr() * * Release Memory Region. * * @base_mr: Base MR contained in siw MR. * @udata: points to user context, unused. */ int siw_dereg_mr(struct ib_mr *base_mr, struct ib_udata *udata) { struct siw_mr *mr = to_siw_mr(base_mr); struct siw_device *sdev = to_siw_dev(base_mr->device); siw_dbg_mem(mr->mem, "deregister MR\n"); atomic_dec(&sdev->num_mr); siw_mr_drop_mem(mr); kfree_rcu(mr, rcu); return 0; } /* * siw_reg_user_mr() * * Register Memory Region. * * @pd: Protection Domain * @start: starting address of MR (virtual address) * @len: len of MR * @rnic_va: not used by siw * @rights: MR access rights * @dmah: dma handle * @udata: user buffer to communicate STag and Key. */ struct ib_mr *siw_reg_user_mr(struct ib_pd *pd, u64 start, u64 len, u64 rnic_va, int rights, struct ib_dmah *dmah, struct ib_udata *udata) { struct siw_mr *mr = NULL; struct siw_umem *umem = NULL; struct siw_ureq_reg_mr ureq; struct siw_device *sdev = to_siw_dev(pd->device); int rv; siw_dbg_pd(pd, "start: 0x%p, va: 0x%p, len: %llu\n", (void *)(uintptr_t)start, (void *)(uintptr_t)rnic_va, (unsigned long long)len); if (dmah) return ERR_PTR(-EOPNOTSUPP); if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) { siw_dbg_pd(pd, "too many mr's\n"); rv = -ENOMEM; goto err_out; } if (!len) { rv = -EINVAL; goto err_out; } umem = siw_umem_get(pd->device, start, len, rights); if (IS_ERR(umem)) { rv = PTR_ERR(umem); siw_dbg_pd(pd, "getting user memory failed: %d\n", rv); umem = NULL; goto err_out; } mr = kzalloc_obj(*mr); if (!mr) { rv = -ENOMEM; goto err_out; } rv = siw_mr_add_mem(mr, pd, umem, start, len, rights); if (rv) goto err_out; if (udata) { struct siw_uresp_reg_mr uresp = {}; struct siw_mem *mem = mr->mem; rv = ib_copy_validate_udata_in(udata, ureq, pad); if (rv) goto err_out; mr->base_mr.lkey |= ureq.stag_key; mr->base_mr.rkey |= ureq.stag_key; mem->stag |= ureq.stag_key; uresp.stag = mem->stag; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; } mr->mem->stag_valid = 1; return &mr->base_mr; err_out: atomic_dec(&sdev->num_mr); if (mr) { if (mr->mem) siw_mr_drop_mem(mr); kfree_rcu(mr, rcu); } else { if (umem) siw_umem_release(umem); } return ERR_PTR(rv); } struct ib_mr *siw_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_sge) { struct siw_device *sdev = to_siw_dev(pd->device); struct siw_mr *mr = NULL; struct siw_pbl *pbl = NULL; int rv; if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) { siw_dbg_pd(pd, "too many mr's\n"); rv = -ENOMEM; goto err_out; } if (mr_type != IB_MR_TYPE_MEM_REG) { siw_dbg_pd(pd, "mr type %d unsupported\n", mr_type); rv = -EOPNOTSUPP; goto err_out; } if (max_sge > SIW_MAX_SGE_PBL) { siw_dbg_pd(pd, "too many sge's: %d\n", max_sge); rv = -ENOMEM; goto err_out; } pbl = siw_pbl_alloc(max_sge); if (IS_ERR(pbl)) { rv = PTR_ERR(pbl); siw_dbg_pd(pd, "pbl allocation failed: %d\n", rv); pbl = NULL; goto err_out; } mr = kzalloc_obj(*mr); if (!mr) { rv = -ENOMEM; goto err_out; } rv = siw_mr_add_mem(mr, pd, pbl, 0, max_sge * PAGE_SIZE, 0); if (rv) goto err_out; mr->mem->is_pbl = 1; siw_dbg_pd(pd, "[MEM %u]: success\n", mr->mem->stag); return &mr->base_mr; err_out: atomic_dec(&sdev->num_mr); if (!mr) { kfree(pbl); } else { if (mr->mem) siw_mr_drop_mem(mr); kfree_rcu(mr, rcu); } siw_dbg_pd(pd, "failed: %d\n", rv); return ERR_PTR(rv); } /* Just used to count number of pages being mapped */ static int siw_set_pbl_page(struct ib_mr *base_mr, u64 buf_addr) { return 0; } int siw_map_mr_sg(struct ib_mr *base_mr, struct scatterlist *sl, int num_sle, unsigned int *sg_off) { struct scatterlist *slp; struct siw_mr *mr = to_siw_mr(base_mr); struct siw_mem *mem = mr->mem; struct siw_pbl *pbl = mem->pbl; struct siw_pble *pble; unsigned long pbl_size; int i, rv; if (!pbl) { siw_dbg_mem(mem, "no PBL allocated\n"); return -EINVAL; } pble = pbl->pbe; if (pbl->max_buf < num_sle) { siw_dbg_mem(mem, "too many SGE's: %d > %d\n", num_sle, pbl->max_buf); return -ENOMEM; } for_each_sg(sl, slp, num_sle, i) { if (sg_dma_len(slp) == 0) { siw_dbg_mem(mem, "empty SGE\n"); return -EINVAL; } if (i == 0) { pble->addr = sg_dma_address(slp); pble->size = sg_dma_len(slp); pble->pbl_off = 0; pbl_size = pble->size; pbl->num_buf = 1; } else { /* Merge PBL entries if adjacent */ if (pble->addr + pble->size == sg_dma_address(slp)) { pble->size += sg_dma_len(slp); } else { pble++; pbl->num_buf++; pble->addr = sg_dma_address(slp); pble->size = sg_dma_len(slp); pble->pbl_off = pbl_size; } pbl_size += sg_dma_len(slp); } siw_dbg_mem(mem, "sge[%d], size %u, addr 0x%p, total %lu\n", i, pble->size, ib_virt_dma_to_ptr(pble->addr), pbl_size); } rv = ib_sg_to_pages(base_mr, sl, num_sle, sg_off, siw_set_pbl_page); if (rv > 0) { mem->len = base_mr->length; mem->va = base_mr->iova; siw_dbg_mem(mem, "%llu bytes, start 0x%p, %u SLE to %u entries\n", mem->len, (void *)(uintptr_t)mem->va, num_sle, pbl->num_buf); } return rv; } /* * siw_get_dma_mr() * * Create a (empty) DMA memory region, where no umem is attached. */ struct ib_mr *siw_get_dma_mr(struct ib_pd *pd, int rights) { struct siw_device *sdev = to_siw_dev(pd->device); struct siw_mr *mr = NULL; int rv; if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) { siw_dbg_pd(pd, "too many mr's\n"); rv = -ENOMEM; goto err_out; } mr = kzalloc_obj(*mr); if (!mr) { rv = -ENOMEM; goto err_out; } rv = siw_mr_add_mem(mr, pd, NULL, 0, ULONG_MAX, rights); if (rv) goto err_out; mr->mem->stag_valid = 1; siw_dbg_pd(pd, "[MEM %u]: success\n", mr->mem->stag); return &mr->base_mr; err_out: if (rv) kfree(mr); atomic_dec(&sdev->num_mr); return ERR_PTR(rv); } /* * siw_create_srq() * * Create Shared Receive Queue of attributes @init_attrs * within protection domain given by @pd. * * @base_srq: Base SRQ contained in siw SRQ. * @init_attrs: SRQ init attributes. * @udata: points to user context */ int siw_create_srq(struct ib_srq *base_srq, struct ib_srq_init_attr *init_attrs, struct ib_udata *udata) { struct siw_srq *srq = to_siw_srq(base_srq); struct ib_srq_attr *attrs = &init_attrs->attr; struct siw_device *sdev = to_siw_dev(base_srq->device); struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); int rv; if (init_attrs->srq_type != IB_SRQT_BASIC) return -EOPNOTSUPP; if (atomic_inc_return(&sdev->num_srq) > SIW_MAX_SRQ) { siw_dbg_pd(base_srq->pd, "too many SRQ's\n"); rv = -ENOMEM; goto err_out; } if (attrs->max_wr == 0 || attrs->max_wr > SIW_MAX_SRQ_WR || attrs->max_sge > SIW_MAX_SGE || attrs->srq_limit > attrs->max_wr) { rv = -EINVAL; goto err_out; } srq->max_sge = attrs->max_sge; srq->num_rqe = roundup_pow_of_two(attrs->max_wr); srq->limit = attrs->srq_limit; if (srq->limit) srq->armed = true; srq->is_kernel_res = !udata; if (udata) srq->recvq = vmalloc_user(srq->num_rqe * sizeof(struct siw_rqe)); else srq->recvq = vcalloc(srq->num_rqe, sizeof(struct siw_rqe)); if (srq->recvq == NULL) { rv = -ENOMEM; goto err_out; } if (udata) { struct siw_uresp_create_srq uresp = {}; size_t length = srq->num_rqe * sizeof(struct siw_rqe); srq->srq_entry = siw_mmap_entry_insert(ctx, srq->recvq, length, &uresp.srq_key); if (!srq->srq_entry) { rv = -ENOMEM; goto err_out; } uresp.num_rqe = srq->num_rqe; if (udata->outlen < sizeof(uresp)) { rv = -EINVAL; goto err_out; } rv = ib_copy_to_udata(udata, &uresp, sizeof(uresp)); if (rv) goto err_out; } spin_lock_init(&srq->lock); siw_dbg_pd(base_srq->pd, "[SRQ]: success\n"); return 0; err_out: if (srq->recvq) { if (ctx) rdma_user_mmap_entry_remove(srq->srq_entry); vfree(srq->recvq); } atomic_dec(&sdev->num_srq); return rv; } /* * siw_modify_srq() * * Modify SRQ. The caller may resize SRQ and/or set/reset notification * limit and (re)arm IB_EVENT_SRQ_LIMIT_REACHED notification. * * NOTE: it is unclear if RDMA core allows for changing the MAX_SGE * parameter. siw_modify_srq() does not check the attrs->max_sge param. */ int siw_modify_srq(struct ib_srq *base_srq, struct ib_srq_attr *attrs, enum ib_srq_attr_mask attr_mask, struct ib_udata *udata) { struct siw_srq *srq = to_siw_srq(base_srq); unsigned long flags; int rv = 0; spin_lock_irqsave(&srq->lock, flags); if (attr_mask & IB_SRQ_MAX_WR) { /* resize request not yet supported */ rv = -EOPNOTSUPP; goto out; } if (attr_mask & IB_SRQ_LIMIT) { if (attrs->srq_limit) { if (unlikely(attrs->srq_limit > srq->num_rqe)) { rv = -EINVAL; goto out; } srq->armed = true; } else { srq->armed = false; } srq->limit = attrs->srq_limit; } out: spin_unlock_irqrestore(&srq->lock, flags); return rv; } /* * siw_query_srq() * * Query SRQ attributes. */ int siw_query_srq(struct ib_srq *base_srq, struct ib_srq_attr *attrs) { struct siw_srq *srq = to_siw_srq(base_srq); unsigned long flags; spin_lock_irqsave(&srq->lock, flags); attrs->max_wr = srq->num_rqe; attrs->max_sge = srq->max_sge; attrs->srq_limit = srq->limit; spin_unlock_irqrestore(&srq->lock, flags); return 0; } /* * siw_destroy_srq() * * Destroy SRQ. * It is assumed that the SRQ is not referenced by any * QP anymore - the code trusts the RDMA core environment to keep track * of QP references. */ int siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata) { struct siw_srq *srq = to_siw_srq(base_srq); struct siw_device *sdev = to_siw_dev(base_srq->device); struct siw_ucontext *ctx = rdma_udata_to_drv_context(udata, struct siw_ucontext, base_ucontext); if (ctx) rdma_user_mmap_entry_remove(srq->srq_entry); vfree(srq->recvq); atomic_dec(&sdev->num_srq); return 0; } /* * siw_post_srq_recv() * * Post a list of receive queue elements to SRQ. * NOTE: The function does not check or lock a certain SRQ state * during the post operation. The code simply trusts the * RDMA core environment. * * @base_srq: Base SRQ contained in siw SRQ * @wr: List of R-WR's * @bad_wr: Updated to failing WR if posting fails. */ int siw_post_srq_recv(struct ib_srq *base_srq, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { struct siw_srq *srq = to_siw_srq(base_srq); unsigned long flags; int rv = 0; if (unlikely(!srq->is_kernel_res)) { siw_dbg_pd(base_srq->pd, "[SRQ]: no kernel post_recv for mapped srq\n"); rv = -EINVAL; goto out; } /* * Serialize potentially multiple producers. * Also needed to serialize potentially multiple * consumers. */ spin_lock_irqsave(&srq->lock, flags); while (wr) { u32 idx = srq->rq_put % srq->num_rqe; struct siw_rqe *rqe = &srq->recvq[idx]; if (rqe->flags) { siw_dbg_pd(base_srq->pd, "SRQ full\n"); rv = -ENOMEM; break; } if (unlikely(wr->num_sge > srq->max_sge)) { siw_dbg_pd(base_srq->pd, "[SRQ]: too many sge's: %d\n", wr->num_sge); rv = -EINVAL; break; } rqe->id = wr->wr_id; rqe->num_sge = wr->num_sge; siw_copy_sgl(wr->sg_list, rqe->sge, wr->num_sge); /* Make sure S-RQE is completely written before valid */ smp_wmb(); rqe->flags = SIW_WQE_VALID; srq->rq_put++; wr = wr->next; } spin_unlock_irqrestore(&srq->lock, flags); out: if (unlikely(rv < 0)) { siw_dbg_pd(base_srq->pd, "[SRQ]: error %d\n", rv); *bad_wr = wr; } return rv; } void siw_qp_event(struct siw_qp *qp, enum ib_event_type etype) { struct ib_event event; struct ib_qp *base_qp = &qp->base_qp; /* * Do not report asynchronous errors on QP which gets * destroyed via verbs interface (siw_destroy_qp()) */ if (qp->attrs.flags & SIW_QP_IN_DESTROY) return; event.event = etype; event.device = base_qp->device; event.element.qp = base_qp; if (base_qp->event_handler) { siw_dbg_qp(qp, "reporting event %d\n", etype); base_qp->event_handler(&event, base_qp->qp_context); } } void siw_cq_event(struct siw_cq *cq, enum ib_event_type etype) { struct ib_event event; struct ib_cq *base_cq = &cq->base_cq; event.event = etype; event.device = base_cq->device; event.element.cq = base_cq; if (base_cq->event_handler) { siw_dbg_cq(cq, "reporting CQ event %d\n", etype); base_cq->event_handler(&event, base_cq->cq_context); } } void siw_srq_event(struct siw_srq *srq, enum ib_event_type etype) { struct ib_event event; struct ib_srq *base_srq = &srq->base_srq; event.event = etype; event.device = base_srq->device; event.element.srq = base_srq; if (base_srq->event_handler) { siw_dbg_pd(srq->base_srq.pd, "reporting SRQ event %d\n", etype); base_srq->event_handler(&event, base_srq->srq_context); } } void siw_port_event(struct siw_device *sdev, u32 port, enum ib_event_type etype) { struct ib_event event; event.event = etype; event.device = &sdev->base_dev; event.element.port_num = port; siw_dbg(&sdev->base_dev, "reporting port event %d\n", etype); ib_dispatch_event(&event); } |
| 4 4 170 86 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * AEAD: Authenticated Encryption with Associated Data * * Copyright (c) 2007-2015 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_AEAD_H #define _CRYPTO_AEAD_H #include <linux/atomic.h> #include <linux/container_of.h> #include <linux/crypto.h> #include <linux/slab.h> #include <linux/types.h> /** * DOC: Authenticated Encryption With Associated Data (AEAD) Cipher API * * The AEAD cipher API is used with the ciphers of type CRYPTO_ALG_TYPE_AEAD * (listed as type "aead" in /proc/crypto) * * The most prominent examples for this type of encryption is GCM and CCM. * However, the kernel supports other types of AEAD ciphers which are defined * with the following cipher string: * * authenc(keyed message digest, block cipher) * * For example: authenc(hmac(sha256), cbc(aes)) * * The example code provided for the symmetric key cipher operation applies * here as well. Naturally all *skcipher* symbols must be exchanged the *aead* * pendants discussed in the following. In addition, for the AEAD operation, * the aead_request_set_ad function must be used to set the pointer to the * associated data memory location before performing the encryption or * decryption operation. Another deviation from the asynchronous block cipher * operation is that the caller should explicitly check for -EBADMSG of the * crypto_aead_decrypt. That error indicates an authentication error, i.e. * a breach in the integrity of the message. In essence, that -EBADMSG error * code is the key bonus an AEAD cipher has over "standard" block chaining * modes. * * Memory Structure: * * The source scatterlist must contain the concatenation of * associated data || plaintext or ciphertext. * * The destination scatterlist has the same layout, except that the plaintext * (resp. ciphertext) will grow (resp. shrink) by the authentication tag size * during encryption (resp. decryption). The authentication tag is generated * during the encryption operation and appended to the ciphertext. During * decryption, the authentication tag is consumed along with the ciphertext and * used to verify the integrity of the plaintext and the associated data. * * In-place encryption/decryption is enabled by using the same scatterlist * pointer for both the source and destination. * * Even in the out-of-place case, space must be reserved in the destination for * the associated data, even though it won't be written to. This makes the * in-place and out-of-place cases more consistent. It is permissible for the * "destination" associated data to alias the "source" associated data. * * As with the other scatterlist crypto APIs, zero-length scatterlist elements * are not allowed in the used part of the scatterlist. Thus, if there is no * associated data, the first element must point to the plaintext/ciphertext. * * To meet the needs of IPsec, a special quirk applies to rfc4106, rfc4309, * rfc4543, and rfc7539esp ciphers. For these ciphers, the final 'ivsize' bytes * of the associated data buffer must contain a second copy of the IV. This is * in addition to the copy passed to aead_request_set_crypt(). These two IV * copies must not differ; different implementations of the same algorithm may * behave differently in that case. Note that the algorithm might not actually * treat the IV as associated data; nevertheless the length passed to * aead_request_set_ad() must include it. */ struct crypto_aead; struct scatterlist; /** * struct aead_request - AEAD request * @base: Common attributes for async crypto requests * @assoclen: Length in bytes of associated data for authentication * @cryptlen: Length of data to be encrypted or decrypted * @iv: Initialisation vector * @src: Source data * @dst: Destination data * @__ctx: Start of private context data */ struct aead_request { struct crypto_async_request base; unsigned int assoclen; unsigned int cryptlen; u8 *iv; struct scatterlist *src; struct scatterlist *dst; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct aead_alg - AEAD cipher definition * @maxauthsize: Set the maximum authentication tag size supported by the * transformation. A transformation may support smaller tag sizes. * As the authentication tag is a message digest to ensure the * integrity of the encrypted data, a consumer typically wants the * largest authentication tag possible as defined by this * variable. * @setauthsize: Set authentication size for the AEAD transformation. This * function is used to specify the consumer requested size of the * authentication tag to be either generated by the transformation * during encryption or the size of the authentication tag to be * supplied during the decryption operation. This function is also * responsible for checking the authentication tag size for * validity. * @setkey: see struct skcipher_alg * @encrypt: see struct skcipher_alg * @decrypt: see struct skcipher_alg * @ivsize: see struct skcipher_alg * @chunksize: see struct skcipher_alg * @init: Initialize the cryptographic transformation object. This function * is used to initialize the cryptographic transformation object. * This function is called only once at the instantiation time, right * after the transformation context was allocated. In case the * cryptographic hardware has some special requirements which need to * be handled by software, this function shall check for the precise * requirement of the transformation and put any software fallbacks * in place. * @exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @init, used to remove various changes set in * @init. * @base: Definition of a generic crypto cipher algorithm. * * All fields except @ivsize is mandatory and must be filled. */ struct aead_alg { int (*setkey)(struct crypto_aead *tfm, const u8 *key, unsigned int keylen); int (*setauthsize)(struct crypto_aead *tfm, unsigned int authsize); int (*encrypt)(struct aead_request *req); int (*decrypt)(struct aead_request *req); int (*init)(struct crypto_aead *tfm); void (*exit)(struct crypto_aead *tfm); unsigned int ivsize; unsigned int maxauthsize; unsigned int chunksize; struct crypto_alg base; }; struct crypto_aead { unsigned int authsize; unsigned int reqsize; struct crypto_tfm base; }; struct crypto_sync_aead { struct crypto_aead base; }; #define MAX_SYNC_AEAD_REQSIZE 384 #define SYNC_AEAD_REQUEST_ON_STACK(name, _tfm) \ char __##name##_desc[sizeof(struct aead_request) + \ MAX_SYNC_AEAD_REQSIZE \ ] CRYPTO_MINALIGN_ATTR; \ struct aead_request *name = \ (((struct aead_request *)__##name##_desc)->base.tfm = \ crypto_sync_aead_tfm((_tfm)), \ (void *)__##name##_desc) static inline struct crypto_aead *__crypto_aead_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_aead, base); } /** * crypto_alloc_aead() - allocate AEAD cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * AEAD cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for an AEAD. The returned struct * crypto_aead is the cipher handle that is required for any subsequent * API invocation for that AEAD. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask); struct crypto_sync_aead *crypto_alloc_sync_aead(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm) { return &tfm->base; } static inline struct crypto_tfm *crypto_sync_aead_tfm(struct crypto_sync_aead *tfm) { return crypto_aead_tfm(&tfm->base); } /** * crypto_free_aead() - zeroize and free aead handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_aead(struct crypto_aead *tfm) { crypto_destroy_tfm(tfm, crypto_aead_tfm(tfm)); } static inline void crypto_free_sync_aead(struct crypto_sync_aead *tfm) { crypto_free_aead(&tfm->base); } /** * crypto_has_aead() - Search for the availability of an aead. * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * aead * @type: specifies the type of the aead * @mask: specifies the mask for the aead * * Return: true when the aead is known to the kernel crypto API; false * otherwise */ int crypto_has_aead(const char *alg_name, u32 type, u32 mask); static inline const char *crypto_aead_driver_name(struct crypto_aead *tfm) { return crypto_tfm_alg_driver_name(crypto_aead_tfm(tfm)); } static inline struct aead_alg *crypto_aead_alg(struct crypto_aead *tfm) { return container_of(crypto_aead_tfm(tfm)->__crt_alg, struct aead_alg, base); } static inline unsigned int crypto_aead_alg_ivsize(struct aead_alg *alg) { return alg->ivsize; } /** * crypto_aead_ivsize() - obtain IV size * @tfm: cipher handle * * The size of the IV for the aead referenced by the cipher handle is * returned. This IV size may be zero if the cipher does not need an IV. * * Return: IV size in bytes */ static inline unsigned int crypto_aead_ivsize(struct crypto_aead *tfm) { return crypto_aead_alg_ivsize(crypto_aead_alg(tfm)); } static inline unsigned int crypto_sync_aead_ivsize(struct crypto_sync_aead *tfm) { return crypto_aead_ivsize(&tfm->base); } /** * crypto_aead_authsize() - obtain maximum authentication data size * @tfm: cipher handle * * The maximum size of the authentication data for the AEAD cipher referenced * by the AEAD cipher handle is returned. The authentication data size may be * zero if the cipher implements a hard-coded maximum. * * The authentication data may also be known as "tag value". * * Return: authentication data size / tag size in bytes */ static inline unsigned int crypto_aead_authsize(struct crypto_aead *tfm) { return tfm->authsize; } static inline unsigned int crypto_sync_aead_authsize(struct crypto_sync_aead *tfm) { return crypto_aead_authsize(&tfm->base); } static inline unsigned int crypto_aead_alg_maxauthsize(struct aead_alg *alg) { return alg->maxauthsize; } static inline unsigned int crypto_aead_maxauthsize(struct crypto_aead *aead) { return crypto_aead_alg_maxauthsize(crypto_aead_alg(aead)); } static inline unsigned int crypto_sync_aead_maxauthsize(struct crypto_sync_aead *tfm) { return crypto_aead_maxauthsize(&tfm->base); } /** * crypto_aead_blocksize() - obtain block size of cipher * @tfm: cipher handle * * The block size for the AEAD referenced with the cipher handle is returned. * The caller may use that information to allocate appropriate memory for the * data returned by the encryption or decryption operation * * Return: block size of cipher */ static inline unsigned int crypto_aead_blocksize(struct crypto_aead *tfm) { return crypto_tfm_alg_blocksize(crypto_aead_tfm(tfm)); } static inline unsigned int crypto_sync_aead_blocksize(struct crypto_sync_aead *tfm) { return crypto_aead_blocksize(&tfm->base); } static inline unsigned int crypto_aead_alignmask(struct crypto_aead *tfm) { return crypto_tfm_alg_alignmask(crypto_aead_tfm(tfm)); } static inline u32 crypto_aead_get_flags(struct crypto_aead *tfm) { return crypto_tfm_get_flags(crypto_aead_tfm(tfm)); } static inline void crypto_aead_set_flags(struct crypto_aead *tfm, u32 flags) { crypto_tfm_set_flags(crypto_aead_tfm(tfm), flags); } static inline void crypto_aead_clear_flags(struct crypto_aead *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_aead_tfm(tfm), flags); } static inline u32 crypto_sync_aead_get_flags(struct crypto_sync_aead *tfm) { return crypto_aead_get_flags(&tfm->base); } static inline void crypto_sync_aead_set_flags(struct crypto_sync_aead *tfm, u32 flags) { crypto_aead_set_flags(&tfm->base, flags); } static inline void crypto_sync_aead_clear_flags(struct crypto_sync_aead *tfm, u32 flags) { crypto_aead_clear_flags(&tfm->base, flags); } /** * crypto_aead_setkey() - set key for cipher * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the AEAD referenced by the cipher * handle. * * Note, the key length determines the cipher type. Many block ciphers implement * different cipher modes depending on the key size, such as AES-128 vs AES-192 * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 * is performed. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_aead_setkey(struct crypto_aead *tfm, const u8 *key, unsigned int keylen); static inline int crypto_sync_aead_setkey(struct crypto_sync_aead *tfm, const u8 *key, unsigned int keylen) { return crypto_aead_setkey(&tfm->base, key, keylen); } /** * crypto_aead_setauthsize() - set authentication data size * @tfm: cipher handle * @authsize: size of the authentication data / tag in bytes * * Set the authentication data size / tag size. AEAD requires an authentication * tag (or MAC) in addition to the associated data. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize); static inline int crypto_sync_aead_setauthsize(struct crypto_sync_aead *tfm, unsigned int authsize) { return crypto_aead_setauthsize(&tfm->base, authsize); } static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req) { return __crypto_aead_cast(req->base.tfm); } static inline struct crypto_sync_aead *crypto_sync_aead_reqtfm(struct aead_request *req) { struct crypto_aead *tfm = crypto_aead_reqtfm(req); return container_of(tfm, struct crypto_sync_aead, base); } /** * crypto_aead_encrypt() - encrypt plaintext * @req: reference to the aead_request handle that holds all information * needed to perform the cipher operation * * Encrypt plaintext data using the aead_request handle. That data structure * and how it is filled with data is discussed with the aead_request_* * functions. * * IMPORTANT NOTE The encryption operation creates the authentication data / * tag. That data is concatenated with the created ciphertext. * The ciphertext memory size is therefore the given number of * block cipher blocks + the size defined by the * crypto_aead_setauthsize invocation. The caller must ensure * that sufficient memory is available for the ciphertext and * the authentication tag. * * Return: 0 if the cipher operation was successful; < 0 if an error occurred */ int crypto_aead_encrypt(struct aead_request *req); /** * crypto_aead_decrypt() - decrypt ciphertext * @req: reference to the aead_request handle that holds all information * needed to perform the cipher operation * * Decrypt ciphertext data using the aead_request handle. That data structure * and how it is filled with data is discussed with the aead_request_* * functions. * * IMPORTANT NOTE The caller must concatenate the ciphertext followed by the * authentication data / tag. That authentication data / tag * must have the size defined by the crypto_aead_setauthsize * invocation. * * * Return: 0 if the cipher operation was successful; -EBADMSG: The AEAD * cipher operation performs the authentication of the data during the * decryption operation. Therefore, the function returns this error if * the authentication of the ciphertext was unsuccessful (i.e. the * integrity of the ciphertext or the associated data was violated); * < 0 if an error occurred. */ int crypto_aead_decrypt(struct aead_request *req); /** * DOC: Asynchronous AEAD Request Handle * * The aead_request data structure contains all pointers to data required for * the AEAD cipher operation. This includes the cipher handle (which can be * used by multiple aead_request instances), pointer to plaintext and * ciphertext, asynchronous callback function, etc. It acts as a handle to the * aead_request_* API calls in a similar way as AEAD handle to the * crypto_aead_* API calls. */ /** * crypto_aead_reqsize() - obtain size of the request data structure * @tfm: cipher handle * * Return: number of bytes */ static inline unsigned int crypto_aead_reqsize(struct crypto_aead *tfm) { return tfm->reqsize; } /** * aead_request_set_tfm() - update cipher handle reference in request * @req: request handle to be modified * @tfm: cipher handle that shall be added to the request handle * * Allow the caller to replace the existing aead handle in the request * data structure with a different one. */ static inline void aead_request_set_tfm(struct aead_request *req, struct crypto_aead *tfm) { req->base.tfm = crypto_aead_tfm(tfm); } static inline void aead_request_set_sync_tfm(struct aead_request *req, struct crypto_sync_aead *tfm) { aead_request_set_tfm(req, &tfm->base); } /** * aead_request_alloc() - allocate request data structure * @tfm: cipher handle to be registered with the request * @gfp: memory allocation flag that is handed to kmalloc by the API call. * * Allocate the request data structure that must be used with the AEAD * encrypt and decrypt API calls. During the allocation, the provided aead * handle is registered in the request data structure. * * Return: allocated request handle in case of success, or NULL if out of memory */ static inline struct aead_request *aead_request_alloc(struct crypto_aead *tfm, gfp_t gfp) { struct aead_request *req; req = kmalloc(sizeof(*req) + crypto_aead_reqsize(tfm), gfp); if (likely(req)) aead_request_set_tfm(req, tfm); return req; } /** * aead_request_free() - zeroize and free request data structure * @req: request data structure cipher handle to be freed */ static inline void aead_request_free(struct aead_request *req) { kfree_sensitive(req); } /** * aead_request_set_callback() - set asynchronous callback function * @req: request handle * @flags: specify zero or an ORing of the flags * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and * increase the wait queue beyond the initial maximum size; * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep * @compl: callback function pointer to be registered with the request handle * @data: The data pointer refers to memory that is not used by the kernel * crypto API, but provided to the callback function for it to use. Here, * the caller can provide a reference to memory the callback function can * operate on. As the callback function is invoked asynchronously to the * related functionality, it may need to access data structures of the * related functionality which can be referenced using this pointer. The * callback function can access the memory via the "data" field in the * crypto_async_request data structure provided to the callback function. * * Setting the callback function that is triggered once the cipher operation * completes * * The callback function is registered with the aead_request handle and * must comply with the following template:: * * void callback_function(struct crypto_async_request *req, int error) */ static inline void aead_request_set_callback(struct aead_request *req, u32 flags, crypto_completion_t compl, void *data) { req->base.complete = compl; req->base.data = data; req->base.flags = flags; } /** * aead_request_set_crypt - set data buffers * @req: request handle * @src: source scatter / gather list * @dst: destination scatter / gather list * @cryptlen: number of bytes to process from @src * @iv: IV for the cipher operation which must comply with the IV size defined * by crypto_aead_ivsize() * * Setting the source data and destination data scatter / gather lists which * hold the associated data concatenated with the plaintext or ciphertext. See * below for the authentication tag. * * For encryption, the source is treated as the plaintext and the * destination is the ciphertext. For a decryption operation, the use is * reversed - the source is the ciphertext and the destination is the plaintext. * * The memory structure for cipher operation has the following structure: * * - AEAD encryption input: assoc data || plaintext * - AEAD encryption output: assoc data || ciphertext || auth tag * - AEAD decryption input: assoc data || ciphertext || auth tag * - AEAD decryption output: assoc data || plaintext * * Albeit the kernel requires the presence of the AAD buffer, however, * the kernel does not fill the AAD buffer in the output case. If the * caller wants to have that data buffer filled, the caller must either * use an in-place cipher operation (i.e. same memory location for * input/output memory location). */ static inline void aead_request_set_crypt(struct aead_request *req, struct scatterlist *src, struct scatterlist *dst, unsigned int cryptlen, u8 *iv) { req->src = src; req->dst = dst; req->cryptlen = cryptlen; req->iv = iv; } /** * aead_request_set_ad - set associated data information * @req: request handle * @assoclen: number of bytes in associated data * * Setting the AD information. This function sets the length of * the associated data. */ static inline void aead_request_set_ad(struct aead_request *req, unsigned int assoclen) { req->assoclen = assoclen; } #endif /* _CRYPTO_AEAD_H */ |
| 23 23 21 21 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * OF helpers for the GPIO API * * Copyright (c) 2007-2008 MontaVista Software, Inc. * * Author: Anton Vorontsov <avorontsov@ru.mvista.com> */ #include <linux/device.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/fwnode.h> #include <linux/io.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/pinctrl/pinctrl.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/gpio/consumer.h> #include <linux/gpio/machine.h> #include "gpiolib.h" #include "gpiolib-of.h" /* * This is Linux-specific flags. By default controllers' and Linux' mapping * match, but GPIO controllers are free to translate their own flags to * Linux-specific in their .xlate callback. Though, 1:1 mapping is recommended. */ enum of_gpio_flags { OF_GPIO_ACTIVE_LOW = 0x1, OF_GPIO_SINGLE_ENDED = 0x2, OF_GPIO_OPEN_DRAIN = 0x4, OF_GPIO_TRANSITORY = 0x8, OF_GPIO_PULL_UP = 0x10, OF_GPIO_PULL_DOWN = 0x20, OF_GPIO_PULL_DISABLE = 0x40, }; /** * of_gpio_named_count() - Count GPIOs for a device * @np: device node to count GPIOs for * @propname: property name containing gpio specifier(s) * * The function returns the count of GPIOs specified for a node. * NOTE: The empty GPIO specifiers count too. * * Returns: * Either number of GPIOs defined in the property, or * * %-EINVAL for an incorrectly formed "gpios" property, or * * %-ENOENT for a missing "gpios" property. * * Example:: * * gpios = <0 * &gpio1 1 2 * 0 * &gpio2 3 4>; * * The above example defines four GPIOs, two of which are not specified. * This function will return '4' */ static int of_gpio_named_count(const struct device_node *np, const char *propname) { return of_count_phandle_with_args(np, propname, "#gpio-cells"); } /** * of_gpio_spi_cs_get_count() - special GPIO counting for SPI * @np: Consuming device node * @con_id: Function within the GPIO consumer * * Some elder GPIO controllers need special quirks. Currently we handle * the Freescale and PPC GPIO controller with bindings that doesn't use the * established "cs-gpios" for chip selects but instead rely on * "gpios" for the chip select lines. If we detect this, we redirect * the counting of "cs-gpios" to count "gpios" transparent to the * driver. * * Returns: * Either number of GPIOs defined in the property, or * * %-EINVAL for an incorrectly formed "gpios" property, or * * %-ENOENT for a missing "gpios" property. */ static int of_gpio_spi_cs_get_count(const struct device_node *np, const char *con_id) { if (!IS_ENABLED(CONFIG_SPI_MASTER)) return 0; if (!con_id || strcmp(con_id, "cs")) return 0; if (!of_device_is_compatible(np, "fsl,spi") && !of_device_is_compatible(np, "aeroflexgaisler,spictrl") && !of_device_is_compatible(np, "ibm,ppc4xx-spi")) return 0; return of_gpio_named_count(np, "gpios"); } int of_gpio_count(const struct fwnode_handle *fwnode, const char *con_id) { const struct device_node *np = to_of_node(fwnode); int ret; char propname[32]; ret = of_gpio_spi_cs_get_count(np, con_id); if (ret > 0) return ret; for_each_gpio_property_name(propname, con_id) { ret = of_gpio_named_count(np, propname); if (ret > 0) break; } return ret ? ret : -ENOENT; } static int of_gpiochip_match_node_and_xlate(struct gpio_chip *chip, const void *data) { const struct of_phandle_args *gpiospec = data; return device_match_of_node(&chip->gpiodev->dev, gpiospec->np) && chip->of_xlate && chip->of_xlate(chip, gpiospec, NULL) >= 0; } static struct gpio_device * of_find_gpio_device_by_xlate(const struct of_phandle_args *gpiospec) { return gpio_device_find(gpiospec, of_gpiochip_match_node_and_xlate); } static struct gpio_desc *of_xlate_and_get_gpiod_flags(struct gpio_chip *chip, struct of_phandle_args *gpiospec, enum of_gpio_flags *flags) { int ret; if (chip->of_gpio_n_cells != gpiospec->args_count) return ERR_PTR(-EINVAL); ret = chip->of_xlate(chip, gpiospec, flags); if (ret < 0) return ERR_PTR(ret); return gpiochip_get_desc(chip, ret); } /* * Overrides stated polarity of a gpio line and warns when there is a * discrepancy. */ static void of_gpio_quirk_polarity(const struct device_node *np, bool active_high, enum of_gpio_flags *flags) { if (active_high) { if (*flags & OF_GPIO_ACTIVE_LOW) { pr_warn("%s GPIO handle specifies active low - ignored\n", of_node_full_name(np)); *flags &= ~OF_GPIO_ACTIVE_LOW; } } else { if (!(*flags & OF_GPIO_ACTIVE_LOW)) pr_info("%s enforce active low on GPIO handle\n", of_node_full_name(np)); *flags |= OF_GPIO_ACTIVE_LOW; } } /* * This quirk does static polarity overrides in cases where existing * DTS specified incorrect polarity. */ static void of_gpio_try_fixup_polarity(const struct device_node *np, const char *propname, enum of_gpio_flags *flags) { static const struct { const char *compatible; const char *propname; bool active_high; } gpios[] = { #if IS_ENABLED(CONFIG_LCD_HX8357) /* * Himax LCD controllers used incorrectly named * "gpios-reset" property and also specified wrong * polarity. */ { "himax,hx8357", "gpios-reset", false }, { "himax,hx8369", "gpios-reset", false }, #endif #if IS_ENABLED(CONFIG_MTD_NAND_JZ4780) /* * The rb-gpios semantics was undocumented and qi,lb60 (along with * the ingenic driver) got it wrong. The active state encodes the * NAND ready state, which is high level. Since there's no signal * inverter on this board, it should be active-high. Let's fix that * here for older DTs so we can re-use the generic nand_gpio_waitrdy() * helper, and be consistent with what other drivers do. */ { "qi,lb60", "rb-gpios", true }, #endif #if IS_ENABLED(CONFIG_IEEE802154_CA8210) /* * According to the datasheet, the NRST pin 27 is an active-low * signal. However, the device tree schema and admittedly * the out-of-tree implementations have been used for a long * time incorrectly by describing reset GPIO as active-high. */ { "cascoda,ca8210", "reset-gpio", false }, #endif #if IS_ENABLED(CONFIG_PCI_LANTIQ) /* * According to the PCI specification, the RST# pin is an * active-low signal. However, most of the device trees that * have been widely used for a long time incorrectly describe * reset GPIO as active-high, and were also using wrong name * for the property. */ { "lantiq,pci-xway", "gpio-reset", false }, #endif #if IS_ENABLED(CONFIG_REGULATOR_S5M8767) /* * According to S5M8767, the DVS and DS pin are * active-high signals. However, exynos5250-spring.dts use * active-low setting. */ { "samsung,s5m8767-pmic", "s5m8767,pmic-buck-dvs-gpios", true }, { "samsung,s5m8767-pmic", "s5m8767,pmic-buck-ds-gpios", true }, #endif #if IS_ENABLED(CONFIG_TOUCHSCREEN_TSC2005) /* * DTS for Nokia N900 incorrectly specified "active high" * polarity for the reset line, while the chip actually * treats it as "active low". */ { "ti,tsc2005", "reset-gpios", false }, #endif #if IS_ENABLED(CONFIG_SND_SOC_WSA881X) /* * WSA881 powerdown is always active low, but some device trees * missed this when first contributed. It also has a very strange * compatible. */ { "sdw10217201000", "powerdown-gpios", false }, #endif }; unsigned int i; for (i = 0; i < ARRAY_SIZE(gpios); i++) { if (of_device_is_compatible(np, gpios[i].compatible) && !strcmp(propname, gpios[i].propname)) { of_gpio_quirk_polarity(np, gpios[i].active_high, flags); break; } } } static void of_gpio_set_polarity_by_property(const struct device_node *np, const char *propname, enum of_gpio_flags *flags) { const struct device_node *np_compat = np; const struct device_node *np_propname = np; static const struct { const char *compatible; const char *gpio_propname; const char *polarity_propname; } gpios[] = { #if IS_ENABLED(CONFIG_FEC) /* Freescale Fast Ethernet Controller */ { "fsl,imx25-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,imx27-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,imx28-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,imx6q-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,mvf600-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,imx6sx-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,imx6ul-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,imx8mq-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,imx8qm-fec", "phy-reset-gpios", "phy-reset-active-high" }, { "fsl,s32v234-fec", "phy-reset-gpios", "phy-reset-active-high" }, #endif #if IS_ENABLED(CONFIG_MMC_ATMELMCI) { "atmel,hsmci", "cd-gpios", "cd-inverted" }, #endif #if IS_ENABLED(CONFIG_PCI_IMX6) { "fsl,imx6q-pcie", "reset-gpio", "reset-gpio-active-high" }, { "fsl,imx6sx-pcie", "reset-gpio", "reset-gpio-active-high" }, { "fsl,imx6qp-pcie", "reset-gpio", "reset-gpio-active-high" }, { "fsl,imx7d-pcie", "reset-gpio", "reset-gpio-active-high" }, { "fsl,imx8mq-pcie", "reset-gpio", "reset-gpio-active-high" }, { "fsl,imx8mm-pcie", "reset-gpio", "reset-gpio-active-high" }, { "fsl,imx8mp-pcie", "reset-gpio", "reset-gpio-active-high" }, #endif /* * The regulator GPIO handles are specified such that the * presence or absence of "enable-active-high" solely controls * the polarity of the GPIO line. Any phandle flags must * be actively ignored. */ #if IS_ENABLED(CONFIG_REGULATOR_FIXED_VOLTAGE) { "regulator-fixed", "gpios", "enable-active-high" }, { "regulator-fixed", "gpio", "enable-active-high" }, { "reg-fixed-voltage", "gpios", "enable-active-high" }, { "reg-fixed-voltage", "gpio", "enable-active-high" }, #endif #if IS_ENABLED(CONFIG_REGULATOR_GPIO) { "regulator-gpio", "enable-gpio", "enable-active-high" }, { "regulator-gpio", "enable-gpios", "enable-active-high" }, #endif }; unsigned int i; bool active_high; #if IS_ENABLED(CONFIG_MMC_ATMELMCI) /* * The Atmel HSMCI has compatible property in the parent node and * gpio property in a child node */ if (of_device_is_compatible(np->parent, "atmel,hsmci")) { np_compat = np->parent; np_propname = np; } #endif for (i = 0; i < ARRAY_SIZE(gpios); i++) { if (of_device_is_compatible(np_compat, gpios[i].compatible) && !strcmp(propname, gpios[i].gpio_propname)) { active_high = of_property_read_bool(np_propname, gpios[i].polarity_propname); of_gpio_quirk_polarity(np, active_high, flags); break; } } } static void of_gpio_flags_quirks(const struct device_node *np, const char *propname, enum of_gpio_flags *flags, int index) { of_gpio_try_fixup_polarity(np, propname, flags); of_gpio_set_polarity_by_property(np, propname, flags); /* * Legacy open drain handling for fixed voltage regulators. */ if (IS_ENABLED(CONFIG_REGULATOR) && of_device_is_compatible(np, "reg-fixed-voltage") && of_property_read_bool(np, "gpio-open-drain")) { *flags |= (OF_GPIO_SINGLE_ENDED | OF_GPIO_OPEN_DRAIN); pr_info("%s uses legacy open drain flag - update the DTS if you can\n", of_node_full_name(np)); } /* * Legacy handling of SPI active high chip select. If we have a * property named "cs-gpios" we need to inspect the child node * to determine if the flags should have inverted semantics. */ if (IS_ENABLED(CONFIG_SPI_MASTER) && !strcmp(propname, "cs-gpios") && of_property_present(np, "cs-gpios")) { u32 cs; int ret; for_each_child_of_node_scoped(np, child) { ret = of_property_read_u32(child, "reg", &cs); if (ret) continue; if (cs == index) { /* * SPI children have active low chip selects * by default. This can be specified negatively * by just omitting "spi-cs-high" in the * device node, or actively by tagging on * GPIO_ACTIVE_LOW as flag in the device * tree. If the line is simultaneously * tagged as active low in the device tree * and has the "spi-cs-high" set, we get a * conflict and the "spi-cs-high" flag will * take precedence. */ bool active_high = of_property_read_bool(child, "spi-cs-high"); of_gpio_quirk_polarity(child, active_high, flags); break; } } } /* Legacy handling of stmmac's active-low PHY reset line */ if (IS_ENABLED(CONFIG_STMMAC_ETH) && !strcmp(propname, "snps,reset-gpio") && of_property_read_bool(np, "snps,reset-active-low")) *flags |= OF_GPIO_ACTIVE_LOW; } /** * of_get_named_gpiod_flags() - Get a GPIO descriptor and flags for GPIO API * @np: device node to get GPIO from * @propname: property name containing gpio specifier(s) * @index: index of the GPIO * @flags: a flags pointer to fill in * * Returns: * GPIO descriptor to use with Linux GPIO API, or one of the errno * value on the error condition. If @flags is not NULL the function also fills * in flags for the GPIO. */ static struct gpio_desc *of_get_named_gpiod_flags(const struct device_node *np, const char *propname, int index, enum of_gpio_flags *flags) { struct of_phandle_args gpiospec; struct gpio_desc *desc; int ret; ret = of_parse_phandle_with_args_map(np, propname, "gpio", index, &gpiospec); if (ret) { pr_debug("%s: can't parse '%s' property of node '%pOF[%d]'\n", __func__, propname, np, index); return ERR_PTR(ret); } struct gpio_device *gdev __free(gpio_device_put) = of_find_gpio_device_by_xlate(&gpiospec); if (!gdev) { desc = ERR_PTR(-EPROBE_DEFER); goto out; } desc = of_xlate_and_get_gpiod_flags(gpio_device_get_chip(gdev), &gpiospec, flags); if (IS_ERR(desc)) goto out; if (flags) of_gpio_flags_quirks(np, propname, flags, index); pr_debug("%s: parsed '%s' property of node '%pOF[%d]' - status (%d)\n", __func__, propname, np, index, PTR_ERR_OR_ZERO(desc)); out: of_node_put(gpiospec.np); return desc; } /* Converts gpio_lookup_flags into bitmask of GPIO_* values */ static unsigned long of_convert_gpio_flags(enum of_gpio_flags flags) { unsigned long lflags = GPIO_LOOKUP_FLAGS_DEFAULT; if (flags & OF_GPIO_ACTIVE_LOW) lflags |= GPIO_ACTIVE_LOW; if (flags & OF_GPIO_SINGLE_ENDED) { if (flags & OF_GPIO_OPEN_DRAIN) lflags |= GPIO_OPEN_DRAIN; else lflags |= GPIO_OPEN_SOURCE; } if (flags & OF_GPIO_TRANSITORY) lflags |= GPIO_TRANSITORY; if (flags & OF_GPIO_PULL_UP) lflags |= GPIO_PULL_UP; if (flags & OF_GPIO_PULL_DOWN) lflags |= GPIO_PULL_DOWN; if (flags & OF_GPIO_PULL_DISABLE) lflags |= GPIO_PULL_DISABLE; return lflags; } static struct gpio_desc *of_find_gpio_rename(struct device_node *np, const char *con_id, unsigned int idx, enum of_gpio_flags *of_flags) { static const struct of_rename_gpio { const char *con_id; const char *legacy_id; /* NULL - same as con_id */ /* * Compatible string can be set to NULL in case where * matching to a particular compatible is not practical, * but it should only be done for gpio names that have * vendor prefix to reduce risk of false positives. * Addition of such entries is strongly discouraged. */ const char *compatible; } gpios[] = { #if IS_ENABLED(CONFIG_LCD_HX8357) /* Himax LCD controllers used "gpios-reset" */ { "reset", "gpios-reset", "himax,hx8357" }, { "reset", "gpios-reset", "himax,hx8369" }, #endif #if IS_ENABLED(CONFIG_MFD_ARIZONA) { "wlf,reset", NULL, NULL }, #endif #if IS_ENABLED(CONFIG_RTC_DRV_MOXART) { "rtc-data", "gpio-rtc-data", "moxa,moxart-rtc" }, { "rtc-sclk", "gpio-rtc-sclk", "moxa,moxart-rtc" }, { "rtc-reset", "gpio-rtc-reset", "moxa,moxart-rtc" }, #endif #if IS_ENABLED(CONFIG_NFC_MRVL_I2C) { "reset", "reset-n-io", "marvell,nfc-i2c" }, #endif #if IS_ENABLED(CONFIG_NFC_MRVL_SPI) { "reset", "reset-n-io", "marvell,nfc-spi" }, #endif #if IS_ENABLED(CONFIG_NFC_MRVL_UART) { "reset", "reset-n-io", "marvell,nfc-uart" }, { "reset", "reset-n-io", "mrvl,nfc-uart" }, #endif #if IS_ENABLED(CONFIG_NFC_S3FWRN5_I2C) { "en", "s3fwrn5,en-gpios", "samsung,s3fwrn5-i2c" }, { "wake", "s3fwrn5,fw-gpios", "samsung,s3fwrn5-i2c" }, #endif #if IS_ENABLED(CONFIG_PCI_LANTIQ) /* MIPS Lantiq PCI */ { "reset", "gpio-reset", "lantiq,pci-xway" }, #endif /* * Some regulator bindings happened before we managed to * establish that GPIO properties should be named * "foo-gpios" so we have this special kludge for them. */ #if IS_ENABLED(CONFIG_REGULATOR_ARIZONA_LDO1) { "wlf,ldoena", NULL, NULL }, /* Arizona */ #endif #if IS_ENABLED(CONFIG_REGULATOR_WM8994) { "wlf,ldo1ena", NULL, NULL }, /* WM8994 */ { "wlf,ldo2ena", NULL, NULL }, /* WM8994 */ #endif #if IS_ENABLED(CONFIG_SND_SOC_CS42L56) { "reset", "cirrus,gpio-nreset", "cirrus,cs42l56" }, #endif #if IS_ENABLED(CONFIG_SND_SOC_MT2701_CS42448) { "i2s1-in-sel-gpio1", NULL, "mediatek,mt2701-cs42448-machine" }, { "i2s1-in-sel-gpio2", NULL, "mediatek,mt2701-cs42448-machine" }, #endif #if IS_ENABLED(CONFIG_SND_SOC_TLV320AIC3X) { "reset", "gpio-reset", "ti,tlv320aic3x" }, { "reset", "gpio-reset", "ti,tlv320aic33" }, { "reset", "gpio-reset", "ti,tlv320aic3007" }, { "reset", "gpio-reset", "ti,tlv320aic3104" }, { "reset", "gpio-reset", "ti,tlv320aic3106" }, #endif #if IS_ENABLED(CONFIG_SPI_GPIO) /* * The SPI GPIO bindings happened before we managed to * establish that GPIO properties should be named * "foo-gpios" so we have this special kludge for them. */ { "miso", "gpio-miso", "spi-gpio" }, { "mosi", "gpio-mosi", "spi-gpio" }, { "sck", "gpio-sck", "spi-gpio" }, #endif /* * The old Freescale bindings use simply "gpios" as name * for the chip select lines rather than "cs-gpios" like * all other SPI hardware. Allow this specifically for * Freescale and PPC devices. */ #if IS_ENABLED(CONFIG_SPI_FSL_SPI) { "cs", "gpios", "fsl,spi" }, { "cs", "gpios", "aeroflexgaisler,spictrl" }, #endif #if IS_ENABLED(CONFIG_SPI_PPC4xx) { "cs", "gpios", "ibm,ppc4xx-spi" }, #endif #if IS_ENABLED(CONFIG_TYPEC_FUSB302) /* * Fairchild FUSB302 host is using undocumented "fcs,int_n" * property without the compulsory "-gpios" suffix. */ { "fcs,int_n", NULL, "fcs,fusb302" }, #endif }; struct gpio_desc *desc; const char *legacy_id; unsigned int i; if (!con_id) return ERR_PTR(-ENOENT); for (i = 0; i < ARRAY_SIZE(gpios); i++) { if (strcmp(con_id, gpios[i].con_id)) continue; if (gpios[i].compatible && !of_device_is_compatible(np, gpios[i].compatible)) continue; legacy_id = gpios[i].legacy_id ?: gpios[i].con_id; desc = of_get_named_gpiod_flags(np, legacy_id, idx, of_flags); if (!gpiod_not_found(desc)) { pr_info("%s uses legacy gpio name '%s' instead of '%s-gpios'\n", of_node_full_name(np), legacy_id, con_id); return desc; } } return ERR_PTR(-ENOENT); } #if IS_ENABLED(CONFIG_SND_SOC_MT2701_CS42448) static struct gpio_desc *of_find_mt2701_gpio(struct device_node *np, const char *con_id, unsigned int idx, enum of_gpio_flags *of_flags) { struct gpio_desc *desc; const char *legacy_id; if (!IS_ENABLED(CONFIG_SND_SOC_MT2701_CS42448)) return ERR_PTR(-ENOENT); if (!of_device_is_compatible(np, "mediatek,mt2701-cs42448-machine")) return ERR_PTR(-ENOENT); if (!con_id || strcmp(con_id, "i2s1-in-sel")) return ERR_PTR(-ENOENT); if (idx == 0) legacy_id = "i2s1-in-sel-gpio1"; else if (idx == 1) legacy_id = "i2s1-in-sel-gpio2"; else return ERR_PTR(-ENOENT); desc = of_get_named_gpiod_flags(np, legacy_id, 0, of_flags); if (!gpiod_not_found(desc)) pr_info("%s is using legacy gpio name '%s' instead of '%s-gpios'\n", of_node_full_name(np), legacy_id, con_id); return desc; } #endif /* * Trigger sources are special, they allow us to use any GPIO as a LED trigger * and have the name "trigger-sources" no matter which kind of phandle it is * pointing to, whether to a GPIO, a USB host, a network PHY etc. So in this case * we allow looking something up that is not named "foo-gpios". */ static struct gpio_desc *of_find_trigger_gpio(struct device_node *np, const char *con_id, unsigned int idx, enum of_gpio_flags *of_flags) { struct gpio_desc *desc; if (!IS_ENABLED(CONFIG_LEDS_TRIGGER_GPIO)) return ERR_PTR(-ENOENT); if (!con_id || strcmp(con_id, "trigger-sources")) return ERR_PTR(-ENOENT); desc = of_get_named_gpiod_flags(np, con_id, idx, of_flags); if (!gpiod_not_found(desc)) pr_debug("%s is used as a trigger\n", of_node_full_name(np)); return desc; } typedef struct gpio_desc *(*of_find_gpio_quirk)(struct device_node *np, const char *con_id, unsigned int idx, enum of_gpio_flags *of_flags); static const of_find_gpio_quirk of_find_gpio_quirks[] = { of_find_gpio_rename, #if IS_ENABLED(CONFIG_SND_SOC_MT2701_CS42448) of_find_mt2701_gpio, #endif of_find_trigger_gpio, NULL }; struct gpio_desc *of_find_gpio(struct device_node *np, const char *con_id, unsigned int idx, unsigned long *flags) { char propname[32]; /* 32 is max size of property name */ enum of_gpio_flags of_flags = 0; const of_find_gpio_quirk *q; struct gpio_desc *desc; /* Try GPIO property "foo-gpios" and "foo-gpio" */ for_each_gpio_property_name(propname, con_id) { desc = of_get_named_gpiod_flags(np, propname, idx, &of_flags); if (!gpiod_not_found(desc)) break; } /* Properly named GPIO was not found, try workarounds */ for (q = of_find_gpio_quirks; gpiod_not_found(desc) && *q; q++) desc = (*q)(np, con_id, idx, &of_flags); if (IS_ERR(desc)) return desc; *flags = of_convert_gpio_flags(of_flags); return desc; } int of_gpiochip_get_lflags(struct gpio_chip *chip, struct fwnode_reference_args *gpiospec, unsigned long *lflags) { enum of_gpio_flags xlate_flags; struct of_phandle_args args; struct gpio_desc *desc; args.np = to_of_node(gpiospec->fwnode); args.args_count = gpiospec->nargs; for (int i = 0; i < args.args_count; i++) args.args[i] = gpiospec->args[i]; desc = of_xlate_and_get_gpiod_flags(chip, &args, &xlate_flags); if (IS_ERR(desc)) return PTR_ERR(desc); *lflags = of_convert_gpio_flags(xlate_flags); return 0; } #ifdef CONFIG_OF_DYNAMIC /** * of_gpiochip_remove_hog - Remove all hogs in a hog device node * @chip: gpio chip to act on * @hog: device node describing the hogs */ static void of_gpiochip_remove_hog(struct gpio_chip *chip, struct device_node *hog) { struct gpio_desc *desc; for_each_gpio_desc_with_flag(chip, desc, GPIOD_FLAG_IS_HOGGED) if (READ_ONCE(desc->hog) == hog) gpiochip_free_own_desc(desc); } static int of_gpiochip_match_node(struct gpio_chip *chip, const void *data) { return device_match_of_node(&chip->gpiodev->dev, data); } static struct gpio_device *of_find_gpio_device_by_node(struct device_node *np) { return gpio_device_find(np, of_gpiochip_match_node); } static int of_gpio_notify(struct notifier_block *nb, unsigned long action, void *arg) { struct gpio_device *gdev __free(gpio_device_put) = NULL; struct of_reconfig_data *rd = arg; int ret; /* * This only supports adding and removing complete gpio-hog nodes. * Modifying an existing gpio-hog node is not supported (except for * changing its "status" property, which is treated the same as * addition/removal). */ switch (of_reconfig_get_state_change(action, arg)) { case OF_RECONFIG_CHANGE_ADD: if (!of_property_read_bool(rd->dn, "gpio-hog")) return NOTIFY_DONE; /* not for us */ if (of_node_test_and_set_flag(rd->dn, OF_POPULATED)) return NOTIFY_DONE; gdev = of_find_gpio_device_by_node(rd->dn->parent); if (!gdev) return NOTIFY_DONE; /* not for us */ ret = gpiochip_add_hog(gpio_device_get_chip(gdev), of_fwnode_handle(rd->dn)); if (ret < 0) { pr_err("%s: failed to add hogs for %pOF\n", __func__, rd->dn); of_node_clear_flag(rd->dn, OF_POPULATED); return notifier_from_errno(ret); } return NOTIFY_OK; case OF_RECONFIG_CHANGE_REMOVE: if (!of_node_check_flag(rd->dn, OF_POPULATED)) return NOTIFY_DONE; /* already depopulated */ gdev = of_find_gpio_device_by_node(rd->dn->parent); if (!gdev) return NOTIFY_DONE; /* not for us */ of_gpiochip_remove_hog(gpio_device_get_chip(gdev), rd->dn); of_node_clear_flag(rd->dn, OF_POPULATED); return NOTIFY_OK; } return NOTIFY_DONE; } struct notifier_block gpio_of_notifier = { .notifier_call = of_gpio_notify, }; #endif /* CONFIG_OF_DYNAMIC */ /** * of_gpio_twocell_xlate - translate twocell gpiospec to the GPIO number and flags * @gc: pointer to the gpio_chip structure * @gpiospec: GPIO specifier as found in the device tree * @flags: a flags pointer to fill in * * This is simple translation function, suitable for the most 1:1 mapped * GPIO chips. This function performs only one sanity check: whether GPIO * is less than ngpios (that is specified in the gpio_chip). * * Returns: * GPIO number (>= 0) on success, negative errno on failure. */ static int of_gpio_twocell_xlate(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags) { /* * We're discouraging gpio_cells < 2, since that way you'll have to * write your own xlate function (that will have to retrieve the GPIO * number and the flags from a single gpio cell -- this is possible, * but not recommended). */ if (gc->of_gpio_n_cells != 2) { WARN_ON(1); return -EINVAL; } if (WARN_ON(gpiospec->args_count < gc->of_gpio_n_cells)) return -EINVAL; if (gpiospec->args[0] >= gc->ngpio) return -EINVAL; if (flags) *flags = gpiospec->args[1]; return gpiospec->args[0]; } /** * of_gpio_threecell_xlate - translate threecell gpiospec to the GPIO number and flags * @gc: pointer to the gpio_chip structure * @gpiospec: GPIO specifier as found in the device tree * @flags: a flags pointer to fill in * * This is simple translation function, suitable for the most 1:n mapped * GPIO chips, i.e. several GPIO chip instances from one device tree node. * In this case the following binding is implied: * * foo-gpios = <&gpio instance offset flags>; * * Returns: * GPIO number (>= 0) on success, negative errno on failure. */ static int of_gpio_threecell_xlate(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags) { if (gc->of_gpio_n_cells != 3) { WARN_ON(1); return -EINVAL; } if (WARN_ON(gpiospec->args_count != 3)) return -EINVAL; /* * Check chip instance number, the driver responds with true if * this is the chip we are looking for. */ if (!gc->of_node_instance_match(gc, gpiospec->args[0])) return -EINVAL; if (gpiospec->args[1] >= gc->ngpio) return -EINVAL; if (flags) *flags = gpiospec->args[2]; return gpiospec->args[1]; } #ifdef CONFIG_PINCTRL static int of_gpiochip_add_pin_range(struct gpio_chip *chip) { struct of_phandle_args pinspec; struct pinctrl_dev *pctldev; struct device_node *np; int index = 0, ret, trim; const char *name; static const char group_names_propname[] = "gpio-ranges-group-names"; bool has_group_names; int offset; /* Offset of the first GPIO line on the chip */ int pin; /* Pin base number in the range */ int count; /* Number of pins/GPIO lines to map */ np = dev_of_node(&chip->gpiodev->dev); if (!np) return 0; has_group_names = of_property_present(np, group_names_propname); for (;; index++) { /* * Ordinary phandles contain 2-3 cells: * gpios = <&gpio [instance] offset flags>; * Ranges always contain one more cell: * gpio-ranges <&pinctrl [gpio_instance] gpio_offet pin_offet count>; * This is why we parse chip->of_gpio_n_cells + 1 cells */ ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", chip->of_gpio_n_cells + 1, index, &pinspec); if (ret) break; pctldev = of_pinctrl_get(pinspec.np); of_node_put(pinspec.np); if (!pctldev) return -EPROBE_DEFER; if (chip->of_gpio_n_cells == 3) { /* First cell is the gpiochip instance number */ offset = pinspec.args[1]; pin = pinspec.args[2]; count = pinspec.args[3]; } else { offset = pinspec.args[0]; pin = pinspec.args[1]; count = pinspec.args[2]; } /* * With multiple GPIO chips per node, check that this chip is the * right instance. */ if (chip->of_node_instance_match && (chip->of_gpio_n_cells == 3) && !chip->of_node_instance_match(chip, pinspec.args[0])) continue; /* Ignore ranges outside of this GPIO chip */ if (offset >= (chip->offset + chip->ngpio)) continue; if (offset + count <= chip->offset) continue; if (count) { /* npins != 0: linear range */ if (has_group_names) { of_property_read_string_index(np, group_names_propname, index, &name); if (strlen(name)) { pr_err("%pOF: Group name of numeric GPIO ranges must be the empty string.\n", np); break; } } /* Trim the range to fit this GPIO chip */ if (chip->offset > offset) { trim = chip->offset - offset; count -= trim; pin += trim; offset = 0; } else { offset -= chip->offset; } if ((offset + count) > chip->ngpio) count = chip->ngpio - offset; ret = gpiochip_add_pin_range(chip, pinctrl_dev_get_devname(pctldev), offset, pin, count); if (ret) return ret; } else { /* npins == 0: special range */ if (pin) { pr_err("%pOF: Illegal gpio-range format.\n", np); break; } if (!has_group_names) { pr_err("%pOF: GPIO group range requested but no %s property.\n", np, group_names_propname); break; } ret = of_property_read_string_index(np, group_names_propname, index, &name); if (ret) break; if (!strlen(name)) { pr_err("%pOF: Group name of GPIO group range cannot be the empty string.\n", np); break; } ret = gpiochip_add_pingroup_range(chip, pctldev, offset, name); if (ret) return ret; } } return 0; } #else static int of_gpiochip_add_pin_range(struct gpio_chip *chip) { return 0; } #endif int of_gpiochip_add(struct gpio_chip *chip) { struct device_node *np; int ret; np = dev_of_node(&chip->gpiodev->dev); if (!np) return 0; if (!chip->of_xlate) { if (chip->of_gpio_n_cells == 3) { if (!chip->of_node_instance_match) return -EINVAL; chip->of_xlate = of_gpio_threecell_xlate; } else { chip->of_gpio_n_cells = 2; chip->of_xlate = of_gpio_twocell_xlate; } } if (chip->of_gpio_n_cells > MAX_PHANDLE_ARGS) return -EINVAL; ret = of_gpiochip_add_pin_range(chip); if (ret) return ret; of_node_get(np); return ret; } void of_gpiochip_remove(struct gpio_chip *chip) { struct device_node *np = dev_of_node(&chip->gpiodev->dev); for_each_child_of_node_scoped(np, child) { if (of_property_present(child, "gpio-hog")) of_node_clear_flag(child, OF_POPULATED); } of_node_put(np); } bool of_gpiochip_instance_match(struct gpio_chip *gc, unsigned int index) { if (gc->of_node_instance_match) return gc->of_node_instance_match(gc, index); return false; } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/em_cmp.c Simple packet data comparison ematch * * Authors: Thomas Graf <tgraf@suug.ch> */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/tc_ematch/tc_em_cmp.h> #include <linux/unaligned.h> #include <net/pkt_cls.h> static inline int cmp_needs_transformation(struct tcf_em_cmp *cmp) { return unlikely(cmp->flags & TCF_EM_CMP_TRANS); } static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { struct tcf_em_cmp *cmp = (struct tcf_em_cmp *) em->data; unsigned char *ptr = tcf_get_base_ptr(skb, cmp->layer); u32 val = 0; if (!ptr) return 0; ptr += cmp->off; if (!tcf_valid_offset(skb, ptr, cmp->align)) return 0; switch (cmp->align) { case TCF_EM_ALIGN_U8: val = *ptr; break; case TCF_EM_ALIGN_U16: val = get_unaligned_be16(ptr); if (cmp_needs_transformation(cmp)) val = be16_to_cpu(val); break; case TCF_EM_ALIGN_U32: /* Worth checking boundaries? The branching seems * to get worse. Visit again. */ val = get_unaligned_be32(ptr); if (cmp_needs_transformation(cmp)) val = be32_to_cpu(val); break; default: return 0; } if (cmp->mask) val &= cmp->mask; switch (cmp->opnd) { case TCF_EM_OPND_EQ: return val == cmp->val; case TCF_EM_OPND_LT: return val < cmp->val; case TCF_EM_OPND_GT: return val > cmp->val; } return 0; } static struct tcf_ematch_ops em_cmp_ops = { .kind = TCF_EM_CMP, .datalen = sizeof(struct tcf_em_cmp), .match = em_cmp_match, .owner = THIS_MODULE, .link = LIST_HEAD_INIT(em_cmp_ops.link) }; static int __init init_em_cmp(void) { return tcf_em_register(&em_cmp_ops); } static void __exit exit_em_cmp(void) { tcf_em_unregister(&em_cmp_ops); } MODULE_DESCRIPTION("ematch classifier for basic data types(8/16/32 bit) against skb data"); MODULE_LICENSE("GPL"); module_init(init_em_cmp); module_exit(exit_em_cmp); MODULE_ALIAS_TCF_EMATCH(TCF_EM_CMP); |
| 4 4 4 4 3 1 4 1 3 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Transport & Protocol Driver for In-System Design, Inc. ISD200 ASIC * * Current development and maintenance: * (C) 2001-2002 Björn Stenberg (bjorn@haxx.se) * * Developed with the assistance of: * (C) 2002 Alan Stern <stern@rowland.org> * * Initial work: * (C) 2000 In-System Design, Inc. (support@in-system.com) * * The ISD200 ASIC does not natively support ATA devices. The chip * does implement an interface, the ATA Command Block (ATACB) which provides * a means of passing ATA commands and ATA register accesses to a device. * * History: * * 2002-10-19: Removed the specialized transfer routines. * (Alan Stern <stern@rowland.harvard.edu>) * 2001-02-24: Removed lots of duplicate code and simplified the structure. * (bjorn@haxx.se) * 2002-01-16: Fixed endianness bug so it works on the ppc arch. * (Luc Saillard <luc@saillard.org>) * 2002-01-17: All bitfields removed. * (bjorn@haxx.se) */ /* Include files */ #include <linux/jiffies.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/ata.h> #include <linux/hdreg.h> #include <linux/scatterlist.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> #include "usb.h" #include "transport.h" #include "protocol.h" #include "debug.h" #include "scsiglue.h" #define DRV_NAME "ums-isd200" MODULE_DESCRIPTION("Driver for In-System Design, Inc. ISD200 ASIC"); MODULE_AUTHOR("Björn Stenberg <bjorn@haxx.se>"); MODULE_LICENSE("GPL"); MODULE_IMPORT_NS("USB_STORAGE"); static int isd200_Initialization(struct us_data *us); /* * The table of devices */ #define UNUSUAL_DEV(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax, \ vendorName, productName, useProtocol, useTransport, \ initFunction, flags) \ { USB_DEVICE_VER(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax), \ .driver_info = (flags) } static const struct usb_device_id isd200_usb_ids[] = { # include "unusual_isd200.h" { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, isd200_usb_ids); #undef UNUSUAL_DEV /* * The flags table */ #define UNUSUAL_DEV(idVendor, idProduct, bcdDeviceMin, bcdDeviceMax, \ vendor_name, product_name, use_protocol, use_transport, \ init_function, Flags) \ { \ .vendorName = vendor_name, \ .productName = product_name, \ .useProtocol = use_protocol, \ .useTransport = use_transport, \ .initFunction = init_function, \ } static const struct us_unusual_dev isd200_unusual_dev_list[] = { # include "unusual_isd200.h" { } /* Terminating entry */ }; #undef UNUSUAL_DEV /* Timeout defines (in Seconds) */ #define ISD200_ENUM_BSY_TIMEOUT 35 #define ISD200_ENUM_DETECT_TIMEOUT 30 #define ISD200_DEFAULT_TIMEOUT 30 /* device flags */ #define DF_ATA_DEVICE 0x0001 #define DF_MEDIA_STATUS_ENABLED 0x0002 #define DF_REMOVABLE_MEDIA 0x0004 /* capability bit definitions */ #define CAPABILITY_DMA 0x01 #define CAPABILITY_LBA 0x02 /* command_setX bit definitions */ #define COMMANDSET_REMOVABLE 0x02 #define COMMANDSET_MEDIA_STATUS 0x10 /* ATA Vendor Specific defines */ #define ATA_ADDRESS_DEVHEAD_STD 0xa0 #define ATA_ADDRESS_DEVHEAD_LBA_MODE 0x40 #define ATA_ADDRESS_DEVHEAD_SLAVE 0x10 /* Action Select bits */ #define ACTION_SELECT_0 0x01 #define ACTION_SELECT_1 0x02 #define ACTION_SELECT_2 0x04 #define ACTION_SELECT_3 0x08 #define ACTION_SELECT_4 0x10 #define ACTION_SELECT_5 0x20 #define ACTION_SELECT_6 0x40 #define ACTION_SELECT_7 0x80 /* Register Select bits */ #define REG_ALTERNATE_STATUS 0x01 #define REG_DEVICE_CONTROL 0x01 #define REG_ERROR 0x02 #define REG_FEATURES 0x02 #define REG_SECTOR_COUNT 0x04 #define REG_SECTOR_NUMBER 0x08 #define REG_CYLINDER_LOW 0x10 #define REG_CYLINDER_HIGH 0x20 #define REG_DEVICE_HEAD 0x40 #define REG_STATUS 0x80 #define REG_COMMAND 0x80 /* ATA registers offset definitions */ #define ATA_REG_ERROR_OFFSET 1 #define ATA_REG_LCYL_OFFSET 4 #define ATA_REG_HCYL_OFFSET 5 #define ATA_REG_STATUS_OFFSET 7 /* ATA error definitions not in <linux/hdreg.h> */ #define ATA_ERROR_MEDIA_CHANGE 0x20 /* ATA command definitions not in <linux/hdreg.h> */ #define ATA_COMMAND_GET_MEDIA_STATUS 0xDA #define ATA_COMMAND_MEDIA_EJECT 0xED /* ATA drive control definitions */ #define ATA_DC_DISABLE_INTERRUPTS 0x02 #define ATA_DC_RESET_CONTROLLER 0x04 #define ATA_DC_REENABLE_CONTROLLER 0x00 /* * General purpose return codes */ #define ISD200_ERROR -1 #define ISD200_GOOD 0 /* * Transport return codes */ #define ISD200_TRANSPORT_GOOD 0 /* Transport good, command good */ #define ISD200_TRANSPORT_FAILED 1 /* Transport good, command failed */ #define ISD200_TRANSPORT_ERROR 2 /* Transport bad (i.e. device dead) */ /* driver action codes */ #define ACTION_READ_STATUS 0 #define ACTION_RESET 1 #define ACTION_REENABLE 2 #define ACTION_SOFT_RESET 3 #define ACTION_ENUM 4 #define ACTION_IDENTIFY 5 /* * ata_cdb struct */ union ata_cdb { struct { unsigned char SignatureByte0; unsigned char SignatureByte1; unsigned char ActionSelect; unsigned char RegisterSelect; unsigned char TransferBlockSize; unsigned char WriteData3F6; unsigned char WriteData1F1; unsigned char WriteData1F2; unsigned char WriteData1F3; unsigned char WriteData1F4; unsigned char WriteData1F5; unsigned char WriteData1F6; unsigned char WriteData1F7; unsigned char Reserved[3]; } generic; struct { unsigned char SignatureByte0; unsigned char SignatureByte1; unsigned char ActionSelect; unsigned char RegisterSelect; unsigned char TransferBlockSize; unsigned char AlternateStatusByte; unsigned char ErrorByte; unsigned char SectorCountByte; unsigned char SectorNumberByte; unsigned char CylinderLowByte; unsigned char CylinderHighByte; unsigned char DeviceHeadByte; unsigned char StatusByte; unsigned char Reserved[3]; } read; struct { unsigned char SignatureByte0; unsigned char SignatureByte1; unsigned char ActionSelect; unsigned char RegisterSelect; unsigned char TransferBlockSize; unsigned char DeviceControlByte; unsigned char FeaturesByte; unsigned char SectorCountByte; unsigned char SectorNumberByte; unsigned char CylinderLowByte; unsigned char CylinderHighByte; unsigned char DeviceHeadByte; unsigned char CommandByte; unsigned char Reserved[3]; } write; }; /* * Inquiry data structure. This is the data returned from the target * after it receives an inquiry. * * This structure may be extended by the number of bytes specified * in the field AdditionalLength. The defined size constant only * includes fields through ProductRevisionLevel. */ /* * DeviceType field */ #define DIRECT_ACCESS_DEVICE 0x00 /* disks */ #define DEVICE_REMOVABLE 0x80 struct inquiry_data { unsigned char DeviceType; unsigned char DeviceTypeModifier; unsigned char Versions; unsigned char Format; unsigned char AdditionalLength; unsigned char Reserved[2]; unsigned char Capability; unsigned char VendorId[8]; unsigned char ProductId[16]; unsigned char ProductRevisionLevel[4]; unsigned char VendorSpecific[20]; unsigned char Reserved3[40]; } __attribute__ ((packed)); /* * INQUIRY data buffer size */ #define INQUIRYDATABUFFERSIZE 36 /* * ISD200 CONFIG data struct */ #define ATACFG_TIMING 0x0f #define ATACFG_ATAPI_RESET 0x10 #define ATACFG_MASTER 0x20 #define ATACFG_BLOCKSIZE 0xa0 #define ATACFGE_LAST_LUN 0x07 #define ATACFGE_DESC_OVERRIDE 0x08 #define ATACFGE_STATE_SUSPEND 0x10 #define ATACFGE_SKIP_BOOT 0x20 #define ATACFGE_CONF_DESC2 0x40 #define ATACFGE_INIT_STATUS 0x80 #define CFG_CAPABILITY_SRST 0x01 struct isd200_config { unsigned char EventNotification; unsigned char ExternalClock; unsigned char ATAInitTimeout; unsigned char ATAConfig; unsigned char ATAMajorCommand; unsigned char ATAMinorCommand; unsigned char ATAExtraConfig; unsigned char Capability; }__attribute__ ((packed)); /* * ISD200 driver information struct */ struct isd200_info { struct inquiry_data InquiryData; u16 *id; struct isd200_config ConfigData; unsigned char *RegsBuf; unsigned char ATARegs[8]; unsigned char DeviceHead; unsigned char DeviceFlags; /* maximum number of LUNs supported */ unsigned char MaxLUNs; unsigned char cmnd[MAX_COMMAND_SIZE]; struct scsi_cmnd srb; struct scatterlist sg; }; /* * Read Capacity Data - returned in Big Endian format */ struct read_capacity_data { __be32 LogicalBlockAddress; __be32 BytesPerBlock; }; /* * Read Block Limits Data - returned in Big Endian format * This structure returns the maximum and minimum block * size for a TAPE device. */ struct read_block_limits { unsigned char Reserved; unsigned char BlockMaximumSize[3]; unsigned char BlockMinimumSize[2]; }; /* * Sense Data Format */ #define SENSE_ERRCODE 0x7f #define SENSE_ERRCODE_VALID 0x80 #define SENSE_FLAG_SENSE_KEY 0x0f #define SENSE_FLAG_BAD_LENGTH 0x20 #define SENSE_FLAG_END_OF_MEDIA 0x40 #define SENSE_FLAG_FILE_MARK 0x80 struct sense_data { unsigned char ErrorCode; unsigned char SegmentNumber; unsigned char Flags; unsigned char Information[4]; unsigned char AdditionalSenseLength; unsigned char CommandSpecificInformation[4]; unsigned char AdditionalSenseCode; unsigned char AdditionalSenseCodeQualifier; unsigned char FieldReplaceableUnitCode; unsigned char SenseKeySpecific[3]; } __attribute__ ((packed)); /* * Default request sense buffer size */ #define SENSE_BUFFER_SIZE 18 /*********************************************************************** * Helper routines ***********************************************************************/ /************************************************************************** * isd200_build_sense * * Builds an artificial sense buffer to report the results of a * failed command. * * RETURNS: * void */ static void isd200_build_sense(struct us_data *us, struct scsi_cmnd *srb) { struct isd200_info *info = (struct isd200_info *)us->extra; struct sense_data *buf = (struct sense_data *) &srb->sense_buffer[0]; unsigned char error = info->ATARegs[ATA_REG_ERROR_OFFSET]; if(error & ATA_ERROR_MEDIA_CHANGE) { buf->ErrorCode = 0x70 | SENSE_ERRCODE_VALID; buf->AdditionalSenseLength = 0xb; buf->Flags = UNIT_ATTENTION; buf->AdditionalSenseCode = 0; buf->AdditionalSenseCodeQualifier = 0; } else if (error & ATA_MCR) { buf->ErrorCode = 0x70 | SENSE_ERRCODE_VALID; buf->AdditionalSenseLength = 0xb; buf->Flags = UNIT_ATTENTION; buf->AdditionalSenseCode = 0; buf->AdditionalSenseCodeQualifier = 0; } else if (error & ATA_TRK0NF) { buf->ErrorCode = 0x70 | SENSE_ERRCODE_VALID; buf->AdditionalSenseLength = 0xb; buf->Flags = NOT_READY; buf->AdditionalSenseCode = 0; buf->AdditionalSenseCodeQualifier = 0; } else if (error & ATA_UNC) { buf->ErrorCode = 0x70 | SENSE_ERRCODE_VALID; buf->AdditionalSenseLength = 0xb; buf->Flags = DATA_PROTECT; buf->AdditionalSenseCode = 0; buf->AdditionalSenseCodeQualifier = 0; } else { buf->ErrorCode = 0; buf->AdditionalSenseLength = 0; buf->Flags = 0; buf->AdditionalSenseCode = 0; buf->AdditionalSenseCodeQualifier = 0; } } /*********************************************************************** * Transport routines ***********************************************************************/ /************************************************************************** * isd200_set_srb(), isd200_srb_set_bufflen() * * Two helpers to facilitate in initialization of scsi_cmnd structure * Will need to change when struct scsi_cmnd changes */ static void isd200_set_srb(struct isd200_info *info, enum dma_data_direction dir, void* buff, unsigned bufflen) { struct scsi_cmnd *srb = &info->srb; if (buff) sg_init_one(&info->sg, buff, bufflen); srb->sc_data_direction = dir; srb->sdb.table.sgl = buff ? &info->sg : NULL; srb->sdb.length = bufflen; srb->sdb.table.nents = buff ? 1 : 0; } static void isd200_srb_set_bufflen(struct scsi_cmnd *srb, unsigned bufflen) { srb->sdb.length = bufflen; } /************************************************************************** * isd200_action * * Routine for sending commands to the isd200 * * RETURNS: * ISD status code */ static int isd200_action( struct us_data *us, int action, void* pointer, int value ) { union ata_cdb ata; /* static to prevent this large struct being placed on the valuable stack */ static struct scsi_device srb_dev; struct isd200_info *info = (struct isd200_info *)us->extra; struct scsi_cmnd *srb = &info->srb; int status; memset(&ata, 0, sizeof(ata)); memcpy(srb->cmnd, info->cmnd, MAX_COMMAND_SIZE); srb->device = &srb_dev; ata.generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ata.generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ata.generic.TransferBlockSize = 1; switch ( action ) { case ACTION_READ_STATUS: usb_stor_dbg(us, " isd200_action(READ_STATUS)\n"); ata.generic.ActionSelect = ACTION_SELECT_0|ACTION_SELECT_2; ata.generic.RegisterSelect = REG_CYLINDER_LOW | REG_CYLINDER_HIGH | REG_STATUS | REG_ERROR; isd200_set_srb(info, DMA_FROM_DEVICE, pointer, value); break; case ACTION_ENUM: usb_stor_dbg(us, " isd200_action(ENUM,0x%02x)\n", value); ata.generic.ActionSelect = ACTION_SELECT_1|ACTION_SELECT_2| ACTION_SELECT_3|ACTION_SELECT_4| ACTION_SELECT_5; ata.generic.RegisterSelect = REG_DEVICE_HEAD; ata.write.DeviceHeadByte = value; isd200_set_srb(info, DMA_NONE, NULL, 0); break; case ACTION_RESET: usb_stor_dbg(us, " isd200_action(RESET)\n"); ata.generic.ActionSelect = ACTION_SELECT_1|ACTION_SELECT_2| ACTION_SELECT_3|ACTION_SELECT_4; ata.generic.RegisterSelect = REG_DEVICE_CONTROL; ata.write.DeviceControlByte = ATA_DC_RESET_CONTROLLER; isd200_set_srb(info, DMA_NONE, NULL, 0); break; case ACTION_REENABLE: usb_stor_dbg(us, " isd200_action(REENABLE)\n"); ata.generic.ActionSelect = ACTION_SELECT_1|ACTION_SELECT_2| ACTION_SELECT_3|ACTION_SELECT_4; ata.generic.RegisterSelect = REG_DEVICE_CONTROL; ata.write.DeviceControlByte = ATA_DC_REENABLE_CONTROLLER; isd200_set_srb(info, DMA_NONE, NULL, 0); break; case ACTION_SOFT_RESET: usb_stor_dbg(us, " isd200_action(SOFT_RESET)\n"); ata.generic.ActionSelect = ACTION_SELECT_1|ACTION_SELECT_5; ata.generic.RegisterSelect = REG_DEVICE_HEAD | REG_COMMAND; ata.write.DeviceHeadByte = info->DeviceHead; ata.write.CommandByte = ATA_CMD_DEV_RESET; isd200_set_srb(info, DMA_NONE, NULL, 0); break; case ACTION_IDENTIFY: usb_stor_dbg(us, " isd200_action(IDENTIFY)\n"); ata.generic.RegisterSelect = REG_COMMAND; ata.write.CommandByte = ATA_CMD_ID_ATA; isd200_set_srb(info, DMA_FROM_DEVICE, info->id, ATA_ID_WORDS * 2); break; default: usb_stor_dbg(us, "Error: Undefined action %d\n", action); return ISD200_ERROR; } memcpy(srb->cmnd, &ata, sizeof(ata.generic)); srb->cmd_len = sizeof(ata.generic); status = usb_stor_Bulk_transport(srb, us); if (status == USB_STOR_TRANSPORT_GOOD) status = ISD200_GOOD; else { usb_stor_dbg(us, " isd200_action(0x%02x) error: %d\n", action, status); status = ISD200_ERROR; /* need to reset device here */ } return status; } /************************************************************************** * isd200_read_regs * * Read ATA Registers * * RETURNS: * ISD status code */ static int isd200_read_regs( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; int retStatus = ISD200_GOOD; int transferStatus; usb_stor_dbg(us, "Entering isd200_IssueATAReadRegs\n"); transferStatus = isd200_action( us, ACTION_READ_STATUS, info->RegsBuf, sizeof(info->ATARegs) ); if (transferStatus != ISD200_TRANSPORT_GOOD) { usb_stor_dbg(us, " Error reading ATA registers\n"); retStatus = ISD200_ERROR; } else { memcpy(info->ATARegs, info->RegsBuf, sizeof(info->ATARegs)); usb_stor_dbg(us, " Got ATA Register[ATA_REG_ERROR_OFFSET] = 0x%x\n", info->ATARegs[ATA_REG_ERROR_OFFSET]); } return retStatus; } /************************************************************************** * Invoke the transport and basic error-handling/recovery methods * * This is used by the protocol layers to actually send the message to * the device and receive the response. */ static void isd200_invoke_transport( struct us_data *us, struct scsi_cmnd *srb, union ata_cdb *ataCdb ) { int need_auto_sense = 0; int transferStatus; int result; /* send the command to the transport layer */ memcpy(srb->cmnd, ataCdb, sizeof(ataCdb->generic)); srb->cmd_len = sizeof(ataCdb->generic); transferStatus = usb_stor_Bulk_transport(srb, us); /* * if the command gets aborted by the higher layers, we need to * short-circuit all other processing */ if (test_bit(US_FLIDX_TIMED_OUT, &us->dflags)) { usb_stor_dbg(us, "-- command was aborted\n"); goto Handle_Abort; } switch (transferStatus) { case USB_STOR_TRANSPORT_GOOD: /* Indicate a good result */ srb->result = SAM_STAT_GOOD; break; case USB_STOR_TRANSPORT_NO_SENSE: usb_stor_dbg(us, "-- transport indicates protocol failure\n"); srb->result = SAM_STAT_CHECK_CONDITION; return; case USB_STOR_TRANSPORT_FAILED: usb_stor_dbg(us, "-- transport indicates command failure\n"); need_auto_sense = 1; break; case USB_STOR_TRANSPORT_ERROR: usb_stor_dbg(us, "-- transport indicates transport error\n"); srb->result = DID_ERROR << 16; /* Need reset here */ return; default: usb_stor_dbg(us, "-- transport indicates unknown error\n"); srb->result = DID_ERROR << 16; /* Need reset here */ return; } if ((scsi_get_resid(srb) > 0) && !((srb->cmnd[0] == REQUEST_SENSE) || (srb->cmnd[0] == INQUIRY) || (srb->cmnd[0] == MODE_SENSE) || (srb->cmnd[0] == LOG_SENSE) || (srb->cmnd[0] == MODE_SENSE_10))) { usb_stor_dbg(us, "-- unexpectedly short transfer\n"); need_auto_sense = 1; } if (need_auto_sense) { result = isd200_read_regs(us); if (test_bit(US_FLIDX_TIMED_OUT, &us->dflags)) { usb_stor_dbg(us, "-- auto-sense aborted\n"); goto Handle_Abort; } if (result == ISD200_GOOD) { isd200_build_sense(us, srb); srb->result = SAM_STAT_CHECK_CONDITION; /* If things are really okay, then let's show that */ if ((srb->sense_buffer[2] & 0xf) == 0x0) srb->result = SAM_STAT_GOOD; } else { srb->result = DID_ERROR << 16; /* Need reset here */ } } /* * Regardless of auto-sense, if we _know_ we have an error * condition, show that in the result code */ if (transferStatus == USB_STOR_TRANSPORT_FAILED) srb->result = SAM_STAT_CHECK_CONDITION; return; /* * abort processing: the bulk-only transport requires a reset * following an abort */ Handle_Abort: srb->result = DID_ABORT << 16; /* permit the reset transfer to take place */ clear_bit(US_FLIDX_ABORTING, &us->dflags); /* Need reset here */ } #ifdef CONFIG_USB_STORAGE_DEBUG static void isd200_log_config(struct us_data *us, struct isd200_info *info) { usb_stor_dbg(us, " Event Notification: 0x%x\n", info->ConfigData.EventNotification); usb_stor_dbg(us, " External Clock: 0x%x\n", info->ConfigData.ExternalClock); usb_stor_dbg(us, " ATA Init Timeout: 0x%x\n", info->ConfigData.ATAInitTimeout); usb_stor_dbg(us, " ATAPI Command Block Size: 0x%x\n", (info->ConfigData.ATAConfig & ATACFG_BLOCKSIZE) >> 6); usb_stor_dbg(us, " Master/Slave Selection: 0x%x\n", info->ConfigData.ATAConfig & ATACFG_MASTER); usb_stor_dbg(us, " ATAPI Reset: 0x%x\n", info->ConfigData.ATAConfig & ATACFG_ATAPI_RESET); usb_stor_dbg(us, " ATA Timing: 0x%x\n", info->ConfigData.ATAConfig & ATACFG_TIMING); usb_stor_dbg(us, " ATA Major Command: 0x%x\n", info->ConfigData.ATAMajorCommand); usb_stor_dbg(us, " ATA Minor Command: 0x%x\n", info->ConfigData.ATAMinorCommand); usb_stor_dbg(us, " Init Status: 0x%x\n", info->ConfigData.ATAExtraConfig & ATACFGE_INIT_STATUS); usb_stor_dbg(us, " Config Descriptor 2: 0x%x\n", info->ConfigData.ATAExtraConfig & ATACFGE_CONF_DESC2); usb_stor_dbg(us, " Skip Device Boot: 0x%x\n", info->ConfigData.ATAExtraConfig & ATACFGE_SKIP_BOOT); usb_stor_dbg(us, " ATA 3 State Suspend: 0x%x\n", info->ConfigData.ATAExtraConfig & ATACFGE_STATE_SUSPEND); usb_stor_dbg(us, " Descriptor Override: 0x%x\n", info->ConfigData.ATAExtraConfig & ATACFGE_DESC_OVERRIDE); usb_stor_dbg(us, " Last LUN Identifier: 0x%x\n", info->ConfigData.ATAExtraConfig & ATACFGE_LAST_LUN); usb_stor_dbg(us, " SRST Enable: 0x%x\n", info->ConfigData.ATAExtraConfig & CFG_CAPABILITY_SRST); } #endif /************************************************************************** * isd200_write_config * * Write the ISD200 Configuration data * * RETURNS: * ISD status code */ static int isd200_write_config( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; int retStatus = ISD200_GOOD; int result; #ifdef CONFIG_USB_STORAGE_DEBUG usb_stor_dbg(us, "Entering isd200_write_config\n"); usb_stor_dbg(us, " Writing the following ISD200 Config Data:\n"); isd200_log_config(us, info); #endif /* let's send the command via the control pipe */ result = usb_stor_ctrl_transfer( us, us->send_ctrl_pipe, 0x01, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, 0x0000, 0x0002, (void *) &info->ConfigData, sizeof(info->ConfigData)); if (result >= 0) { usb_stor_dbg(us, " ISD200 Config Data was written successfully\n"); } else { usb_stor_dbg(us, " Request to write ISD200 Config Data failed!\n"); retStatus = ISD200_ERROR; } usb_stor_dbg(us, "Leaving isd200_write_config %08X\n", retStatus); return retStatus; } /************************************************************************** * isd200_read_config * * Reads the ISD200 Configuration data * * RETURNS: * ISD status code */ static int isd200_read_config( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; int retStatus = ISD200_GOOD; int result; usb_stor_dbg(us, "Entering isd200_read_config\n"); /* read the configuration information from ISD200. Use this to */ /* determine what the special ATA CDB bytes are. */ result = usb_stor_ctrl_transfer( us, us->recv_ctrl_pipe, 0x02, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, 0x0000, 0x0002, (void *) &info->ConfigData, sizeof(info->ConfigData)); if (result >= 0) { usb_stor_dbg(us, " Retrieved the following ISD200 Config Data:\n"); #ifdef CONFIG_USB_STORAGE_DEBUG isd200_log_config(us, info); #endif } else { usb_stor_dbg(us, " Request to get ISD200 Config Data failed!\n"); retStatus = ISD200_ERROR; } usb_stor_dbg(us, "Leaving isd200_read_config %08X\n", retStatus); return retStatus; } /************************************************************************** * isd200_atapi_soft_reset * * Perform an Atapi Soft Reset on the device * * RETURNS: * NT status code */ static int isd200_atapi_soft_reset( struct us_data *us ) { int retStatus = ISD200_GOOD; int transferStatus; usb_stor_dbg(us, "Entering isd200_atapi_soft_reset\n"); transferStatus = isd200_action( us, ACTION_SOFT_RESET, NULL, 0 ); if (transferStatus != ISD200_TRANSPORT_GOOD) { usb_stor_dbg(us, " Error issuing Atapi Soft Reset\n"); retStatus = ISD200_ERROR; } usb_stor_dbg(us, "Leaving isd200_atapi_soft_reset %08X\n", retStatus); return retStatus; } /************************************************************************** * isd200_srst * * Perform an SRST on the device * * RETURNS: * ISD status code */ static int isd200_srst( struct us_data *us ) { int retStatus = ISD200_GOOD; int transferStatus; usb_stor_dbg(us, "Entering isd200_SRST\n"); transferStatus = isd200_action( us, ACTION_RESET, NULL, 0 ); /* check to see if this request failed */ if (transferStatus != ISD200_TRANSPORT_GOOD) { usb_stor_dbg(us, " Error issuing SRST\n"); retStatus = ISD200_ERROR; } else { /* delay 10ms to give the drive a chance to see it */ msleep(10); transferStatus = isd200_action( us, ACTION_REENABLE, NULL, 0 ); if (transferStatus != ISD200_TRANSPORT_GOOD) { usb_stor_dbg(us, " Error taking drive out of reset\n"); retStatus = ISD200_ERROR; } else { /* delay 50ms to give the drive a chance to recover after SRST */ msleep(50); } } usb_stor_dbg(us, "Leaving isd200_srst %08X\n", retStatus); return retStatus; } /************************************************************************** * isd200_try_enum * * Helper function for isd200_manual_enum(). Does ENUM and READ_STATUS * and tries to analyze the status registers * * RETURNS: * ISD status code */ static int isd200_try_enum(struct us_data *us, unsigned char master_slave, int detect ) { int status = ISD200_GOOD; unsigned long endTime; struct isd200_info *info = (struct isd200_info *)us->extra; unsigned char *regs = info->RegsBuf; int recheckAsMaster = 0; if ( detect ) endTime = jiffies + ISD200_ENUM_DETECT_TIMEOUT * HZ; else endTime = jiffies + ISD200_ENUM_BSY_TIMEOUT * HZ; /* loop until we detect !BSY or timeout */ while(1) { status = isd200_action( us, ACTION_ENUM, NULL, master_slave ); if ( status != ISD200_GOOD ) break; status = isd200_action( us, ACTION_READ_STATUS, regs, 8 ); if ( status != ISD200_GOOD ) break; if (!detect) { if (regs[ATA_REG_STATUS_OFFSET] & ATA_BUSY) { usb_stor_dbg(us, " %s status is still BSY, try again...\n", master_slave == ATA_ADDRESS_DEVHEAD_STD ? "Master" : "Slave"); } else { usb_stor_dbg(us, " %s status !BSY, continue with next operation\n", master_slave == ATA_ADDRESS_DEVHEAD_STD ? "Master" : "Slave"); break; } } /* check for ATA_BUSY and */ /* ATA_DF (workaround ATA Zip drive) and */ /* ATA_ERR (workaround for Archos CD-ROM) */ else if (regs[ATA_REG_STATUS_OFFSET] & (ATA_BUSY | ATA_DF | ATA_ERR)) { usb_stor_dbg(us, " Status indicates it is not ready, try again...\n"); } /* check for DRDY, ATA devices set DRDY after SRST */ else if (regs[ATA_REG_STATUS_OFFSET] & ATA_DRDY) { usb_stor_dbg(us, " Identified ATA device\n"); info->DeviceFlags |= DF_ATA_DEVICE; info->DeviceHead = master_slave; break; } /* * check Cylinder High/Low to * determine if it is an ATAPI device */ else if (regs[ATA_REG_HCYL_OFFSET] == 0xEB && regs[ATA_REG_LCYL_OFFSET] == 0x14) { /* * It seems that the RICOH * MP6200A CD/RW drive will * report itself okay as a * slave when it is really a * master. So this check again * as a master device just to * make sure it doesn't report * itself okay as a master also */ if ((master_slave & ATA_ADDRESS_DEVHEAD_SLAVE) && !recheckAsMaster) { usb_stor_dbg(us, " Identified ATAPI device as slave. Rechecking again as master\n"); recheckAsMaster = 1; master_slave = ATA_ADDRESS_DEVHEAD_STD; } else { usb_stor_dbg(us, " Identified ATAPI device\n"); info->DeviceHead = master_slave; status = isd200_atapi_soft_reset(us); break; } } else { usb_stor_dbg(us, " Not ATA, not ATAPI - Weird\n"); break; } /* check for timeout on this request */ if (time_after_eq(jiffies, endTime)) { if (!detect) usb_stor_dbg(us, " BSY check timeout, just continue with next operation...\n"); else usb_stor_dbg(us, " Device detect timeout!\n"); break; } } return status; } /************************************************************************** * isd200_manual_enum * * Determines if the drive attached is an ATA or ATAPI and if it is a * master or slave. * * RETURNS: * ISD status code */ static int isd200_manual_enum(struct us_data *us) { struct isd200_info *info = (struct isd200_info *)us->extra; int retStatus = ISD200_GOOD; usb_stor_dbg(us, "Entering isd200_manual_enum\n"); retStatus = isd200_read_config(us); if (retStatus == ISD200_GOOD) { int isslave; /* master or slave? */ retStatus = isd200_try_enum( us, ATA_ADDRESS_DEVHEAD_STD, 0); if (retStatus == ISD200_GOOD) retStatus = isd200_try_enum( us, ATA_ADDRESS_DEVHEAD_SLAVE, 0); if (retStatus == ISD200_GOOD) { retStatus = isd200_srst(us); if (retStatus == ISD200_GOOD) /* ata or atapi? */ retStatus = isd200_try_enum( us, ATA_ADDRESS_DEVHEAD_STD, 1); } isslave = (info->DeviceHead & ATA_ADDRESS_DEVHEAD_SLAVE) ? 1 : 0; if (!(info->ConfigData.ATAConfig & ATACFG_MASTER)) { usb_stor_dbg(us, " Setting Master/Slave selection to %d\n", isslave); info->ConfigData.ATAConfig &= 0x3f; info->ConfigData.ATAConfig |= (isslave<<6); retStatus = isd200_write_config(us); } } usb_stor_dbg(us, "Leaving isd200_manual_enum %08X\n", retStatus); return(retStatus); } static void isd200_fix_driveid(u16 *id) { #ifndef __LITTLE_ENDIAN # ifdef __BIG_ENDIAN int i; for (i = 0; i < ATA_ID_WORDS; i++) id[i] = __le16_to_cpu(id[i]); # else # error "Please fix <asm/byteorder.h>" # endif #endif } static void isd200_dump_driveid(struct us_data *us, u16 *id) { usb_stor_dbg(us, " Identify Data Structure:\n"); usb_stor_dbg(us, " config = 0x%x\n", id[ATA_ID_CONFIG]); usb_stor_dbg(us, " cyls = 0x%x\n", id[ATA_ID_CYLS]); usb_stor_dbg(us, " heads = 0x%x\n", id[ATA_ID_HEADS]); usb_stor_dbg(us, " track_bytes = 0x%x\n", id[4]); usb_stor_dbg(us, " sector_bytes = 0x%x\n", id[5]); usb_stor_dbg(us, " sectors = 0x%x\n", id[ATA_ID_SECTORS]); usb_stor_dbg(us, " serial_no[0] = 0x%x\n", *(char *)&id[ATA_ID_SERNO]); usb_stor_dbg(us, " buf_type = 0x%x\n", id[20]); usb_stor_dbg(us, " buf_size = 0x%x\n", id[ATA_ID_BUF_SIZE]); usb_stor_dbg(us, " ecc_bytes = 0x%x\n", id[22]); usb_stor_dbg(us, " fw_rev[0] = 0x%x\n", *(char *)&id[ATA_ID_FW_REV]); usb_stor_dbg(us, " model[0] = 0x%x\n", *(char *)&id[ATA_ID_PROD]); usb_stor_dbg(us, " max_multsect = 0x%x\n", id[ATA_ID_MAX_MULTSECT] & 0xff); usb_stor_dbg(us, " dword_io = 0x%x\n", id[ATA_ID_DWORD_IO]); usb_stor_dbg(us, " capability = 0x%x\n", id[ATA_ID_CAPABILITY] >> 8); usb_stor_dbg(us, " tPIO = 0x%x\n", id[ATA_ID_OLD_PIO_MODES] >> 8); usb_stor_dbg(us, " tDMA = 0x%x\n", id[ATA_ID_OLD_DMA_MODES] >> 8); usb_stor_dbg(us, " field_valid = 0x%x\n", id[ATA_ID_FIELD_VALID]); usb_stor_dbg(us, " cur_cyls = 0x%x\n", id[ATA_ID_CUR_CYLS]); usb_stor_dbg(us, " cur_heads = 0x%x\n", id[ATA_ID_CUR_HEADS]); usb_stor_dbg(us, " cur_sectors = 0x%x\n", id[ATA_ID_CUR_SECTORS]); usb_stor_dbg(us, " cur_capacity = 0x%x\n", ata_id_u32(id, 57)); usb_stor_dbg(us, " multsect = 0x%x\n", id[ATA_ID_MULTSECT] & 0xff); usb_stor_dbg(us, " lba_capacity = 0x%x\n", ata_id_u32(id, ATA_ID_LBA_CAPACITY)); usb_stor_dbg(us, " command_set_1 = 0x%x\n", id[ATA_ID_COMMAND_SET_1]); usb_stor_dbg(us, " command_set_2 = 0x%x\n", id[ATA_ID_COMMAND_SET_2]); } /************************************************************************** * isd200_get_inquiry_data * * Get inquiry data * * RETURNS: * ISD status code */ static int isd200_get_inquiry_data( struct us_data *us ) { struct isd200_info *info = (struct isd200_info *)us->extra; int retStatus; u16 *id = info->id; usb_stor_dbg(us, "Entering isd200_get_inquiry_data\n"); /* set default to Master */ info->DeviceHead = ATA_ADDRESS_DEVHEAD_STD; /* attempt to manually enumerate this device */ retStatus = isd200_manual_enum(us); if (retStatus == ISD200_GOOD) { int transferStatus; /* check for an ATA device */ if (info->DeviceFlags & DF_ATA_DEVICE) { /* this must be an ATA device */ /* perform an ATA Command Identify */ transferStatus = isd200_action( us, ACTION_IDENTIFY, id, ATA_ID_WORDS * 2); if (transferStatus != ISD200_TRANSPORT_GOOD) { /* Error issuing ATA Command Identify */ usb_stor_dbg(us, " Error issuing ATA Command Identify\n"); retStatus = ISD200_ERROR; } else { /* ATA Command Identify successful */ int i; __be16 *src; __u16 *dest; isd200_fix_driveid(id); isd200_dump_driveid(us, id); /* Prevent division by 0 in isd200_scsi_to_ata() */ if (id[ATA_ID_HEADS] == 0 || id[ATA_ID_SECTORS] == 0) { usb_stor_dbg(us, " Invalid ATA Identify data\n"); retStatus = ISD200_ERROR; goto Done; } memset(&info->InquiryData, 0, sizeof(info->InquiryData)); /* Standard IDE interface only supports disks */ info->InquiryData.DeviceType = DIRECT_ACCESS_DEVICE; /* The length must be at least 36 (5 + 31) */ info->InquiryData.AdditionalLength = 0x1F; if (id[ATA_ID_COMMAND_SET_1] & COMMANDSET_MEDIA_STATUS) { /* set the removable bit */ info->InquiryData.DeviceTypeModifier = DEVICE_REMOVABLE; info->DeviceFlags |= DF_REMOVABLE_MEDIA; } /* Fill in vendor identification fields */ src = (__be16 *)&id[ATA_ID_PROD]; dest = (__u16*)info->InquiryData.VendorId; for (i = 0; i < 4; i++) dest[i] = be16_to_cpu(src[i]); src = (__be16 *)&id[ATA_ID_PROD + 8/2]; dest = (__u16*)info->InquiryData.ProductId; for (i=0;i<8;i++) dest[i] = be16_to_cpu(src[i]); src = (__be16 *)&id[ATA_ID_FW_REV]; dest = (__u16*)info->InquiryData.ProductRevisionLevel; for (i=0;i<2;i++) dest[i] = be16_to_cpu(src[i]); /* determine if it supports Media Status Notification */ if (id[ATA_ID_COMMAND_SET_2] & COMMANDSET_MEDIA_STATUS) { usb_stor_dbg(us, " Device supports Media Status Notification\n"); /* * Indicate that it is enabled, even * though it is not. * This allows the lock/unlock of the * media to work correctly. */ info->DeviceFlags |= DF_MEDIA_STATUS_ENABLED; } else info->DeviceFlags &= ~DF_MEDIA_STATUS_ENABLED; } } else { /* * this must be an ATAPI device * use an ATAPI protocol (Transparent SCSI) */ us->protocol_name = "Transparent SCSI"; us->proto_handler = usb_stor_transparent_scsi_command; usb_stor_dbg(us, "Protocol changed to: %s\n", us->protocol_name); /* Free driver structure */ us->extra_destructor(info); kfree(info); us->extra = NULL; us->extra_destructor = NULL; } } Done: usb_stor_dbg(us, "Leaving isd200_get_inquiry_data %08X\n", retStatus); return(retStatus); } /************************************************************************** * isd200_scsi_to_ata * * Translate SCSI commands to ATA commands. * * RETURNS: * 1 if the command needs to be sent to the transport layer * 0 otherwise */ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us, union ata_cdb * ataCdb) { struct isd200_info *info = (struct isd200_info *)us->extra; u16 *id = info->id; int sendToTransport = 1; unsigned char sectnum, head; unsigned short cylinder; unsigned long lba; unsigned long blockCount; unsigned char senseData[8] = { 0, 0, 0, 0, 0, 0, 0, 0 }; memset(ataCdb, 0, sizeof(union ata_cdb)); /* SCSI Command */ switch (srb->cmnd[0]) { case INQUIRY: usb_stor_dbg(us, " ATA OUT - INQUIRY\n"); /* copy InquiryData */ usb_stor_set_xfer_buf((unsigned char *) &info->InquiryData, sizeof(info->InquiryData), srb); srb->result = SAM_STAT_GOOD; sendToTransport = 0; break; case MODE_SENSE: usb_stor_dbg(us, " ATA OUT - SCSIOP_MODE_SENSE\n"); /* Initialize the return buffer */ usb_stor_set_xfer_buf(senseData, sizeof(senseData), srb); if (info->DeviceFlags & DF_MEDIA_STATUS_ENABLED) { ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ataCdb->generic.TransferBlockSize = 1; ataCdb->generic.RegisterSelect = REG_COMMAND; ataCdb->write.CommandByte = ATA_COMMAND_GET_MEDIA_STATUS; isd200_srb_set_bufflen(srb, 0); } else { usb_stor_dbg(us, " Media Status not supported, just report okay\n"); srb->result = SAM_STAT_GOOD; sendToTransport = 0; } break; case TEST_UNIT_READY: usb_stor_dbg(us, " ATA OUT - SCSIOP_TEST_UNIT_READY\n"); if (info->DeviceFlags & DF_MEDIA_STATUS_ENABLED) { ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ataCdb->generic.TransferBlockSize = 1; ataCdb->generic.RegisterSelect = REG_COMMAND; ataCdb->write.CommandByte = ATA_COMMAND_GET_MEDIA_STATUS; isd200_srb_set_bufflen(srb, 0); } else { usb_stor_dbg(us, " Media Status not supported, just report okay\n"); srb->result = SAM_STAT_GOOD; sendToTransport = 0; } break; case READ_CAPACITY: { unsigned long capacity; struct read_capacity_data readCapacityData; usb_stor_dbg(us, " ATA OUT - SCSIOP_READ_CAPACITY\n"); if (ata_id_has_lba(id)) capacity = ata_id_u32(id, ATA_ID_LBA_CAPACITY) - 1; else capacity = (id[ATA_ID_HEADS] * id[ATA_ID_CYLS] * id[ATA_ID_SECTORS]) - 1; readCapacityData.LogicalBlockAddress = cpu_to_be32(capacity); readCapacityData.BytesPerBlock = cpu_to_be32(0x200); usb_stor_set_xfer_buf((unsigned char *) &readCapacityData, sizeof(readCapacityData), srb); srb->result = SAM_STAT_GOOD; sendToTransport = 0; } break; case READ_10: usb_stor_dbg(us, " ATA OUT - SCSIOP_READ\n"); lba = be32_to_cpu(*(__be32 *)&srb->cmnd[2]); blockCount = (unsigned long)srb->cmnd[7]<<8 | (unsigned long)srb->cmnd[8]; if (ata_id_has_lba(id)) { sectnum = (unsigned char)(lba); cylinder = (unsigned short)(lba>>8); head = ATA_ADDRESS_DEVHEAD_LBA_MODE | (unsigned char)(lba>>24 & 0x0F); } else { sectnum = (u8)((lba % id[ATA_ID_SECTORS]) + 1); cylinder = (u16)(lba / (id[ATA_ID_SECTORS] * id[ATA_ID_HEADS])); head = (u8)((lba / id[ATA_ID_SECTORS]) % id[ATA_ID_HEADS]); } ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ataCdb->generic.TransferBlockSize = 1; ataCdb->generic.RegisterSelect = REG_SECTOR_COUNT | REG_SECTOR_NUMBER | REG_CYLINDER_LOW | REG_CYLINDER_HIGH | REG_DEVICE_HEAD | REG_COMMAND; ataCdb->write.SectorCountByte = (unsigned char)blockCount; ataCdb->write.SectorNumberByte = sectnum; ataCdb->write.CylinderHighByte = (unsigned char)(cylinder>>8); ataCdb->write.CylinderLowByte = (unsigned char)cylinder; ataCdb->write.DeviceHeadByte = (head | ATA_ADDRESS_DEVHEAD_STD); ataCdb->write.CommandByte = ATA_CMD_PIO_READ; break; case WRITE_10: usb_stor_dbg(us, " ATA OUT - SCSIOP_WRITE\n"); lba = be32_to_cpu(*(__be32 *)&srb->cmnd[2]); blockCount = (unsigned long)srb->cmnd[7]<<8 | (unsigned long)srb->cmnd[8]; if (ata_id_has_lba(id)) { sectnum = (unsigned char)(lba); cylinder = (unsigned short)(lba>>8); head = ATA_ADDRESS_DEVHEAD_LBA_MODE | (unsigned char)(lba>>24 & 0x0F); } else { sectnum = (u8)((lba % id[ATA_ID_SECTORS]) + 1); cylinder = (u16)(lba / (id[ATA_ID_SECTORS] * id[ATA_ID_HEADS])); head = (u8)((lba / id[ATA_ID_SECTORS]) % id[ATA_ID_HEADS]); } ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ataCdb->generic.TransferBlockSize = 1; ataCdb->generic.RegisterSelect = REG_SECTOR_COUNT | REG_SECTOR_NUMBER | REG_CYLINDER_LOW | REG_CYLINDER_HIGH | REG_DEVICE_HEAD | REG_COMMAND; ataCdb->write.SectorCountByte = (unsigned char)blockCount; ataCdb->write.SectorNumberByte = sectnum; ataCdb->write.CylinderHighByte = (unsigned char)(cylinder>>8); ataCdb->write.CylinderLowByte = (unsigned char)cylinder; ataCdb->write.DeviceHeadByte = (head | ATA_ADDRESS_DEVHEAD_STD); ataCdb->write.CommandByte = ATA_CMD_PIO_WRITE; break; case ALLOW_MEDIUM_REMOVAL: usb_stor_dbg(us, " ATA OUT - SCSIOP_MEDIUM_REMOVAL\n"); if (info->DeviceFlags & DF_REMOVABLE_MEDIA) { usb_stor_dbg(us, " srb->cmnd[4] = 0x%X\n", srb->cmnd[4]); ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ataCdb->generic.TransferBlockSize = 1; ataCdb->generic.RegisterSelect = REG_COMMAND; ataCdb->write.CommandByte = (srb->cmnd[4] & 0x1) ? ATA_CMD_MEDIA_LOCK : ATA_CMD_MEDIA_UNLOCK; isd200_srb_set_bufflen(srb, 0); } else { usb_stor_dbg(us, " Not removable media, just report okay\n"); srb->result = SAM_STAT_GOOD; sendToTransport = 0; } break; case START_STOP: usb_stor_dbg(us, " ATA OUT - SCSIOP_START_STOP_UNIT\n"); usb_stor_dbg(us, " srb->cmnd[4] = 0x%X\n", srb->cmnd[4]); if ((srb->cmnd[4] & 0x3) == 0x2) { usb_stor_dbg(us, " Media Eject\n"); ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ataCdb->generic.TransferBlockSize = 0; ataCdb->generic.RegisterSelect = REG_COMMAND; ataCdb->write.CommandByte = ATA_COMMAND_MEDIA_EJECT; } else if ((srb->cmnd[4] & 0x3) == 0x1) { usb_stor_dbg(us, " Get Media Status\n"); ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand; ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand; ataCdb->generic.TransferBlockSize = 1; ataCdb->generic.RegisterSelect = REG_COMMAND; ataCdb->write.CommandByte = ATA_COMMAND_GET_MEDIA_STATUS; isd200_srb_set_bufflen(srb, 0); } else { usb_stor_dbg(us, " Nothing to do, just report okay\n"); srb->result = SAM_STAT_GOOD; sendToTransport = 0; } break; default: usb_stor_dbg(us, "Unsupported SCSI command - 0x%X\n", srb->cmnd[0]); srb->result = DID_ERROR << 16; sendToTransport = 0; break; } return(sendToTransport); } /************************************************************************** * isd200_free_info * * Frees the driver structure. */ static void isd200_free_info_ptrs(void *info_) { struct isd200_info *info = (struct isd200_info *) info_; if (info) { kfree(info->id); kfree(info->RegsBuf); kfree(info->srb.sense_buffer); } } /************************************************************************** * isd200_init_info * * Allocates (if necessary) and initializes the driver structure. * * RETURNS: * error status code */ static int isd200_init_info(struct us_data *us) { struct isd200_info *info; info = kzalloc_obj(struct isd200_info); if (!info) return -ENOMEM; info->id = kzalloc(ATA_ID_WORDS * 2, GFP_KERNEL); info->RegsBuf = kmalloc(sizeof(info->ATARegs), GFP_KERNEL); info->srb.sense_buffer = kmalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL); if (!info->id || !info->RegsBuf || !info->srb.sense_buffer) { isd200_free_info_ptrs(info); kfree(info); return -ENOMEM; } us->extra = info; us->extra_destructor = isd200_free_info_ptrs; return 0; } /************************************************************************** * Initialization for the ISD200 */ static int isd200_Initialization(struct us_data *us) { int rc = 0; usb_stor_dbg(us, "ISD200 Initialization...\n"); /* Initialize ISD200 info struct */ if (isd200_init_info(us) < 0) { usb_stor_dbg(us, "ERROR Initializing ISD200 Info struct\n"); rc = -ENOMEM; } else { /* Get device specific data */ if (isd200_get_inquiry_data(us) != ISD200_GOOD) { usb_stor_dbg(us, "ISD200 Initialization Failure\n"); rc = -EINVAL; } else { usb_stor_dbg(us, "ISD200 Initialization complete\n"); } } return rc; } /************************************************************************** * Protocol and Transport for the ISD200 ASIC * * This protocol and transport are for ATA devices connected to an ISD200 * ASIC. An ATAPI device that is connected as a slave device will be * detected in the driver initialization function and the protocol will * be changed to an ATAPI protocol (Transparent SCSI). * */ static void isd200_ata_command(struct scsi_cmnd *srb, struct us_data *us) { int sendToTransport, orig_bufflen; union ata_cdb ataCdb; /* Make sure driver was initialized */ if (us->extra == NULL) { usb_stor_dbg(us, "ERROR Driver not initialized\n"); srb->result = DID_ERROR << 16; return; } scsi_set_resid(srb, 0); /* scsi_bufflen might change in protocol translation to ata */ orig_bufflen = scsi_bufflen(srb); sendToTransport = isd200_scsi_to_ata(srb, us, &ataCdb); /* send the command to the transport layer */ if (sendToTransport) isd200_invoke_transport(us, srb, &ataCdb); isd200_srb_set_bufflen(srb, orig_bufflen); } static struct scsi_host_template isd200_host_template; static int isd200_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct us_data *us; int result; result = usb_stor_probe1(&us, intf, id, (id - isd200_usb_ids) + isd200_unusual_dev_list, &isd200_host_template); if (result) return result; us->protocol_name = "ISD200 ATA/ATAPI"; us->proto_handler = isd200_ata_command; result = usb_stor_probe2(us); return result; } static struct usb_driver isd200_driver = { .name = DRV_NAME, .probe = isd200_probe, .disconnect = usb_stor_disconnect, .suspend = usb_stor_suspend, .resume = usb_stor_resume, .reset_resume = usb_stor_reset_resume, .pre_reset = usb_stor_pre_reset, .post_reset = usb_stor_post_reset, .id_table = isd200_usb_ids, .soft_unbind = 1, .no_dynamic_id = 1, }; module_usb_stor_driver(isd200_driver, isd200_host_template, DRV_NAME); |
| 14 14 13 13 13 3 6 13 12 10 11 2 12 2 2 6 2 14 39 6 1 2 2 2 10 73 73 18 4 62 62 60 62 53 54 73 73 14 14 60 3 14 60 3 14384 14380 14371 14449 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/audit.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /** * tomoyo_print_bprm - Print "struct linux_binprm" for auditing. * * @bprm: Pointer to "struct linux_binprm". * @dump: Pointer to "struct tomoyo_page_dump". * * Returns the contents of @bprm on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_bprm(struct linux_binprm *bprm, struct tomoyo_page_dump *dump) { static const int tomoyo_buffer_len = 4096 * 2; char *buffer = kzalloc(tomoyo_buffer_len, GFP_NOFS); char *cp; char *last_start; int len; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; bool truncated = false; if (!buffer) return NULL; len = snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ "); cp = buffer + len; if (!argv_count) { memmove(cp, "} envp[]={ ", 11); cp += 11; } last_start = cp; while (argv_count || envp_count) { if (!tomoyo_dump_page(bprm, pos, dump)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (offset < PAGE_SIZE) { const char *kaddr = dump->data; const unsigned char c = kaddr[offset++]; if (cp == last_start) *cp++ = '"'; if (cp >= buffer + tomoyo_buffer_len - 32) { /* Reserve some room for "..." string. */ truncated = true; } else if (c == '\\') { *cp++ = '\\'; *cp++ = '\\'; } else if (c > ' ' && c < 127) { *cp++ = c; } else if (!c) { *cp++ = '"'; *cp++ = ' '; last_start = cp; } else { *cp++ = '\\'; *cp++ = (c >> 6) + '0'; *cp++ = ((c >> 3) & 7) + '0'; *cp++ = (c & 7) + '0'; } if (c) continue; if (argv_count) { if (--argv_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } memmove(cp, "} envp[]={ ", 11); cp += 11; last_start = cp; truncated = false; } } else if (envp_count) { if (--envp_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } } } if (!argv_count && !envp_count) break; } offset = 0; } *cp++ = '}'; *cp = '\0'; return buffer; out: snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ ... } envp[]= { ... }"); return buffer; } /** * tomoyo_filetype - Get string representation of file type. * * @mode: Mode value for stat(). * * Returns file type string. */ static inline const char *tomoyo_filetype(const umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case 0: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FILE]; case S_IFDIR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_DIRECTORY]; case S_IFLNK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SYMLINK]; case S_IFIFO: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FIFO]; case S_IFSOCK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SOCKET]; case S_IFBLK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_BLOCK_DEV]; case S_IFCHR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_CHAR_DEV]; } return "unknown"; /* This should not happen. */ } /** * tomoyo_print_header - Get header line of audit log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns string representation. * * This function uses kmalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_header(struct tomoyo_request_info *r) { struct tomoyo_time stamp; const pid_t gpid = task_pid_nr(current); struct tomoyo_obj_info *obj = r->obj; static const int tomoyo_buffer_len = 4096; char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS); int pos; u8 i; if (!buffer) return NULL; tomoyo_convert_time(ktime_get_real_seconds(), &stamp); pos = snprintf(buffer, tomoyo_buffer_len - 1, "#%04u/%02u/%02u %02u:%02u:%02u# profile=%u mode=%s granted=%s (global-pid=%u) task={ pid=%u ppid=%u uid=%u gid=%u euid=%u egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec, r->profile, tomoyo_mode[r->mode], str_yes_no(r->granted), gpid, tomoyo_sys_getpid(), tomoyo_sys_getppid(), from_kuid(&init_user_ns, current_uid()), from_kgid(&init_user_ns, current_gid()), from_kuid(&init_user_ns, current_euid()), from_kgid(&init_user_ns, current_egid()), from_kuid(&init_user_ns, current_suid()), from_kgid(&init_user_ns, current_sgid()), from_kuid(&init_user_ns, current_fsuid()), from_kgid(&init_user_ns, current_fsgid())); if (!obj) goto no_obj_info; if (!obj->validate_done) { tomoyo_get_attributes(obj); obj->validate_done = true; } for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) { struct tomoyo_mini_stat *stat; unsigned int dev; umode_t mode; if (!obj->stat_valid[i]) continue; stat = &obj->stat[i]; dev = stat->dev; mode = stat->mode; if (i & 1) { pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u.parent={ uid=%u gid=%u ino=%llu perm=0%o }", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), stat->ino, stat->mode & S_IALLUGO); continue; } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u={ uid=%u gid=%u ino=%llu major=%u minor=%u perm=0%o type=%s", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), stat->ino, MAJOR(dev), MINOR(dev), mode & S_IALLUGO, tomoyo_filetype(mode)); if (S_ISCHR(mode) || S_ISBLK(mode)) { dev = stat->rdev; pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " dev_major=%u dev_minor=%u", MAJOR(dev), MINOR(dev)); } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " }"); } no_obj_info: if (pos < tomoyo_buffer_len - 1) return buffer; kfree(buffer); return NULL; } /** * tomoyo_init_log - Allocate buffer for audit logs. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns pointer to allocated memory. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf = NULL; char *bprm_info = NULL; const char *header = NULL; char *realpath = NULL; const char *symlink = NULL; int pos; const char *domainname = r->domain->domainname->name; header = tomoyo_print_header(r); if (!header) return NULL; /* +10 is for '\n' etc. and '\0'. */ len += strlen(domainname) + strlen(header) + 10; if (r->ee) { struct file *file = r->ee->bprm->file; realpath = tomoyo_realpath_from_path(&file->f_path); bprm_info = tomoyo_print_bprm(r->ee->bprm, &r->ee->dump); if (!realpath || !bprm_info) goto out; /* +80 is for " exec={ realpath=\"%s\" argc=%d envc=%d %s }" */ len += strlen(realpath) + 80 + strlen(bprm_info); } else if (r->obj && r->obj->symlink_target) { symlink = r->obj->symlink_target->name; /* +18 is for " symlink.target=\"%s\"" */ len += 18 + strlen(symlink); } len = kmalloc_size_roundup(len); buf = kzalloc(len, GFP_NOFS); if (!buf) goto out; len--; pos = snprintf(buf, len, "%s", header); if (realpath) { struct linux_binprm *bprm = r->ee->bprm; pos += snprintf(buf + pos, len - pos, " exec={ realpath=\"%s\" argc=%d envc=%d %s }", realpath, bprm->argc, bprm->envc, bprm_info); } else if (symlink) pos += snprintf(buf + pos, len - pos, " symlink.target=\"%s\"", symlink); pos += snprintf(buf + pos, len - pos, "\n%s\n", domainname); vsnprintf(buf + pos, len - pos, fmt, args); out: kfree(realpath); kfree(bprm_info); kfree(header); return buf; } /* Wait queue for /sys/kernel/security/tomoyo/audit. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_log_wait); /* Structure for audit log. */ struct tomoyo_log { struct list_head list; char *log; int size; }; /* The list for "struct tomoyo_log". */ static LIST_HEAD(tomoyo_log); /* Lock for "struct list_head tomoyo_log". */ static DEFINE_SPINLOCK(tomoyo_log_lock); /* Length of "struct list_head tomoyo_log". */ static unsigned int tomoyo_log_count; /** * tomoyo_get_audit - Get audit mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * @matched_acl: Pointer to "struct tomoyo_acl_info". * @is_granted: True if granted log, false otherwise. * * Returns true if this request should be audited, false otherwise. */ static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index, const struct tomoyo_acl_info *matched_acl, const bool is_granted) { u8 mode; const u8 category = tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return false; p = tomoyo_profile(ns, profile); if (tomoyo_log_count >= p->pref[TOMOYO_PREF_MAX_AUDIT_LOG]) return false; if (is_granted && matched_acl && matched_acl->cond && matched_acl->cond->grant_log != TOMOYO_GRANTLOG_AUTO) return matched_acl->cond->grant_log == TOMOYO_GRANTLOG_YES; mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[category]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; if (is_granted) return mode & TOMOYO_CONFIG_WANT_GRANT_LOG; return mode & TOMOYO_CONFIG_WANT_REJECT_LOG; } /** * tomoyo_write_log2 - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns nothing. */ void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf; struct tomoyo_log *entry; bool quota_exceeded = false; if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type, r->matched_acl, r->granted)) goto out; buf = tomoyo_init_log(r, len, fmt, args); if (!buf) goto out; entry = kzalloc_obj(*entry, GFP_NOFS); if (!entry) { kfree(buf); goto out; } entry->log = buf; len = kmalloc_size_roundup(strlen(buf) + 1); /* * The entry->size is used for memory quota checks. * Don't go beyond strlen(entry->log). */ entry->size = len + kmalloc_size_roundup(sizeof(*entry)); spin_lock(&tomoyo_log_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT] && tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] + entry->size >= tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT]) { quota_exceeded = true; } else { tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] += entry->size; list_add_tail(&entry->list, &tomoyo_log); tomoyo_log_count++; } spin_unlock(&tomoyo_log_lock); if (quota_exceeded) { kfree(buf); kfree(entry); goto out; } wake_up(&tomoyo_log_wait); out: return; } /** * tomoyo_write_log - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int len; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); } /** * tomoyo_read_log - Read an audit log. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ void tomoyo_read_log(struct tomoyo_io_buffer *head) { struct tomoyo_log *ptr = NULL; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_log_lock); if (!list_empty(&tomoyo_log)) { ptr = list_entry(tomoyo_log.next, typeof(*ptr), list); list_del(&ptr->list); tomoyo_log_count--; tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] -= ptr->size; } spin_unlock(&tomoyo_log_lock); if (ptr) { head->read_buf = ptr->log; head->r.w[head->r.w_pos++] = head->read_buf; kfree(ptr); } } /** * tomoyo_poll_log - Wait for an audit log. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log. */ __poll_t tomoyo_poll_log(struct file *file, poll_table *wait) { if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_log_wait, wait); if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; return 0; } |
| 119 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * acpi.h - ACPI Interface * * Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> */ #ifndef _LINUX_ACPI_H #define _LINUX_ACPI_H #include <linux/cleanup.h> #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/mod_devicetable.h> #include <linux/property.h> #include <linux/uuid.h> #include <linux/node.h> struct irq_domain; struct irq_domain_ops; #ifndef _LINUX #define _LINUX #endif #include <acpi/acpi.h> #include <acpi/acpi_numa.h> #ifdef CONFIG_ACPI #include <linux/list.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/fw_table.h> #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> #include <acpi/acpi_io.h> #include <asm/acpi.h> #ifdef CONFIG_ACPI_TABLE_LIB #define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "ACPI") #define __init_or_acpilib #define __initdata_or_acpilib #else #define EXPORT_SYMBOL_ACPI_LIB(x) #define __init_or_acpilib __init #define __initdata_or_acpilib __initdata #endif static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return adev ? adev->handle : NULL; } #define ACPI_COMPANION(dev) to_acpi_device_node((dev)->fwnode) #define ACPI_COMPANION_SET(dev, adev) set_primary_fwnode(dev, (adev) ? \ acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) #define ACPI_HANDLE_FWNODE(fwnode) \ acpi_device_handle(to_acpi_device_node(fwnode)) static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; fwnode = kzalloc_obj(struct fwnode_handle); if (!fwnode) return NULL; fwnode_init(fwnode, &acpi_static_fwnode_ops); return fwnode; } static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) { if (WARN_ON(!is_acpi_static_node(fwnode))) return; kfree(fwnode); } static inline bool has_acpi_companion(struct device *dev) { return is_acpi_device_node(dev->fwnode); } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, false)); } static inline const char *acpi_dev_name(struct acpi_device *adev) { return dev_name(&adev->dev); } struct device *acpi_get_first_physical_node(struct acpi_device *adev); enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, ACPI_IRQ_MODEL_IOAPIC, ACPI_IRQ_MODEL_IOSAPIC, ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, ACPI_IRQ_MODEL_GIC_V5, ACPI_IRQ_MODEL_LPIC, ACPI_IRQ_MODEL_RINTC, ACPI_IRQ_MODEL_COUNT }; extern enum acpi_irq_model_id acpi_irq_model; enum acpi_interrupt_id { ACPI_INTERRUPT_PMI = 1, ACPI_INTERRUPT_INIT, ACPI_INTERRUPT_CPEI, ACPI_INTERRUPT_COUNT }; #define ACPI_SPACE_MEM 0 enum acpi_address_range_id { ACPI_ADDRESS_RANGE_MEMORY = 1, ACPI_ADDRESS_RANGE_RESERVED = 2, ACPI_ADDRESS_RANGE_ACPI = 3, ACPI_ADDRESS_RANGE_NVS = 4, ACPI_ADDRESS_RANGE_COUNT }; /* Table Handlers */ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); /* Debugger support */ struct acpi_debugger_ops { int (*create_thread)(acpi_osd_exec_callback function, void *context); ssize_t (*write_log)(const char *msg); ssize_t (*read_cmd)(char *buffer, size_t length); int (*wait_command_ready)(bool single_step, char *buffer, size_t length); int (*notify_command_complete)(void); }; struct acpi_debugger { const struct acpi_debugger_ops *ops; struct module *owner; struct mutex lock; }; #ifdef CONFIG_ACPI_DEBUGGER int __init acpi_debugger_init(void); int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops); void acpi_unregister_debugger(const struct acpi_debugger_ops *ops); int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context); ssize_t acpi_debugger_write_log(const char *msg); ssize_t acpi_debugger_read_cmd(char *buffer, size_t buffer_length); int acpi_debugger_wait_command_ready(void); int acpi_debugger_notify_command_complete(void); #else static inline int acpi_debugger_init(void) { return -ENODEV; } static inline int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops) { return -ENODEV; } static inline void acpi_unregister_debugger(const struct acpi_debugger_ops *ops) { } static inline int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context) { return -ENODEV; } static inline int acpi_debugger_write_log(const char *msg) { return -ENODEV; } static inline int acpi_debugger_read_cmd(char *buffer, u32 buffer_length) { return -ENODEV; } static inline int acpi_debugger_wait_command_ready(void) { return -ENODEV; } static inline int acpi_debugger_notify_command_complete(void) { return -ENODEV; } #endif #define BAD_MADT_ENTRY(entry, end) ( \ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); void acpi_boot_table_prepare (void); void acpi_boot_table_init (void); int acpi_mps_check (void); int acpi_numa_init (void); int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); static inline struct acpi_table_header *acpi_get_table_pointer(char *signature, u32 instance) { struct acpi_table_header *table; int status = acpi_get_table(signature, instance, &table); if (ACPI_FAILURE(status)) return ERR_PTR(-ENOENT); return table; } DEFINE_FREE(acpi_put_table, struct acpi_table_header *, if (!IS_ERR_OR_NULL(_T)) acpi_put_table(_T)) int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init_or_acpilib acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_entries_array(char *id, unsigned long table_size, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_cedt(enum acpi_cedt_type id, acpi_tbl_entry_handler_arg handler_arg, void *arg); int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else static inline void acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } #endif void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); #if defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) void acpi_arch_dma_setup(struct device *dev); #else static inline void acpi_arch_dma_setup(struct device *dev) { } #endif #ifdef CONFIG_ARM64 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); #else static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif #ifdef CONFIG_RISCV void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); #else static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } #endif #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) #endif static inline bool invalid_logical_cpuid(u32 cpuid) { return (int)cpuid < 0; } static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) { return phys_id == PHYS_CPUID_INVALID; } int __init acpi_get_madt_revision(void); /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ struct acpi_processor_power; #ifdef CONFIG_ACPI_PROCESSOR_CSTATE bool acpi_processor_claim_cst_control(void); int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info); #else static inline bool acpi_processor_claim_cst_control(void) { return false; } static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info) { return -ENODEV; } #endif #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ acpi_handle acpi_get_processor_handle(int cpu); /** * acpi_get_cpu_uid() - Get ACPI Processor UID of from MADT table * @cpu: Logical CPU number (0-based) * @uid: Pointer to store ACPI Processor UID * * Return: 0 on success (ACPI Processor ID stored in *uid); * -EINVAL if CPU number is invalid or out of range; * -ENODEV if ACPI Processor UID for the CPU is not found. */ int acpi_get_cpu_uid(unsigned int cpu, u32 *uid); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); void acpi_irq_stats_init(void); extern u32 acpi_irq_handled; extern u32 acpi_irq_not_handled; extern unsigned int acpi_sci_irq; extern bool acpi_no_s5; #define INVALID_ACPI_IRQ ((unsigned)-1) static inline bool acpi_sci_irq_valid(void) { return acpi_sci_irq != INVALID_ACPI_IRQ; } extern int sbf_port; int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); typedef struct fwnode_handle *(*acpi_gsi_domain_disp_fn)(u32); void acpi_set_irq_model(enum acpi_irq_model_id model, acpi_gsi_domain_disp_fn fn); acpi_gsi_domain_disp_fn acpi_get_gsi_dispatcher(void); void acpi_set_gsi_to_irq_fallback(u32 (*)(u32)); struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, unsigned int size, struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data); #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else static inline int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { return -1; } #endif /* * This function undoes the effect of one call to acpi_register_gsi(). * If this matches the last registration, any IRQ resources for gsi * are freed. */ void acpi_unregister_gsi (u32 gsi); struct pci_dev; struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin); int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); #ifdef CONFIG_PCI void acpi_penalize_sci_irq(int irq, int trigger, int polarity); #else static inline void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { } #endif void acpi_pci_irq_disable (struct pci_dev *dev); extern int ec_read(u8 addr, u8 *val); extern int ec_write(u8 addr, u8 val); extern int ec_transaction(u8 command, const u8 *wdata, unsigned wdata_len, u8 *rdata, unsigned rdata_len); extern acpi_handle ec_get_handle(void); extern bool acpi_is_pnp_device(struct acpi_device *); #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE) typedef void (*wmi_notify_handler) (union acpi_object *data, void *context); int wmi_instance_count(const char *guid); extern acpi_status wmi_evaluate_method(const char *guid, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out); extern acpi_status wmi_query_block(const char *guid, u8 instance, struct acpi_buffer *out); extern acpi_status wmi_set_block(const char *guid, u8 instance, const struct acpi_buffer *in); extern acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, void *data); extern acpi_status wmi_remove_notify_handler(const char *guid); extern bool wmi_has_guid(const char *guid); extern char *wmi_get_acpi_device_uid(const char *guid); #endif /* CONFIG_ACPI_WMI */ #define ACPI_VIDEO_OUTPUT_SWITCHING 0x0001 #define ACPI_VIDEO_DEVICE_POSTING 0x0002 #define ACPI_VIDEO_ROM_AVAILABLE 0x0004 #define ACPI_VIDEO_BACKLIGHT 0x0008 #define ACPI_VIDEO_BACKLIGHT_FORCE_VENDOR 0x0010 #define ACPI_VIDEO_BACKLIGHT_FORCE_VIDEO 0x0020 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VENDOR 0x0040 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VIDEO 0x0080 #define ACPI_VIDEO_BACKLIGHT_DMI_VENDOR 0x0100 #define ACPI_VIDEO_BACKLIGHT_DMI_VIDEO 0x0200 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VENDOR 0x0400 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_THERMAL_LIB int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp); int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp); int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp); int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp); #endif #ifdef CONFIG_ACPI_HMAT int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord); #else static inline int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_ACPI_NUMA int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); /** * pxm_to_online_node - Map proximity ID to online node * @pxm: ACPI proximity ID * * This is similar to pxm_to_node(), but always returns an online * node. When the mapped node from a given proximity ID is offline, it * looks up the node distance table and returns the nearest online node. * * ACPI device drivers, which are called after the NUMA initialization has * completed in the kernel, can call this interface to obtain their device * NUMA topology from ACPI tables. Such drivers do not have to deal with * offline nodes. A node may be offline when SRAT memory entry does not exist, * or NUMA is disabled, ex. "numa=off" on x86. */ static inline int pxm_to_online_node(int pxm) { int node = pxm_to_node(pxm); return numa_map_to_online_node(node); } #else static inline int pxm_to_online_node(int pxm) { return 0; } static inline int acpi_map_pxm_to_node(int pxm) { return 0; } static inline int acpi_get_node(acpi_handle handle) { return 0; } #endif extern int pnpacpi_disabled; #define PXM_INVAL (-1) bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable, u8 wake_capable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); int acpi_dev_get_dma_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, void *arg) { return acpi_dev_filter_resource_type(ares, (unsigned long)arg); } struct acpi_device *acpi_resource_consumer(struct resource *res); int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION extern int acpi_check_s4_hw_signature; #endif #ifdef CONFIG_PM_SLEEP void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); void __init acpi_nvs_nosave_s3(void); void __init acpi_sleep_no_blacklist(void); #endif /* CONFIG_PM_SLEEP */ int acpi_register_wakeup_handler( int wake_irq, bool (*wakeup)(void *context), void *context); void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context); struct acpi_osc_context { char *uuid_str; /* UUID string */ int rev; struct acpi_buffer cap; /* list of DWORD capabilities */ struct acpi_buffer ret; /* free by caller if success */ }; acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Number of _OSC capability DWORDS depends on bridge type */ #define OSC_PCI_CAPABILITY_DWORDS 3 #define OSC_CXL_CAPABILITY_DWORDS 5 /* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ #define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */ #define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ #define OSC_REQUEST_ERROR 0x00000002 /* return */ #define OSC_INVALID_UUID_ERROR 0x00000004 /* return */ #define OSC_INVALID_REVISION_ERROR 0x00000008 /* return */ #define OSC_CAPABILITIES_MASK_ERROR 0x00000010 /* return */ /* Platform-Wide Capabilities _OSC: Capabilities DWORD 2: Support Field */ #define OSC_SB_PAD_SUPPORT 0x00000001 #define OSC_SB_PPC_OST_SUPPORT 0x00000002 #define OSC_SB_PR3_SUPPORT 0x00000004 #define OSC_SB_HOTPLUG_OST_SUPPORT 0x00000008 #define OSC_SB_APEI_SUPPORT 0x00000010 #define OSC_SB_CPC_SUPPORT 0x00000020 #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT 0x00000200 #define OSC_SB_OVER_16_PSTATES_SUPPORT 0x00000400 #define OSC_SB_GED_SUPPORT 0x00000800 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_BATTERY_CHARGE_LIMITING_SUPPORT 0x00080000 #define OSC_SB_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc2_support_acked; extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 #define OSC_USB_DP_TUNNELING 0x00000002 #define OSC_USB_PCIE_TUNNELING 0x00000004 #define OSC_USB_XDOMAIN 0x00000008 extern u32 osc_sb_native_usb4_control; /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */ #define OSC_PCI_EXT_CONFIG_SUPPORT 0x00000001 #define OSC_PCI_ASPM_SUPPORT 0x00000002 #define OSC_PCI_CLOCK_PM_SUPPORT 0x00000004 #define OSC_PCI_SEGMENT_GROUPS_SUPPORT 0x00000008 #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 #define OSC_PCI_SHPC_NATIVE_HP_CONTROL 0x00000002 #define OSC_PCI_EXPRESS_PME_CONTROL 0x00000004 #define OSC_PCI_EXPRESS_AER_CONTROL 0x00000008 #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 /* CXL _OSC: Capabilities DWORD 4: Support Field */ #define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001 #define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002 #define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004 #define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008 /* CXL _OSC: Capabilities DWORD 5: Control Field */ #define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001 static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_CONTROL_DWORD]; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_EXT_CONTROL_DWORD]; } #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 #define ACPI_GSB_ACCESS_ATTRIB_WORD 0x00000008 #define ACPI_GSB_ACCESS_ATTRIB_BLOCK 0x0000000A #define ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE 0x0000000B #define ACPI_GSB_ACCESS_ATTRIB_WORD_CALL 0x0000000C #define ACPI_GSB_ACCESS_ATTRIB_BLOCK_CALL 0x0000000D #define ACPI_GSB_ACCESS_ATTRIB_RAW_BYTES 0x0000000E #define ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS 0x0000000F /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ defined(CONFIG_ACPI_CONTAINER) #define ACPI_HOTPLUG_OST #endif /* _OST Source Event Code (OSPM Action) */ #define ACPI_OST_EC_OSPM_SHUTDOWN 0x100 #define ACPI_OST_EC_OSPM_EJECT 0x103 #define ACPI_OST_EC_OSPM_INSERTION 0x200 /* _OST General Processing Status Code */ #define ACPI_OST_SC_SUCCESS 0x0 #define ACPI_OST_SC_NON_SPECIFIC_FAILURE 0x1 #define ACPI_OST_SC_UNRECOGNIZED_NOTIFY 0x2 /* _OST OS Shutdown Processing (0x100) Status Code */ #define ACPI_OST_SC_OS_SHUTDOWN_DENIED 0x80 #define ACPI_OST_SC_OS_SHUTDOWN_IN_PROGRESS 0x81 #define ACPI_OST_SC_OS_SHUTDOWN_COMPLETED 0x82 #define ACPI_OST_SC_OS_SHUTDOWN_NOT_SUPPORTED 0x83 /* _OST Ejection Request (0x3, 0x103) Status Code */ #define ACPI_OST_SC_EJECT_NOT_SUPPORTED 0x80 #define ACPI_OST_SC_DEVICE_IN_USE 0x81 #define ACPI_OST_SC_DEVICE_BUSY 0x82 #define ACPI_OST_SC_EJECT_DEPENDENCY_BUSY 0x83 #define ACPI_OST_SC_EJECT_IN_PROGRESS 0x84 /* _OST Insertion Request (0x200) Status Code */ #define ACPI_OST_SC_INSERT_IN_PROGRESS 0x80 #define ACPI_OST_SC_DRIVER_LOAD_FAILURE 0x81 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 enum acpi_predicate { all_versions, less_than_or_equal, equal, greater_than_or_equal, }; /* Table must be terminted by a NULL entry */ struct acpi_platform_list { char oem_id[ACPI_OEM_ID_SIZE+1]; char oem_table_id[ACPI_OEM_TABLE_ID_SIZE+1]; u32 oem_revision; char *table; enum acpi_predicate pred; char *reason; u32 data; }; int acpi_match_platform_list(const struct acpi_platform_list *plat); extern void acpi_early_init(void); extern void acpi_subsystem_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data); const struct acpi_device_id *acpi_match_acpi_device(const struct acpi_device_id *ids, const struct acpi_device *adev); const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev); const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(const struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, const struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { adev->flags.visited = true; } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { adev->flags.visited = false; } enum acpi_reconfig_event { ACPI_RECONFIG_DEVICE_ADD = 0, ACPI_RECONFIG_DEVICE_REMOVE, }; int acpi_reconfig_notifier_register(struct notifier_block *nb); int acpi_reconfig_notifier_unregister(struct notifier_block *nb); #ifdef CONFIG_ACPI_GTDT int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count); int acpi_gtdt_map_ppi(int type); bool acpi_gtdt_c3stop(int type); #endif #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER static __always_inline void acpi_arch_set_root_pointer(u64 addr) { } #endif #ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER static __always_inline u64 acpi_arch_get_root_pointer(void) { return 0; } #endif int acpi_get_local_u64_address(acpi_handle handle, u64 *addr); int acpi_get_local_address(acpi_handle handle, u32 *addr); const char *acpi_get_subsystem_id(acpi_handle handle); #ifdef CONFIG_ACPI_MRRM int acpi_mrrm_max_mem_region(void); #endif #define ACPI_CMOS_RTC_IDS \ { "PNP0B00", }, \ { "PNP0B01", }, \ { "PNP0B02", }, \ { "", } extern bool cmos_rtc_platform_device_present; #else /* !CONFIG_ACPI */ #define acpi_disabled 1 #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) #define ACPI_HANDLE_FWNODE(fwnode) (NULL) /* Get rid of the -Wunused-variable for adev */ #define acpi_dev_uid_match(adev, uid2) (adev && false) #define acpi_dev_hid_uid_match(adev, hid2, uid2) (adev && false) struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) { return false; } static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) { return false; } struct acpi_device; static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer) { return -ENODEV; } static inline struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) { return NULL; } static inline bool acpi_reduced_hardware(void) { return false; } static inline void acpi_dev_put(struct acpi_device *adev) {} static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return false; } static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_device *to_acpi_device_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_data_node *to_acpi_data_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return false; } static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return NULL; } static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return NULL; } static inline bool has_acpi_companion(struct device *dev) { return false; } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { } static inline const char *acpi_dev_name(struct acpi_device *adev) { return NULL; } static inline struct device *acpi_get_first_physical_node(struct acpi_device *adev) { return NULL; } static inline void acpi_early_init(void) { } static inline void acpi_subsystem_init(void) { } static inline int early_acpi_boot_init(void) { return 0; } static inline int acpi_boot_init(void) { return 0; } static inline void acpi_boot_table_prepare(void) { } static inline void acpi_boot_table_init(void) { } static inline int acpi_mps_check(void) { return 0; } static inline int acpi_check_resource_conflict(struct resource *res) { return 0; } static inline int acpi_check_region(resource_size_t start, resource_size_t n, const char *name) { return 0; } struct acpi_table_header; static inline int acpi_table_parse(char *id, int (*handler)(struct acpi_table_header *)) { return -ENODEV; } static inline int acpi_get_cpu_uid(unsigned int cpu, u32 *uid) { *uid = cpu; return 0; } static inline int acpi_nvs_register(__u64 start, __u64 size) { return 0; } static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data) { return 0; } struct acpi_device_id; static inline const struct acpi_device_id *acpi_match_acpi_device( const struct acpi_device_id *ids, const struct acpi_device *adev) { return NULL; } static inline const struct acpi_device_id *acpi_match_device( const struct acpi_device_id *ids, const struct device *dev) { return NULL; } static inline const void *acpi_device_get_match_data(const struct device *dev) { return NULL; } static inline bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv) { return false; } static inline bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs) { return false; } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { return NULL; } static inline union acpi_object *acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4, acpi_object_type type) { return NULL; } static inline int acpi_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { return -ENODEV; } static inline int acpi_device_modalias(struct device *dev, char *buf, int size) { return -ENODEV; } static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, const struct property_entry *properties) { return NULL; } static inline bool acpi_dma_supported(const struct acpi_device *adev) { return false; } static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) { return DEV_DMA_NOT_SUPPORTED; } static inline int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map) { return -ENODEV; } static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { return 0; } static inline int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id) { return 0; } #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { } static inline int acpi_reconfig_notifier_register(struct notifier_block *nb) { return -EINVAL; } static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb) { return -EINVAL; } static inline struct acpi_device *acpi_resource_consumer(struct resource *res) { return NULL; } static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) { return -ENODEV; } static inline const char *acpi_get_subsystem_id(acpi_handle handle) { return ERR_PTR(-ENODEV); } static inline int acpi_register_wakeup_handler(int wake_irq, bool (*wakeup)(void *context), void *context) { return -ENXIO; } static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } struct acpi_osc_context; static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { return 0; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { return 0; } static inline bool acpi_sleep_state_supported(u8 sleep_state) { return false; } static inline acpi_handle acpi_get_processor_handle(int cpu) { return NULL; } static inline int acpi_mrrm_max_mem_region(void) { return 1; } #define cmos_rtc_platform_device_present false #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HMAT int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid, resource_size_t *size); #else static inline int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid, resource_size_t *size) { return -EOPNOTSUPP; } #endif extern void arch_post_acpi_subsys_init(void); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_ioapic_add(acpi_handle root); #else static inline int acpi_ioapic_add(acpi_handle root) { return 0; } #endif #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, u32 val_a, u32 val_b)); acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); struct acpi_s2idle_dev_ops { struct list_head list_node; void (*prepare)(void); void (*check)(void); void (*restore)(void); }; #if defined(CONFIG_SUSPEND) && defined(CONFIG_X86) int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); #else /* CONFIG_SUSPEND && CONFIG_X86 */ static inline int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg) { return -ENODEV; } static inline void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg) { } #endif /* CONFIG_SUSPEND && CONFIG_X86 */ void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0) #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM) int acpi_dev_suspend(struct device *dev, bool wakeup); int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); bool acpi_dev_state_d0(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } static inline bool acpi_storage_d3(struct device *dev) { return false; } static inline bool acpi_dev_state_d0(struct device *dev) { return true; } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); int acpi_subsys_restore_early(struct device *dev); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; } static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } static inline int acpi_subsys_restore_early(struct device *dev) { return 0; } #endif #if defined(CONFIG_ACPI_EC) && defined(CONFIG_PM_SLEEP) void acpi_ec_mark_gpe_for_wake(void); void acpi_ec_set_gpe_wake_mask(u8 action); #else static inline void acpi_ec_mark_gpe_for_wake(void) {} static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI char *acpi_handle_path(acpi_handle handle); __printf(3, 4) void acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...); void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status); #else /* !CONFIG_ACPI */ static inline __printf(3, 4) void acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} static inline void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status) {} #endif /* !CONFIG_ACPI */ #if defined(CONFIG_ACPI) && defined(CONFIG_DYNAMIC_DEBUG) __printf(3, 4) void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const char *fmt, ...); #endif /* * acpi_handle_<level>: Print message with ACPI prefix and object path * * These interfaces acquire the global namespace mutex to obtain an object * path. In interrupt context, it shows the object path as <n/a>. */ #define acpi_handle_emerg(handle, fmt, ...) \ acpi_handle_printk(KERN_EMERG, handle, fmt, ##__VA_ARGS__) #define acpi_handle_alert(handle, fmt, ...) \ acpi_handle_printk(KERN_ALERT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_crit(handle, fmt, ...) \ acpi_handle_printk(KERN_CRIT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_err(handle, fmt, ...) \ acpi_handle_printk(KERN_ERR, handle, fmt, ##__VA_ARGS__) #define acpi_handle_warn(handle, fmt, ...) \ acpi_handle_printk(KERN_WARNING, handle, fmt, ##__VA_ARGS__) #define acpi_handle_notice(handle, fmt, ...) \ acpi_handle_printk(KERN_NOTICE, handle, fmt, ##__VA_ARGS__) #define acpi_handle_info(handle, fmt, ...) \ acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__) #if defined(DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__) #else #if defined(CONFIG_DYNAMIC_DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ _dynamic_func_call(fmt, __acpi_handle_debug, \ handle, pr_fmt(fmt), ##__VA_ARGS__) #else #define acpi_handle_debug(handle, fmt, ...) \ ({ \ if (0) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__); \ 0; \ }) #endif #endif #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable) { return -ENXIO; } #endif static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index, bool *wake_capable) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); } static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *con_id, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, con_id, index, NULL); } static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, NULL); } /* Device properties */ #ifdef CONFIG_ACPI int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args); static inline int acpi_node_get_property_reference( const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, name, index, NR_FWNODE_REFERENCE_ARGS, args); } static inline bool acpi_dev_has_props(const struct acpi_device *adev) { return !list_empty(&adev->data.properties); } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, union acpi_object *properties); int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); #define ACPI_TABLE_ID_LEN 5 /** * struct acpi_probe_entry - boot-time probing entry * @id: ACPI table name * @type: Optional subtable type to match * (if @id contains subtables) * @subtable_valid: Optional callback to check the validity of * the subtable * @probe_table: Callback to the driver being probed when table * match is successful * @probe_subtbl: Callback to the driver being probed when table and * subtable match (and optional callback is successful) * @driver_data: Sideband data provided back to the driver */ struct acpi_probe_entry { __u8 id[ACPI_TABLE_ID_LEN]; __u8 type; acpi_probe_entry_validate_subtbl subtable_valid; union { acpi_tbl_table_handler probe_table; acpi_tbl_entry_handler probe_subtbl; }; kernel_ulong_t driver_data; }; void arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr); #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_table = fn, \ .driver_data = data, \ } #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ subtable, valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_subtbl = fn, \ .driver_data = data, \ } #define ACPI_PROBE_TABLE(name) __##name##_acpi_probe_table #define ACPI_PROBE_TABLE_END(name) __##name##_acpi_probe_table_end int __acpi_probe_device_table(struct acpi_probe_entry *start, int nr); #define acpi_probe_device_table(t) \ ({ \ extern struct acpi_probe_entry ACPI_PROBE_TABLE(t), \ ACPI_PROBE_TABLE_END(t); \ __acpi_probe_device_table(&ACPI_PROBE_TABLE(t), \ (&ACPI_PROBE_TABLE_END(t) - \ &ACPI_PROBE_TABLE(t))); \ }) #else static inline int acpi_dev_get_property(struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return -ENXIO; } static inline int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return -ENXIO; } static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { return ERR_PTR(-ENXIO); } static inline int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint) { return -ENXIO; } #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ (void *) subtable, \ (void *) valid, \ (void *) fn, \ (void *) data } #define acpi_probe_device_table(t) ({ int __r = 0; __r;}) #endif #ifdef CONFIG_ACPI_TABLE_UPGRADE void acpi_table_upgrade(void); #else static inline void acpi_table_upgrade(void) { } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_ACPI_WATCHDOG) extern bool acpi_has_watchdog(void); #else static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE extern bool qdf2400_e44_present; int acpi_parse_spcr(bool enable_earlycon, bool enable_console); #else static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) { return -ENODEV; } #endif #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); const struct cpumask *acpi_irq_get_affinity(acpi_handle handle, unsigned int index); #else static inline int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) { return -EINVAL; } static inline const struct cpumask *acpi_irq_get_affinity(acpi_handle handle, unsigned int index) { return NULL; } #endif #ifdef CONFIG_ACPI_LPIT int lpit_read_residency_count_address(u64 *address); #else static inline int lpit_read_residency_count_address(u64 *address) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_PROCESSOR_IDLE #ifndef arch_get_idle_state_flags static inline unsigned int arch_get_idle_state_flags(u32 arch_flags) { return 0; } #endif #endif /* CONFIG_ACPI_PROCESSOR_IDLE */ #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); void acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id, cpumask_t *cpus); int find_acpi_cache_level_from_id(u32 cache_id); int acpi_pptt_get_cpumask_from_cache_id(u32 cache_id, cpumask_t *cpus); #else static inline int acpi_pptt_cpu_is_thread(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology(unsigned int cpu, int level) { return -EINVAL; } static inline int find_acpi_cpu_topology_cluster(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) { return -EINVAL; } static inline void acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id, cpumask_t *cpus) { } static inline int find_acpi_cache_level_from_id(u32 cache_id) { return -ENOENT; } static inline int acpi_pptt_get_cpumask_from_cache_id(u32 cache_id, cpumask_t *cpus) { return -ENOENT; } #endif void acpi_arch_init(void); #ifdef CONFIG_ACPI_PCC void acpi_init_pcc(void); #else static inline void acpi_init_pcc(void) { } #endif #ifdef CONFIG_ACPI_FFH void acpi_init_ffh(void); extern int acpi_ffh_address_space_arch_setup(void *handler_ctxt, void **region_ctxt); extern int acpi_ffh_address_space_arch_handler(acpi_integer *value, void *region_context); #else static inline void acpi_init_ffh(void) { } #endif #ifdef CONFIG_ACPI extern void acpi_device_notify(struct device *dev); extern void acpi_device_notify_remove(struct device *dev); #else static inline void acpi_device_notify(struct device *dev) { } static inline void acpi_device_notify_remove(struct device *dev) { } #endif static inline void acpi_use_parent_companion(struct device *dev) { ACPI_COMPANION_SET(dev, ACPI_COMPANION(dev->parent)); } #ifdef CONFIG_ACPI_NUMA bool acpi_node_backed_by_real_pxm(int nid); #else static inline bool acpi_node_backed_by_real_pxm(int nid) { return false; } #endif #endif /*_LINUX_ACPI_H*/ |
| 5 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2009 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> struct nft_lookup { struct nft_set *set; u8 sreg; u8 dreg; bool dreg_set; bool invert; struct nft_set_binding binding; }; static const struct nft_set_ext * __nft_set_do_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { #ifdef CONFIG_MITIGATION_RETPOLINE if (set->ops == &nft_set_hash_fast_type.ops) return nft_hash_lookup_fast(net, set, key); if (set->ops == &nft_set_hash_type.ops) return nft_hash_lookup(net, set, key); if (set->ops == &nft_set_rhash_type.ops) return nft_rhash_lookup(net, set, key); if (set->ops == &nft_set_bitmap_type.ops) return nft_bitmap_lookup(net, set, key); if (set->ops == &nft_set_pipapo_type.ops) return nft_pipapo_lookup(net, set, key); #if defined(CONFIG_X86_64) && !defined(CONFIG_UML) if (set->ops == &nft_set_pipapo_avx2_type.ops) return nft_pipapo_avx2_lookup(net, set, key); #endif if (set->ops == &nft_set_rbtree_type.ops) return nft_rbtree_lookup(net, set, key); WARN_ON_ONCE(1); #endif return set->ops->lookup(net, set, key); } static unsigned int nft_base_seq(const struct net *net) { /* pairs with smp_store_release() in nf_tables_commit() */ return smp_load_acquire(&net->nft.base_seq); } static bool nft_lookup_should_retry(const struct net *net, unsigned int seq) { return unlikely(seq != nft_base_seq(net)); } const struct nft_set_ext * nft_set_do_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { const struct nft_set_ext *ext; unsigned int base_seq; do { base_seq = nft_base_seq(net); ext = __nft_set_do_lookup(net, set, key); if (ext) break; /* No match? There is a small chance that lookup was * performed in the old generation, but nf_tables_commit() * already unlinked a (matching) element. * * We need to repeat the lookup to make sure that we didn't * miss a matching element in the new generation. */ } while (nft_lookup_should_retry(net, base_seq)); return ext; } EXPORT_SYMBOL_GPL(nft_set_do_lookup); void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; const struct net *net = nft_net(pkt); const struct nft_set_ext *ext; bool found; ext = nft_set_do_lookup(net, set, ®s->data[priv->sreg]); found = !!ext ^ priv->invert; if (!found) { ext = nft_set_catchall_lookup(net, set); if (!ext) { regs->verdict.code = NFT_BREAK; return; } } if (ext) { if (priv->dreg_set) nft_data_copy(®s->data[priv->dreg], nft_set_ext_data(ext), set->dlen); nft_set_elem_update_expr(ext, regs, pkt); } } static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { [NFTA_LOOKUP_SET] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_LOOKUP_SET_ID] = { .type = NLA_U32 }, [NFTA_LOOKUP_SREG] = NLA_POLICY_MAX(NLA_BE32, NFT_REG32_MAX), [NFTA_LOOKUP_DREG] = NLA_POLICY_MAX(NLA_BE32, NFT_REG32_MAX), [NFTA_LOOKUP_FLAGS] = NLA_POLICY_MASK(NLA_BE32, NFT_LOOKUP_F_INV), }; static int nft_lookup_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_lookup *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; u32 flags; int err; if (tb[NFTA_LOOKUP_SET] == NULL || tb[NFTA_LOOKUP_SREG] == NULL) return -EINVAL; set = nft_set_lookup_global(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET], tb[NFTA_LOOKUP_SET_ID], genmask); if (IS_ERR(set)) return PTR_ERR(set); err = nft_parse_register_load(ctx, tb[NFTA_LOOKUP_SREG], &priv->sreg, set->klen); if (err < 0) return err; if (tb[NFTA_LOOKUP_FLAGS]) { flags = ntohl(nla_get_be32(tb[NFTA_LOOKUP_FLAGS])); if (flags & NFT_LOOKUP_F_INV) priv->invert = true; } if (tb[NFTA_LOOKUP_DREG] != NULL) { if (priv->invert) return -EINVAL; if (!(set->flags & NFT_SET_MAP)) return -EINVAL; err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG], &priv->dreg, NULL, nft_set_datatype(set), set->dlen); if (err < 0) return err; priv->dreg_set = true; } else if (set->flags & NFT_SET_MAP) { /* Map given, but user asks for lookup only (i.e. to * ignore value assoicated with key). * * This makes no sense for anonymous maps since they are * scoped to the rule, but for named sets this can be useful. */ if (set->flags & NFT_SET_ANONYMOUS) return -EINVAL; } priv->binding.flags = set->flags & NFT_SET_MAP; err = nf_tables_bind_set(ctx, set, &priv->binding); if (err < 0) return err; priv->set = set; return 0; } static void nft_lookup_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_lookup *priv = nft_expr_priv(expr); nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase); } static void nft_lookup_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_lookup *priv = nft_expr_priv(expr); nf_tables_activate_set(ctx, priv->set); } static void nft_lookup_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_lookup *priv = nft_expr_priv(expr); nf_tables_destroy_set(ctx, priv->set); } static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_lookup *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_LOOKUP_F_INV : 0; if (nla_put_string(skb, NFTA_LOOKUP_SET, priv->set->name)) goto nla_put_failure; if (nft_dump_register(skb, NFTA_LOOKUP_SREG, priv->sreg)) goto nla_put_failure; if (priv->dreg_set) if (nft_dump_register(skb, NFTA_LOOKUP_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_LOOKUP_FLAGS, htonl(flags))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int nft_lookup_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_lookup *priv = nft_expr_priv(expr); struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), .type = NFT_ITER_UPDATE, .fn = nft_setelem_validate, }; if (!(priv->set->flags & NFT_SET_MAP) || priv->set->dtype != NFT_DATA_VERDICT) return 0; priv->set->ops->walk(ctx, priv->set, &iter); if (!iter.err) iter.err = nft_set_catchall_validate(ctx, priv->set); if (iter.err < 0) return iter.err; return 0; } static const struct nft_expr_ops nft_lookup_ops = { .type = &nft_lookup_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), .eval = nft_lookup_eval, .init = nft_lookup_init, .activate = nft_lookup_activate, .deactivate = nft_lookup_deactivate, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, .validate = nft_lookup_validate, }; struct nft_expr_type nft_lookup_type __read_mostly = { .name = "lookup", .ops = &nft_lookup_ops, .policy = nft_lookup_policy, .maxattr = NFTA_LOOKUP_MAX, .owner = THIS_MODULE, }; |
| 546 12 11 12 12 3 3 3 3 1 2 174 174 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Performance events x86 architecture code * * Copyright (C) 2008 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * * For licencing details see kernel-base/COPYING */ #include <linux/perf_event.h> #include <linux/capability.h> #include <linux/notifier.h> #include <linux/hardirq.h> #include <linux/kprobes.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kdebug.h> #include <linux/kvm_types.h> #include <linux/sched/mm.h> #include <linux/sched/clock.h> #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/device.h> #include <linux/nospec.h> #include <linux/static_call.h> #include <linux/kvm_types.h> #include <asm/apic.h> #include <asm/stacktrace.h> #include <asm/msr.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/alternative.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include <asm/timer.h> #include <asm/desc.h> #include <asm/ldt.h> #include <asm/unwind.h> #include <asm/uprobes.h> #include <asm/ibt.h> #include "perf_event.h" struct x86_pmu x86_pmu __read_mostly; static struct pmu pmu; DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, .pmu = &pmu, }; static DEFINE_PER_CPU(bool, guest_lvtpc_loaded); DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key); DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key); DEFINE_STATIC_KEY_FALSE(perf_is_hybrid); /* * This here uses DEFINE_STATIC_CALL_NULL() to get a static_call defined * from just a typename, as opposed to an actual function. */ DEFINE_STATIC_CALL_NULL(x86_pmu_handle_irq, *x86_pmu.handle_irq); DEFINE_STATIC_CALL_NULL(x86_pmu_disable_all, *x86_pmu.disable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable); DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign); DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); DEFINE_STATIC_CALL_NULL(x86_pmu_set_period, *x86_pmu.set_period); DEFINE_STATIC_CALL_NULL(x86_pmu_update, *x86_pmu.update); DEFINE_STATIC_CALL_NULL(x86_pmu_limit_period, *x86_pmu.limit_period); DEFINE_STATIC_CALL_NULL(x86_pmu_schedule_events, *x86_pmu.schedule_events); DEFINE_STATIC_CALL_NULL(x86_pmu_get_event_constraints, *x86_pmu.get_event_constraints); DEFINE_STATIC_CALL_NULL(x86_pmu_put_event_constraints, *x86_pmu.put_event_constraints); DEFINE_STATIC_CALL_NULL(x86_pmu_start_scheduling, *x86_pmu.start_scheduling); DEFINE_STATIC_CALL_NULL(x86_pmu_commit_scheduling, *x86_pmu.commit_scheduling); DEFINE_STATIC_CALL_NULL(x86_pmu_stop_scheduling, *x86_pmu.stop_scheduling); DEFINE_STATIC_CALL_NULL(x86_pmu_sched_task, *x86_pmu.sched_task); DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases); DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter); DEFINE_STATIC_CALL_NULL(x86_pmu_late_setup, *x86_pmu.late_setup); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable, *x86_pmu.pebs_enable); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable, *x86_pmu.pebs_disable); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable_all, *x86_pmu.pebs_enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable_all, *x86_pmu.pebs_disable_all); /* * This one is magic, it will get called even when PMU init fails (because * there is no PMU), in which case it should simply return NULL. */ DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs); u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; u64 __read_mostly hw_cache_extra_regs [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; /* * Propagate event elapsed time into the generic event. * Can only be executed on the CPU where the event is active. * Returns the delta events processed. */ u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int shift = 64 - x86_pmu.cntval_bits; u64 prev_raw_count, new_raw_count; u64 delta; if (unlikely(!hwc->event_base)) return 0; /* * Careful: an NMI might modify the previous event value. * * Our tactic to handle this is to first atomically read and * exchange a new raw count - then add that new-prev delta * count to the generic event atomically: */ prev_raw_count = local64_read(&hwc->prev_count); do { new_raw_count = rdpmc(hwc->event_base_rdpmc); } while (!local64_try_cmpxchg(&hwc->prev_count, &prev_raw_count, new_raw_count)); /* * Now we have the new raw value and have updated the prev * timestamp already. We can now calculate the elapsed delta * (event-)time and add that to the generic event. * * Careful, not all hw sign-extends above the physical width * of the count. */ delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; local64_add(delta, &event->count); local64_sub(delta, &hwc->period_left); return new_raw_count; } /* * Find and validate any extra registers to set up. */ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) { struct extra_reg *extra_regs = hybrid(event->pmu, extra_regs); struct hw_perf_event_extra *reg; struct extra_reg *er; reg = &event->hw.extra_reg; if (!extra_regs) return 0; for (er = extra_regs; er->msr; er++) { if (er->event != (config & er->config_mask)) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; /* Check if the extra msrs can be safely accessed*/ if (!er->extra_msr_access) return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; reg->reg = er->msr; break; } return 0; } static atomic_t active_events; static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC static inline u64 get_possible_counter_mask(void) { u64 cntr_mask = x86_pmu.cntr_mask64; int i; if (!is_hybrid()) return cntr_mask; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) cntr_mask |= x86_pmu.hybrid_pmu[i].cntr_mask64; return cntr_mask; } static bool reserve_pmc_hardware(void) { u64 cntr_mask = get_possible_counter_mask(); int i, end; for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) { if (!reserve_perfctr_nmi(x86_pmu_event_addr(i))) goto perfctr_fail; } for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) { if (!reserve_evntsel_nmi(x86_pmu_config_addr(i))) goto eventsel_fail; } return true; eventsel_fail: end = i; for_each_set_bit(i, (unsigned long *)&cntr_mask, end) release_evntsel_nmi(x86_pmu_config_addr(i)); i = X86_PMC_IDX_MAX; perfctr_fail: end = i; for_each_set_bit(i, (unsigned long *)&cntr_mask, end) release_perfctr_nmi(x86_pmu_event_addr(i)); return false; } static void release_pmc_hardware(void) { u64 cntr_mask = get_possible_counter_mask(); int i; for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) { release_perfctr_nmi(x86_pmu_event_addr(i)); release_evntsel_nmi(x86_pmu_config_addr(i)); } } #else static bool reserve_pmc_hardware(void) { return true; } static void release_pmc_hardware(void) {} #endif bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask, unsigned long *fixed_cntr_mask) { u64 val, val_fail = -1, val_new= ~0; int i, reg, reg_fail = -1, ret = 0; int bios_fail = 0; int reg_safe = -1; /* * Check to see if the BIOS enabled any of the counters, if so * complain and bail. */ for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) { reg = x86_pmu_config_addr(i); ret = rdmsrq_safe(reg, &val); if (ret) goto msr_fail; if (val & ARCH_PERFMON_EVENTSEL_ENABLE) { bios_fail = 1; val_fail = val; reg_fail = reg; } else { reg_safe = i; } } if (*(u64 *)fixed_cntr_mask) { reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; ret = rdmsrq_safe(reg, &val); if (ret) goto msr_fail; for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) { if (fixed_counter_disabled(i, pmu)) continue; if (val & (0x03ULL << i*4)) { bios_fail = 1; val_fail = val; reg_fail = reg; } } } /* * If all the counters are enabled, the below test will always * fail. The tools will also become useless in this scenario. * Just fail and disable the hardware counters. */ if (reg_safe == -1) { reg = reg_safe; goto msr_fail; } /* * Read the current value, change it and read it back to see if it * matches, this is needed to detect certain hardware emulators * (qemu/kvm) that don't trap on the MSR access and always return 0s. */ reg = x86_pmu_event_addr(reg_safe); if (rdmsrq_safe(reg, &val)) goto msr_fail; val ^= 0xffffUL; ret = wrmsrq_safe(reg, val); ret |= rdmsrq_safe(reg, &val_new); if (ret || val != val_new) goto msr_fail; /* * We still allow the PMU driver to operate: */ if (bios_fail) { pr_cont("Broken BIOS detected, complain to your hardware vendor.\n"); pr_err(FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail); } return true; msr_fail: if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { pr_cont("PMU not available due to virtualization, using software events only.\n"); } else { pr_cont("Broken PMU hardware detected, using software events only.\n"); pr_err("Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); } return false; } static void hw_perf_event_destroy(struct perf_event *event) { x86_release_hardware(); atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) { hw_perf_event_destroy(event); /* undo the lbr/bts event accounting */ x86_del_exclusive(x86_lbr_exclusive_lbr); } static inline int x86_pmu_initialized(void) { return x86_pmu.handle_irq != NULL; } static inline int set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) { struct perf_event_attr *attr = &event->attr; unsigned int cache_type, cache_op, cache_result; u64 config, val; config = attr->config; cache_type = (config >> 0) & 0xff; if (cache_type >= PERF_COUNT_HW_CACHE_MAX) return -EINVAL; cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX); cache_op = (config >> 8) & 0xff; if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) return -EINVAL; cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX); cache_result = (config >> 16) & 0xff; if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX); val = hybrid_var(event->pmu, hw_cache_event_ids)[cache_type][cache_op][cache_result]; if (val == 0) return -ENOENT; if (val == -1) return -EINVAL; hwc->config |= val; attr->config1 = hybrid_var(event->pmu, hw_cache_extra_regs)[cache_type][cache_op][cache_result]; return x86_pmu_extra_regs(val, event); } int x86_reserve_hardware(void) { int err = 0; if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); if (atomic_read(&pmc_refcount) == 0) { if (!reserve_pmc_hardware()) { err = -EBUSY; } else { reserve_ds_buffers(); reserve_lbr_buffers(); } } if (!err) atomic_inc(&pmc_refcount); mutex_unlock(&pmc_reserve_mutex); } return err; } void x86_release_hardware(void) { if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { release_pmc_hardware(); release_ds_buffers(); release_lbr_buffers(); mutex_unlock(&pmc_reserve_mutex); } } /* * Check if we can create event of a certain type (that no conflicting events * are present). */ int x86_add_exclusive(unsigned int what) { int i; /* * When lbr_pt_coexist we allow PT to coexist with either LBR or BTS. * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) goto fail_unlock; } atomic_inc(&x86_pmu.lbr_exclusive[what]); mutex_unlock(&pmc_reserve_mutex); } out: atomic_inc(&active_events); return 0; fail_unlock: mutex_unlock(&pmc_reserve_mutex); return -EBUSY; } void x86_del_exclusive(unsigned int what) { atomic_dec(&active_events); /* * See the comment in x86_add_exclusive(). */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); } int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; u64 config; if (!is_sampling_event(event)) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); } if (attr->type == event->pmu->type) return x86_pmu_extra_regs(event->attr.config, event); if (attr->type == PERF_TYPE_HW_CACHE) return set_ext_hw_attr(hwc, event); if (attr->config >= x86_pmu.max_events) return -EINVAL; attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events); /* * The generic map: */ config = x86_pmu.event_map(attr->config); if (config == 0) return -ENOENT; if (config == -1LL) return -EINVAL; hwc->config |= config; return 0; } /* * check that branch_sample_type is compatible with * settings needed for precise_ip > 1 which implies * using the LBR to capture ALL taken branches at the * priv levels of the measurement */ static inline int precise_br_compat(struct perf_event *event) { u64 m = event->attr.branch_sample_type; u64 b = 0; /* must capture all branches */ if (!(m & PERF_SAMPLE_BRANCH_ANY)) return 0; m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_user) b |= PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_kernel) b |= PERF_SAMPLE_BRANCH_KERNEL; /* * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86 */ return m == b; } int x86_pmu_max_precise(struct pmu *pmu) { int precise = 0; if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { /* arch PEBS */ if (x86_pmu.arch_pebs) { precise = 2; if (hybrid(pmu, arch_pebs_cap).pdists) precise++; return precise; } /* legacy PEBS - support for constant skid */ precise++; /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; if (x86_pmu.pebs_prec_dist) precise++; } return precise; } int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { int precise = x86_pmu_max_precise(event->pmu); if (event->attr.precise_ip > precise) return -EOPNOTSUPP; /* There's no sense in having PEBS for non sampling events: */ if (!is_sampling_event(event)) return -EINVAL; } /* * check that PEBS LBR correction does not conflict with * whatever the user is asking with attr->branch_sample_type */ if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format < 2) { u64 *br_type = &event->attr.branch_sample_type; if (has_branch_stack(event)) { if (!precise_br_compat(event)) return -EOPNOTSUPP; /* branch_sample_type is compatible */ } else { /* * user did not specify branch_sample_type * * For PEBS fixups, we capture all * the branches at the priv level of the * event. */ *br_type = PERF_SAMPLE_BRANCH_ANY; if (!event->attr.exclude_user) *br_type |= PERF_SAMPLE_BRANCH_USER; if (!event->attr.exclude_kernel) *br_type |= PERF_SAMPLE_BRANCH_KERNEL; } } if (branch_sample_call_stack(event)) event->attach_state |= PERF_ATTACH_TASK_DATA; /* * Generate PMC IRQs: * (keep 'enabled' bit clear for now) */ event->hw.config = ARCH_PERFMON_EVENTSEL_INT; /* * Count user and OS events unless requested not to */ if (!event->attr.exclude_user) event->hw.config |= ARCH_PERFMON_EVENTSEL_USR; if (!event->attr.exclude_kernel) event->hw.config |= ARCH_PERFMON_EVENTSEL_OS; if (event->attr.type == event->pmu->type) event->hw.config |= x86_pmu_get_event_config(event); if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) { s64 left = event->attr.sample_period; x86_pmu.limit_period(event, &left); if (left > event->attr.sample_period) return -EINVAL; } /* sample_regs_user never support XMM registers */ if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK)) return -EINVAL; /* * Besides the general purpose registers, XMM registers may * be collected in PEBS on some platforms, e.g. Icelake */ if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) { if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS)) return -EINVAL; if (!event->attr.precise_ip) return -EINVAL; } return x86_setup_perfctr(event); } /* * Setup the hardware configuration for a given attr_type */ static int __x86_pmu_event_init(struct perf_event *event) { int err; if (!x86_pmu_initialized()) return -ENODEV; err = x86_reserve_hardware(); if (err) return err; atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; event->hw.last_cpu = -1; event->hw.last_tag = ~0ULL; event->hw.dyn_constraint = ~0ULL; /* mark unused */ event->hw.extra_reg.idx = EXTRA_REG_NONE; event->hw.branch_reg.idx = EXTRA_REG_NONE; return x86_pmu.hw_config(event); } void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) { struct hw_perf_event *hwc = &cpuc->events[idx]->hw; u64 val; if (!test_bit(idx, cpuc->active_mask)) continue; rdmsrq(x86_pmu_config_addr(idx), val); if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE)) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrq(x86_pmu_config_addr(idx), val); if (is_counter_pair(hwc)) wrmsrq(x86_pmu_config_addr(idx + 1), 0); } } struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data) { return static_call(x86_pmu_guest_get_msrs)(nr, data); } EXPORT_SYMBOL_FOR_KVM(perf_guest_get_msrs); /* * There may be PMI landing after enabled=0. The PMI hitting could be before or * after disable_all. * * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. * It will not be re-enabled in the NMI handler again, because enabled=0. After * handling the NMI, disable_all will be called, which will not change the * state either. If PMI hits after disable_all, the PMU is already disabled * before entering NMI handler. The NMI handler will not change the state * either. * * So either situation is harmless. */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu_initialized()) return; if (!cpuc->enabled) return; cpuc->n_added = 0; cpuc->enabled = 0; barrier(); static_call(x86_pmu_disable_all)(); } void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) { struct hw_perf_event *hwc = &cpuc->events[idx]->hw; if (!test_bit(idx, cpuc->active_mask)) continue; __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } } int is_x86_event(struct perf_event *event) { /* * For a non-hybrid platforms, the type of X86 pmu is * always PERF_TYPE_RAW. * For a hybrid platform, the PERF_PMU_CAP_EXTENDED_HW_TYPE * is a unique capability for the X86 PMU. * Use them to detect a X86 event. */ if (event->pmu->type == PERF_TYPE_RAW || event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_HW_TYPE) return true; return false; } struct pmu *x86_get_pmu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); /* * All CPUs of the hybrid type have been offline. * The x86_get_pmu() should not be invoked. */ if (WARN_ON_ONCE(!cpuc->pmu)) return &pmu; return cpuc->pmu; } /* * Event scheduler state: * * Assign events iterating over all events and counters, beginning * with events with least weights first. Keep the current iterator * state in struct sched_state. */ struct sched_state { int weight; int event; /* event index */ int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ int nr_gp; /* number of GP counters used */ u64 used; }; /* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */ #define SCHED_STATES_MAX 2 struct perf_sched { int max_weight; int max_events; int max_gp; int saved_states; struct event_constraint **constraints; struct sched_state state; struct sched_state saved[SCHED_STATES_MAX]; }; /* * Initialize iterator that runs through all events and counters. */ static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints, int num, int wmin, int wmax, int gpmax) { int idx; memset(sched, 0, sizeof(*sched)); sched->max_events = num; sched->max_weight = wmax; sched->max_gp = gpmax; sched->constraints = constraints; for (idx = 0; idx < num; idx++) { if (constraints[idx]->weight == wmin) break; } sched->state.event = idx; /* start with min weight */ sched->state.weight = wmin; sched->state.unassigned = num; } static void perf_sched_save_state(struct perf_sched *sched) { if (WARN_ON_ONCE(sched->saved_states >= SCHED_STATES_MAX)) return; sched->saved[sched->saved_states] = sched->state; sched->saved_states++; } static bool perf_sched_restore_state(struct perf_sched *sched) { if (!sched->saved_states) return false; sched->saved_states--; sched->state = sched->saved[sched->saved_states]; /* this assignment didn't work out */ /* XXX broken vs EVENT_PAIR */ sched->state.used &= ~BIT_ULL(sched->state.counter); /* try the next one */ sched->state.counter++; return true; } /* * Select a counter for the current event to schedule. Return true on * success. */ static bool __perf_sched_find_counter(struct perf_sched *sched) { struct event_constraint *c; int idx; if (!sched->state.unassigned) return false; if (sched->state.event >= sched->max_events) return false; c = sched->constraints[sched->state.event]; /* Prefer fixed purpose counters */ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { u64 mask = BIT_ULL(idx); if (sched->state.used & mask) continue; sched->state.used |= mask; goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { u64 mask = BIT_ULL(idx); if (c->flags & PERF_X86_EVENT_PAIR) mask |= mask << 1; if (sched->state.used & mask) continue; if (sched->state.nr_gp++ >= sched->max_gp) return false; sched->state.used |= mask; goto done; } return false; done: sched->state.counter = idx; if (c->overlap) perf_sched_save_state(sched); return true; } static bool perf_sched_find_counter(struct perf_sched *sched) { while (!__perf_sched_find_counter(sched)) { if (!perf_sched_restore_state(sched)) return false; } return true; } /* * Go through all unassigned events and find the next one to schedule. * Take events with the least weight first. Return true on success. */ static bool perf_sched_next_event(struct perf_sched *sched) { struct event_constraint *c; if (!sched->state.unassigned || !--sched->state.unassigned) return false; do { /* next event */ sched->state.event++; if (sched->state.event >= sched->max_events) { /* next weight */ sched->state.event = 0; sched->state.weight++; if (sched->state.weight > sched->max_weight) return false; } c = sched->constraints[sched->state.event]; } while (c->weight != sched->state.weight); sched->state.counter = 0; /* start with first counter */ return true; } /* * Assign a counter for each event. */ int perf_assign_events(struct event_constraint **constraints, int n, int wmin, int wmax, int gpmax, int *assign) { struct perf_sched sched; perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax); do { if (!perf_sched_find_counter(&sched)) break; /* failed */ if (assign) assign[sched.state.event] = sched.state.counter; } while (perf_sched_next_event(&sched)); return sched.state.unassigned; } EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c; struct perf_event *e; int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; u64 used_mask = 0; /* * Compute the number of events already present; see x86_pmu_add(), * validate_group() and x86_pmu_commit_txn(). For the former two * cpuc->n_events hasn't been updated yet, while for the latter * cpuc->n_txn contains the number of events added in the current * transaction. */ n0 = cpuc->n_events; if (cpuc->txn_flags & PERF_PMU_TXN_ADD) n0 -= cpuc->n_txn; static_call_cond(x86_pmu_start_scheduling)(cpuc); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { c = cpuc->event_constraint[i]; /* * Previously scheduled events should have a cached constraint, * while new events should not have one. */ WARN_ON_ONCE((c && i >= n0) || (!c && i < n0)); /* * Request constraints for new events; or for those events that * have a dynamic constraint -- for those the constraint can * change due to external factors (sibling state, allow_tfa). */ if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) { c = static_call(x86_pmu_get_event_constraints)(cpuc, i, cpuc->event_list[i]); cpuc->event_constraint[i] = c; } wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } /* * fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { u64 mask; hwc = &cpuc->event_list[i]->hw; c = cpuc->event_constraint[i]; /* never assigned */ if (hwc->idx == -1) break; /* constraint still honored */ if (!test_bit(hwc->idx, c->idxmsk)) break; mask = BIT_ULL(hwc->idx); if (is_counter_pair(hwc)) mask |= mask << 1; /* not already used */ if (used_mask & mask) break; used_mask |= mask; if (assign) assign[i] = hwc->idx; } /* slow path */ if (i != n) { int gpmax = x86_pmu_max_num_counters(cpuc->pmu); /* * Do not allow scheduling of more than half the available * generic counters. * * This helps avoid counter starvation of sibling thread by * ensuring at most half the counters cannot be in exclusive * mode. There is no designated counters for the limits. Any * N/2 counters can be used. This helps with events with * specific counter constraints. */ if (is_ht_workaround_enabled() && !cpuc->is_fake && READ_ONCE(cpuc->excl_cntrs->exclusive_present)) gpmax /= 2; /* * Reduce the amount of available counters to allow fitting * the extra Merge events needed by large increment events. */ if (x86_pmu.flags & PMU_FL_PAIR) { gpmax -= cpuc->n_pair; WARN_ON(gpmax <= 0); } unsched = perf_assign_events(cpuc->event_constraint, n, wmin, wmax, gpmax, assign); } /* * In case of success (unsched = 0), mark events as committed, * so we do not put_constraint() in case new events are added * and fail to be scheduled * * We invoke the lower level commit callback to lock the resource * * We do not need to do all of this in case we are called to * validate an event group (assign == NULL) */ if (!unsched && assign) { for (i = 0; i < n; i++) static_call_cond(x86_pmu_commit_scheduling)(cpuc, i, assign[i]); } else { for (i = n0; i < n; i++) { e = cpuc->event_list[i]; /* * release events that failed scheduling */ static_call_cond(x86_pmu_put_event_constraints)(cpuc, e); cpuc->event_constraint[i] = NULL; } } static_call_cond(x86_pmu_stop_scheduling)(cpuc); return unsched ? -EINVAL : 0; } static int add_nr_metric_event(struct cpu_hw_events *cpuc, struct perf_event *event) { if (is_metric_event(event)) { if (cpuc->n_metric == INTEL_TD_METRIC_NUM) return -EINVAL; cpuc->n_metric++; cpuc->n_txn_metric++; } return 0; } static void del_nr_metric_event(struct cpu_hw_events *cpuc, struct perf_event *event) { if (is_metric_event(event)) cpuc->n_metric--; } static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event, int max_count, int n) { union perf_capabilities intel_cap = hybrid(cpuc->pmu, intel_cap); if (intel_cap.perf_metrics && add_nr_metric_event(cpuc, event)) return -EINVAL; if (n >= max_count + cpuc->n_metric) return -EINVAL; cpuc->event_list[n] = event; if (is_counter_pair(&event->hw)) { cpuc->n_pair++; cpuc->n_txn_pair++; } return 0; } /* * dogrp: true if must collect siblings events (group) * returns total number of events and error code */ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp) { struct perf_event *event; int n, max_count; max_count = x86_pmu_num_counters(cpuc->pmu) + x86_pmu_num_counters_fixed(cpuc->pmu); /* current number of events already accepted */ n = cpuc->n_events; if (!cpuc->n_events) cpuc->pebs_output = 0; if (!cpuc->is_fake && leader->attr.precise_ip) { /* * For PEBS->PT, if !aux_event, the group leader (PT) went * away, the group was broken down and this singleton event * can't schedule any more. */ if (is_pebs_pt(leader) && !leader->aux_event) return -EINVAL; /* * pebs_output: 0: no PEBS so far, 1: PT, 2: DS */ if (cpuc->pebs_output && cpuc->pebs_output != is_pebs_pt(leader) + 1) return -EINVAL; cpuc->pebs_output = is_pebs_pt(leader) + 1; } if (is_x86_event(leader)) { if (collect_event(cpuc, leader, max_count, n)) return -EINVAL; n++; } if (!dogrp) return n; for_each_sibling_event(event, leader) { if (!is_x86_event(event) || event->state <= PERF_EVENT_STATE_OFF) continue; if (collect_event(cpuc, event, max_count, n)) return -EINVAL; n++; } return n; } static inline void x86_assign_hw_event(struct perf_event *event, struct cpu_hw_events *cpuc, int i) { struct hw_perf_event *hwc = &event->hw; int idx; idx = hwc->idx = cpuc->assign[i]; hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; static_call_cond(x86_pmu_assign)(event, idx); switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: case INTEL_PMC_IDX_FIXED_VLBR: hwc->config_base = 0; hwc->event_base = 0; break; case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: /* All the metric events are mapped onto the fixed counter 3. */ idx = INTEL_PMC_IDX_FIXED_SLOTS; fallthrough; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1: hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; hwc->event_base = x86_pmu_fixed_ctr_addr(idx - INTEL_PMC_IDX_FIXED); hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | INTEL_PMC_FIXED_RDPMC_BASE; break; default: hwc->config_base = x86_pmu_config_addr(hwc->idx); hwc->event_base = x86_pmu_event_addr(hwc->idx); hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx); break; } } /** * x86_perf_rdpmc_index - Return PMC counter used for event * @event: the perf_event to which the PMC counter was assigned * * The counter assigned to this performance event may change if interrupts * are enabled. This counter should thus never be used while interrupts are * enabled. Before this function is used to obtain the assigned counter the * event should be checked for validity using, for example, * perf_event_read_local(), within the same interrupt disabled section in * which this counter is planned to be used. * * Return: The index of the performance monitoring counter assigned to * @perf_event. */ int x86_perf_rdpmc_index(struct perf_event *event) { lockdep_assert_irqs_disabled(); return event->hw.event_base_rdpmc; } static inline int match_prev_assignment(struct perf_event *event, struct cpu_hw_events *cpuc, int i) { struct hw_perf_event *hwc = &event->hw; return hwc->idx == cpuc->assign[i] && hwc->last_cpu == smp_processor_id() && hwc->last_tag == cpuc->tags[i] && !is_acr_event_group(event); } static void x86_pmu_start(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; struct hw_perf_event *hwc; int i, added = cpuc->n_added; if (!x86_pmu_initialized()) return; if (cpuc->enabled) return; if (cpuc->n_added) { int n_running = cpuc->n_events - cpuc->n_added; /* * The late setup (after counters are scheduled) * is required for some cases, e.g., PEBS counters * snapshotting. Because an accurate counter index * is needed. */ static_call_cond(x86_pmu_late_setup)(); /* * apply assignment obtained either from * hw_perf_group_sched_in() or x86_pmu_enable() * * step1: save events moving to new counters */ for (i = 0; i < n_running; i++) { event = cpuc->event_list[i]; hwc = &event->hw; /* * we can avoid reprogramming counter if: * - assigned same counter as last time * - running on same CPU as last time * - no other event has used the counter since */ if (hwc->idx == -1 || match_prev_assignment(event, cpuc, i)) continue; /* * Ensure we don't accidentally enable a stopped * counter simply because we rescheduled. */ if (hwc->state & PERF_HES_STOPPED) hwc->state |= PERF_HES_ARCH; x86_pmu_stop(event, PERF_EF_UPDATE); cpuc->events[hwc->idx] = NULL; } /* * step2: reprogram moved events into new counters */ for (i = 0; i < cpuc->n_events; i++) { event = cpuc->event_list[i]; hwc = &event->hw; if (!match_prev_assignment(event, cpuc, i)) x86_assign_hw_event(event, cpuc, i); else if (i < n_running) continue; cpuc->events[hwc->idx] = event; if (hwc->state & PERF_HES_ARCH) { static_call(x86_pmu_set_period)(event); continue; } /* * if cpuc->enabled = 0, then no wrmsr as * per x86_pmu_enable_event() */ x86_pmu_start(event, PERF_EF_RELOAD); } cpuc->n_added = 0; perf_events_lapic_init(); } cpuc->enabled = 1; barrier(); static_call(x86_pmu_enable_all)(added); } DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); /* * Set the next IRQ period, based on the hwc->period_left value. * To be called with the event disabled in hw: */ int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0, idx = hwc->idx; if (unlikely(!hwc->event_base)) return 0; /* * If we are way outside a reasonable range then just skip forward: */ if (unlikely(left <= -period)) { left = period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } /* * Quirk: certain CPUs dont like it if just 1 hw_event is left: */ if (unlikely(left < 2)) left = 2; if (left > x86_pmu.max_period) left = x86_pmu.max_period; static_call_cond(x86_pmu_limit_period)(event, &left); this_cpu_write(pmc_prev_left[idx], left); /* * The hw event starts counting from this event offset, * mark it to be able to extra future deltas: */ local64_set(&hwc->prev_count, (u64)-left); wrmsrq(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* * Sign extend the Merge event counter's upper 16 bits since * we currently declare a 48-bit counter width */ if (is_counter_pair(hwc)) wrmsrq(x86_pmu_event_addr(idx + 1), 0xffff); perf_event_update_userpage(event); return ret; } void x86_pmu_enable_event(struct perf_event *event) { if (__this_cpu_read(cpu_hw_events.enabled)) __x86_pmu_enable_event(&event->hw, ARCH_PERFMON_EVENTSEL_ENABLE); } /* * Add a single event to the PMU. * * The event is added to the group of enabled events * but only if it can be scheduled with existing events. */ static int x86_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc; int assign[X86_PMC_IDX_MAX]; int n, n0, ret; hwc = &event->hw; n0 = cpuc->n_events; ret = n = collect_events(cpuc, event, false); if (ret < 0) goto out; hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (!(flags & PERF_EF_START)) hwc->state |= PERF_HES_ARCH; /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole. * * If commit fails, we'll call ->del() on all events * for which ->add() was called. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; ret = static_call(x86_pmu_schedule_events)(cpuc, n, assign); if (ret) goto out; /* * copy new assignment, now we know it is possible * will be used by hw_perf_enable() */ memcpy(cpuc->assign, assign, n*sizeof(int)); done_collect: /* * Commit the collect_events() state. See x86_pmu_del() and * x86_pmu_*_txn(). */ cpuc->n_events = n; cpuc->n_added += n - n0; cpuc->n_txn += n - n0; /* * This is before x86_pmu_enable() will call x86_pmu_start(), * so we enable LBRs before an event needs them etc.. */ static_call_cond(x86_pmu_add)(event); ret = 0; out: return ret; } static void x86_pmu_start(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = event->hw.idx; if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) return; if (WARN_ON_ONCE(idx == -1)) return; if (flags & PERF_EF_RELOAD) { WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); static_call(x86_pmu_set_period)(event); } event->hw.state = 0; __set_bit(idx, cpuc->active_mask); static_call(x86_pmu_enable)(event); perf_event_update_userpage(event); } void perf_event_print_debug(void) { u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed; unsigned long *cntr_mask, *fixed_cntr_mask; struct event_constraint *pebs_constraints; struct cpu_hw_events *cpuc; u64 pebs, debugctl; int cpu, idx; guard(irqsave)(); cpu = smp_processor_id(); cpuc = &per_cpu(cpu_hw_events, cpu); cntr_mask = hybrid(cpuc->pmu, cntr_mask); fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask); pebs_constraints = hybrid(cpuc->pmu, pebs_constraints); if (!*(u64 *)cntr_mask) return; if (x86_pmu.version >= 2) { rdmsrq(MSR_CORE_PERF_GLOBAL_CTRL, ctrl); rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, status); rdmsrq(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow); rdmsrq(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed); pr_info("\n"); pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl); pr_info("CPU#%d: status: %016llx\n", cpu, status); pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); if (pebs_constraints) { rdmsrq(MSR_IA32_PEBS_ENABLE, pebs); pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); } if (x86_pmu.lbr_nr) { rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl); pr_info("CPU#%d: debugctl: %016llx\n", cpu, debugctl); } } pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) { rdmsrq(x86_pmu_config_addr(idx), pmc_ctrl); rdmsrq(x86_pmu_event_addr(idx), pmc_count); prev_left = per_cpu(pmc_prev_left[idx], cpu); pr_info("CPU#%d: gen-PMC%d ctrl: %016llx\n", cpu, idx, pmc_ctrl); pr_info("CPU#%d: gen-PMC%d count: %016llx\n", cpu, idx, pmc_count); pr_info("CPU#%d: gen-PMC%d left: %016llx\n", cpu, idx, prev_left); } for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) { if (fixed_counter_disabled(idx, cpuc->pmu)) continue; rdmsrq(x86_pmu_fixed_ctr_addr(idx), pmc_count); pr_info("CPU#%d: fixed-PMC%d count: %016llx\n", cpu, idx, pmc_count); } } void x86_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; if (test_bit(hwc->idx, cpuc->active_mask)) { static_call(x86_pmu_disable)(event); __clear_bit(hwc->idx, cpuc->active_mask); WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; } if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { /* * Drain the remaining delta count out of a event * that we are disabling: */ static_call(x86_pmu_update)(event); hwc->state |= PERF_HES_UPTODATE; } } static void x86_pmu_del(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); union perf_capabilities intel_cap = hybrid(cpuc->pmu, intel_cap); int i; /* * If we're called during a txn, we only need to undo x86_pmu.add. * The events never got scheduled and ->cancel_txn will truncate * the event_list. * * XXX assumes any ->del() called during a TXN will only be on * an event added during that same TXN. */ if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto do_del; __set_bit(event->hw.idx, cpuc->dirty); /* * Not a TXN, therefore cleanup properly. */ x86_pmu_stop(event, PERF_EF_UPDATE); cpuc->events[event->hw.idx] = NULL; for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) break; } if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */ return; /* If we have a newly added event; make sure to decrease n_added. */ if (i >= cpuc->n_events - cpuc->n_added) --cpuc->n_added; static_call_cond(x86_pmu_put_event_constraints)(cpuc, event); /* Delete the array entry. */ while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; if (intel_cap.perf_metrics) del_nr_metric_event(cpuc, event); perf_event_update_userpage(event); do_del: /* * This is after x86_pmu_stop(); so we disable LBRs after any * event can need them etc.. */ static_call_cond(x86_pmu_del)(event); } int x86_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; struct cpu_hw_events *cpuc; struct perf_event *event; int idx, handled = 0; u64 last_period; u64 val; cpuc = this_cpu_ptr(&cpu_hw_events); /* * Some chipsets need to unmask the LVTPC in a particular spot * inside the nmi handler. As a result, the unmasking was pushed * into all the nmi handlers. * * This generic handler doesn't seem to have any issues where the * unmasking occurs so it was left at the top. */ apic_write(APIC_LVTPC, APIC_DM_NMI); for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) { if (!test_bit(idx, cpuc->active_mask)) continue; event = cpuc->events[idx]; last_period = event->hw.last_period; val = static_call(x86_pmu_update)(event); if (val & (1ULL << (x86_pmu.cntval_bits - 1))) continue; /* * event overflow */ handled++; if (!static_call(x86_pmu_set_period)(event)) continue; perf_sample_data_init(&data, 0, last_period); perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); perf_event_overflow(event, &data, regs); } if (handled) inc_perf_irq_stat(); return handled; } void perf_events_lapic_init(void) { if (!x86_pmu.apic || !x86_pmu_initialized()) return; /* * Always use NMI for PMU */ apic_write(APIC_LVTPC, APIC_DM_NMI); } #ifdef CONFIG_PERF_GUEST_MEDIATED_PMU void perf_load_guest_lvtpc(u32 guest_lvtpc) { u32 masked = guest_lvtpc & APIC_LVT_MASKED; apic_write(APIC_LVTPC, APIC_DM_FIXED | PERF_GUEST_MEDIATED_PMI_VECTOR | masked); this_cpu_write(guest_lvtpc_loaded, true); } EXPORT_SYMBOL_FOR_KVM(perf_load_guest_lvtpc); void perf_put_guest_lvtpc(void) { this_cpu_write(guest_lvtpc_loaded, false); apic_write(APIC_LVTPC, APIC_DM_NMI); } EXPORT_SYMBOL_FOR_KVM(perf_put_guest_lvtpc); #endif /* CONFIG_PERF_GUEST_MEDIATED_PMU */ static int perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { u64 start_clock; u64 finish_clock; int ret; /* * Ignore all NMIs when the CPU's LVTPC is configured to route PMIs to * PERF_GUEST_MEDIATED_PMI_VECTOR, i.e. when an NMI time can't be due * to a PMI. Attempting to handle a PMI while the guest's context is * loaded will generate false positives and clobber guest state. Note, * the LVTPC is switched to/from the dedicated mediated PMI IRQ vector * while host events are quiesced. */ if (this_cpu_read(guest_lvtpc_loaded)) return NMI_DONE; /* * All PMUs/events that share this PMI handler should make sure to * increment active_events for their events. */ if (!atomic_read(&active_events)) return NMI_DONE; start_clock = sched_clock(); ret = static_call(x86_pmu_handle_irq)(regs); finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); return ret; } NOKPROBE_SYMBOL(perf_event_nmi_handler); struct event_constraint emptyconstraint; struct event_constraint unconstrained; static int x86_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int i; for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) cpuc->kfree_on_online[i] = NULL; if (x86_pmu.cpu_prepare) return x86_pmu.cpu_prepare(cpu); return 0; } static int x86_pmu_dead_cpu(unsigned int cpu) { if (x86_pmu.cpu_dead) x86_pmu.cpu_dead(cpu); return 0; } static int x86_pmu_online_cpu(unsigned int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int i; for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) { kfree(cpuc->kfree_on_online[i]); cpuc->kfree_on_online[i] = NULL; } return 0; } static int x86_pmu_starting_cpu(unsigned int cpu) { if (x86_pmu.cpu_starting) x86_pmu.cpu_starting(cpu); return 0; } static int x86_pmu_dying_cpu(unsigned int cpu) { if (x86_pmu.cpu_dying) x86_pmu.cpu_dying(cpu); return 0; } static void __init pmu_check_apic(void) { if (boot_cpu_has(X86_FEATURE_APIC)) return; x86_pmu.apic = 0; pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); pr_info("no hardware sampling interrupt available.\n"); /* * If we have a PMU initialized but no APIC * interrupts, we cannot sample hardware * events (user-space has to fall back and * sample via a hrtimer based software event): */ pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; } static struct attribute_group x86_pmu_format_group __ro_after_init = { .name = "format", .attrs = NULL, }; ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_attr *pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); u64 config = 0; if (pmu_attr->id < x86_pmu.max_events) config = x86_pmu.event_map(pmu_attr->id); /* string trumps id */ if (pmu_attr->event_str) return sprintf(page, "%s\n", pmu_attr->event_str); return x86_pmu.events_sysfs_show(page, config); } EXPORT_SYMBOL_GPL(events_sysfs_show); ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_ht_attr *pmu_attr = container_of(attr, struct perf_pmu_events_ht_attr, attr); /* * Report conditional events depending on Hyper-Threading. * * This is overly conservative as usually the HT special * handling is not needed if the other CPU thread is idle. * * Note this does not (and cannot) handle the case when thread * siblings are invisible, for example with virtualization * if they are owned by some other guest. The user tool * has to re-read when a thread sibling gets onlined later. */ return sprintf(page, "%s", topology_max_smt_threads() > 1 ? pmu_attr->event_str_ht : pmu_attr->event_str_noht); } ssize_t events_hybrid_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_hybrid_attr *pmu_attr = container_of(attr, struct perf_pmu_events_hybrid_attr, attr); struct x86_hybrid_pmu *pmu; const char *str, *next_str; int i; if (hweight64(pmu_attr->pmu_type) == 1) return sprintf(page, "%s", pmu_attr->event_str); /* * Hybrid PMUs may support the same event name, but with different * event encoding, e.g., the mem-loads event on an Atom PMU has * different event encoding from a Core PMU. * * The event_str includes all event encodings. Each event encoding * is divided by ";". The order of the event encodings must follow * the order of the hybrid PMU index. */ pmu = container_of(dev_get_drvdata(dev), struct x86_hybrid_pmu, pmu); str = pmu_attr->event_str; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { if (!(x86_pmu.hybrid_pmu[i].pmu_type & pmu_attr->pmu_type)) continue; if (x86_pmu.hybrid_pmu[i].pmu_type & pmu->pmu_type) { next_str = strchr(str, ';'); if (next_str) return snprintf(page, next_str - str + 1, "%s", str); else return sprintf(page, "%s", str); } str = strchr(str, ';'); str++; } return 0; } EXPORT_SYMBOL_GPL(events_hybrid_sysfs_show); EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); EVENT_ATTR(cache-references, CACHE_REFERENCES ); EVENT_ATTR(cache-misses, CACHE_MISSES ); EVENT_ATTR(branch-instructions, BRANCH_INSTRUCTIONS ); EVENT_ATTR(branch-misses, BRANCH_MISSES ); EVENT_ATTR(bus-cycles, BUS_CYCLES ); EVENT_ATTR(stalled-cycles-frontend, STALLED_CYCLES_FRONTEND ); EVENT_ATTR(stalled-cycles-backend, STALLED_CYCLES_BACKEND ); EVENT_ATTR(ref-cycles, REF_CPU_CYCLES ); static struct attribute *empty_attrs; static struct attribute *events_attr[] = { EVENT_PTR(CPU_CYCLES), EVENT_PTR(INSTRUCTIONS), EVENT_PTR(CACHE_REFERENCES), EVENT_PTR(CACHE_MISSES), EVENT_PTR(BRANCH_INSTRUCTIONS), EVENT_PTR(BRANCH_MISSES), EVENT_PTR(BUS_CYCLES), EVENT_PTR(STALLED_CYCLES_FRONTEND), EVENT_PTR(STALLED_CYCLES_BACKEND), EVENT_PTR(REF_CPU_CYCLES), NULL, }; /* * Remove all undefined events (x86_pmu.event_map(id) == 0) * out of events_attr attributes. */ static umode_t is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct perf_pmu_events_attr *pmu_attr; if (idx >= x86_pmu.max_events) return 0; pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); /* str trumps id */ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0; } static struct attribute_group x86_pmu_events_group __ro_after_init = { .name = "events", .attrs = events_attr, .is_visible = is_visible, }; ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) { u64 umask = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; u64 cmask = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24; bool edge = (config & ARCH_PERFMON_EVENTSEL_EDGE); bool pc = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL); bool any = (config & ARCH_PERFMON_EVENTSEL_ANY); bool inv = (config & ARCH_PERFMON_EVENTSEL_INV); ssize_t ret; /* * We have whole page size to spend and just little data * to write, so we can safely use sprintf. */ ret = sprintf(page, "event=0x%02llx", event); if (umask) ret += sprintf(page + ret, ",umask=0x%02llx", umask); if (edge) ret += sprintf(page + ret, ",edge"); if (pc) ret += sprintf(page + ret, ",pc"); if (any) ret += sprintf(page + ret, ",any"); if (inv) ret += sprintf(page + ret, ",inv"); if (cmask) ret += sprintf(page + ret, ",cmask=0x%02llx", cmask); ret += sprintf(page + ret, "\n"); return ret; } static struct attribute_group x86_pmu_attr_group; static struct attribute_group x86_pmu_caps_group; static void x86_pmu_static_call_update(void) { static_call_update(x86_pmu_handle_irq, x86_pmu.handle_irq); static_call_update(x86_pmu_disable_all, x86_pmu.disable_all); static_call_update(x86_pmu_enable_all, x86_pmu.enable_all); static_call_update(x86_pmu_enable, x86_pmu.enable); static_call_update(x86_pmu_disable, x86_pmu.disable); static_call_update(x86_pmu_assign, x86_pmu.assign); static_call_update(x86_pmu_add, x86_pmu.add); static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); static_call_update(x86_pmu_set_period, x86_pmu.set_period); static_call_update(x86_pmu_update, x86_pmu.update); static_call_update(x86_pmu_limit_period, x86_pmu.limit_period); static_call_update(x86_pmu_schedule_events, x86_pmu.schedule_events); static_call_update(x86_pmu_get_event_constraints, x86_pmu.get_event_constraints); static_call_update(x86_pmu_put_event_constraints, x86_pmu.put_event_constraints); static_call_update(x86_pmu_start_scheduling, x86_pmu.start_scheduling); static_call_update(x86_pmu_commit_scheduling, x86_pmu.commit_scheduling); static_call_update(x86_pmu_stop_scheduling, x86_pmu.stop_scheduling); static_call_update(x86_pmu_sched_task, x86_pmu.sched_task); static_call_update(x86_pmu_drain_pebs, x86_pmu.drain_pebs); static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases); static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs); static_call_update(x86_pmu_filter, x86_pmu.filter); static_call_update(x86_pmu_late_setup, x86_pmu.late_setup); static_call_update(x86_pmu_pebs_enable, x86_pmu.pebs_enable); static_call_update(x86_pmu_pebs_disable, x86_pmu.pebs_disable); static_call_update(x86_pmu_pebs_enable_all, x86_pmu.pebs_enable_all); static_call_update(x86_pmu_pebs_disable_all, x86_pmu.pebs_disable_all); } static void _x86_pmu_read(struct perf_event *event) { static_call(x86_pmu_update)(event); } void x86_pmu_show_pmu_cap(struct pmu *pmu) { pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic counters: %d\n", x86_pmu_num_counters(pmu)); pr_info("... generic bitmap: %016llx\n", hybrid(pmu, cntr_mask64)); pr_info("... fixed-purpose counters: %d\n", x86_pmu_num_counters_fixed(pmu)); pr_info("... fixed-purpose bitmap: %016llx\n", hybrid(pmu, fixed_cntr_mask64)); pr_info("... value mask: %016llx\n", x86_pmu.cntval_mask); pr_info("... max period: %016llx\n", x86_pmu.max_period); pr_info("... global_ctrl mask: %016llx\n", hybrid(pmu, intel_ctrl)); } static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; int err; pr_info("Performance Events: "); switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: err = intel_pmu_init(); break; case X86_VENDOR_AMD: err = amd_pmu_init(); break; case X86_VENDOR_HYGON: err = amd_pmu_init(); x86_pmu.name = "HYGON"; break; case X86_VENDOR_ZHAOXIN: case X86_VENDOR_CENTAUR: err = zhaoxin_pmu_init(); break; default: err = -ENOTSUPP; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); err = 0; goto out_bad_pmu; } pmu_check_apic(); /* sanity check that the hardware exists or is emulated */ if (!check_hw_exists(&pmu, x86_pmu.cntr_mask, x86_pmu.fixed_cntr_mask)) goto out_bad_pmu; pr_cont("%s PMU driver.\n", x86_pmu.name); /* enable userspace RDPMC usage by default */ x86_pmu.attr_rdpmc = X86_USER_RDPMC_CONDITIONAL_ENABLE; for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); if (!x86_pmu.intel_ctrl) x86_pmu.intel_ctrl = x86_pmu.cntr_mask64; if (!x86_pmu.config_mask) x86_pmu.config_mask = X86_RAW_EVENT_MASK; perf_events_lapic_init(); register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI"); unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, x86_pmu.cntr_mask64, 0, x86_pmu_num_counters(NULL), 0, 0); x86_pmu_format_group.attrs = x86_pmu.format_attrs; if (!x86_pmu.events_sysfs_show) x86_pmu_events_group.attrs = &empty_attrs; pmu.attr_update = x86_pmu.attr_update; if (!is_hybrid()) x86_pmu_show_pmu_cap(NULL); if (!x86_pmu.read) x86_pmu.read = _x86_pmu_read; if (!x86_pmu.guest_get_msrs) x86_pmu.guest_get_msrs = (void *)&__static_call_return0; if (!x86_pmu.set_period) x86_pmu.set_period = x86_perf_event_set_period; if (!x86_pmu.update) x86_pmu.update = x86_perf_event_update; x86_pmu_static_call_update(); /* * Install callbacks. Core will call them for each online * cpu. */ err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "perf/x86:prepare", x86_pmu_prepare_cpu, x86_pmu_dead_cpu); if (err) return err; err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING, "perf/x86:starting", x86_pmu_starting_cpu, x86_pmu_dying_cpu); if (err) goto out; err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "perf/x86:online", x86_pmu_online_cpu, NULL); if (err) goto out1; if (!is_hybrid()) { err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); if (err) goto out2; } else { struct x86_hybrid_pmu *hybrid_pmu; int i, j; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { hybrid_pmu = &x86_pmu.hybrid_pmu[i]; hybrid_pmu->pmu = pmu; hybrid_pmu->pmu.type = -1; hybrid_pmu->pmu.attr_update = x86_pmu.attr_update; hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE; err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name, (hybrid_pmu->pmu_type == hybrid_big) ? PERF_TYPE_RAW : -1); if (err) break; } if (i < x86_pmu.num_hybrid_pmus) { for (j = 0; j < i; j++) perf_pmu_unregister(&x86_pmu.hybrid_pmu[j].pmu); pr_warn("Failed to register hybrid PMUs\n"); kfree(x86_pmu.hybrid_pmu); x86_pmu.hybrid_pmu = NULL; x86_pmu.num_hybrid_pmus = 0; goto out2; } } return 0; out2: cpuhp_remove_state(CPUHP_AP_PERF_X86_ONLINE); out1: cpuhp_remove_state(CPUHP_AP_PERF_X86_STARTING); out: cpuhp_remove_state(CPUHP_PERF_X86_PREPARE); out_bad_pmu: memset(&x86_pmu, 0, sizeof(x86_pmu)); return err; } early_initcall(init_hw_perf_events); static void x86_pmu_read(struct perf_event *event) { static_call(x86_pmu_read)(event); } /* * Start group events scheduling transaction * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time * * We only support PERF_PMU_TXN_ADD transactions. Save the * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD * transactions. */ static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); WARN_ON_ONCE(cpuc->txn_flags); /* txn already in flight */ cpuc->txn_flags = txn_flags; if (txn_flags & ~PERF_PMU_TXN_ADD) return; perf_pmu_disable(pmu); __this_cpu_write(cpu_hw_events.n_txn, 0); __this_cpu_write(cpu_hw_events.n_txn_pair, 0); __this_cpu_write(cpu_hw_events.n_txn_metric, 0); } /* * Stop group events scheduling transaction * Clear the flag and pmu::enable() will perform the * schedulability test. */ static void x86_pmu_cancel_txn(struct pmu *pmu) { unsigned int txn_flags; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ txn_flags = cpuc->txn_flags; cpuc->txn_flags = 0; if (txn_flags & ~PERF_PMU_TXN_ADD) return; /* * Truncate collected array by the number of events added in this * transaction. See x86_pmu_add() and x86_pmu_*_txn(). */ __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn)); __this_cpu_sub(cpu_hw_events.n_pair, __this_cpu_read(cpu_hw_events.n_txn_pair)); __this_cpu_sub(cpu_hw_events.n_metric, __this_cpu_read(cpu_hw_events.n_txn_metric)); perf_pmu_enable(pmu); } /* * Commit group events scheduling transaction * Perform the group schedulability test as a whole * Return 0 if success * * Does not cancel the transaction on failure; expects the caller to do this. */ static int x86_pmu_commit_txn(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int assign[X86_PMC_IDX_MAX]; int n, ret; WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) { cpuc->txn_flags = 0; return 0; } n = cpuc->n_events; if (!x86_pmu_initialized()) return -EAGAIN; ret = static_call(x86_pmu_schedule_events)(cpuc, n, assign); if (ret) return ret; /* * copy new assignment, now we know it is possible * will be used by hw_perf_enable() */ memcpy(cpuc->assign, assign, n*sizeof(int)); cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; } /* * a fake_cpuc is used to validate event groups. Due to * the extra reg logic, we need to also allocate a fake * per_core and per_cpu structure. Otherwise, group events * using extra reg may conflict without the kernel being * able to catch this when the last event gets added to * the group. */ static void free_fake_cpuc(struct cpu_hw_events *cpuc) { intel_cpuc_finish(cpuc); kfree(cpuc); } static struct cpu_hw_events *allocate_fake_cpuc(struct pmu *event_pmu) { struct cpu_hw_events *cpuc; int cpu; cpuc = kzalloc_obj(*cpuc); if (!cpuc) return ERR_PTR(-ENOMEM); cpuc->is_fake = 1; if (is_hybrid()) { struct x86_hybrid_pmu *h_pmu; h_pmu = hybrid_pmu(event_pmu); if (cpumask_empty(&h_pmu->supported_cpus)) goto error; cpu = cpumask_first(&h_pmu->supported_cpus); } else cpu = raw_smp_processor_id(); cpuc->pmu = event_pmu; if (intel_cpuc_prepare(cpuc, cpu)) goto error; return cpuc; error: free_fake_cpuc(cpuc); return ERR_PTR(-ENOMEM); } /* * validate that we can schedule this event */ static int validate_event(struct perf_event *event) { struct cpu_hw_events *fake_cpuc; struct event_constraint *c; int ret = 0; fake_cpuc = allocate_fake_cpuc(event->pmu); if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); c = x86_pmu.get_event_constraints(fake_cpuc, 0, event); if (!c || !c->weight) ret = -EINVAL; if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(fake_cpuc, event); free_fake_cpuc(fake_cpuc); return ret; } /* * validate a single event group * * validation include: * - check events are compatible which each other * - events do not compete for the same counter * - number of events <= number of counters * * validation ensures the group can be loaded onto the * PMU if it was the only group available. */ static int validate_group(struct perf_event *event) { struct perf_event *leader = event->group_leader; struct cpu_hw_events *fake_cpuc; int ret = -EINVAL, n; /* * Reject events from different hybrid PMUs. */ if (is_hybrid()) { struct perf_event *sibling; struct pmu *pmu = NULL; if (is_x86_event(leader)) pmu = leader->pmu; for_each_sibling_event(sibling, leader) { if (!is_x86_event(sibling)) continue; if (!pmu) pmu = sibling->pmu; else if (pmu != sibling->pmu) return ret; } } fake_cpuc = allocate_fake_cpuc(event->pmu); if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); /* * the event is not yet connected with its * siblings therefore we must first collect * existing siblings, then add the new event * before we can simulate the scheduling */ n = collect_events(fake_cpuc, leader, true); if (n < 0) goto out; fake_cpuc->n_events = n; n = collect_events(fake_cpuc, event, false); if (n < 0) goto out; fake_cpuc->n_events = 0; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out: free_fake_cpuc(fake_cpuc); return ret; } static int x86_pmu_event_init(struct perf_event *event) { struct x86_hybrid_pmu *pmu = NULL; int err; if ((event->attr.type != event->pmu->type) && (event->attr.type != PERF_TYPE_HARDWARE) && (event->attr.type != PERF_TYPE_HW_CACHE)) return -ENOENT; if (is_hybrid() && (event->cpu != -1)) { pmu = hybrid_pmu(event->pmu); if (!cpumask_test_cpu(event->cpu, &pmu->supported_cpus)) return -ENOENT; } err = __x86_pmu_event_init(event); if (!err) { if (event->group_leader != event) err = validate_group(event); else err = validate_event(event); } if (err) { if (event->destroy) event->destroy(event); event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; return err; } void perf_clear_dirty_counters(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; /* Don't need to clear the assigned counter. */ for (i = 0; i < cpuc->n_events; i++) __clear_bit(cpuc->assign[i], cpuc->dirty); if (bitmap_empty(cpuc->dirty, X86_PMC_IDX_MAX)) return; for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) { if (i >= INTEL_PMC_IDX_FIXED) { /* Metrics and fake events don't have corresponding HW counters. */ if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask))) continue; wrmsrq(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0); } else { wrmsrq(x86_pmu_event_addr(i), 0); } } bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX); } static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; /* * This function relies on not being called concurrently in two * tasks in the same mm. Otherwise one task could observe * perf_rdpmc_allowed > 1 and return all the way back to * userspace with CR4.PCE clear while another task is still * doing on_each_cpu_mask() to propagate CR4.PCE. * * For now, this can't happen because all callers hold mmap_lock * for write. If this changes, we'll need a different solution. */ mmap_assert_write_locked(mm); if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1) on_each_cpu_mask(mm_cpumask(mm), cr4_update_pce, NULL, 1); } static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) on_each_cpu_mask(mm_cpumask(mm), cr4_update_pce, NULL, 1); } static int x86_pmu_event_idx(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; if (!(hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) return 0; if (is_metric_idx(hwc->idx)) return INTEL_PMC_FIXED_RDPMC_METRICS + 1; else return hwc->event_base_rdpmc + 1; } static ssize_t get_attr_rdpmc(struct device *cdev, struct device_attribute *attr, char *buf) { return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc); } /* * Behaviors of rdpmc value: * - rdpmc = 0 * global user space rdpmc and counter level's user space rdpmc of all * counters are both disabled. * - rdpmc = 1 * global user space rdpmc is enabled in mmap enabled time window and * counter level's user space rdpmc is enabled for only non system-wide * events. Counter level's user space rdpmc of system-wide events is * still disabled by default. This won't introduce counter data leak for * non system-wide events since their count data would be cleared when * context switches. * - rdpmc = 2 * global user space rdpmc and counter level's user space rdpmc of all * counters are enabled unconditionally. * * Suppose the rdpmc value won't be changed frequently, don't dynamically * reschedule events to make the new rpdmc value take effect on active perf * events immediately, the new rdpmc value would only impact the new * activated perf events. This makes code simpler and cleaner. */ static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { static DEFINE_MUTEX(rdpmc_mutex); unsigned long val; ssize_t ret; ret = kstrtoul(buf, 0, &val); if (ret) return ret; if (val > 2) return -EINVAL; if (x86_pmu.attr_rdpmc_broken) return -ENOTSUPP; guard(mutex)(&rdpmc_mutex); if (val != x86_pmu.attr_rdpmc) { /* * Changing into or out of never available or always available, * aka perf-event-bypassing mode. This path is extremely slow, * but only root can trigger it, so it's okay. */ if (val == 0) static_branch_inc(&rdpmc_never_available_key); else if (x86_pmu.attr_rdpmc == X86_USER_RDPMC_NEVER_ENABLE) static_branch_dec(&rdpmc_never_available_key); if (val == 2) static_branch_inc(&rdpmc_always_available_key); else if (x86_pmu.attr_rdpmc == X86_USER_RDPMC_ALWAYS_ENABLE) static_branch_dec(&rdpmc_always_available_key); on_each_cpu(cr4_update_pce, NULL, 1); x86_pmu.attr_rdpmc = val; } return count; } static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc); static struct attribute *x86_pmu_attrs[] = { &dev_attr_rdpmc.attr, NULL, }; static struct attribute_group x86_pmu_attr_group __ro_after_init = { .attrs = x86_pmu_attrs, }; static ssize_t max_precise_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct pmu *pmu = dev_get_drvdata(cdev); return snprintf(buf, PAGE_SIZE, "%d\n", x86_pmu_max_precise(pmu)); } static DEVICE_ATTR_RO(max_precise); static struct attribute *x86_pmu_caps_attrs[] = { &dev_attr_max_precise.attr, NULL }; static struct attribute_group x86_pmu_caps_group __ro_after_init = { .name = "caps", .attrs = x86_pmu_caps_attrs, }; static const struct attribute_group *x86_pmu_attr_groups[] = { &x86_pmu_attr_group, &x86_pmu_format_group, &x86_pmu_events_group, &x86_pmu_caps_group, NULL, }; static void x86_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, struct task_struct *task, bool sched_in) { static_call_cond(x86_pmu_sched_task)(pmu_ctx, task, sched_in); } void perf_check_microcode(void) { if (x86_pmu.check_microcode) x86_pmu.check_microcode(); } static int x86_pmu_check_period(struct perf_event *event, u64 value) { if (x86_pmu.check_period && x86_pmu.check_period(event, value)) return -EINVAL; if (value && x86_pmu.limit_period) { s64 left = value; x86_pmu.limit_period(event, &left); if (left > value) return -EINVAL; } return 0; } static int x86_pmu_aux_output_match(struct perf_event *event) { if (!(pmu.capabilities & PERF_PMU_CAP_AUX_OUTPUT)) return 0; if (x86_pmu.aux_output_match) return x86_pmu.aux_output_match(event); return 0; } static bool x86_pmu_filter(struct pmu *pmu, int cpu) { bool ret = false; static_call_cond(x86_pmu_filter)(pmu, cpu, &ret); return ret; } static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, .attr_groups = x86_pmu_attr_groups, .event_init = x86_pmu_event_init, .event_mapped = x86_pmu_event_mapped, .event_unmapped = x86_pmu_event_unmapped, .add = x86_pmu_add, .del = x86_pmu_del, .start = x86_pmu_start, .stop = x86_pmu_stop, .read = x86_pmu_read, .start_txn = x86_pmu_start_txn, .cancel_txn = x86_pmu_cancel_txn, .commit_txn = x86_pmu_commit_txn, .event_idx = x86_pmu_event_idx, .sched_task = x86_pmu_sched_task, .check_period = x86_pmu_check_period, .aux_output_match = x86_pmu_aux_output_match, .filter = x86_pmu_filter, }; void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { struct cyc2ns_data data; u64 offset; userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_rdpmc = !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT); userpg->pmc_width = x86_pmu.cntval_bits; if (!using_native_sched_clock() || !sched_clock_stable()) return; cyc2ns_read_begin(&data); offset = data.cyc2ns_offset + __sched_clock_offset; /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. */ userpg->cap_user_time = 1; userpg->time_mult = data.cyc2ns_mul; userpg->time_shift = data.cyc2ns_shift; userpg->time_offset = offset - now; /* * cap_user_time_zero doesn't make sense when we're using a different * time base for the records. */ if (!event->attr.use_clockid) { userpg->cap_user_time_zero = 1; userpg->time_zero = offset; } cyc2ns_read_end(); } /* * Determine whether the regs were taken from an irq/exception handler rather * than from perf_arch_fetch_caller_regs(). */ static bool perf_hw_regs(struct pt_regs *regs) { return regs->flags & X86_EFLAGS_FIXED; } void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct unwind_state state; unsigned long addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ return; } if (perf_hw_regs(regs)) { if (perf_callchain_store(entry, regs->ip)) return; unwind_start(&state, current, regs, NULL); } else { unwind_start(&state, current, NULL, (void *)regs->sp); } for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; } } static inline int valid_user_frame(const void __user *fp, unsigned long size) { return __access_ok(fp, size); } static unsigned long get_segment_base(unsigned int segment) { struct desc_struct *desc; unsigned int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; /* * If we're not in a valid context with a real (not just lazy) * user mm, then don't even try. */ if (!nmi_uaccess_okay()) return 0; /* IRQs are off, so this synchronizes with smp_store_release */ ldt = smp_load_acquire(¤t->mm->context.ldt); if (!ldt || idx >= ldt->nr_entries) return 0; desc = &ldt->entries[idx]; #else return 0; #endif } else { if (idx >= GDT_ENTRIES) return 0; desc = raw_cpu_ptr(gdt_page.gdt) + idx; } return get_desc_base(desc); } #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry) { /* 32-bit process in 64-bit kernel. */ unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const struct stack_frame_ia32 __user *fp; u32 ret_addr; if (user_64bit_mode(regs)) return 0; cs_base = get_segment_base(regs->cs); ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); /* see perf_callchain_user() below for why we do this */ if (is_uprobe_at_func_entry(regs) && !get_user(ret_addr, (const u32 __user *)regs->sp)) perf_callchain_store(entry, ret_addr); while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; if (__get_user(frame.next_frame, &fp->next_frame)) break; if (__get_user(frame.return_address, &fp->return_address)) break; perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } pagefault_enable(); return 1; } #else static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry) { return 0; } #endif void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; const struct stack_frame __user *fp; unsigned long ret_addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ return; } /* * We don't know what to do with VM86 stacks.. ignore them for now. */ if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; fp = (void __user *)regs->bp; perf_callchain_store(entry, regs->ip); if (!nmi_uaccess_okay()) return; if (perf_callchain_user32(regs, entry)) return; pagefault_disable(); /* * If we are called from uprobe handler, and we are indeed at the very * entry to user function (which is normally a `push %rbp` instruction, * under assumption of application being compiled with frame pointers), * we should read return address from *regs->sp before proceeding * to follow frame pointers, otherwise we'll skip immediate caller * as %rbp is not yet setup. */ if (is_uprobe_at_func_entry(regs) && !get_user(ret_addr, (const unsigned long __user *)regs->sp)) perf_callchain_store(entry, ret_addr); while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; if (__get_user(frame.next_frame, &fp->next_frame)) break; if (__get_user(frame.return_address, &fp->return_address)) break; perf_callchain_store(entry, frame.return_address); fp = (void __user *)frame.next_frame; } pagefault_enable(); } /* * Deal with code segment offsets for the various execution modes: * * VM86 - the good olde 16 bit days, where the linear address is * 20 bits and we use regs->ip + 0x10 * regs->cs. * * IA32 - Where we need to look at GDT/LDT segment descriptor tables * to figure out what the 32bit base address is. * * X32 - has TIF_X32 set, but is running in x86_64 * * X86_64 - CS,DS,SS,ES are all zero based. */ static unsigned long code_segment_base(struct pt_regs *regs) { /* * For IA32 we look at the GDT/LDT segment base to convert the * effective IP to a linear address. */ #ifdef CONFIG_X86_32 /* * If we are in VM86 mode, add the segment offset to convert to a * linear address. */ if (regs->flags & X86_VM_MASK) return 0x10 * regs->cs; if (user_mode(regs) && regs->cs != __USER_CS) return get_segment_base(regs->cs); #else if (user_mode(regs) && !user_64bit_mode(regs) && regs->cs != __USER32_CS) return get_segment_base(regs->cs); #endif return 0; } unsigned long perf_arch_instruction_pointer(struct pt_regs *regs) { return regs->ip + code_segment_base(regs); } static unsigned long common_misc_flags(struct pt_regs *regs) { if (regs->flags & PERF_EFLAGS_EXACT) return PERF_RECORD_MISC_EXACT_IP; return 0; } static unsigned long guest_misc_flags(struct pt_regs *regs) { unsigned long guest_state = perf_guest_state(); if (!(guest_state & PERF_GUEST_ACTIVE)) return 0; if (guest_state & PERF_GUEST_USER) return PERF_RECORD_MISC_GUEST_USER; else return PERF_RECORD_MISC_GUEST_KERNEL; } static unsigned long host_misc_flags(struct pt_regs *regs) { if (user_mode(regs)) return PERF_RECORD_MISC_USER; else return PERF_RECORD_MISC_KERNEL; } unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) { unsigned long flags = common_misc_flags(regs); flags |= guest_misc_flags(regs); return flags; } unsigned long perf_arch_misc_flags(struct pt_regs *regs) { unsigned long flags = common_misc_flags(regs); flags |= host_misc_flags(regs); return flags; } void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) { /* This API doesn't currently support enumerating hybrid PMUs. */ if (WARN_ON_ONCE(cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) || !x86_pmu_initialized()) { memset(cap, 0, sizeof(*cap)); return; } /* * Note, hybrid CPU models get tracked as having hybrid PMUs even when * all E-cores are disabled via BIOS. When E-cores are disabled, the * base PMU holds the correct number of counters for P-cores. */ cap->version = x86_pmu.version; cap->num_counters_gp = x86_pmu_num_counters(NULL); cap->num_counters_fixed = x86_pmu_num_counters_fixed(NULL); cap->bit_width_gp = cap->num_counters_gp ? x86_pmu.cntval_bits : 0; cap->bit_width_fixed = cap->num_counters_fixed ? x86_pmu.cntval_bits : 0; cap->events_mask = (unsigned int)x86_pmu.events_maskl; cap->events_mask_len = x86_pmu.events_mask_len; cap->pebs_ept = x86_pmu.pebs_ept; cap->mediated = !!(pmu.capabilities & PERF_PMU_CAP_MEDIATED_VPMU); } EXPORT_SYMBOL_FOR_KVM(perf_get_x86_pmu_capability); u64 perf_get_hw_event_config(int hw_event) { int max = x86_pmu.max_events; if (hw_event < max) return x86_pmu.event_map(array_index_nospec(hw_event, max)); return 0; } EXPORT_SYMBOL_FOR_KVM(perf_get_hw_event_config); |
| 16 1 7 5 3 12 3 3 3 3 5 7 5 20 2 2 14 2 1 2 2 2 1 1 299 299 1 1 1 1 8 7 2 21 10 9 9 9 11 2 1 2 2 2 2 2 2 1 1 1 14 1 22 1 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Isovalent */ #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <linux/netdevice.h> #include <net/tcx.h> int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { bool created, ingress = attr->attach_type == BPF_TCX_INGRESS; struct net *net = current->nsproxy->net_ns; struct bpf_mprog_entry *entry, *entry_new; struct bpf_prog *replace_prog = NULL; struct net_device *dev; int ret; rtnl_lock(); dev = __dev_get_by_index(net, attr->target_ifindex); if (!dev) { ret = -ENODEV; goto out; } if (attr->attach_flags & BPF_F_REPLACE) { replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, prog->type); if (IS_ERR(replace_prog)) { ret = PTR_ERR(replace_prog); replace_prog = NULL; goto out; } } entry = tcx_entry_fetch_or_create(dev, ingress, &created); if (!entry) { ret = -ENOMEM; goto out; } ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog, attr->attach_flags, attr->relative_fd, attr->expected_revision); if (!ret) { if (entry != entry_new) { tcx_entry_update(dev, entry_new, ingress); tcx_entry_sync(); tcx_skeys_inc(ingress); } bpf_mprog_commit(entry); } else if (created) { tcx_entry_free(entry); } out: if (replace_prog) bpf_prog_put(replace_prog); rtnl_unlock(); return ret; } int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { bool ingress = attr->attach_type == BPF_TCX_INGRESS; struct net *net = current->nsproxy->net_ns; struct bpf_mprog_entry *entry, *entry_new; struct net_device *dev; int ret; rtnl_lock(); dev = __dev_get_by_index(net, attr->target_ifindex); if (!dev) { ret = -ENODEV; goto out; } entry = tcx_entry_fetch(dev, ingress); if (!entry) { ret = -ENOENT; goto out; } ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags, attr->relative_fd, attr->expected_revision); if (!ret) { if (!tcx_entry_is_active(entry_new)) entry_new = NULL; tcx_entry_update(dev, entry_new, ingress); tcx_entry_sync(); tcx_skeys_dec(ingress); bpf_mprog_commit(entry); if (!entry_new) tcx_entry_free(entry); } out: rtnl_unlock(); return ret; } void tcx_uninstall(struct net_device *dev, bool ingress) { struct bpf_mprog_entry *entry, *entry_new = NULL; struct bpf_tuple tuple = {}; struct bpf_mprog_fp *fp; struct bpf_mprog_cp *cp; bool active; entry = tcx_entry_fetch(dev, ingress); if (!entry) return; active = tcx_entry(entry)->miniq_active; if (active) bpf_mprog_clear_all(entry, &entry_new); tcx_entry_update(dev, entry_new, ingress); tcx_entry_sync(); bpf_mprog_foreach_tuple(entry, fp, cp, tuple) { if (tuple.link) tcx_link(tuple.link)->dev = NULL; else bpf_prog_put(tuple.prog); tcx_skeys_dec(ingress); } if (!active) tcx_entry_free(entry); } int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { bool ingress = attr->query.attach_type == BPF_TCX_INGRESS; struct net *net = current->nsproxy->net_ns; struct net_device *dev; int ret; rtnl_lock(); dev = __dev_get_by_index(net, attr->query.target_ifindex); if (!dev) { ret = -ENODEV; goto out; } ret = bpf_mprog_query(attr, uattr, tcx_entry_fetch(dev, ingress)); out: rtnl_unlock(); return ret; } static int tcx_link_prog_attach(struct bpf_link *link, u32 flags, u32 id_or_fd, u64 revision) { struct tcx_link *tcx = tcx_link(link); bool created, ingress = link->attach_type == BPF_TCX_INGRESS; struct bpf_mprog_entry *entry, *entry_new; struct net_device *dev = tcx->dev; int ret; ASSERT_RTNL(); entry = tcx_entry_fetch_or_create(dev, ingress, &created); if (!entry) return -ENOMEM; ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags, id_or_fd, revision); if (!ret) { if (entry != entry_new) { tcx_entry_update(dev, entry_new, ingress); tcx_entry_sync(); tcx_skeys_inc(ingress); } bpf_mprog_commit(entry); } else if (created) { tcx_entry_free(entry); } return ret; } static void tcx_link_release(struct bpf_link *link) { struct tcx_link *tcx = tcx_link(link); bool ingress = link->attach_type == BPF_TCX_INGRESS; struct bpf_mprog_entry *entry, *entry_new; struct net_device *dev; int ret = 0; rtnl_lock(); dev = tcx->dev; if (!dev) goto out; entry = tcx_entry_fetch(dev, ingress); if (!entry) { ret = -ENOENT; goto out; } ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0); if (!ret) { if (!tcx_entry_is_active(entry_new)) entry_new = NULL; tcx_entry_update(dev, entry_new, ingress); tcx_entry_sync(); tcx_skeys_dec(ingress); bpf_mprog_commit(entry); if (!entry_new) tcx_entry_free(entry); tcx->dev = NULL; } out: WARN_ON_ONCE(ret); rtnl_unlock(); } static int tcx_link_update(struct bpf_link *link, struct bpf_prog *nprog, struct bpf_prog *oprog) { struct tcx_link *tcx = tcx_link(link); bool ingress = link->attach_type == BPF_TCX_INGRESS; struct bpf_mprog_entry *entry, *entry_new; struct net_device *dev; int ret = 0; rtnl_lock(); dev = tcx->dev; if (!dev) { ret = -ENOLINK; goto out; } if (oprog && link->prog != oprog) { ret = -EPERM; goto out; } oprog = link->prog; if (oprog == nprog) { bpf_prog_put(nprog); goto out; } entry = tcx_entry_fetch(dev, ingress); if (!entry) { ret = -ENOENT; goto out; } ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog, BPF_F_REPLACE | BPF_F_ID, link->prog->aux->id, 0); if (!ret) { WARN_ON_ONCE(entry != entry_new); oprog = xchg(&link->prog, nprog); bpf_prog_put(oprog); bpf_mprog_commit(entry); } out: rtnl_unlock(); return ret; } static void tcx_link_dealloc(struct bpf_link *link) { kfree(tcx_link(link)); } static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) { const struct tcx_link *tcx = tcx_link(link); u32 ifindex = 0; rtnl_lock(); if (tcx->dev) ifindex = tcx->dev->ifindex; rtnl_unlock(); seq_printf(seq, "ifindex:\t%u\n", ifindex); seq_printf(seq, "attach_type:\t%u (%s)\n", link->attach_type, link->attach_type == BPF_TCX_INGRESS ? "ingress" : "egress"); } static int tcx_link_fill_info(const struct bpf_link *link, struct bpf_link_info *info) { const struct tcx_link *tcx = tcx_link(link); u32 ifindex = 0; rtnl_lock(); if (tcx->dev) ifindex = tcx->dev->ifindex; rtnl_unlock(); info->tcx.ifindex = ifindex; info->tcx.attach_type = link->attach_type; return 0; } static int tcx_link_detach(struct bpf_link *link) { tcx_link_release(link); return 0; } static const struct bpf_link_ops tcx_link_lops = { .release = tcx_link_release, .detach = tcx_link_detach, .dealloc = tcx_link_dealloc, .update_prog = tcx_link_update, .show_fdinfo = tcx_link_fdinfo, .fill_link_info = tcx_link_fill_info, }; static int tcx_link_init(struct tcx_link *tcx, struct bpf_link_primer *link_primer, const union bpf_attr *attr, struct net_device *dev, struct bpf_prog *prog) { bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog, attr->link_create.attach_type); tcx->dev = dev; return bpf_link_prime(&tcx->link, link_primer); } int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct net_device *dev; struct tcx_link *tcx; int ret; rtnl_lock(); dev = __dev_get_by_index(net, attr->link_create.target_ifindex); if (!dev) { ret = -ENODEV; goto out; } tcx = kzalloc_obj(*tcx, GFP_USER); if (!tcx) { ret = -ENOMEM; goto out; } ret = tcx_link_init(tcx, &link_primer, attr, dev, prog); if (ret) { kfree(tcx); goto out; } ret = tcx_link_prog_attach(&tcx->link, attr->link_create.flags, attr->link_create.tcx.relative_fd, attr->link_create.tcx.expected_revision); if (ret) { tcx->dev = NULL; bpf_link_cleanup(&link_primer); goto out; } ret = bpf_link_settle(&link_primer); out: rtnl_unlock(); return ret; } |
| 5 5 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2010 Werner Fink, Jiri Slaby */ #include <linux/console.h> #include <linux/kernel.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/tty_driver.h> /* * This is handler for /proc/consoles */ static int show_console_dev(struct seq_file *m, void *v) { static const struct { short flag; char name; } con_flags[] = { { CON_ENABLED, 'E' }, { CON_CONSDEV, 'C' }, { CON_BOOT, 'B' }, { CON_NBCON, 'N' }, { CON_PRINTBUFFER, 'p' }, { CON_BRL, 'b' }, { CON_ANYTIME, 'a' }, }; char flags[ARRAY_SIZE(con_flags) + 1]; struct console *con = v; unsigned int a; dev_t dev = 0; if (con->device) { const struct tty_driver *driver; int index; /* * Take console_lock to serialize device() callback with * other console operations. For example, fg_console is * modified under console_lock when switching vt. */ console_lock(); driver = con->device(con, &index); console_unlock(); if (driver) { dev = MKDEV(driver->major, driver->minor_start); dev += index; } } for (a = 0; a < ARRAY_SIZE(con_flags); a++) flags[a] = (con->flags & con_flags[a].flag) ? con_flags[a].name : ' '; flags[a] = 0; seq_setwidth(m, 21 - 1); seq_printf(m, "%s%d", con->name, con->index); seq_pad(m, ' '); seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-', ((con->flags & CON_NBCON) || con->write) ? 'W' : '-', con->unblank ? 'U' : '-', flags); if (dev) seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev)); seq_putc(m, '\n'); return 0; } static void *c_start(struct seq_file *m, loff_t *pos) __acquires(&console_mutex) { struct console *con; loff_t off = 0; /* * Hold the console_list_lock to guarantee safe traversal of the * console list. SRCU cannot be used because there is no * place to store the SRCU cookie. */ console_list_lock(); for_each_console(con) if (off++ == *pos) break; return con; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) { struct console *con = v; ++*pos; return hlist_entry_safe(con->node.next, struct console, node); } static void c_stop(struct seq_file *m, void *v) __releases(&console_mutex) { console_list_unlock(); } static const struct seq_operations consoles_op = { .start = c_start, .next = c_next, .stop = c_stop, .show = show_console_dev }; static int __init proc_consoles_init(void) { proc_create_seq("consoles", 0, NULL, &consoles_op); return 0; } fs_initcall(proc_consoles_init); |
| 1 1 1 1 1 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLKTRACE_H #define BLKTRACE_H #include <linux/blk-mq.h> #include <linux/relay.h> #include <linux/compat.h> #include <uapi/linux/blktrace_api.h> #include <linux/list.h> #include <linux/blk_types.h> #if defined(CONFIG_BLK_DEV_IO_TRACE) #include <linux/sysfs.h> struct blk_trace { int version; int trace_state; struct rchan *rchan; unsigned long __percpu *sequence; unsigned char __percpu *msg_data; u64 act_mask; u64 start_lba; u64 end_lba; u32 pid; u32 dev; struct dentry *dir; struct list_head running_list; atomic_t dropped; }; extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); __printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream * @q: queue the io is for * @fmt: format to print message in * args... Variable argument list for format * * Description: * Records a (simple) message onto the blktrace stream. * * NOTE: BLK_TN_MAX_MSG characters are output at most. * NOTE: Can not use 'static inline' due to presence of var args... * **/ #define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) #define BLK_TN_MAX_MSG 128 static inline bool blk_trace_note_message_enabled(struct request_queue *q) { struct blk_trace *bt; bool ret; rcu_read_lock(); bt = rcu_dereference(q->blk_trace); ret = bt && (bt->act_mask & BLK_TC_NOTIFY); rcu_read_unlock(); return ret; } extern void blk_add_driver_data(struct request *rq, void *data, size_t len); extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, char __user *arg); extern int blk_trace_startstop(struct request_queue *q, int start); extern int blk_trace_remove(struct request_queue *q); #else /* !CONFIG_BLK_DEV_IO_TRACE */ # define blk_trace_ioctl(bdev, cmd, arg) (-ENOTTY) # define blk_trace_shutdown(q) do { } while (0) # define blk_add_driver_data(rq, data, len) do {} while (0) # define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY) # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) # define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0) # define blk_trace_note_message_enabled(q) (false) static inline int blk_trace_remove(struct request_queue *q) { return -ENOTTY; } #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_COMPAT struct compat_blk_user_trace_setup { char name[BLKTRACE_BDEV_SIZE]; u16 act_mask; u32 buf_size; u32 buf_nr; compat_u64 start_lba; compat_u64 end_lba; u32 pid; }; #define BLKTRACESETUP32 _IOWR(0x12, 115, struct compat_blk_user_trace_setup) #endif void blk_fill_rwbs(char *rwbs, blk_opf_t opf); static inline sector_t blk_rq_trace_sector(struct request *rq) { /* * Tracing should ignore starting sector for passthrough requests and * requests where starting sector didn't get set. */ if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1) return 0; return blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) { return blk_rq_is_passthrough(rq) ? 0 : blk_rq_sectors(rq); } #endif |
| 67 4 133 56 53 17 15 7 7 17 21 3 71 71 71 71 67 71 11 71 71 71 7 13 49 1 13 2 68 41 4 1 3 1 1 57 52 5 129 37 1 1 94 75 66 4 4 71 4 1 36 36 1 70 84 2 6 5 1 8 71 81 81 31 3 34 58 57 57 1 58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to mapping data to requests */ #include <linux/kernel.h> #include <linux/sched/task_stack.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/uio.h> #include "blk.h" struct bio_map_data { bool is_our_pages : 1; bool is_null_mapped : 1; struct iov_iter iter; struct iovec iov[]; }; static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data, gfp_t gfp_mask) { struct bio_map_data *bmd; if (data->nr_segs > UIO_MAXIOV) return NULL; bmd = kmalloc_flex(*bmd, iov, data->nr_segs, gfp_mask); if (!bmd) return NULL; bmd->iter = *data; if (iter_is_iovec(data)) { memcpy(bmd->iov, iter_iov(data), sizeof(struct iovec) * data->nr_segs); bmd->iter.__iov = bmd->iov; } return bmd; } static inline void blk_mq_map_bio_put(struct bio *bio) { bio_put(bio); } static struct bio *blk_rq_map_bio_alloc(struct request *rq, unsigned int nr_vecs, gfp_t gfp_mask) { struct block_device *bdev = rq->q->disk ? rq->q->disk->part0 : NULL; struct bio *bio; bio = bio_alloc_bioset(bdev, nr_vecs, rq->cmd_flags, gfp_mask, &fs_bio_set); if (!bio) return NULL; return bio; } /** * bio_copy_from_iter - copy all pages from iov_iter to bio * @bio: The &struct bio which describes the I/O as destination * @iter: iov_iter as source * * Copy all pages from iov_iter to bio. * Returns 0 on success, or error on failure. */ static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { ssize_t ret; ret = copy_page_from_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, iter); if (!iov_iter_count(iter)) break; if (ret < bvec->bv_len) return -EFAULT; } return 0; } /** * bio_copy_to_iter - copy all pages from bio to iov_iter * @bio: The &struct bio which describes the I/O as source * @iter: iov_iter as destination * * Copy all pages from bio to iov_iter. * Returns 0 on success, or error on failure. */ static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter) { struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { ssize_t ret; ret = copy_page_to_iter(bvec->bv_page, bvec->bv_offset, bvec->bv_len, &iter); if (!iov_iter_count(&iter)) break; if (ret < bvec->bv_len) return -EFAULT; } return 0; } /** * bio_uncopy_user - finish previously mapped bio * @bio: bio being terminated * * Free pages allocated from bio_copy_user_iov() and write back data * to user space in case of a read. */ static int bio_uncopy_user(struct bio *bio) { struct bio_map_data *bmd = bio->bi_private; int ret = 0; if (!bmd->is_null_mapped) { /* * if we're in a workqueue, the request is orphaned, so * don't copy into a random user address space, just free * and return -EINTR so user space doesn't expect any data. */ if (!current->mm) ret = -EINTR; else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); } kfree(bmd); return ret; } static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, struct iov_iter *iter, gfp_t gfp_mask) { struct bio_map_data *bmd; struct page *page; struct bio *bio; int i = 0, ret; int nr_pages; unsigned int len = iter->count; unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0; bmd = bio_alloc_map_data(iter, gfp_mask); if (!bmd) return -ENOMEM; /* * We need to do a deep copy of the iov_iter including the iovecs. * The caller provided iov might point to an on-stack or otherwise * shortlived one. */ bmd->is_our_pages = !map_data; bmd->is_null_mapped = (map_data && map_data->null_mapped); nr_pages = bio_max_segs(DIV_ROUND_UP(offset + len, PAGE_SIZE)); ret = -ENOMEM; bio = blk_rq_map_bio_alloc(rq, nr_pages, gfp_mask); if (!bio) goto out_bmd; if (map_data) { nr_pages = 1U << map_data->page_order; i = map_data->offset / PAGE_SIZE; } while (len) { unsigned int bytes = PAGE_SIZE; bytes -= offset; if (bytes > len) bytes = len; if (map_data) { if (i == map_data->nr_entries * nr_pages) { ret = -ENOMEM; goto cleanup; } page = map_data->pages[i / nr_pages]; page += (i % nr_pages); i++; } else { page = alloc_page(GFP_NOIO | gfp_mask); if (!page) { ret = -ENOMEM; goto cleanup; } } if (bio_add_page(bio, page, bytes, offset) < bytes) { if (!map_data) __free_page(page); break; } len -= bytes; offset = 0; } if (map_data) map_data->offset += bio->bi_iter.bi_size; /* * success */ if (iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) { ret = bio_copy_from_iter(bio, iter); if (ret) goto cleanup; } else if (map_data && map_data->from_user) { struct iov_iter iter2 = *iter; /* This is the copy-in part of SG_DXFER_TO_FROM_DEV. */ iter2.data_source = ITER_SOURCE; ret = bio_copy_from_iter(bio, &iter2); if (ret) goto cleanup; } else { if (bmd->is_our_pages) zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } bio->bi_private = bmd; ret = blk_rq_append_bio(rq, bio); if (ret) goto cleanup; return 0; cleanup: if (!map_data) bio_free_pages(bio); blk_mq_map_bio_put(bio); out_bmd: kfree(bmd); return ret; } static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { unsigned int nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS); struct bio *bio; int ret; if (!iov_iter_count(iter)) return -EINVAL; bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask); if (!bio) return -ENOMEM; /* * No alignment requirements on our part to support arbitrary * passthrough commands. */ ret = bio_iov_iter_get_pages(bio, iter, 0); if (ret) goto out_put; ret = blk_rq_append_bio(rq, bio); if (ret) goto out_release; return 0; out_release: bio_release_pages(bio, false); out_put: blk_mq_map_bio_put(bio); return ret; } static void bio_invalidate_vmalloc_pages(struct bio *bio) { #ifdef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE if (bio->bi_private && !op_is_write(bio_op(bio))) { unsigned long i, len = 0; for (i = 0; i < bio->bi_vcnt; i++) len += bio->bi_io_vec[i].bv_len; invalidate_kernel_vmap_range(bio->bi_private, len); } #endif } static void bio_map_kern_endio(struct bio *bio) { bio_invalidate_vmalloc_pages(bio); blk_mq_map_bio_put(bio); } static struct bio *bio_map_kern(struct request *rq, void *data, unsigned int len, gfp_t gfp_mask) { unsigned int nr_vecs = bio_add_max_vecs(data, len); struct bio *bio; bio = blk_rq_map_bio_alloc(rq, nr_vecs, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); if (is_vmalloc_addr(data)) { bio->bi_private = data; if (!bio_add_vmalloc(bio, data, len)) { blk_mq_map_bio_put(bio); return ERR_PTR(-EINVAL); } } else { bio_add_virt_nofail(bio, data, len); } bio->bi_end_io = bio_map_kern_endio; return bio; } static void bio_copy_kern_endio(struct bio *bio) { bio_free_pages(bio); blk_mq_map_bio_put(bio); } static void bio_copy_kern_endio_read(struct bio *bio) { char *p = bio->bi_private; struct bio_vec *bvec; struct bvec_iter_all iter_all; bio_for_each_segment_all(bvec, bio, iter_all) { memcpy_from_bvec(p, bvec); p += bvec->bv_len; } bio_copy_kern_endio(bio); } /** * bio_copy_kern - copy kernel address into bio * @rq: request to fill * @data: pointer to buffer to copy * @len: length in bytes * @op: bio/request operation * @gfp_mask: allocation flags for bio and page allocation * * copy the kernel address into a bio suitable for io to a block * device. Returns an error pointer in case of error. */ static struct bio *bio_copy_kern(struct request *rq, void *data, unsigned int len, gfp_t gfp_mask) { enum req_op op = req_op(rq); unsigned long kaddr = (unsigned long)data; unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = kaddr >> PAGE_SHIFT; struct bio *bio; void *p = data; int nr_pages = 0; /* * Overflow, abort */ if (end < start) return ERR_PTR(-EINVAL); nr_pages = end - start; bio = blk_rq_map_bio_alloc(rq, nr_pages, gfp_mask); if (!bio) return ERR_PTR(-ENOMEM); while (len) { struct page *page; unsigned int bytes = PAGE_SIZE; if (bytes > len) bytes = len; page = alloc_page(GFP_NOIO | __GFP_ZERO | gfp_mask); if (!page) goto cleanup; if (op_is_write(op)) memcpy(page_address(page), p, bytes); __bio_add_page(bio, page, bytes, 0); len -= bytes; p += bytes; } if (op_is_write(op)) { bio->bi_end_io = bio_copy_kern_endio; } else { bio->bi_end_io = bio_copy_kern_endio_read; bio->bi_private = data; } return bio; cleanup: bio_free_pages(bio); blk_mq_map_bio_put(bio); return ERR_PTR(-ENOMEM); } /* * Append a bio to a passthrough request. Only works if the bio can be merged * into the request based on the driver constraints. */ int blk_rq_append_bio(struct request *rq, struct bio *bio) { const struct queue_limits *lim = &rq->q->limits; unsigned int max_bytes = lim->max_hw_sectors << SECTOR_SHIFT; unsigned int nr_segs = 0; int ret; /* check that the data layout matches the hardware restrictions */ ret = bio_split_io_at(bio, lim, &nr_segs, max_bytes, 0); if (ret) { /* if we would have to split the bio, copy instead */ if (ret > 0) ret = -EREMOTEIO; return ret; } if (rq->bio) { if (!ll_back_merge_fn(rq, bio, nr_segs)) return -EINVAL; rq->phys_gap_bit = bio_seg_gap(rq->q, rq->biotail, bio, rq->phys_gap_bit); rq->biotail->bi_next = bio; rq->biotail = bio; rq->__data_len += bio->bi_iter.bi_size; bio_crypt_free_ctx(bio); return 0; } rq->nr_phys_segments = nr_segs; rq->bio = rq->biotail = bio; rq->__data_len = bio->bi_iter.bi_size; rq->phys_gap_bit = bio->bi_bvec_gap_bit; return 0; } EXPORT_SYMBOL(blk_rq_append_bio); /* Prepare bio for passthrough IO given ITER_BVEC iter */ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) { unsigned int max_bytes = rq->q->limits.max_hw_sectors << SECTOR_SHIFT; struct bio *bio; int ret; if (!iov_iter_count(iter) || iov_iter_count(iter) > max_bytes) return -EINVAL; /* reuse the bvecs from the iterator instead of allocating new ones */ bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL); if (!bio) return -ENOMEM; bio_iov_bvec_set(bio, iter); ret = blk_rq_append_bio(rq, bio); if (ret) blk_mq_map_bio_put(bio); return ret; } /** * blk_rq_map_user_iov - map user data to a request, for passthrough requests * @q: request queue where request should be inserted * @rq: request to map data to * @map_data: pointer to the rq_map_data holding pages (if necessary) * @iter: iovec iterator * @gfp_mask: memory allocation flags * * Description: * Data will be mapped directly for zero copy I/O, if possible. Otherwise * a kernel bounce buffer is used. * * A matching blk_rq_unmap_user() must be issued at the end of I/O, while * still in process context. */ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, const struct iov_iter *iter, gfp_t gfp_mask) { bool copy = false, map_bvec = false; unsigned long align = blk_lim_dma_alignment_and_pad(&q->limits); struct bio *bio = NULL; struct iov_iter i; int ret = -EINVAL; if (map_data) copy = true; else if (iov_iter_alignment(iter) & align) copy = true; else if (iov_iter_is_bvec(iter)) map_bvec = true; else if (!user_backed_iter(iter)) copy = true; else if (queue_virt_boundary(q)) copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter); if (map_bvec) { ret = blk_rq_map_user_bvec(rq, iter); if (!ret) return 0; if (ret != -EREMOTEIO) goto fail; /* fall back to copying the data on limits mismatches */ copy = true; } i = *iter; do { if (copy) ret = bio_copy_user_iov(rq, map_data, &i, gfp_mask); else ret = bio_map_user_iov(rq, &i, gfp_mask); if (ret) { if (ret == -EREMOTEIO) ret = -EINVAL; goto unmap_rq; } if (!bio) bio = rq->bio; } while (iov_iter_count(&i)); return 0; unmap_rq: blk_rq_unmap_user(bio); fail: rq->bio = NULL; return ret; } EXPORT_SYMBOL(blk_rq_map_user_iov); int blk_rq_map_user(struct request_queue *q, struct request *rq, struct rq_map_data *map_data, void __user *ubuf, unsigned long len, gfp_t gfp_mask) { struct iov_iter i; int ret = import_ubuf(rq_data_dir(rq), ubuf, len, &i); if (unlikely(ret < 0)) return ret; return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask); } EXPORT_SYMBOL(blk_rq_map_user); int blk_rq_map_user_io(struct request *req, struct rq_map_data *map_data, void __user *ubuf, unsigned long buf_len, gfp_t gfp_mask, bool vec, int iov_count, bool check_iter_count, int rw) { int ret = 0; if (vec) { struct iovec fast_iov[UIO_FASTIOV]; struct iovec *iov = fast_iov; struct iov_iter iter; ret = import_iovec(rw, ubuf, iov_count ? iov_count : buf_len, UIO_FASTIOV, &iov, &iter); if (ret < 0) return ret; if (iov_count) { /* SG_IO howto says that the shorter of the two wins */ iov_iter_truncate(&iter, buf_len); if (check_iter_count && !iov_iter_count(&iter)) { kfree(iov); return -EINVAL; } } ret = blk_rq_map_user_iov(req->q, req, map_data, &iter, gfp_mask); kfree(iov); } else if (buf_len) { ret = blk_rq_map_user(req->q, req, map_data, ubuf, buf_len, gfp_mask); } return ret; } EXPORT_SYMBOL(blk_rq_map_user_io); /** * blk_rq_unmap_user - unmap a request with user data * @bio: start of bio list * * Description: * Unmap a rq previously mapped by blk_rq_map_user(). The caller must * supply the original rq->bio from the blk_rq_map_user() return, since * the I/O completion may have changed rq->bio. */ int blk_rq_unmap_user(struct bio *bio) { struct bio *next_bio; int ret = 0, ret2; while (bio) { if (bio->bi_private) { ret2 = bio_uncopy_user(bio); if (ret2 && !ret) ret = ret2; } else { bio_release_pages(bio, bio_data_dir(bio) == READ); } if (bio_integrity(bio)) bio_integrity_unmap_user(bio); next_bio = bio; bio = bio->bi_next; blk_mq_map_bio_put(next_bio); } return ret; } EXPORT_SYMBOL(blk_rq_unmap_user); /** * blk_rq_map_kern - map kernel data to a request, for passthrough requests * @rq: request to fill * @kbuf: the kernel buffer * @len: length of user data * @gfp_mask: memory allocation flags * * Description: * Data will be mapped directly if possible. Otherwise a bounce * buffer is used. Can be called multiple times to append multiple * buffers. */ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, gfp_t gfp_mask) { unsigned long addr = (unsigned long) kbuf; struct bio *bio; int ret; if (len > (queue_max_hw_sectors(rq->q) << SECTOR_SHIFT)) return -EINVAL; if (!len || !kbuf) return -EINVAL; if (!blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf)) bio = bio_copy_kern(rq, kbuf, len, gfp_mask); else bio = bio_map_kern(rq, kbuf, len, gfp_mask); if (IS_ERR(bio)) return PTR_ERR(bio); ret = blk_rq_append_bio(rq, bio); if (unlikely(ret)) blk_mq_map_bio_put(bio); return ret; } EXPORT_SYMBOL(blk_rq_map_kern); |
| 8 8 7 7 8 2 1 1 3 1 1 5 9 2 2 43 32 32 9 8 1 1 2 2 1 2 2 1 1 1 1 1 1 1 1 1 2 1 1 1 3 5 5 1 13 4 8 8 5 1 1 1 1 1 31 19 1 1 8 2 29 13 1 1 1 3 2 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Ioctl handler * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/capability.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/if_bridge.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/times.h> #include <net/net_namespace.h> #include <linux/uaccess.h> #include "br_private.h" static int get_bridge_ifindices(struct net *net, int *indices, int num) { struct net_device *dev; int i = 0; rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (i >= num) break; if (netif_is_bridge_master(dev)) indices[i++] = dev->ifindex; } rcu_read_unlock(); return i; } /* called with RTNL */ static void get_port_ifindices(struct net_bridge *br, int *ifindices, int num) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->port_no < num) ifindices[p->port_no] = p->dev->ifindex; } } /* * Format up to a page worth of forwarding table entries * userbuf -- where to copy result * maxnum -- maximum number of entries desired * (limited to a page for sanity) * offset -- number of records to skip */ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, unsigned long maxnum, unsigned long offset) { int num; void *buf; size_t size; /* Clamp size to PAGE_SIZE, test maxnum to avoid overflow */ if (maxnum > PAGE_SIZE/sizeof(struct __fdb_entry)) maxnum = PAGE_SIZE/sizeof(struct __fdb_entry); size = maxnum * sizeof(struct __fdb_entry); buf = kmalloc(size, GFP_USER); if (!buf) return -ENOMEM; num = br_fdb_fillbuf(br, buf, maxnum, offset); if (num > 0) { if (copy_to_user(userbuf, buf, array_size(num, sizeof(struct __fdb_entry)))) num = -EFAULT; } kfree(buf); return num; } /* called with RTNL */ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) { struct net *net = dev_net(br->dev); struct net_device *dev; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; dev = __dev_get_by_index(net, ifindex); if (dev == NULL) return -EINVAL; if (isadd) ret = br_add_if(br, dev, NULL); else ret = br_del_if(br, dev); return ret; } #define BR_UARGS_MAX 4 static int br_dev_read_uargs(unsigned long *args, size_t nr_args, void __user **argp, void __user *data) { int ret; if (nr_args < 2 || nr_args > BR_UARGS_MAX) return -EINVAL; if (in_compat_syscall()) { unsigned int cargs[BR_UARGS_MAX]; int i; ret = copy_from_user(cargs, data, nr_args * sizeof(*cargs)); if (ret) goto fault; for (i = 0; i < nr_args; ++i) args[i] = cargs[i]; *argp = compat_ptr(args[1]); } else { ret = copy_from_user(args, data, nr_args * sizeof(*args)); if (ret) goto fault; *argp = (void __user *)args[1]; } return 0; fault: return -EFAULT; } /* * Legacy ioctl's through SIOCDEVPRIVATE * This interface is deprecated because it was too difficult * to do the translation for 32/64bit ioctl compatibility. */ int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p = NULL; unsigned long args[4]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_ADD_IF: case BRCTL_DEL_IF: return add_del_if(br, args[1], args[0] == BRCTL_ADD_IF); case BRCTL_GET_BRIDGE_INFO: { struct __bridge_info b; memset(&b, 0, sizeof(struct __bridge_info)); rcu_read_lock(); memcpy(&b.designated_root, &br->designated_root, 8); memcpy(&b.bridge_id, &br->bridge_id, 8); b.root_path_cost = br->root_path_cost; b.max_age = jiffies_to_clock_t(br->max_age); b.hello_time = jiffies_to_clock_t(br->hello_time); b.forward_delay = br->forward_delay; b.bridge_max_age = br->bridge_max_age; b.bridge_hello_time = br->bridge_hello_time; b.bridge_forward_delay = jiffies_to_clock_t(br->bridge_forward_delay); b.topology_change = br->topology_change; b.topology_change_detected = br->topology_change_detected; b.root_port = br->root_port; b.stp_enabled = (br->stp_enabled != BR_NO_STP); b.ageing_time = jiffies_to_clock_t(br->ageing_time); b.hello_timer_value = br_timer_value(&br->hello_timer); b.tcn_timer_value = br_timer_value(&br->tcn_timer); b.topology_change_timer_value = br_timer_value(&br->topology_change_timer); b.gc_timer_value = br_timer_value(&br->gc_work.timer); rcu_read_unlock(); if (copy_to_user((void __user *)args[1], &b, sizeof(b))) return -EFAULT; return 0; } case BRCTL_GET_PORT_LIST: { int num, *indices; num = args[2]; if (num < 0) return -EINVAL; if (num == 0) num = 256; if (num > BR_MAX_PORTS) num = BR_MAX_PORTS; indices = kzalloc_objs(int, num); if (indices == NULL) return -ENOMEM; get_port_ifindices(br, indices, num); if (copy_to_user(argp, indices, array_size(num, sizeof(int)))) num = -EFAULT; kfree(indices); return num; } case BRCTL_SET_BRIDGE_FORWARD_DELAY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_forward_delay(br, args[1]); break; case BRCTL_SET_BRIDGE_HELLO_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_hello_time(br, args[1]); break; case BRCTL_SET_BRIDGE_MAX_AGE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_max_age(br, args[1]); break; case BRCTL_SET_AGEING_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_ageing_time(br, args[1]); break; case BRCTL_GET_PORT_INFO: { struct __port_info p; struct net_bridge_port *pt; rcu_read_lock(); if ((pt = br_get_port(br, args[2])) == NULL) { rcu_read_unlock(); return -EINVAL; } memset(&p, 0, sizeof(struct __port_info)); memcpy(&p.designated_root, &pt->designated_root, 8); memcpy(&p.designated_bridge, &pt->designated_bridge, 8); p.port_id = pt->port_id; p.designated_port = pt->designated_port; p.path_cost = pt->path_cost; p.designated_cost = pt->designated_cost; p.state = pt->state; p.top_change_ack = pt->topology_change_ack; p.config_pending = pt->config_pending; p.message_age_timer_value = br_timer_value(&pt->message_age_timer); p.forward_delay_timer_value = br_timer_value(&pt->forward_delay_timer); p.hold_timer_value = br_timer_value(&pt->hold_timer); rcu_read_unlock(); if (copy_to_user(argp, &p, sizeof(p))) return -EFAULT; return 0; } case BRCTL_SET_BRIDGE_STP_STATE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_stp_set_enabled(br, args[1], NULL); break; case BRCTL_SET_BRIDGE_PRIORITY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_stp_set_bridge_priority(br, args[1]); ret = 0; break; case BRCTL_SET_PORT_PRIORITY: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_port_priority(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_SET_PATH_COST: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_path_cost(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_GET_FDB_ENTRIES: return get_fdb_entries(br, argp, args[2], args[3]); default: ret = -EOPNOTSUPP; } if (!ret) { if (p) br_ifinfo_notify(RTM_NEWLINK, NULL, p); else netdev_state_change(br->dev); } return ret; } static int old_deviceless(struct net *net, void __user *data) { unsigned long args[3]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_GET_VERSION: return BRCTL_VERSION; case BRCTL_GET_BRIDGES: { int *indices; int ret = 0; if (args[2] >= 2048) return -ENOMEM; indices = kzalloc_objs(int, args[2]); if (indices == NULL) return -ENOMEM; args[2] = get_bridge_ifindices(net, indices, args[2]); ret = copy_to_user(argp, indices, array_size(args[2], sizeof(int))) ? -EFAULT : args[2]; kfree(indices); return ret; } case BRCTL_ADD_BRIDGE: case BRCTL_DEL_BRIDGE: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, argp, IFNAMSIZ)) return -EFAULT; buf[IFNAMSIZ-1] = 0; if (args[0] == BRCTL_ADD_BRIDGE) return br_add_bridge(net, buf); return br_del_bridge(net, buf); } } return -EOPNOTSUPP; } int br_ioctl_stub(struct net *net, unsigned int cmd, void __user *uarg) { int ret = -EOPNOTSUPP; struct ifreq ifr; if (cmd == SIOCBRADDIF || cmd == SIOCBRDELIF) { void __user *data; char *colon; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (get_user_ifreq(&ifr, &data, uarg)) return -EFAULT; ifr.ifr_name[IFNAMSIZ - 1] = 0; colon = strchr(ifr.ifr_name, ':'); if (colon) *colon = 0; } rtnl_lock(); switch (cmd) { case SIOCGIFBR: case SIOCSIFBR: ret = old_deviceless(net, uarg); break; case SIOCBRADDBR: case SIOCBRDELBR: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } if (copy_from_user(buf, uarg, IFNAMSIZ)) { ret = -EFAULT; break; } buf[IFNAMSIZ-1] = 0; if (cmd == SIOCBRADDBR) ret = br_add_bridge(net, buf); else ret = br_del_bridge(net, buf); } break; case SIOCBRADDIF: case SIOCBRDELIF: { struct net_device *dev; dev = __dev_get_by_name(net, ifr.ifr_name); if (!dev || !netif_device_present(dev)) { ret = -ENODEV; break; } if (!netif_is_bridge_master(dev)) { ret = -EOPNOTSUPP; break; } ret = add_del_if(netdev_priv(dev), ifr.ifr_ifindex, cmd == SIOCBRADDIF); } break; } rtnl_unlock(); return ret; } |
| 10 1 8 1 28 5 1 23 1 5 1 1 5 4 2 3 4 4 1 1 3 4 1 1 2 8 8 8 8 8 8 8 8 1 16 15 1 3 3 3 3 3 3 3 3 8 1 1 3 3 1 1 3 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 | // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ #include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mpls.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/tc_act/tc_mpls.h> #include <net/mpls.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_mpls.h> #include <net/tc_wrapper.h> static struct tc_action_ops act_mpls_ops; #define ACT_MPLS_TTL_DEFAULT 255 static __be32 tcf_mpls_get_lse(struct mpls_shim_hdr *lse, struct tcf_mpls_params *p, bool set_bos) { u32 new_lse = 0; if (lse) new_lse = be32_to_cpu(lse->label_stack_entry); if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET) { new_lse &= ~MPLS_LS_LABEL_MASK; new_lse |= p->tcfm_label << MPLS_LS_LABEL_SHIFT; } if (p->tcfm_ttl) { new_lse &= ~MPLS_LS_TTL_MASK; new_lse |= p->tcfm_ttl << MPLS_LS_TTL_SHIFT; } if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET) { new_lse &= ~MPLS_LS_TC_MASK; new_lse |= p->tcfm_tc << MPLS_LS_TC_SHIFT; } if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET) { new_lse &= ~MPLS_LS_S_MASK; new_lse |= p->tcfm_bos << MPLS_LS_S_SHIFT; } else if (set_bos) { new_lse |= 1 << MPLS_LS_S_SHIFT; } return cpu_to_be32(new_lse); } TC_INDIRECT_SCOPE int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; __be32 new_lse; int mac_len; tcf_lastuse_update(&m->tcf_tm); bstats_update(this_cpu_ptr(m->common.cpu_bstats), skb); /* Ensure 'data' points at mac_header prior calling mpls manipulating * functions. */ if (skb_at_tc_ingress(skb)) { skb_push_rcsum(skb, skb->mac_len); mac_len = skb->mac_len; } else { mac_len = skb_network_offset(skb); } p = rcu_dereference_bh(m->mpls_p); switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: if (skb_mpls_pop(skb, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true))); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_MAC_PUSH: if (skb_vlan_tag_present(skb)) { if (__vlan_insert_inner_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb), ETH_HLEN) < 0) goto drop; skb->protocol = skb->vlan_proto; __vlan_hwaccel_clear_tag(skb); } new_lse = tcf_mpls_get_lse(NULL, p, mac_len || !eth_p_mpls(skb->protocol)); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false)) goto drop; break; case TCA_MPLS_ACT_MODIFY: if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) goto drop; new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false); if (skb_mpls_update_lse(skb, new_lse)) goto drop; break; case TCA_MPLS_ACT_DEC_TTL: if (skb_mpls_dec_ttl(skb)) goto drop; break; } if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); return p->action; drop: qstats_drop_inc(this_cpu_ptr(m->common.cpu_qstats)); return TC_ACT_SHOT; } static int valid_label(const struct nlattr *attr, struct netlink_ext_ack *extack) { const u32 *label = nla_data(attr); if (nla_len(attr) != sizeof(*label)) { NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length"); return -EINVAL; } if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) { NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range"); return -EINVAL; } return 0; } static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { [TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)), [TCA_MPLS_PROTO] = { .type = NLA_U16 }, [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, valid_label), [TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7), [TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1), [TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1), }; static int tcf_mpls_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_mpls_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_MPLS_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_mpls_params *p; struct tc_mpls *parm; bool exists = false; struct tcf_mpls *m; int ret = 0, err; u8 mpls_ttl = 0; u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes"); return -EINVAL; } err = nla_parse_nested(tb, TCA_MPLS_MAX, nla, mpls_policy, extack); if (err < 0) return err; if (!tb[TCA_MPLS_PARMS]) { NL_SET_ERR_MSG_MOD(extack, "No MPLS params"); return -EINVAL; } parm = nla_data(tb[TCA_MPLS_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } /* Verify parameters against action type. */ switch (parm->m_action) { case TCA_MPLS_ACT_POP: if (!tb[TCA_MPLS_PROTO]) { NL_SET_ERR_MSG_MOD(extack, "Protocol must be set for MPLS pop"); err = -EINVAL; goto release_idr; } if (!eth_proto_is_802_3(nla_get_be16(tb[TCA_MPLS_PROTO]))) { NL_SET_ERR_MSG_MOD(extack, "Invalid protocol type for MPLS pop"); err = -EINVAL; goto release_idr; } if (tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) { NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC or BOS cannot be used with MPLS pop"); err = -EINVAL; goto release_idr; } break; case TCA_MPLS_ACT_DEC_TTL: if (tb[TCA_MPLS_PROTO] || tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) { NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC, BOS or protocol cannot be used with MPLS dec_ttl"); err = -EINVAL; goto release_idr; } break; case TCA_MPLS_ACT_PUSH: case TCA_MPLS_ACT_MAC_PUSH: if (!tb[TCA_MPLS_LABEL]) { NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push"); err = -EINVAL; goto release_idr; } if (tb[TCA_MPLS_PROTO] && !eth_p_mpls(nla_get_be16(tb[TCA_MPLS_PROTO]))) { NL_SET_ERR_MSG_MOD(extack, "Protocol must be an MPLS type for MPLS push"); err = -EPROTONOSUPPORT; goto release_idr; } /* Push needs a TTL - if not specified, set a default value. */ if (!tb[TCA_MPLS_TTL]) { #if IS_ENABLED(CONFIG_MPLS) mpls_ttl = net->mpls.default_ttl ? net->mpls.default_ttl : ACT_MPLS_TTL_DEFAULT; #else mpls_ttl = ACT_MPLS_TTL_DEFAULT; #endif } break; case TCA_MPLS_ACT_MODIFY: if (tb[TCA_MPLS_PROTO]) { NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be used with MPLS modify"); err = -EINVAL; goto release_idr; } break; default: NL_SET_ERR_MSG_MOD(extack, "Unknown MPLS action"); err = -EINVAL; goto release_idr; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; m = to_mpls(*a); p = kzalloc_obj(*p); if (!p) { err = -ENOMEM; goto put_chain; } p->tcfm_action = parm->m_action; p->tcfm_label = nla_get_u32_default(tb[TCA_MPLS_LABEL], ACT_MPLS_LABEL_NOT_SET); p->tcfm_tc = nla_get_u8_default(tb[TCA_MPLS_TC], ACT_MPLS_TC_NOT_SET); p->tcfm_ttl = nla_get_u8_default(tb[TCA_MPLS_TTL], mpls_ttl); p->tcfm_bos = nla_get_u8_default(tb[TCA_MPLS_BOS], ACT_MPLS_BOS_NOT_SET); p->tcfm_proto = nla_get_be16_default(tb[TCA_MPLS_PROTO], htons(ETH_P_MPLS_UC)); p->action = parm->action; spin_lock_bh(&m->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p = rcu_replace_pointer(m->mpls_p, p, lockdep_is_held(&m->tcf_lock)); spin_unlock_bh(&m->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) kfree_rcu(p, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static void tcf_mpls_cleanup(struct tc_action *a) { struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; p = rcu_dereference_protected(m->mpls_p, 1); if (p) kfree_rcu(p, rcu); } static int tcf_mpls_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); const struct tcf_mpls *m = to_mpls(a); const struct tcf_mpls_params *p; struct tc_mpls opt = { .index = m->tcf_index, .refcnt = refcount_read(&m->tcf_refcnt) - ref, .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, }; struct tcf_t t; rcu_read_lock(); p = rcu_dereference(m->mpls_p); opt.m_action = p->tcfm_action; opt.action = p->action; if (nla_put(skb, TCA_MPLS_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET && nla_put_u32(skb, TCA_MPLS_LABEL, p->tcfm_label)) goto nla_put_failure; if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET && nla_put_u8(skb, TCA_MPLS_TC, p->tcfm_tc)) goto nla_put_failure; if (p->tcfm_ttl && nla_put_u8(skb, TCA_MPLS_TTL, p->tcfm_ttl)) goto nla_put_failure; if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET && nla_put_u8(skb, TCA_MPLS_BOS, p->tcfm_bos)) goto nla_put_failure; if (nla_put_be16(skb, TCA_MPLS_PROTO, p->tcfm_proto)) goto nla_put_failure; tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MPLS_TM, sizeof(t), &t, TCA_MPLS_PAD)) goto nla_put_failure; rcu_read_unlock(); return skb->len; nla_put_failure: rcu_read_unlock(); nlmsg_trim(skb, b); return -EMSGSIZE; } static int tcf_mpls_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; switch (tcf_mpls_action(act)) { case TCA_MPLS_ACT_PUSH: entry->id = FLOW_ACTION_MPLS_PUSH; entry->mpls_push.proto = tcf_mpls_proto(act); entry->mpls_push.label = tcf_mpls_label(act); entry->mpls_push.tc = tcf_mpls_tc(act); entry->mpls_push.bos = tcf_mpls_bos(act); entry->mpls_push.ttl = tcf_mpls_ttl(act); break; case TCA_MPLS_ACT_POP: entry->id = FLOW_ACTION_MPLS_POP; entry->mpls_pop.proto = tcf_mpls_proto(act); break; case TCA_MPLS_ACT_MODIFY: entry->id = FLOW_ACTION_MPLS_MANGLE; entry->mpls_mangle.label = tcf_mpls_label(act); entry->mpls_mangle.tc = tcf_mpls_tc(act); entry->mpls_mangle.bos = tcf_mpls_bos(act); entry->mpls_mangle.ttl = tcf_mpls_ttl(act); break; case TCA_MPLS_ACT_DEC_TTL: NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"dec_ttl\" option is used"); return -EOPNOTSUPP; case TCA_MPLS_ACT_MAC_PUSH: NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"mac_push\" option is used"); return -EOPNOTSUPP; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported MPLS mode offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; switch (tcf_mpls_action(act)) { case TCA_MPLS_ACT_PUSH: fl_action->id = FLOW_ACTION_MPLS_PUSH; break; case TCA_MPLS_ACT_POP: fl_action->id = FLOW_ACTION_MPLS_POP; break; case TCA_MPLS_ACT_MODIFY: fl_action->id = FLOW_ACTION_MPLS_MANGLE; break; default: return -EOPNOTSUPP; } } return 0; } static struct tc_action_ops act_mpls_ops = { .kind = "mpls", .id = TCA_ID_MPLS, .owner = THIS_MODULE, .act = tcf_mpls_act, .dump = tcf_mpls_dump, .init = tcf_mpls_init, .cleanup = tcf_mpls_cleanup, .offload_act_setup = tcf_mpls_offload_act_setup, .size = sizeof(struct tcf_mpls), }; MODULE_ALIAS_NET_ACT("mpls"); static __net_init int mpls_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_mpls_ops.net_id); return tc_action_net_init(net, tn, &act_mpls_ops); } static void __net_exit mpls_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_mpls_ops.net_id); } static struct pernet_operations mpls_net_ops = { .init = mpls_init_net, .exit_batch = mpls_exit_net, .id = &act_mpls_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init mpls_init_module(void) { return tcf_register_action(&act_mpls_ops, &mpls_net_ops); } static void __exit mpls_cleanup_module(void) { tcf_unregister_action(&act_mpls_ops, &mpls_net_ops); } module_init(mpls_init_module); module_exit(mpls_cleanup_module); MODULE_SOFTDEP("post: mpls_gso"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MPLS manipulation actions"); |
| 12 12 13 1 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Plantronics USB HID Driver * * Copyright (c) 2014 JD Cole <jd.cole@plantronics.com> * Copyright (c) 2015-2018 Terry Junge <terry.junge@plantronics.com> */ #include "hid-ids.h" #include <linux/hid.h> #include <linux/module.h> #include <linux/jiffies.h> #define PLT_HID_1_0_PAGE 0xffa00000 #define PLT_HID_2_0_PAGE 0xffa20000 #define PLT_BASIC_TELEPHONY 0x0003 #define PLT_BASIC_EXCEPTION 0x0005 #define PLT_VOL_UP 0x00b1 #define PLT_VOL_DOWN 0x00b2 #define PLT_MIC_MUTE 0x00b5 #define PLT1_VOL_UP (PLT_HID_1_0_PAGE | PLT_VOL_UP) #define PLT1_VOL_DOWN (PLT_HID_1_0_PAGE | PLT_VOL_DOWN) #define PLT1_MIC_MUTE (PLT_HID_1_0_PAGE | PLT_MIC_MUTE) #define PLT2_VOL_UP (PLT_HID_2_0_PAGE | PLT_VOL_UP) #define PLT2_VOL_DOWN (PLT_HID_2_0_PAGE | PLT_VOL_DOWN) #define PLT2_MIC_MUTE (PLT_HID_2_0_PAGE | PLT_MIC_MUTE) #define HID_TELEPHONY_MUTE (HID_UP_TELEPHONY | 0x2f) #define HID_CONSUMER_MUTE (HID_UP_CONSUMER | 0xe2) #define PLT_DA60 0xda60 #define PLT_BT300_MIN 0x0413 #define PLT_BT300_MAX 0x0418 #define PLT_DOUBLE_KEY_TIMEOUT 5 /* ms */ struct plt_drv_data { unsigned long device_type; unsigned long last_key_ts; unsigned long double_key_to; __u16 last_key; }; static int plantronics_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { unsigned short mapped_key; struct plt_drv_data *drv_data = hid_get_drvdata(hdev); unsigned long plt_type = drv_data->device_type; int allow_mute = usage->hid == HID_TELEPHONY_MUTE; int allow_consumer = field->application == HID_CP_CONSUMERCONTROL && (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER && usage->hid != HID_CONSUMER_MUTE; /* special case for PTT products */ if (field->application == HID_GD_JOYSTICK) goto defaulted; /* non-standard types or multi-HID interfaces - plt_type is PID */ if (!(plt_type & HID_USAGE_PAGE)) { switch (plt_type) { case PLT_DA60: if (allow_consumer) goto defaulted; if (usage->hid == HID_CONSUMER_MUTE) { mapped_key = KEY_MICMUTE; goto mapped; } break; default: if (allow_consumer || allow_mute) goto defaulted; } goto ignored; } /* handle standard consumer control mapping */ /* and standard telephony mic mute mapping */ if (allow_consumer || allow_mute) goto defaulted; /* handle vendor unique types - plt_type is 0xffa0uuuu or 0xffa2uuuu */ /* if not 'basic telephony compliant' - map vendor unique controls */ if (!((plt_type & HID_USAGE) >= PLT_BASIC_TELEPHONY && (plt_type & HID_USAGE) != PLT_BASIC_EXCEPTION) && !((field->application ^ plt_type) & HID_USAGE_PAGE)) switch (usage->hid) { case PLT1_VOL_UP: case PLT2_VOL_UP: mapped_key = KEY_VOLUMEUP; goto mapped; case PLT1_VOL_DOWN: case PLT2_VOL_DOWN: mapped_key = KEY_VOLUMEDOWN; goto mapped; case PLT1_MIC_MUTE: case PLT2_MIC_MUTE: mapped_key = KEY_MICMUTE; goto mapped; } /* * Future mapping of call control or other usages, * if and when keys are defined would go here * otherwise, ignore everything else that was not mapped */ ignored: hid_dbg(hdev, "usage: %08x (appl: %08x) - ignored\n", usage->hid, field->application); return -1; defaulted: hid_dbg(hdev, "usage: %08x (appl: %08x) - defaulted\n", usage->hid, field->application); return 0; mapped: hid_map_usage_clear(hi, usage, bit, max, EV_KEY, mapped_key); hid_dbg(hdev, "usage: %08x (appl: %08x) - mapped to key %d\n", usage->hid, field->application, mapped_key); return 1; } static int plantronics_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { struct plt_drv_data *drv_data = hid_get_drvdata(hdev); unsigned long prev_tsto, cur_ts; __u16 prev_key, cur_key; /* Usages are filtered in plantronics_usages. */ /* HZ too low for ms resolution - double key detection disabled */ /* or it is a key release - handle key presses only. */ if (!drv_data->double_key_to || !value) return 0; prev_tsto = drv_data->last_key_ts + drv_data->double_key_to; cur_ts = drv_data->last_key_ts = jiffies; prev_key = drv_data->last_key; cur_key = drv_data->last_key = usage->code; /* If the same key occurs in <= double_key_to -- ignore it */ if (prev_key == cur_key && time_before_eq(cur_ts, prev_tsto)) { hid_dbg(hdev, "double key %d ignored\n", cur_key); return 1; /* Ignore the repeated key. */ } return 0; } static unsigned long plantronics_device_type(struct hid_device *hdev) { unsigned i, col_page; unsigned long plt_type = hdev->product; /* multi-HID interfaces? - plt_type is PID */ if (plt_type >= PLT_BT300_MIN && plt_type <= PLT_BT300_MAX) goto exit; /* determine primary vendor page */ for (i = 0; i < hdev->maxcollection; i++) { col_page = hdev->collection[i].usage & HID_USAGE_PAGE; if (col_page == PLT_HID_2_0_PAGE) { plt_type = hdev->collection[i].usage; break; } if (col_page == PLT_HID_1_0_PAGE) plt_type = hdev->collection[i].usage; } exit: hid_dbg(hdev, "plt_type decoded as: %08lx\n", plt_type); return plt_type; } static int plantronics_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct plt_drv_data *drv_data; int ret; drv_data = devm_kzalloc(&hdev->dev, sizeof(*drv_data), GFP_KERNEL); if (!drv_data) return -ENOMEM; ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); return ret; } drv_data->device_type = plantronics_device_type(hdev); drv_data->double_key_to = msecs_to_jiffies(PLT_DOUBLE_KEY_TIMEOUT); drv_data->last_key_ts = jiffies - drv_data->double_key_to; /* if HZ does not allow ms resolution - disable double key detection */ if (drv_data->double_key_to < PLT_DOUBLE_KEY_TIMEOUT) drv_data->double_key_to = 0; hid_set_drvdata(hdev, drv_data); ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT | HID_CONNECT_HIDINPUT_FORCE | HID_CONNECT_HIDDEV_FORCE); if (ret) hid_err(hdev, "hw start failed\n"); return ret; } static const struct hid_device_id plantronics_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, HID_ANY_ID) }, { } }; MODULE_DEVICE_TABLE(hid, plantronics_devices); static const struct hid_usage_id plantronics_usages[] = { { HID_CP_VOLUMEUP, EV_KEY, HID_ANY_ID }, { HID_CP_VOLUMEDOWN, EV_KEY, HID_ANY_ID }, { HID_TELEPHONY_MUTE, EV_KEY, HID_ANY_ID }, { HID_CONSUMER_MUTE, EV_KEY, HID_ANY_ID }, { PLT2_VOL_UP, EV_KEY, HID_ANY_ID }, { PLT2_VOL_DOWN, EV_KEY, HID_ANY_ID }, { PLT2_MIC_MUTE, EV_KEY, HID_ANY_ID }, { PLT1_VOL_UP, EV_KEY, HID_ANY_ID }, { PLT1_VOL_DOWN, EV_KEY, HID_ANY_ID }, { PLT1_MIC_MUTE, EV_KEY, HID_ANY_ID }, { HID_TERMINATOR, HID_TERMINATOR, HID_TERMINATOR } }; static struct hid_driver plantronics_driver = { .name = "plantronics", .id_table = plantronics_devices, .usage_table = plantronics_usages, .input_mapping = plantronics_input_mapping, .event = plantronics_event, .probe = plantronics_probe, }; module_hid_driver(plantronics_driver); MODULE_AUTHOR("JD Cole <jd.cole@plantronics.com>"); MODULE_AUTHOR("Terry Junge <terry.junge@plantronics.com>"); MODULE_DESCRIPTION("Plantronics USB HID Driver"); MODULE_LICENSE("GPL"); |
| 17 17 17 17 9 2 6 17 3 1 1 1 23 6 17 2 2 2 2 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 | /* * Copyright (c) 2006-2008 Intel Corporation * Copyright (c) 2007 Dave Airlie <airlied@linux.ie> * Copyright (c) 2008 Red Hat Inc. * Copyright (c) 2016 Intel Corporation * * Permission to use, copy, modify, distribute, and sell this software and its * documentation for any purpose is hereby granted without fee, provided that * the above copyright notice appear in all copies and that both that copyright * notice and this permission notice appear in supporting documentation, and * that the name of the copyright holders not be used in advertising or * publicity pertaining to distribution of the software without specific, * written prior permission. The copyright holders make no representations * about the suitability of this software for any purpose. It is provided "as * is" without express or implied warranty. * * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE * OF THIS SOFTWARE. */ #include <drm/drm_device.h> #include <drm/drm_drv.h> #include <drm/drm_dumb_buffers.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem.h> #include <drm/drm_mode.h> #include <drm/drm_print.h> #include "drm_crtc_internal.h" #include "drm_internal.h" /** * DOC: overview * * The KMS API doesn't standardize backing storage object creation and leaves it * to driver-specific ioctls. Furthermore actually creating a buffer object even * for GEM-based drivers is done through a driver-specific ioctl - GEM only has * a common userspace interface for sharing and destroying objects. While not an * issue for full-fledged graphics stacks that include device-specific userspace * components (in libdrm for instance), this limit makes DRM-based early boot * graphics unnecessarily complex. * * Dumb objects partly alleviate the problem by providing a standard API to * create dumb buffers suitable for scanout, which can then be used to create * KMS frame buffers. * * To support dumb objects drivers must implement the &drm_driver.dumb_create * and &drm_driver.dumb_map_offset operations (the latter defaults to * drm_gem_dumb_map_offset() if not set). Drivers that don't use GEM handles * additionally need to implement the &drm_driver.dumb_destroy operation. See * the callbacks for further details. * * Note that dumb objects may not be used for gpu acceleration, as has been * attempted on some ARM embedded platforms. Such drivers really must have * a hardware-specific ioctl to allocate suitable buffer objects. */ static int drm_mode_align_dumb(struct drm_mode_create_dumb *args, unsigned long hw_pitch_align, unsigned long hw_size_align) { u32 pitch = args->pitch; u32 size; if (!pitch) return -EINVAL; if (hw_pitch_align) { pitch = roundup(pitch, hw_pitch_align); if (pitch < hw_pitch_align) return -EINVAL; } if (!hw_size_align) hw_size_align = PAGE_SIZE; else if (!IS_ALIGNED(hw_size_align, PAGE_SIZE)) return -EINVAL; /* TODO: handle this if necessary */ if (check_mul_overflow(args->height, pitch, &size)) return -EINVAL; size = roundup(size, hw_size_align); if (!size) return -EINVAL; args->pitch = pitch; args->size = size; return 0; } /** * drm_mode_size_dumb - Calculates the scanline and buffer sizes for dumb buffers * @dev: DRM device * @args: Parameters for the dumb buffer * @hw_pitch_align: Hardware scanline alignment in bytes * @hw_size_align: Hardware buffer-size alignment in bytes * * The helper drm_mode_size_dumb() calculates the size of the buffer * allocation and the scanline size for a dumb buffer. Callers have to * set the buffers width, height and color mode in the argument @arg. * The helper validates the correctness of the input and tests for * possible overflows. If successful, it returns the dumb buffer's * required scanline pitch and size in &args. * * The parameter @hw_pitch_align allows the driver to specifies an * alignment for the scanline pitch, if the hardware requires any. The * calculated pitch will be a multiple of the alignment. The parameter * @hw_size_align allows to specify an alignment for buffer sizes. The * provided alignment should represent requirements of the graphics * hardware. drm_mode_size_dumb() handles GEM-related constraints * automatically across all drivers and hardware. For example, the * returned buffer size is always a multiple of PAGE_SIZE, which is * required by mmap(). * * Returns: * Zero on success, or a negative error code otherwise. */ int drm_mode_size_dumb(struct drm_device *dev, struct drm_mode_create_dumb *args, unsigned long hw_pitch_align, unsigned long hw_size_align) { u64 pitch = 0; u32 fourcc; /* * The scanline pitch depends on the buffer width and the color * format. The latter is specified as a color-mode constant for * which we first have to find the corresponding color format. * * Different color formats can have the same color-mode constant. * For example XRGB8888 and BGRX8888 both have a color mode of 32. * It is possible to use different formats for dumb-buffer allocation * and rendering as long as all involved formats share the same * color-mode constant. */ fourcc = drm_driver_color_mode_format(dev, args->bpp); if (fourcc != DRM_FORMAT_INVALID) { const struct drm_format_info *info = drm_format_info(fourcc); if (!info) return -EINVAL; pitch = drm_format_info_min_pitch(info, 0, args->width); } else if (args->bpp) { /* * Some userspace throws in arbitrary values for bpp and * relies on the kernel to figure it out. In this case we * fall back to the old method of using bpp directly. The * over-commitment of memory from the rounding is acceptable * for compatibility with legacy userspace. We have a number * of deprecated legacy values that are explicitly supported. */ switch (args->bpp) { default: drm_warn_once(dev, "Unknown color mode %u; guessing buffer size.\n", args->bpp); fallthrough; /* * These constants represent various YUV formats supported by * drm_gem_afbc_get_bpp(). */ case 12: // DRM_FORMAT_YUV420_8BIT case 15: // DRM_FORMAT_YUV420_10BIT case 30: // DRM_FORMAT_VUY101010 fallthrough; /* * Used by Mesa and Gstreamer to allocate NV formats and others * as RGB buffers. Technically, XRGB16161616F formats are RGB, * but the dumb buffers are not supposed to be used for anything * beyond 32 bits per pixels. */ case 10: // DRM_FORMAT_NV{15,20,30}, DRM_FORMAT_P010 case 64: // DRM_FORMAT_{XRGB,XBGR,ARGB,ABGR}16161616F pitch = args->width * DIV_ROUND_UP(args->bpp, SZ_8); break; } } if (!pitch || pitch > U32_MAX) return -EINVAL; args->pitch = pitch; return drm_mode_align_dumb(args, hw_pitch_align, hw_size_align); } EXPORT_SYMBOL(drm_mode_size_dumb); int drm_mode_create_dumb(struct drm_device *dev, struct drm_mode_create_dumb *args, struct drm_file *file_priv) { u32 cpp, stride, size; if (!dev->driver->dumb_create) return -ENOSYS; if (!args->width || !args->height || !args->bpp) return -EINVAL; /* overflow checks for 32bit size calculations */ if (args->bpp > U32_MAX - 8) return -EINVAL; cpp = DIV_ROUND_UP(args->bpp, 8); if (cpp > U32_MAX / args->width) return -EINVAL; stride = cpp * args->width; if (args->height > U32_MAX / stride) return -EINVAL; /* test for wrap-around */ size = args->height * stride; if (PAGE_ALIGN(size) == 0) return -EINVAL; /* * handle, pitch and size are output parameters. Zero them out to * prevent drivers from accidentally using uninitialized data. Since * not all existing userspace is clearing these fields properly we * cannot reject IOCTL with garbage in them. */ args->handle = 0; args->pitch = 0; args->size = 0; return dev->driver->dumb_create(file_priv, dev, args); } int drm_mode_create_dumb_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_create_dumb *args = data; int err; err = drm_mode_create_dumb(dev, args, file_priv); if (err) { args->handle = 0; args->pitch = 0; args->size = 0; } return err; } static int drm_mode_mmap_dumb(struct drm_device *dev, struct drm_mode_map_dumb *args, struct drm_file *file_priv) { if (!dev->driver->dumb_create) return -ENOSYS; if (dev->driver->dumb_map_offset) return dev->driver->dumb_map_offset(file_priv, dev, args->handle, &args->offset); else return drm_gem_dumb_map_offset(file_priv, dev, args->handle, &args->offset); } /** * drm_mode_mmap_dumb_ioctl - create an mmap offset for a dumb backing storage buffer * @dev: DRM device * @data: ioctl data * @file_priv: DRM file info * * Allocate an offset in the drm device node's address space to be able to * memory map a dumb buffer. * * Called by the user via ioctl. * * Returns: * Zero on success, negative errno on failure. */ int drm_mode_mmap_dumb_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_map_dumb *args = data; int err; err = drm_mode_mmap_dumb(dev, args, file_priv); if (err) args->offset = 0; return err; } int drm_mode_destroy_dumb(struct drm_device *dev, u32 handle, struct drm_file *file_priv) { if (!dev->driver->dumb_create) return -ENOSYS; return drm_gem_handle_delete(file_priv, handle); } int drm_mode_destroy_dumb_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_destroy_dumb *args = data; return drm_mode_destroy_dumb(dev, args->handle, file_priv); } |
| 5 3 2 5 3 3 3 1 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0+ /* * REINER SCT cyberJack pinpad/e-com USB Chipcard Reader Driver * * Copyright (C) 2001 REINER SCT * Author: Matthias Bruestle * * Contact: support@reiner-sct.com (see MAINTAINERS) * * This program is largely derived from work by the linux-usb group * and associated source files. Please see the usb/serial files for * individual credits and copyrights. * * Thanks to Greg Kroah-Hartman (greg@kroah.com) for his help and * patience. * * In case of problems, please write to the contact e-mail address * mentioned above. * * Please note that later models of the cyberjack reader family are * supported by a libusb-based userspace device driver. * * Homepage: http://www.reiner-sct.de/support/treiber_cyberjack.php#linux */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/tty_flip.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/usb/serial.h> #define CYBERJACK_LOCAL_BUF_SIZE 32 #define DRIVER_AUTHOR "Matthias Bruestle" #define DRIVER_DESC "REINER SCT cyberJack pinpad/e-com USB Chipcard Reader Driver" #define CYBERJACK_VENDOR_ID 0x0C4B #define CYBERJACK_PRODUCT_ID 0x0100 /* Function prototypes */ static int cyberjack_port_probe(struct usb_serial_port *port); static void cyberjack_port_remove(struct usb_serial_port *port); static int cyberjack_open(struct tty_struct *tty, struct usb_serial_port *port); static void cyberjack_close(struct usb_serial_port *port); static int cyberjack_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count); static unsigned int cyberjack_write_room(struct tty_struct *tty); static void cyberjack_read_int_callback(struct urb *urb); static void cyberjack_read_bulk_callback(struct urb *urb); static void cyberjack_write_bulk_callback(struct urb *urb); static const struct usb_device_id id_table[] = { { USB_DEVICE(CYBERJACK_VENDOR_ID, CYBERJACK_PRODUCT_ID) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, id_table); static struct usb_serial_driver cyberjack_device = { .driver = { .name = "cyberjack", }, .description = "Reiner SCT Cyberjack USB card reader", .id_table = id_table, .num_ports = 1, .num_bulk_out = 1, .port_probe = cyberjack_port_probe, .port_remove = cyberjack_port_remove, .open = cyberjack_open, .close = cyberjack_close, .write = cyberjack_write, .write_room = cyberjack_write_room, .read_int_callback = cyberjack_read_int_callback, .read_bulk_callback = cyberjack_read_bulk_callback, .write_bulk_callback = cyberjack_write_bulk_callback, }; static struct usb_serial_driver * const serial_drivers[] = { &cyberjack_device, NULL }; struct cyberjack_private { spinlock_t lock; /* Lock for SMP */ short rdtodo; /* Bytes still to read */ unsigned char wrbuf[5*64]; /* Buffer for collecting data to write */ short wrfilled; /* Overall data size we already got */ short wrsent; /* Data already sent */ }; static int cyberjack_port_probe(struct usb_serial_port *port) { struct cyberjack_private *priv; int result; priv = kmalloc_obj(struct cyberjack_private); if (!priv) return -ENOMEM; spin_lock_init(&priv->lock); priv->rdtodo = 0; priv->wrfilled = 0; priv->wrsent = 0; usb_set_serial_port_data(port, priv); result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); if (result) dev_err(&port->dev, "usb_submit_urb(read int) failed\n"); return 0; } static void cyberjack_port_remove(struct usb_serial_port *port) { struct cyberjack_private *priv; usb_kill_urb(port->interrupt_in_urb); priv = usb_get_serial_port_data(port); kfree(priv); } static int cyberjack_open(struct tty_struct *tty, struct usb_serial_port *port) { struct cyberjack_private *priv; unsigned long flags; dev_dbg(&port->dev, "%s - usb_clear_halt\n", __func__); usb_clear_halt(port->serial->dev, port->write_urb->pipe); priv = usb_get_serial_port_data(port); spin_lock_irqsave(&priv->lock, flags); priv->rdtodo = 0; priv->wrfilled = 0; priv->wrsent = 0; spin_unlock_irqrestore(&priv->lock, flags); return 0; } static void cyberjack_close(struct usb_serial_port *port) { usb_kill_urb(port->write_urb); usb_kill_urb(port->read_urb); } static int cyberjack_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count) { struct device *dev = &port->dev; struct cyberjack_private *priv = usb_get_serial_port_data(port); unsigned long flags; int result; int wrexpected; if (count == 0) { dev_dbg(dev, "%s - write request of 0 bytes\n", __func__); return 0; } if (!test_and_clear_bit(0, &port->write_urbs_free)) { dev_dbg(dev, "%s - already writing\n", __func__); return 0; } spin_lock_irqsave(&priv->lock, flags); if (count+priv->wrfilled > sizeof(priv->wrbuf)) { /* To much data for buffer. Reset buffer. */ priv->wrfilled = 0; spin_unlock_irqrestore(&priv->lock, flags); set_bit(0, &port->write_urbs_free); return 0; } /* Copy data */ memcpy(priv->wrbuf + priv->wrfilled, buf, count); usb_serial_debug_data(dev, __func__, count, priv->wrbuf + priv->wrfilled); priv->wrfilled += count; if (priv->wrfilled >= 3) { wrexpected = ((int)priv->wrbuf[2]<<8)+priv->wrbuf[1]+3; dev_dbg(dev, "%s - expected data: %d\n", __func__, wrexpected); } else wrexpected = sizeof(priv->wrbuf); if (priv->wrfilled >= wrexpected) { /* We have enough data to begin transmission */ int length; dev_dbg(dev, "%s - transmitting data (frame 1)\n", __func__); length = (wrexpected > port->bulk_out_size) ? port->bulk_out_size : wrexpected; memcpy(port->write_urb->transfer_buffer, priv->wrbuf, length); priv->wrsent = length; /* set up our urb */ port->write_urb->transfer_buffer_length = length; /* send the data out the bulk port */ result = usb_submit_urb(port->write_urb, GFP_ATOMIC); if (result) { dev_err(&port->dev, "%s - failed submitting write urb, error %d\n", __func__, result); /* Throw away data. No better idea what to do with it. */ priv->wrfilled = 0; priv->wrsent = 0; spin_unlock_irqrestore(&priv->lock, flags); set_bit(0, &port->write_urbs_free); return 0; } dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent); dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled); if (priv->wrsent >= priv->wrfilled) { dev_dbg(dev, "%s - buffer cleaned\n", __func__); memset(priv->wrbuf, 0, sizeof(priv->wrbuf)); priv->wrfilled = 0; priv->wrsent = 0; } } spin_unlock_irqrestore(&priv->lock, flags); return count; } static unsigned int cyberjack_write_room(struct tty_struct *tty) { /* FIXME: .... */ return CYBERJACK_LOCAL_BUF_SIZE; } static void cyberjack_read_int_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct cyberjack_private *priv = usb_get_serial_port_data(port); struct device *dev = &port->dev; unsigned char *data = urb->transfer_buffer; int status = urb->status; unsigned long flags; int result; /* the urb might have been killed. */ if (status) return; usb_serial_debug_data(dev, __func__, urb->actual_length, data); /* React only to interrupts signaling a bulk_in transfer */ if (urb->actual_length == 4 && data[0] == 0x01) { short old_rdtodo; /* This is a announcement of coming bulk_ins. */ unsigned short size = ((unsigned short)data[3]<<8)+data[2]+3; spin_lock_irqsave(&priv->lock, flags); old_rdtodo = priv->rdtodo; if (old_rdtodo > SHRT_MAX - size) { dev_dbg(dev, "Too many bulk_in urbs to do.\n"); spin_unlock_irqrestore(&priv->lock, flags); goto resubmit; } /* "+=" is probably more fault tolerant than "=" */ priv->rdtodo += size; dev_dbg(dev, "%s - rdtodo: %d\n", __func__, priv->rdtodo); spin_unlock_irqrestore(&priv->lock, flags); if (!old_rdtodo) { result = usb_submit_urb(port->read_urb, GFP_ATOMIC); if (result) dev_err(dev, "%s - failed resubmitting read urb, error %d\n", __func__, result); dev_dbg(dev, "%s - usb_submit_urb(read urb)\n", __func__); } } resubmit: result = usb_submit_urb(port->interrupt_in_urb, GFP_ATOMIC); if (result) dev_err(&port->dev, "usb_submit_urb(read int) failed\n"); dev_dbg(dev, "%s - usb_submit_urb(int urb)\n", __func__); } static void cyberjack_read_bulk_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct cyberjack_private *priv = usb_get_serial_port_data(port); struct device *dev = &port->dev; unsigned char *data = urb->transfer_buffer; unsigned long flags; short todo; int result; int status = urb->status; usb_serial_debug_data(dev, __func__, urb->actual_length, data); if (status) { dev_dbg(dev, "%s - nonzero read bulk status received: %d\n", __func__, status); return; } if (urb->actual_length) { tty_insert_flip_string(&port->port, data, urb->actual_length); tty_flip_buffer_push(&port->port); } spin_lock_irqsave(&priv->lock, flags); /* Reduce urbs to do by one. */ priv->rdtodo -= urb->actual_length; /* Just to be sure */ if (priv->rdtodo < 0) priv->rdtodo = 0; todo = priv->rdtodo; spin_unlock_irqrestore(&priv->lock, flags); dev_dbg(dev, "%s - rdtodo: %d\n", __func__, todo); /* Continue to read if we have still urbs to do. */ if (todo /* || (urb->actual_length==port->bulk_in_endpointAddress)*/) { result = usb_submit_urb(port->read_urb, GFP_ATOMIC); if (result) dev_err(dev, "%s - failed resubmitting read urb, error %d\n", __func__, result); dev_dbg(dev, "%s - usb_submit_urb(read urb)\n", __func__); } } static void cyberjack_write_bulk_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct cyberjack_private *priv = usb_get_serial_port_data(port); struct device *dev = &port->dev; int status = urb->status; unsigned long flags; bool resubmitted = false; if (status) { dev_dbg(dev, "%s - nonzero write bulk status received: %d\n", __func__, status); set_bit(0, &port->write_urbs_free); return; } spin_lock_irqsave(&priv->lock, flags); /* only do something if we have more data to send */ if (priv->wrfilled) { int length, blksize, result; dev_dbg(dev, "%s - transmitting data (frame n)\n", __func__); length = ((priv->wrfilled - priv->wrsent) > port->bulk_out_size) ? port->bulk_out_size : (priv->wrfilled - priv->wrsent); memcpy(port->write_urb->transfer_buffer, priv->wrbuf + priv->wrsent, length); priv->wrsent += length; /* set up our urb */ port->write_urb->transfer_buffer_length = length; /* send the data out the bulk port */ result = usb_submit_urb(port->write_urb, GFP_ATOMIC); if (result) { dev_err(dev, "%s - failed submitting write urb, error %d\n", __func__, result); /* Throw away data. No better idea what to do with it. */ priv->wrfilled = 0; priv->wrsent = 0; goto exit; } resubmitted = true; dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent); dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled); blksize = ((int)priv->wrbuf[2]<<8)+priv->wrbuf[1]+3; if (priv->wrsent >= priv->wrfilled || priv->wrsent >= blksize) { dev_dbg(dev, "%s - buffer cleaned\n", __func__); memset(priv->wrbuf, 0, sizeof(priv->wrbuf)); priv->wrfilled = 0; priv->wrsent = 0; } } exit: spin_unlock_irqrestore(&priv->lock, flags); if (!resubmitted) set_bit(0, &port->write_urbs_free); usb_serial_port_softint(port); } module_usb_serial_driver(serial_drivers, id_table); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); |
| 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 | // SPDX-License-Identifier: GPL-2.0 /* * Vidtv serves as a reference DVB driver and helps validate the existing APIs * in the media subsystem. It can also aid developers working on userspace * applications. * * This file contains the code for a 'channel' abstraction. * * When vidtv boots, it will create some hardcoded channels. * Their services will be concatenated to populate the SDT. * Their programs will be concatenated to populate the PAT * Their events will be concatenated to populate the EIT * For each program in the PAT, a PMT section will be created * The PMT section for a channel will be assigned its streams. * Every stream will have its corresponding encoder polled to produce TS packets * These packets may be interleaved by the mux and then delivered to the bridge * * * Copyright (C) 2020 Daniel W. S. Almeida */ #include <linux/dev_printk.h> #include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/types.h> #include "vidtv_channel.h" #include "vidtv_common.h" #include "vidtv_encoder.h" #include "vidtv_mux.h" #include "vidtv_psi.h" #include "vidtv_s302m.h" static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e) { struct vidtv_encoder *tmp = NULL; struct vidtv_encoder *curr = e; while (curr) { /* forward the call to the derived type */ tmp = curr; curr = curr->next; tmp->destroy(tmp); } } #define ENCODING_ISO8859_15 "\x0b" #define TS_NIT_PID 0x10 /* * init an audio only channel with a s302m encoder */ struct vidtv_channel *vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id) { const __be32 s302m_fid = cpu_to_be32(VIDTV_S302M_FORMAT_IDENTIFIER); char *event_text = ENCODING_ISO8859_15 "Bagatelle No. 25 in A minor for solo piano, also known as F\xfcr Elise, composed by Ludwig van Beethoven"; char *event_name = ENCODING_ISO8859_15 "Ludwig van Beethoven: F\xfcr Elise"; struct vidtv_s302m_encoder_init_args encoder_args = {}; char *iso_language_code = ENCODING_ISO8859_15 "eng"; char *provider = ENCODING_ISO8859_15 "LinuxTV.org"; char *name = ENCODING_ISO8859_15 "Beethoven"; const u16 s302m_es_pid = 0x111; /* packet id for the ES */ const u16 s302m_program_pid = 0x101; /* packet id for PMT*/ const u16 s302m_service_id = 0x880; const u16 s302m_program_num = 0x880; const u16 s302m_beethoven_event_id = 1; struct vidtv_channel *s302m; s302m = kzalloc_obj(*s302m); if (!s302m) return NULL; s302m->name = kstrdup(name, GFP_KERNEL); if (!s302m->name) goto free_s302m; s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id, false, true); if (!s302m->service) goto free_name; s302m->service->descriptor = (struct vidtv_psi_desc *) vidtv_psi_service_desc_init(NULL, DIGITAL_RADIO_SOUND_SERVICE, name, provider); if (!s302m->service->descriptor) goto free_service; s302m->transport_stream_id = transport_stream_id; s302m->program = vidtv_psi_pat_program_init(NULL, s302m_service_id, s302m_program_pid); if (!s302m->program) goto free_service; s302m->program_num = s302m_program_num; s302m->streams = vidtv_psi_pmt_stream_init(NULL, STREAM_PRIVATE_DATA, s302m_es_pid); if (!s302m->streams) goto free_program; s302m->streams->descriptor = (struct vidtv_psi_desc *) vidtv_psi_registration_desc_init(NULL, s302m_fid, NULL, 0); if (!s302m->streams->descriptor) goto free_streams; encoder_args.es_pid = s302m_es_pid; s302m->encoders = vidtv_s302m_encoder_init(encoder_args); if (!s302m->encoders) goto free_streams; s302m->events = vidtv_psi_eit_event_init(NULL, s302m_beethoven_event_id); if (!s302m->events) goto free_encoders; s302m->events->descriptor = (struct vidtv_psi_desc *) vidtv_psi_short_event_desc_init(NULL, iso_language_code, event_name, event_text); if (!s302m->events->descriptor) goto free_events; if (head) { while (head->next) head = head->next; head->next = s302m; } return s302m; free_events: vidtv_psi_eit_event_destroy(s302m->events); free_encoders: vidtv_s302m_encoder_destroy(s302m->encoders); free_streams: vidtv_psi_pmt_stream_destroy(s302m->streams); free_program: vidtv_psi_pat_program_destroy(s302m->program); free_service: vidtv_psi_sdt_service_destroy(s302m->service); free_name: kfree(s302m->name); free_s302m: kfree(s302m); return NULL; } static struct vidtv_psi_table_eit_event *vidtv_channel_eit_event_cat_into_new(struct vidtv_mux *m) { /* Concatenate the events */ const struct vidtv_channel *cur_chnl = m->channels; struct vidtv_psi_table_eit_event *curr = NULL; struct vidtv_psi_table_eit_event *head = NULL; struct vidtv_psi_table_eit_event *tail = NULL; struct vidtv_psi_desc *desc = NULL; u16 event_id; if (!cur_chnl) return NULL; while (cur_chnl) { curr = cur_chnl->events; if (!curr) dev_warn_ratelimited(m->dev, "No events found for channel %s\n", cur_chnl->name); while (curr) { event_id = be16_to_cpu(curr->event_id); tail = vidtv_psi_eit_event_init(tail, event_id); if (!tail) { vidtv_psi_eit_event_destroy(head); return NULL; } desc = vidtv_psi_desc_clone(curr->descriptor); vidtv_psi_desc_assign(&tail->descriptor, desc); if (!head) head = tail; curr = curr->next; } cur_chnl = cur_chnl->next; } return head; } static struct vidtv_psi_table_sdt_service *vidtv_channel_sdt_serv_cat_into_new(struct vidtv_mux *m) { /* Concatenate the services */ const struct vidtv_channel *cur_chnl = m->channels; struct vidtv_psi_table_sdt_service *curr = NULL; struct vidtv_psi_table_sdt_service *head = NULL; struct vidtv_psi_table_sdt_service *tail = NULL; struct vidtv_psi_desc *desc = NULL; u16 service_id; if (!cur_chnl) return NULL; while (cur_chnl) { curr = cur_chnl->service; if (!curr) dev_warn_ratelimited(m->dev, "No services found for channel %s\n", cur_chnl->name); while (curr) { service_id = be16_to_cpu(curr->service_id); tail = vidtv_psi_sdt_service_init(tail, service_id, curr->EIT_schedule, curr->EIT_present_following); if (!tail) goto free; desc = vidtv_psi_desc_clone(curr->descriptor); if (!desc) goto free_tail; vidtv_psi_desc_assign(&tail->descriptor, desc); if (!head) head = tail; curr = curr->next; } cur_chnl = cur_chnl->next; } return head; free_tail: vidtv_psi_sdt_service_destroy(tail); free: vidtv_psi_sdt_service_destroy(head); return NULL; } static struct vidtv_psi_table_pat_program* vidtv_channel_pat_prog_cat_into_new(struct vidtv_mux *m) { /* Concatenate the programs */ const struct vidtv_channel *cur_chnl = m->channels; struct vidtv_psi_table_pat_program *curr = NULL; struct vidtv_psi_table_pat_program *head = NULL; struct vidtv_psi_table_pat_program *tail = NULL; u16 serv_id; u16 pid; if (!cur_chnl) return NULL; while (cur_chnl) { curr = cur_chnl->program; if (!curr) dev_warn_ratelimited(m->dev, "No programs found for channel %s\n", cur_chnl->name); while (curr) { serv_id = be16_to_cpu(curr->service_id); pid = vidtv_psi_get_pat_program_pid(curr); tail = vidtv_psi_pat_program_init(tail, serv_id, pid); if (!tail) { vidtv_psi_pat_program_destroy(head); return NULL; } if (!head) head = tail; curr = curr->next; } cur_chnl = cur_chnl->next; } /* Add the NIT table */ vidtv_psi_pat_program_init(tail, 0, TS_NIT_PID); return head; } /* * Match channels to their respective PMT sections, then assign the * streams */ static void vidtv_channel_pmt_match_sections(struct vidtv_channel *channels, struct vidtv_psi_table_pmt **sections, u32 nsections) { struct vidtv_psi_table_pmt *curr_section = NULL; struct vidtv_psi_table_pmt_stream *head = NULL; struct vidtv_psi_table_pmt_stream *tail = NULL; struct vidtv_psi_table_pmt_stream *s = NULL; struct vidtv_channel *cur_chnl = channels; struct vidtv_psi_desc *desc = NULL; u16 e_pid; /* elementary stream pid */ u16 curr_id; u32 j; while (cur_chnl) { for (j = 0; j < nsections; ++j) { curr_section = sections[j]; if (!curr_section) continue; curr_id = be16_to_cpu(curr_section->header.id); /* we got a match */ if (curr_id == cur_chnl->program_num) { s = cur_chnl->streams; /* clone the streams for the PMT */ while (s) { e_pid = vidtv_psi_pmt_stream_get_elem_pid(s); tail = vidtv_psi_pmt_stream_init(tail, s->type, e_pid); if (!tail) { vidtv_psi_pmt_stream_destroy(head); return; } if (!head) head = tail; desc = vidtv_psi_desc_clone(s->descriptor); vidtv_psi_desc_assign(&tail->descriptor, desc); s = s->next; } vidtv_psi_pmt_stream_assign(curr_section, head); break; } } cur_chnl = cur_chnl->next; } } static void vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e) { struct vidtv_psi_desc_service_list_entry *tmp; while (e) { tmp = e; e = e->next; kfree(tmp); } } static struct vidtv_psi_desc_service_list_entry *vidtv_channel_build_service_list(struct vidtv_psi_table_sdt_service *s) { struct vidtv_psi_desc_service_list_entry *curr_e = NULL; struct vidtv_psi_desc_service_list_entry *head_e = NULL; struct vidtv_psi_desc_service_list_entry *prev_e = NULL; struct vidtv_psi_desc *desc = s->descriptor; struct vidtv_psi_desc_service *s_desc; while (s) { while (desc) { if (s->descriptor->type != SERVICE_DESCRIPTOR) goto next_desc; s_desc = (struct vidtv_psi_desc_service *)desc; curr_e = kzalloc_obj(*curr_e); if (!curr_e) { vidtv_channel_destroy_service_list(head_e); return NULL; } curr_e->service_id = s->service_id; curr_e->service_type = s_desc->service_type; if (!head_e) head_e = curr_e; if (prev_e) prev_e->next = curr_e; prev_e = curr_e; next_desc: desc = desc->next; } s = s->next; } return head_e; } int vidtv_channel_si_init(struct vidtv_mux *m) { struct vidtv_psi_desc_service_list_entry *service_list = NULL; struct vidtv_psi_table_pat_program *programs = NULL; struct vidtv_psi_table_sdt_service *services = NULL; struct vidtv_psi_table_eit_event *events = NULL; m->si.pat = vidtv_psi_pat_table_init(m->transport_stream_id); if (!m->si.pat) return -ENOMEM; m->si.sdt = vidtv_psi_sdt_table_init(m->network_id, m->transport_stream_id); if (!m->si.sdt) goto free_pat; programs = vidtv_channel_pat_prog_cat_into_new(m); if (!programs) goto free_sdt; services = vidtv_channel_sdt_serv_cat_into_new(m); if (!services) goto free_programs; events = vidtv_channel_eit_event_cat_into_new(m); if (!events) goto free_services; /* look for a service descriptor for every service */ service_list = vidtv_channel_build_service_list(services); if (!service_list) goto free_events; /* use these descriptors to build the NIT */ m->si.nit = vidtv_psi_nit_table_init(m->network_id, m->transport_stream_id, m->network_name, service_list); if (!m->si.nit) goto free_service_list; m->si.eit = vidtv_psi_eit_table_init(m->network_id, m->transport_stream_id, programs->service_id); if (!m->si.eit) goto free_nit; /* assemble all programs and assign to PAT */ vidtv_psi_pat_program_assign(m->si.pat, programs); programs = NULL; /* assemble all services and assign to SDT */ vidtv_psi_sdt_service_assign(m->si.sdt, services); services = NULL; /* assemble all events and assign to EIT */ vidtv_psi_eit_event_assign(m->si.eit, events); events = NULL; m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, m->pcr_pid); if (!m->si.pmt_secs) goto free_eit; vidtv_channel_pmt_match_sections(m->channels, m->si.pmt_secs, m->si.pat->num_pmt); vidtv_channel_destroy_service_list(service_list); return 0; free_eit: vidtv_psi_eit_table_destroy(m->si.eit); free_nit: vidtv_psi_nit_table_destroy(m->si.nit); free_service_list: vidtv_channel_destroy_service_list(service_list); free_events: vidtv_psi_eit_event_destroy(events); free_services: vidtv_psi_sdt_service_destroy(services); free_programs: vidtv_psi_pat_program_destroy(programs); free_sdt: vidtv_psi_sdt_table_destroy(m->si.sdt); free_pat: vidtv_psi_pat_table_destroy(m->si.pat); return -EINVAL; } void vidtv_channel_si_destroy(struct vidtv_mux *m) { u32 i; for (i = 0; i < m->si.pat->num_pmt; ++i) vidtv_psi_pmt_table_destroy(m->si.pmt_secs[i]); vidtv_psi_pat_table_destroy(m->si.pat); kfree(m->si.pmt_secs); vidtv_psi_sdt_table_destroy(m->si.sdt); vidtv_psi_nit_table_destroy(m->si.nit); vidtv_psi_eit_table_destroy(m->si.eit); } int vidtv_channels_init(struct vidtv_mux *m) { /* this is the place to add new 'channels' for vidtv */ m->channels = vidtv_channel_s302m_init(NULL, m->transport_stream_id); if (!m->channels) return -ENOMEM; return 0; } void vidtv_channels_destroy(struct vidtv_mux *m) { struct vidtv_channel *curr = m->channels; struct vidtv_channel *tmp = NULL; while (curr) { kfree(curr->name); vidtv_psi_sdt_service_destroy(curr->service); vidtv_psi_pat_program_destroy(curr->program); vidtv_psi_pmt_stream_destroy(curr->streams); vidtv_channel_encoder_destroy(curr->encoders); vidtv_psi_eit_event_destroy(curr->events); tmp = curr; curr = curr->next; kfree(tmp); } } |
| 31 11 18 12 140 53 135 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * * These are the definitions needed for the sctp_ulpevent type. The * sctp_ulpevent type is used to carry information from the state machine * upwards to the ULP. * * This file is part of the SCTP kernel implementation * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Jon Grimm <jgrimm@us.ibm.com> * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Sridhar Samudrala <sri@us.ibm.com> */ #ifndef __sctp_ulpevent_h__ #define __sctp_ulpevent_h__ /* A structure to carry information to the ULP (e.g. Sockets API) */ /* Warning: This sits inside an skb.cb[] area. Be very careful of * growing this structure as it is at the maximum limit now. * * sctp_ulpevent is saved in sk->cb(48 bytes), whose last 4 bytes * have been taken by sock_skb_cb, So here it has to use 'packed' * to make sctp_ulpevent fit into the rest 44 bytes. */ struct sctp_ulpevent { struct sctp_association *asoc; struct sctp_chunk *chunk; unsigned int rmem_len; union { __u32 mid; __u16 ssn; }; union { __u32 ppid; __u32 fsn; }; __u32 tsn; __u32 cumtsn; __u16 stream; __u16 flags; __u16 msg_flags; } __packed; /* Retrieve the skb this event sits inside of. */ static inline struct sk_buff *sctp_event2skb(const struct sctp_ulpevent *ev) { return container_of((void *)ev, struct sk_buff, cb); } /* Retrieve & cast the event sitting inside the skb. */ static inline struct sctp_ulpevent *sctp_skb2event(struct sk_buff *skb) { return (struct sctp_ulpevent *)skb->cb; } void sctp_ulpevent_free(struct sctp_ulpevent *); int sctp_ulpevent_is_notification(const struct sctp_ulpevent *); unsigned int sctp_queue_purge_ulpevents(struct sk_buff_head *list); struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( const struct sctp_association *asoc, __u16 flags, __u16 state, __u16 error, __u16 outbound, __u16 inbound, struct sctp_chunk *chunk, gfp_t gfp); void sctp_ulpevent_notify_peer_addr_change(struct sctp_transport *transport, int state, int error); struct sctp_ulpevent *sctp_ulpevent_make_remote_error( const struct sctp_association *asoc, struct sctp_chunk *chunk, __u16 flags, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_send_failed( const struct sctp_association *asoc, struct sctp_chunk *chunk, __u16 flags, __u32 error, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_send_failed_event( const struct sctp_association *asoc, struct sctp_chunk *chunk, __u16 flags, __u32 error, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_shutdown_event( const struct sctp_association *asoc, __u16 flags, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_pdapi( const struct sctp_association *asoc, __u32 indication, __u32 sid, __u32 seq, __u32 flags, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_adaptation_indication( const struct sctp_association *asoc, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, struct sctp_chunk *chunk, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_authkey( const struct sctp_association *asoc, __u16 key_id, __u32 indication, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_sender_dry_event( const struct sctp_association *asoc, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_stream_reset_event( const struct sctp_association *asoc, __u16 flags, __u16 stream_num, __be16 *stream_list, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_assoc_reset_event( const struct sctp_association *asoc, __u16 flags, __u32 local_tsn, __u32 remote_tsn, gfp_t gfp); struct sctp_ulpevent *sctp_ulpevent_make_stream_change_event( const struct sctp_association *asoc, __u16 flags, __u32 strchange_instrms, __u32 strchange_outstrms, gfp_t gfp); struct sctp_ulpevent *sctp_make_reassembled_event( struct net *net, struct sk_buff_head *queue, struct sk_buff *f_frag, struct sk_buff *l_frag); void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event, struct msghdr *); void sctp_ulpevent_read_rcvinfo(const struct sctp_ulpevent *event, struct msghdr *); void sctp_ulpevent_read_nxtinfo(const struct sctp_ulpevent *event, struct msghdr *, struct sock *sk); __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event); static inline void sctp_ulpevent_type_set(__u16 *subscribe, __u16 sn_type, __u8 on) { if (sn_type > SCTP_SN_TYPE_MAX) return; if (on) *subscribe |= (1 << (sn_type - SCTP_SN_TYPE_BASE)); else *subscribe &= ~(1 << (sn_type - SCTP_SN_TYPE_BASE)); } /* Is this event type enabled? */ static inline bool sctp_ulpevent_type_enabled(__u16 subscribe, __u16 sn_type) { if (sn_type > SCTP_SN_TYPE_MAX) return false; return subscribe & (1 << (sn_type - SCTP_SN_TYPE_BASE)); } /* Given an event subscription, is this event enabled? */ static inline bool sctp_ulpevent_is_enabled(const struct sctp_ulpevent *event, __u16 subscribe) { __u16 sn_type; if (!sctp_ulpevent_is_notification(event)) return true; sn_type = sctp_ulpevent_get_notification_type(event); return sctp_ulpevent_type_enabled(subscribe, sn_type); } #endif /* __sctp_ulpevent_h__ */ |
| 786 788 784 782 1 1 26 26 26 26 3 1 2 80 75 9 14 14 12 2 4 10 4 1 4 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/bpf_local_storage.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(sk_cache); static struct bpf_local_storage_data * bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_map *smap; sk_storage = rcu_dereference_check(sk->sk_bpf_storage, bpf_rcu_lock_held()); if (!sk_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = bpf_sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; return bpf_selem_unlink(SELEM(sdata)); } /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { struct bpf_local_storage *sk_storage; u32 uncharge; rcu_read_lock_dont_migrate(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) goto out; uncharge = bpf_local_storage_destroy(sk_storage); if (uncharge) atomic_sub(uncharge, &sk->sk_omem_alloc); out: rcu_read_unlock_migrate(); } static void bpf_sk_storage_map_free(struct bpf_map *map) { bpf_local_storage_map_free(map, &sk_cache); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { return bpf_local_storage_map_alloc(attr, &sk_cache); } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_sk_storage_lookup(sock->sk, map, true); sockfd_put(sock); return sdata ? sdata->data : NULL; } return ERR_PTR(err); } static long bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_local_storage_update( sock->sk, (struct bpf_local_storage_map *)map, value, map_flags, false); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } return err; } static long bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) { struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { err = bpf_sk_storage_del(sock->sk, map); sockfd_put(sock); return err; } return err; } static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_elem *copy_selem; copy_selem = bpf_selem_alloc(smap, newsk, NULL, false); if (!copy_selem) return NULL; if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data, true); else copy_map_value(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data); return copy_selem; } int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { struct bpf_local_storage *new_sk_storage = NULL; struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; int ret = 0; RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); rcu_read_lock_dont_migrate(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { struct bpf_local_storage_elem *copy_selem; struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); if (!smap || !(smap->map.map_flags & BPF_F_CLONE)) continue; /* Note that for lockless listeners adding new element * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ map = bpf_map_inc_not_zero(&smap->map); if (IS_ERR(map)) continue; copy_selem = bpf_sk_storage_clone_elem(newsk, smap, selem); if (!copy_selem) { ret = -ENOMEM; bpf_map_put(map); goto out; } if (new_sk_storage) { ret = bpf_selem_link_map(smap, new_sk_storage, copy_selem); if (ret) { bpf_selem_free(copy_selem, true); atomic_sub(smap->elem_size, &newsk->sk_omem_alloc); bpf_map_put(map); goto out; } bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { ret = bpf_local_storage_alloc(newsk, smap, copy_selem); if (ret) { bpf_selem_free(copy_selem, true); atomic_sub(smap->elem_size, &newsk->sk_omem_alloc); bpf_map_put(map); goto out; } new_sk_storage = rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } out: rcu_read_unlock_migrate(); /* In case of an error, don't free anything explicitly here, the * caller is responsible to call bpf_sk_storage_free. */ return ret; } BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { struct bpf_local_storage_data *sdata; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = bpf_sk_storage_lookup(sk, map, true); if (sdata) return (unsigned long)sdata->data; if (flags == BPF_SK_STORAGE_GET_F_CREATE && /* Cannot add new elem to a going away sk. * Otherwise, the new elem may become a leak * (and also other memory issues during map * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { sdata = bpf_local_storage_update( sk, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, false); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ sock_put(sk); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } return (unsigned long)NULL; } BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk)) return -EINVAL; if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; err = bpf_sk_storage_del(sk, map); sock_put(sk); return err; } return -ENOENT; } static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct sock *sk = (struct sock *)owner; int optmem_max; optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); /* same check as in sock_kmalloc() */ if (size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { atomic_add(size, &sk->sk_omem_alloc); return 0; } return -ENOMEM; } static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct sock *sk = owner; atomic_sub(size, &sk->sk_omem_alloc); } static struct bpf_local_storage __rcu ** bpf_sk_storage_ptr(void *owner) { struct sock *sk = owner; return &sk->sk_bpf_storage; } const struct bpf_map_ops sk_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = bpf_sk_storage_map_alloc, .map_free = bpf_sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_local_storage_charge = bpf_sk_storage_charge, .map_local_storage_uncharge = bpf_sk_storage_uncharge, .map_owner_storage_ptr = bpf_sk_storage_ptr, .map_mem_usage = bpf_local_storage_map_mem_usage, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_CTX, /* context is 'struct sock' */ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_delete_proto = { .func = bpf_sk_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) { if (prog->aux->dst_prog) return false; /* Ensure the tracing program is not tracing * any bpf_sk_storage*() function and also * use the bpf_sk_storage_(get|delete) helper. */ switch (prog->expected_attach_type) { case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: /* bpf_sk_storage has no trace point */ return true; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: return !!strncmp(prog->aux->attach_func_name, "bpf_sk_storage", strlen("bpf_sk_storage")); default: return false; } return false; } BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return (unsigned long)NULL; return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags); } BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return -EPERM; return ____bpf_sk_storage_delete(map, sk); } const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = { .func = bpf_sk_storage_get_tracing, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, .allowed = bpf_sk_storage_tracing_allowed, }; const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = { .func = bpf_sk_storage_delete_tracing, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .allowed = bpf_sk_storage_tracing_allowed, }; struct bpf_sk_storage_diag { u32 nr_maps; struct bpf_map *maps[]; }; /* The reply will be like: * INET_DIAG_BPF_SK_STORAGES (nla_nest) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * .... */ static int nla_value_size(u32 value_size) { /* SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) */ return nla_total_size(0) + nla_total_size(sizeof(u32)) + nla_total_size_64bit(value_size); } void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag) { u32 i; if (!diag) return; for (i = 0; i < diag->nr_maps; i++) bpf_map_put(diag->maps[i]); kfree(diag); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_free); static bool diag_check_dup(const struct bpf_sk_storage_diag *diag, const struct bpf_map *map) { u32 i; for (i = 0; i < diag->nr_maps; i++) { if (diag->maps[i] == map) return true; } return false; } struct bpf_sk_storage_diag * bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) { struct bpf_sk_storage_diag *diag; struct nlattr *nla; u32 nr_maps = 0; int rem, err; /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) return ERR_PTR(-EPERM); nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, nla_stgs, rem) { if (nla_len(nla) != sizeof(u32)) return ERR_PTR(-EINVAL); nr_maps++; } diag = kzalloc_flex(*diag, maps, nr_maps); if (!diag) return ERR_PTR(-ENOMEM); nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, nla_stgs, rem) { int map_fd = nla_get_u32(nla); struct bpf_map *map = bpf_map_get(map_fd); if (IS_ERR(map)) { err = PTR_ERR(map); goto err_free; } if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) { bpf_map_put(map); err = -EINVAL; goto err_free; } if (diag_check_dup(diag, map)) { bpf_map_put(map); err = -EEXIST; goto err_free; } diag->maps[diag->nr_maps++] = map; } return diag; err_free: bpf_sk_storage_diag_free(diag); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); static int diag_get(struct bpf_local_storage_map *smap, struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; /* It cannot exceed max nlattr's payload */ BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) return -EMSGSIZE; if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id)) goto errout; nla_value = nla_reserve_64bit(skb, SK_DIAG_BPF_STORAGE_MAP_VALUE, smap->map.value_size, SK_DIAG_BPF_STORAGE_PAD); if (!nla_value) goto errout; if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, nla_data(nla_value), sdata->data, true); else copy_map_value(&smap->map, nla_data(nla_value), sdata->data); check_and_init_map_value(&smap->map, nla_data(nla_value)); nla_nest_end(skb, nla_stg); return 0; errout: nla_nest_cancel(skb, nla_stg); return -EMSGSIZE; } static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { smap = rcu_dereference(SDATA(selem)->smap); if (!smap) continue; diag_size += nla_value_size(smap->map.value_size); if (nla_stgs && diag_get(smap, SDATA(selem), skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; u32 i; *res_diag_size = 0; /* No map has been specified. Dump all. */ if (!diag->nr_maps) return bpf_sk_storage_diag_put_all(sk, skb, stg_array_type, res_diag_size); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { sdata = bpf_local_storage_lookup(sk_storage, (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) continue; diag_size += nla_value_size(diag->maps[i]->value_size); if (nla_stgs && diag_get((struct bpf_local_storage_map *)diag->maps[i], sdata, skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); struct bpf_iter_seq_sk_storage_map_info { struct bpf_map *map; unsigned int bucket_id; unsigned skip_elems; }; static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, struct bpf_local_storage_elem *prev_selem) __acquires(RCU) __releases(RCU) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; struct bpf_local_storage_map_bucket *b; smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; /* try to find next selem in the same bucket */ selem = prev_selem; count = 0; while (selem) { selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)), struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; rcu_read_unlock(); skip_elems = 0; break; } sk_storage = rcu_dereference(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; } count++; } for (i = bucket_id; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); count = 0; hlist_for_each_entry_rcu(selem, &b->list, map_node) { sk_storage = rcu_dereference(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; return selem; } count++; } rcu_read_unlock(); skip_elems = 0; } info->bucket_id = i; info->skip_elems = 0; return NULL; } static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) return NULL; if (*pos == 0) ++*pos; return selem; } static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; ++*pos; ++info->skip_elems; return bpf_sk_storage_map_seq_find_next(seq->private, v); } struct bpf_iter__bpf_sk_storage_map { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(struct sock *, sk); __bpf_md_ptr(void *, value); }; DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, struct bpf_map *map, struct sock *sk, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; meta.seq = seq; prog = bpf_iter_get_info(&meta, selem == NULL); if (prog) { ctx.meta = &meta; ctx.map = info->map; if (selem) { sk_storage = rcu_dereference(selem->local_storage); ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); } return ret; } static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) { return __bpf_sk_storage_map_seq_show(seq, v); } static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { if (!v) (void)__bpf_sk_storage_map_seq_show(seq, v); else rcu_read_unlock(); } static int bpf_iter_init_sk_storage_map(void *priv_data, struct bpf_iter_aux_info *aux) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_inc_with_uref(aux->map); seq_info->map = aux->map; return 0; } static void bpf_iter_fini_sk_storage_map(void *priv_data) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_put_with_uref(seq_info->map); } static int bpf_iter_attach_map(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) { struct bpf_map *map; int err = -EINVAL; if (!linfo->map.map_fd) return -EBADF; map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto put_map; if (prog->aux->max_rdwr_access > map->value_size) { err = -EACCES; goto put_map; } aux->map = map; return 0; put_map: bpf_map_put_with_uref(map); return err; } static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) { bpf_map_put_with_uref(aux->map); } static const struct seq_operations bpf_sk_storage_map_seq_ops = { .start = bpf_sk_storage_map_seq_start, .next = bpf_sk_storage_map_seq_next, .stop = bpf_sk_storage_map_seq_stop, .show = bpf_sk_storage_map_seq_show, }; static const struct bpf_iter_seq_info iter_seq_info = { .seq_ops = &bpf_sk_storage_map_seq_ops, .init_seq_private = bpf_iter_init_sk_storage_map, .fini_seq_private = bpf_iter_fini_sk_storage_map, .seq_priv_size = sizeof(struct bpf_iter_seq_sk_storage_map_info), }; static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, .show_fdinfo = bpf_iter_map_show_fdinfo, .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), PTR_TO_BTF_ID_OR_NULL }, { offsetof(struct bpf_iter__bpf_sk_storage_map, value), PTR_TO_BUF | PTR_MAYBE_NULL }, }, .seq_info = &iter_seq_info, }; static int __init bpf_sk_storage_map_iter_init(void) { bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK]; return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info); } late_initcall(bpf_sk_storage_map_iter_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #ifndef RXE_LOC_H #define RXE_LOC_H /* rxe_av.c */ void rxe_init_av(struct rdma_ah_attr *attr, struct rxe_av *av); int rxe_av_chk_attr(struct rxe_qp *qp, struct rdma_ah_attr *attr); int rxe_ah_chk_attr(struct rxe_ah *ah, struct rdma_ah_attr *attr); void rxe_av_from_attr(u8 port_num, struct rxe_av *av, struct rdma_ah_attr *attr); void rxe_av_to_attr(struct rxe_av *av, struct rdma_ah_attr *attr); void rxe_av_fill_ip_info(struct rxe_av *av, struct rdma_ah_attr *attr); struct rxe_av *rxe_get_av(struct rxe_pkt_info *pkt, struct rxe_ah **ahp); /* rxe_cq.c */ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, int comp_vector, struct ib_udata *udata, struct rxe_create_cq_resp __user *uresp); int rxe_cq_resize_queue(struct rxe_cq *cq, int new_cqe, struct rxe_resize_cq_resp __user *uresp, struct ib_udata *udata); int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited); void rxe_cq_cleanup(struct rxe_pool_elem *elem); /* rxe_mcast.c */ struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid); int rxe_attach_mcast(struct ib_qp *ibqp, union ib_gid *mgid, u16 mlid); int rxe_detach_mcast(struct ib_qp *ibqp, union ib_gid *mgid, u16 mlid); void rxe_cleanup_mcg(struct kref *kref); /* rxe_mmap.c */ struct rxe_mmap_info { struct list_head pending_mmaps; struct ib_ucontext *context; struct kref ref; void *obj; struct mminfo info; }; void rxe_mmap_release(struct kref *ref); struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *dev, u32 size, struct ib_udata *udata, void *obj); int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma); /* rxe_mr.c */ u8 rxe_get_next_key(u32 last_key); void rxe_mr_init(int access, struct rxe_mr *mr); void rxe_mr_init_dma(int access, struct rxe_mr *mr); int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, int access, struct rxe_mr *mr); int rxe_mr_init_fast(int max_pages, struct rxe_mr *mr); int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length); int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, unsigned int length, enum rxe_mr_copy_dir dir); int copy_data(struct rxe_pd *pd, int access, struct rxe_dma_info *dma, void *addr, int length, enum rxe_mr_copy_dir dir); int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); enum resp_states rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, u64 compare, u64 swap_add, u64 *orig_val); enum resp_states rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value); struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, enum rxe_mr_lookup_type type); int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length); int advance_dma_data(struct rxe_dma_info *dma, unsigned int length); int rxe_invalidate_mr(struct rxe_qp *qp, u32 key); int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe); void rxe_mr_cleanup(struct rxe_pool_elem *elem); /* defined in rxe_mr.c; used in rxe_mr.c and rxe_odp.c */ extern spinlock_t atomic_ops_lock; /* rxe_mw.c */ int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata); int rxe_dealloc_mw(struct ib_mw *ibmw); int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe); int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey); struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey); void rxe_mw_cleanup(struct rxe_pool_elem *elem); /* rxe_net.c */ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, int paylen, struct rxe_pkt_info *pkt); int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb); int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct sk_buff *skb); const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num); /* rxe_qp.c */ int rxe_qp_chk_init(struct rxe_dev *rxe, struct ib_qp_init_attr *init); int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, struct ib_qp_init_attr *init, struct rxe_create_qp_resp __user *uresp, struct ib_pd *ibpd, struct ib_udata *udata); int rxe_qp_to_init(struct rxe_qp *qp, struct ib_qp_init_attr *init); int rxe_qp_chk_attr(struct rxe_dev *rxe, struct rxe_qp *qp, struct ib_qp_attr *attr, int mask); int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, struct ib_udata *udata); int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask); void rxe_qp_error(struct rxe_qp *qp); int rxe_qp_chk_destroy(struct rxe_qp *qp); void rxe_qp_cleanup(struct rxe_pool_elem *elem); static inline int qp_num(struct rxe_qp *qp) { return qp->ibqp.qp_num; } static inline enum ib_qp_type qp_type(struct rxe_qp *qp) { return qp->ibqp.qp_type; } static inline enum ib_qp_state qp_state(struct rxe_qp *qp) { return qp->attr.qp_state; } static inline int qp_mtu(struct rxe_qp *qp) { if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) return qp->attr.path_mtu; else return IB_MTU_4096; } static inline bool is_odp_mr(struct rxe_mr *mr) { return IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && mr->umem && mr->umem->is_odp; } void free_rd_atomic_resource(struct resp_res *res); static inline void rxe_advance_resp_resource(struct rxe_qp *qp) { qp->resp.res_head++; if (unlikely(qp->resp.res_head == qp->attr.max_dest_rd_atomic)) qp->resp.res_head = 0; } void retransmit_timer(struct timer_list *t); void rnr_nak_timer(struct timer_list *t); /* rxe_srq.c */ int rxe_srq_chk_init(struct rxe_dev *rxe, struct ib_srq_init_attr *init); int rxe_srq_from_init(struct rxe_dev *rxe, struct rxe_srq *srq, struct ib_srq_init_attr *init, struct ib_udata *udata, struct rxe_create_srq_resp __user *uresp); int rxe_srq_chk_attr(struct rxe_dev *rxe, struct rxe_srq *srq, struct ib_srq_attr *attr, enum ib_srq_attr_mask mask); int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq, struct ib_srq_attr *attr, enum ib_srq_attr_mask mask, struct rxe_modify_srq_cmd *ucmd, struct ib_udata *udata); void rxe_srq_cleanup(struct rxe_pool_elem *elem); void rxe_dealloc(struct ib_device *ib_dev); int rxe_completer(struct rxe_qp *qp); int rxe_requester(struct rxe_qp *qp); int rxe_sender(struct rxe_qp *qp); int rxe_receiver(struct rxe_qp *qp); /* rxe_icrc.c */ int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt); void rxe_icrc_generate(struct sk_buff *skb, struct rxe_pkt_info *pkt); void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb); void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb); static inline unsigned int wr_opcode_mask(int opcode, struct rxe_qp *qp) { return rxe_wr_opcode_info[opcode].mask[qp->ibqp.qp_type]; } /* rxe_odp.c */ extern const struct mmu_interval_notifier_ops rxe_mn_ops; #if defined CONFIG_INFINIBAND_ON_DEMAND_PAGING int rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova, int access_flags, struct rxe_mr *mr); int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, enum rxe_mr_copy_dir dir); enum resp_states rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, u64 compare, u64 swap_add, u64 *orig_val); int rxe_odp_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length); enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value); int rxe_ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs); #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */ static inline int rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova, int access_flags, struct rxe_mr *mr) { return -EOPNOTSUPP; } static inline int rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length, enum rxe_mr_copy_dir dir) { return -EOPNOTSUPP; } static inline enum resp_states rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, u64 compare, u64 swap_add, u64 *orig_val) { return RESPST_ERR_UNSUPPORTED_OPCODE; } static inline int rxe_odp_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length) { return -EOPNOTSUPP; } static inline enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) { return RESPST_ERR_UNSUPPORTED_OPCODE; } static inline int rxe_ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs) { return -EOPNOTSUPP; } #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */ #endif /* RXE_LOC_H */ |
| 654 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Filesystem superblock creation and reconfiguration context. * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_FS_CONTEXT_H #define _LINUX_FS_CONTEXT_H #include <linux/kernel.h> #include <linux/refcount.h> #include <linux/errno.h> #include <linux/security.h> #include <linux/mutex.h> struct cred; struct dentry; struct file_operations; struct file_system_type; struct mnt_namespace; struct net; struct pid_namespace; struct super_block; struct user_namespace; struct vfsmount; struct path; enum fs_context_purpose { FS_CONTEXT_FOR_MOUNT, /* New superblock for explicit mount */ FS_CONTEXT_FOR_SUBMOUNT, /* New superblock for automatic submount */ FS_CONTEXT_FOR_RECONFIGURE, /* Superblock reconfiguration (remount) */ }; /* * Userspace usage phase for fsopen/fspick. */ enum fs_context_phase { FS_CONTEXT_CREATE_PARAMS, /* Loading params for sb creation */ FS_CONTEXT_CREATING, /* A superblock is being created */ FS_CONTEXT_AWAITING_MOUNT, /* Superblock created, awaiting fsmount() */ FS_CONTEXT_AWAITING_RECONF, /* Awaiting initialisation for reconfiguration */ FS_CONTEXT_RECONF_PARAMS, /* Loading params for reconfiguration */ FS_CONTEXT_RECONFIGURING, /* Reconfiguring the superblock */ FS_CONTEXT_FAILED, /* Failed to correctly transition a context */ }; /* * Type of parameter value. */ enum fs_value_type { fs_value_is_undefined, fs_value_is_flag, /* Value not given a value */ fs_value_is_string, /* Value is a string */ fs_value_is_blob, /* Value is a binary blob */ fs_value_is_filename, /* Value is a filename* + dirfd */ fs_value_is_file, /* Value is a file* */ }; /* * Configuration parameter. */ struct fs_parameter { const char *key; /* Parameter name */ enum fs_value_type type:8; /* The type of value here */ union { char *string; void *blob; struct filename *name; struct file *file; }; size_t size; int dirfd; }; struct p_log { const char *prefix; struct fc_log *log; }; /* * Filesystem context for holding the parameters used in the creation or * reconfiguration of a superblock. * * Superblock creation fills in ->root whereas reconfiguration begins with this * already set. * * See Documentation/filesystems/mount_api.rst */ struct fs_context { const struct fs_context_operations *ops; struct mutex uapi_mutex; /* Userspace access mutex */ struct file_system_type *fs_type; void *fs_private; /* The filesystem's context */ void *sget_key; struct dentry *root; /* The root and superblock */ struct user_namespace *user_ns; /* The user namespace for this mount */ struct net *net_ns; /* The network namespace for this mount */ const struct cred *cred; /* The mounter's credentials */ struct p_log log; /* Logging buffer */ const char *source; /* The source name (eg. dev path) */ void *security; /* LSM options */ void *s_fs_info; /* Proposed s_fs_info */ unsigned int sb_flags; /* Proposed superblock flags (SB_*) */ unsigned int sb_flags_mask; /* Superblock flags that were changed */ unsigned int s_iflags; /* OR'd with sb->s_iflags */ enum fs_context_purpose purpose:8; enum fs_context_phase phase:8; /* The phase the context is in */ bool need_free:1; /* Need to call ops->free() */ bool global:1; /* Goes into &init_user_ns */ bool oldapi:1; /* Coming from mount(2) */ bool exclusive:1; /* create new superblock, reject existing one */ }; struct fs_context_operations { void (*free)(struct fs_context *fc); int (*dup)(struct fs_context *fc, struct fs_context *src_fc); int (*parse_param)(struct fs_context *fc, struct fs_parameter *param); int (*parse_monolithic)(struct fs_context *fc, void *data); int (*get_tree)(struct fs_context *fc); int (*reconfigure)(struct fs_context *fc); }; /* * fs_context manipulation functions. */ extern struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, unsigned int sb_flags); extern struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, unsigned int sb_flags, unsigned int sb_flags_mask); extern struct fs_context *fs_context_for_submount(struct file_system_type *fs_type, struct dentry *reference); extern struct fs_context *vfs_dup_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param); extern int vfs_parse_fs_qstr(struct fs_context *fc, const char *key, const struct qstr *value); static inline int vfs_parse_fs_string(struct fs_context *fc, const char *key, const char *value) { return vfs_parse_fs_qstr(fc, key, value ? &QSTR(value) : NULL); } int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, char *(*sep)(char **)); extern int generic_parse_monolithic(struct fs_context *fc, void *data); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); extern int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); extern int get_tree_single(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); extern int get_tree_keyed(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), void *key); int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc); #define GET_TREE_BDEV_QUIET_LOOKUP 0x0001 int get_tree_bdev_flags(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), unsigned int flags); extern int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); extern const struct file_operations fscontext_fops; /* * Mount error, warning and informational message logging. This structure is * shareable between a mount and a subordinate mount. */ struct fc_log { refcount_t usage; u8 head; /* Insertion index in buffer[] */ u8 tail; /* Removal index in buffer[] */ u8 need_free; /* Mask of kfree'able items in buffer[] */ struct module *owner; /* Owner module for strings that don't then need freeing */ char *buffer[8]; }; extern __attribute__((format(printf, 4, 5))) void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...); #define __logfc(fc, l, fmt, ...) \ logfc((fc)->log.log, NULL, (l), (fmt), ## __VA_ARGS__) #define __plogp(p, prefix, l, fmt, ...) \ logfc((p)->log, (prefix), (l), (fmt), ## __VA_ARGS__) #define __plog(p, l, fmt, ...) __plogp(p, (p)->prefix, l, fmt, ## __VA_ARGS__) /** * infof - Store supplementary informational message * @fc: The context in which to log the informational message * @fmt: The format string * * Store the supplementary informational message for the process if the process * has enabled the facility. */ #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__) #define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) #define infofcp(fc, prefix, fmt, ...) \ __plogp((&(fc)->log), prefix, 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message * @fc: The context in which to log the error message * @fmt: The format string * * Store the supplementary warning message for the process if the process has * enabled the facility. */ #define warnf(fc, fmt, ...) __logfc(fc, 'w', fmt, ## __VA_ARGS__) #define warn_plog(p, fmt, ...) __plog(p, 'w', fmt, ## __VA_ARGS__) #define warnfc(fc, fmt, ...) __plog((&(fc)->log), 'w', fmt, ## __VA_ARGS__) #define warnfcp(fc, prefix, fmt, ...) \ __plogp((&(fc)->log), prefix, 'w', fmt, ## __VA_ARGS__) /** * errorf - Store supplementary error message * @fc: The context in which to log the error message * @fmt: The format string * * Store the supplementary error message for the process if the process has * enabled the facility. */ #define errorf(fc, fmt, ...) __logfc(fc, 'e', fmt, ## __VA_ARGS__) #define error_plog(p, fmt, ...) __plog(p, 'e', fmt, ## __VA_ARGS__) #define errorfc(fc, fmt, ...) __plog((&(fc)->log), 'e', fmt, ## __VA_ARGS__) #define errorfcp(fc, prefix, fmt, ...) \ __plogp((&(fc)->log), prefix, 'e', fmt, ## __VA_ARGS__) /** * invalf - Store supplementary invalid argument error message * @fc: The context in which to log the error message * @fmt: The format string * * Store the supplementary error message for the process if the process has * enabled the facility and return -EINVAL. */ #define invalf(fc, fmt, ...) (errorf(fc, fmt, ## __VA_ARGS__), -EINVAL) #define inval_plog(p, fmt, ...) (error_plog(p, fmt, ## __VA_ARGS__), -EINVAL) #define invalfc(fc, fmt, ...) (errorfc(fc, fmt, ## __VA_ARGS__), -EINVAL) #define invalfcp(fc, prefix, fmt, ...) \ (errorfcp(fc, prefix, fmt, ## __VA_ARGS__), -EINVAL) #endif /* _LINUX_FS_CONTEXT_H */ |
| 12 13 13 12 86 92 1 5 86 75 10 7 2 2 3 86 26 7 10 43 4 8 4 5 4 6 5 47 3 3 44 44 8 12 6 6 25 1 4 7 5 18 1 2 3 32 44 32 10 92 8 22 2 27 21 27 21 13 21 12 8 21 8 8 26 13 13 27 20 7 14 13 12 2 12 10 10 108 6 104 2 2 101 100 104 4 98 2 6 92 3 10 9 98 15 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/plist.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/freezer.h> #include "futex.h" /* * READ this before attempting to hack on futexes! * * Basic futex operation and ordering guarantees * ============================================= * * The waiter reads the futex value in user space and calls * futex_wait(). This function computes the hash bucket and acquires * the hash bucket lock. After that it reads the futex user space value * again and verifies that the data has not changed. If it has not changed * it enqueues itself into the hash bucket, releases the hash bucket lock * and schedules. * * The waker side modifies the user space value of the futex and calls * futex_wake(). This function computes the hash bucket and acquires the * hash bucket lock. Then it looks for waiters on that futex in the hash * bucket and wakes them. * * In futex wake up scenarios where no tasks are blocked on a futex, taking * the hb spinlock can be avoided and simply return. In order for this * optimization to work, ordering guarantees must exist so that the waiter * being added to the list is acknowledged when the list is concurrently being * checked by the waker, avoiding scenarios like the following: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * uval = *futex; * *futex = newval; * sys_futex(WAKE, futex); * futex_wake(futex); * if (queue_empty()) * return; * if (uval == val) * lock(hash_bucket(futex)); * queue(); * unlock(hash_bucket(futex)); * schedule(); * * This would cause the waiter on CPU 0 to wait forever because it * missed the transition of the user space value from val to newval * and the waker did not find the waiter in the hash bucket queue. * * The correct serialization ensures that a waiter either observes * the changed user space value before blocking or is woken by a * concurrent waker: * * CPU 0 CPU 1 * val = *futex; * sys_futex(WAIT, futex, val); * futex_wait(futex, val); * * waiters++; (a) * smp_mb(); (A) <-- paired with -. * | * lock(hash_bucket(futex)); | * | * uval = *futex; | * | *futex = newval; * | sys_futex(WAKE, futex); * | futex_wake(futex); * | * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); * schedule(); if (waiters) * lock(hash_bucket(futex)); * else wake_waiters(futex); * waiters--; (b) unlock(hash_bucket(futex)); * * Where (A) orders the waiters increment and the futex value read through * atomic operations (see futex_hb_waiters_inc) and where (B) orders the write * to futex and the waiters read (see futex_hb_waiters_pending()). * * This yields the following case (where X:=waiters, Y:=futex): * * X = Y = 0 * * w[X]=1 w[Y]=1 * MB MB * r[Y]=y r[X]=x * * Which guarantees that x==0 && y==0 is impossible; which translates back into * the guarantee that we cannot both miss the futex variable change and the * enqueue. * * Note that a new waiter is accounted for in (a) even when it is possible that * the wait call can return error, in which case we backtrack from it in (b). * Refer to the comment in futex_q_lock(). * * Similarly, in order to account for waiters being requeued on another * address we always increment the waiters for the destination bucket before * acquiring the lock. It then decrements them again after releasing it - * the code that actually moves the futex(es) between hash buckets (requeue_futex) * will do the additional required waiter count housekeeping. This is done for * double_lock_hb() and double_unlock_hb(), respectively. */ bool __futex_wake_mark(struct futex_q *q) { if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) return false; __futex_unqueue(q); /* * The waiting task can free the futex_q as soon as q->lock_ptr = NULL * is written, without taking any locks. This is possible in the event * of a spurious wakeup, for example. A memory barrier is required here * to prevent the following store to lock_ptr from getting ahead of the * plist_del in __futex_unqueue(). */ smp_store_release(&q->lock_ptr, NULL); return true; } /* * The hash bucket lock must be held when this is called. * Afterwards, the futex_q must not be accessed. Callers * must ensure to later call wake_up_q() for the actual * wakeups to occur. */ void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q) { struct task_struct *p = q->task; get_task_struct(p); if (!__futex_wake_mark(q)) { put_task_struct(p); return; } /* * Queue the task for later wakeup for after we've released * the hb->lock. */ wake_q_add_safe(wake_q, p); } /* * If requested, clear the robust list pending op and unlock the futex */ static bool futex_robust_unlock(u32 __user *uaddr, unsigned int flags, void __user *pop) { if (!(flags & FLAGS_ROBUST_UNLOCK)) return true; /* First unlock the futex, which requires release semantics. */ scoped_user_write_access(uaddr, efault) unsafe_atomic_store_release_user(0, uaddr, efault); /* * Clear the pending list op now. If that fails, then the task is in * deeper trouble as the robust list head is usually part of the TLS. * The chance of survival is close to zero. */ return futex_robust_list_clear_pending(pop, flags); efault: return false; } /* * Wake up waiters matching bitset queued on this futex (uaddr). */ int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop, int nr_wake, u32 bitset) { union futex_key key = FUTEX_KEY_INIT; struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); int ret; if (!bitset) return -EINVAL; ret = get_futex_key(uaddr, flags, &key, FUTEX_READ); if (unlikely(ret != 0)) return ret; if (!futex_robust_unlock(uaddr, flags, pop)) return -EFAULT; if ((flags & FLAGS_STRICT) && !nr_wake) return 0; CLASS(hbr, hbr)(&key); auto hb = hbr.hb; /* Make sure we really have tasks to wakeup */ if (!futex_hb_waiters_pending(hb)) return ret; spin_lock(&hb->lock); plist_for_each_entry_safe(this, next, &hb->chain, list) { if (futex_match (&this->key, &key)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; break; } /* Check if one of the bits is set in both bitsets */ if (!(this->bitset & bitset)) continue; this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } spin_unlock(&hb->lock); wake_up_q(&wake_q); return ret; } static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) { unsigned int op = (encoded_op & 0x70000000) >> 28; unsigned int cmp = (encoded_op & 0x0f000000) >> 24; int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11); int cmparg = sign_extend32(encoded_op & 0x00000fff, 11); int oldval, ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { if (oparg < 0 || oparg > 31) { /* * kill this print and return -EINVAL when userspace * is sane again */ pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", current->comm, oparg); oparg &= 31; } oparg = 1 << oparg; } pagefault_disable(); ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr); pagefault_enable(); if (ret) return ret; switch (cmp) { case FUTEX_OP_CMP_EQ: return oldval == cmparg; case FUTEX_OP_CMP_NE: return oldval != cmparg; case FUTEX_OP_CMP_LT: return oldval < cmparg; case FUTEX_OP_CMP_GE: return oldval >= cmparg; case FUTEX_OP_CMP_LE: return oldval <= cmparg; case FUTEX_OP_CMP_GT: return oldval > cmparg; default: return -ENOSYS; } } /* * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_q *this, *next; int ret, op_ret; DEFINE_WAKE_Q(wake_q); retry: ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ); if (unlikely(ret != 0)) return ret; ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE); if (unlikely(ret != 0)) return ret; retry_private: if (1) { CLASS(hbr, hbr1)(&key1); CLASS(hbr, hbr2)(&key2); auto hb1 = hbr1.hb; auto hb2 = hbr2.hb; double_lock_hb(hb1, hb2); op_ret = futex_atomic_op_inuser(op, uaddr2); if (unlikely(op_ret < 0)) { double_unlock_hb(hb1, hb2); if (!IS_ENABLED(CONFIG_MMU) || unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) { /* * we don't get EFAULT from MMU faults if we don't have * an MMU, but we might get them from range checking */ ret = op_ret; return ret; } if (op_ret == -EFAULT) { ret = fault_in_user_writeable(uaddr2); if (ret) return ret; } cond_resched(); if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } plist_for_each_entry_safe(this, next, &hb1->chain, list) { if (futex_match(&this->key, &key1)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++ret >= nr_wake) break; } } if (op_ret > 0) { op_ret = 0; plist_for_each_entry_safe(this, next, &hb2->chain, list) { if (futex_match(&this->key, &key2)) { if (this->pi_state || this->rt_waiter) { ret = -EINVAL; goto out_unlock; } this->wake(&wake_q, this); if (++op_ret >= nr_wake2) break; } } ret += op_ret; } out_unlock: double_unlock_hb(hb1, hb2); } wake_up_q(&wake_q); return ret; } static long futex_wait_restart(struct restart_block *restart); /** * futex_do_wait() - wait for wakeup, timeout, or signal * @q: the futex_q to queue up on * @timeout: the prepared hrtimer_sleeper, or null for no timeout */ void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout) { /* Arm the timer */ if (timeout) hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS); /* * If we have been removed from the hash list, then another task * has tried to wake us, and we can skip the call to schedule(). */ if (likely(!plist_node_empty(&q->list))) { /* * If the timer has already expired, current will already be * flagged for rescheduling. Only call schedule if there * is no timeout, or if it has yet to expire. */ if (!timeout || timeout->task) schedule(); } __set_current_state(TASK_RUNNING); } /** * futex_unqueue_multiple - Remove various futexes from their hash bucket * @v: The list of futexes to unqueue * @count: Number of futexes in the list * * Helper to unqueue a list of futexes. This can't fail. * * Return: * - >=0 - Index of the last futex that was awoken; * - -1 - No futex was awoken */ int futex_unqueue_multiple(struct futex_vector *v, int count) { int ret = -1, i; for (i = 0; i < count; i++) { if (!futex_unqueue(&v[i].q)) ret = i; } return ret; } /** * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes * @vs: The futex list to wait on * @count: The size of the list * @woken: Index of the last woken futex, if any. Used to notify the * caller that it can return this index to userspace (return parameter) * * Prepare multiple futexes in a single step and enqueue them. This may fail if * the futex list is invalid or if any futex was already awoken. On success the * task is ready to interruptible sleep. * * Return: * - 1 - One of the futexes was woken by another thread * - 0 - Success * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL */ int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) { bool retry = false; int ret, i; u32 uval; /* * Make sure to have a reference on the private_hash such that we * don't block on rehash after changing the task state below. */ guard(private_hash)(current->mm); /* * Enqueuing multiple futexes is tricky, because we need to enqueue * each futex on the list before dealing with the next one to avoid * deadlocking on the hash bucket. But, before enqueuing, we need to * make sure that current->state is TASK_INTERRUPTIBLE, so we don't * lose any wake events, which cannot be done before the get_futex_key * of the next key, because it calls get_user_pages, which can sleep. * Thus, we fetch the list of futexes keys in two steps, by first * pinning all the memory keys in the futex key, and only then we read * each key and queue the corresponding futex. * * Private futexes doesn't need to recalculate hash in retry, so skip * get_futex_key() when retrying. */ retry: for (i = 0; i < count; i++) { if (!(vs[i].w.flags & FLAGS_SHARED) && retry) continue; ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), vs[i].w.flags, &vs[i].q.key, FUTEX_READ); if (unlikely(ret)) return ret; } set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); for (i = 0; i < count; i++) { u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; struct futex_q *q = &vs[i].q; u32 val = vs[i].w.val; if (1) { CLASS(hbr, hbr)(&q->key); auto hb = hbr.hb; futex_q_lock(q, hb); ret = futex_get_value_locked(&uval, uaddr); if (!ret && uval == val) { /* * The bucket lock can't be held while dealing with the * next futex. Queue each futex at this moment so hb can * be unlocked. */ futex_queue(q, hb, current); continue; } futex_q_unlock(hb); __release(q->lock_ptr); } __set_current_state(TASK_RUNNING); /* * Even if something went wrong, if we find out that a futex * was woken, we don't return error and return this index to * userspace */ *woken = futex_unqueue_multiple(vs, i); if (*woken >= 0) return 1; if (ret) { /* * If we need to handle a page fault, we need to do so * without any lock and any enqueued futex (otherwise * we could lose some wakeup). So we do it here, after * undoing all the work done so far. In success, we * retry all the work. */ if (get_user(uval, uaddr)) return -EFAULT; retry = true; goto retry; } if (uval != val) return -EWOULDBLOCK; } return 0; } /** * futex_sleep_multiple - Check sleeping conditions and sleep * @vs: List of futexes to wait for * @count: Length of vs * @to: Timeout * * Sleep if and only if the timeout hasn't expired and no futex on the list has * been woken up. */ static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { if (to && !to->task) return; for (; count; count--, vs++) { if (!READ_ONCE(vs->q.lock_ptr)) return; } schedule(); } /** * futex_wait_multiple - Prepare to wait on and enqueue several futexes * @vs: The list of futexes to wait on * @count: The number of objects * @to: Timeout before giving up and returning to userspace * * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function * sleeps on a group of futexes and returns on the first futex that is * wake, or after the timeout has elapsed. * * Return: * - >=0 - Hint to the futex that was awoken * - <0 - On error */ int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to) { int ret, hint = 0; if (to) hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); while (1) { ret = futex_wait_multiple_setup(vs, count, &hint); if (ret) { if (ret > 0) { /* A futex was woken during setup */ ret = hint; } return ret; } futex_sleep_multiple(vs, count, to); __set_current_state(TASK_RUNNING); ret = futex_unqueue_multiple(vs, count); if (ret >= 0) return ret; if (to && !to->task) return -ETIMEDOUT; else if (signal_pending(current)) return -ERESTARTSYS; /* * The final case is a spurious wakeup, for * which just retry. */ } } /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address * @val: the expected value * @flags: futex flags (FLAGS_SHARED, etc.) * @q: the associated futex_q * @key2: the second futex_key if used for requeue PI * @task: Task queueing this futex * * Setup the futex_q and locate the hash_bucket. Get the futex value and * compare it with the expected value. Handle atomic faults internally. * Return with the hb lock held on success, and unlocked on failure. * * Return: * - 0 - uaddr contains val and hb has been locked; * - <0 - On error and the hb is unlocked. A possible reason: the uaddr can not * be read, does not contain the expected value or is not properly aligned. */ int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, union futex_key *key2, struct task_struct *task) { u32 uval; int ret; /* * Access the page AFTER the hash-bucket is locked. * Order is important: * * Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val); * Userspace waker: if (cond(var)) { var = new; futex_wake(&var); } * * The basic logical guarantee of a futex is that it blocks ONLY * if cond(var) is known to be true at the time of blocking, for * any cond. If we locked the hash-bucket after testing *uaddr, that * would open a race condition where we could block indefinitely with * cond(var) false, which would violate the guarantee. * * On the other hand, we insert q and release the hash-bucket only * after testing *uaddr. This guarantees that futex_wait() will NOT * absorb a wakeup if *uaddr does not match the desired values * while the syscall executes. */ retry: ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ); if (unlikely(ret != 0)) return ret; retry_private: if (1) { CLASS(hbr, hbr)(&q->key); auto hb = hbr.hb; futex_q_lock(q, hb); ret = futex_get_value_locked(&uval, uaddr); if (ret) { futex_q_unlock(hb); __release(q->lock_ptr); ret = get_user(uval, uaddr); if (ret) return ret; if (!(flags & FLAGS_SHARED)) goto retry_private; goto retry; } if (uval != val) { futex_q_unlock(hb); __release(q->lock_ptr); return -EWOULDBLOCK; } if (key2 && futex_match(&q->key, key2)) { futex_q_unlock(hb); __release(q->lock_ptr); return -EINVAL; } /* * The task state is guaranteed to be set before another task can * wake it. set_current_state() is implemented using smp_store_mb() and * futex_queue() calls spin_unlock() upon completion, both serializing * access to the hash list and forcing another memory barrier. */ if (task == current) set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); futex_queue(q, hb, task); } return ret; } int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset) { struct futex_q q = futex_q_init; int ret; if (!bitset) return -EINVAL; q.bitset = bitset; retry: /* * Prepare to wait on uaddr. On success, it holds hb->lock and q * is initialized. */ ret = futex_wait_setup(uaddr, val, flags, &q, NULL, current); if (ret) return ret; /* futex_queue and wait for wakeup, timeout, or a signal. */ futex_do_wait(&q, to); /* If we were woken (and unqueued), we succeeded, whatever. */ if (!futex_unqueue(&q)) return 0; if (to && !to->task) return -ETIMEDOUT; /* * We expect signal_pending(current), but we might be the * victim of a spurious wakeup as well. */ if (!signal_pending(current)) goto retry; return -ERESTARTSYS; } int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) { struct hrtimer_sleeper timeout, *to; struct restart_block *restart; int ret; to = futex_setup_timer(abs_time, &timeout, flags, current->timer_slack_ns); ret = __futex_wait(uaddr, flags, val, to, bitset); /* No timeout, nothing to clean up. */ if (!to) return ret; hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); if (ret == -ERESTARTSYS) { restart = ¤t->restart_block; restart->futex.uaddr = uaddr; restart->futex.val = val; restart->futex.time = *abs_time; restart->futex.bitset = bitset; restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; return set_restart_fn(restart, futex_wait_restart); } return ret; } static long futex_wait_restart(struct restart_block *restart) { u32 __user *uaddr = restart->futex.uaddr; ktime_t *tp = NULL; if (restart->futex.flags & FLAGS_HAS_TIMEOUT) tp = &restart->futex.time; restart->fn = do_no_restart_syscall; return (long)futex_wait(uaddr, restart->futex.flags, restart->futex.val, tp, restart->futex.bitset); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * File: pep-gprs.c * * GPRS over Phonet pipe end point socket * * Copyright (C) 2008 Nokia Corporation. * * Author: Rémi Denis-Courmont */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_ether.h> #include <linux/if_arp.h> #include <net/sock.h> #include <linux/if_phonet.h> #include <net/tcp_states.h> #include <net/phonet/gprs.h> #include <trace/events/sock.h> #define GPRS_DEFAULT_MTU 1400 struct gprs_dev { struct sock *sk; void (*old_state_change)(struct sock *); void (*old_data_ready)(struct sock *); void (*old_write_space)(struct sock *); struct net_device *dev; }; static __be16 gprs_type_trans(struct sk_buff *skb) { const u8 *pvfc; u8 buf; pvfc = skb_header_pointer(skb, 0, 1, &buf); if (!pvfc) return htons(0); /* Look at IP version field */ switch (*pvfc >> 4) { case 4: return htons(ETH_P_IP); case 6: return htons(ETH_P_IPV6); } return htons(0); } static void gprs_writeable(struct gprs_dev *gp) { struct net_device *dev = gp->dev; if (pep_writeable(gp->sk)) netif_wake_queue(dev); } /* * Socket callbacks */ static void gprs_state_change(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; if (sk->sk_state == TCP_CLOSE_WAIT) { struct net_device *dev = gp->dev; netif_stop_queue(dev); netif_carrier_off(dev); } } static int gprs_recv(struct gprs_dev *gp, struct sk_buff *skb) { struct net_device *dev = gp->dev; int err = 0; __be16 protocol = gprs_type_trans(skb); if (!protocol) { err = -EINVAL; goto drop; } if (skb_headroom(skb) & 3) { struct sk_buff *rskb, *fs; int flen = 0; /* Phonet Pipe data header may be misaligned (3 bytes), * so wrap the IP packet as a single fragment of an head-less * socket buffer. The network stack will pull what it needs, * but at least, the whole IP payload is not memcpy'd. */ rskb = netdev_alloc_skb(dev, 0); if (!rskb) { err = -ENOBUFS; goto drop; } skb_shinfo(rskb)->frag_list = skb; rskb->len += skb->len; rskb->data_len += rskb->len; rskb->truesize += rskb->len; /* Avoid nested fragments */ skb_walk_frags(skb, fs) flen += fs->len; skb->next = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->len -= flen; skb->data_len -= flen; skb->truesize -= flen; skb = rskb; } skb->protocol = protocol; skb_reset_mac_header(skb); skb->dev = dev; if (likely(dev->flags & IFF_UP)) { dev->stats.rx_packets++; dev->stats.rx_bytes += skb->len; netif_rx(skb); skb = NULL; } else err = -ENODEV; drop: if (skb) { dev_kfree_skb(skb); dev->stats.rx_dropped++; } return err; } static void gprs_data_ready(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; struct sk_buff *skb; trace_sk_data_ready(sk); while ((skb = pep_read(sk)) != NULL) { skb_orphan(skb); gprs_recv(gp, skb); } } static void gprs_write_space(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; if (netif_running(gp->dev)) gprs_writeable(gp); } /* * Network device callbacks */ static int gprs_open(struct net_device *dev) { struct gprs_dev *gp = netdev_priv(dev); gprs_writeable(gp); return 0; } static int gprs_close(struct net_device *dev) { netif_stop_queue(dev); return 0; } static netdev_tx_t gprs_xmit(struct sk_buff *skb, struct net_device *dev) { struct gprs_dev *gp = netdev_priv(dev); struct sock *sk = gp->sk; int len, err; switch (skb->protocol) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): break; default: dev_kfree_skb(skb); return NETDEV_TX_OK; } skb_orphan(skb); skb_set_owner_w(skb, sk); len = skb->len; err = pep_write(sk, skb); if (err) { net_dbg_ratelimited("%s: TX error (%d)\n", dev->name, err); dev->stats.tx_aborted_errors++; dev->stats.tx_errors++; } else { dev->stats.tx_packets++; dev->stats.tx_bytes += len; } netif_stop_queue(dev); if (pep_writeable(sk)) netif_wake_queue(dev); return NETDEV_TX_OK; } static const struct net_device_ops gprs_netdev_ops = { .ndo_open = gprs_open, .ndo_stop = gprs_close, .ndo_start_xmit = gprs_xmit, }; static void gprs_setup(struct net_device *dev) { dev->features = NETIF_F_FRAGLIST; dev->type = ARPHRD_PHONET_PIPE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->mtu = GPRS_DEFAULT_MTU; dev->min_mtu = 576; dev->max_mtu = (PHONET_MAX_MTU - 11); dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 10; dev->netdev_ops = &gprs_netdev_ops; dev->needs_free_netdev = true; } /* * External interface */ /* * Attach a GPRS interface to a datagram socket. * Returns the interface index on success, negative error code on error. */ int gprs_attach(struct sock *sk) { static const char ifname[] = "gprs%d"; struct gprs_dev *gp; struct net_device *dev; int err; if (unlikely(sk->sk_type == SOCK_STREAM)) return -EINVAL; /* need packet boundaries */ /* Create net device */ dev = alloc_netdev(sizeof(*gp), ifname, NET_NAME_UNKNOWN, gprs_setup); if (!dev) return -ENOMEM; gp = netdev_priv(dev); gp->sk = sk; gp->dev = dev; netif_stop_queue(dev); err = register_netdev(dev); if (err) { free_netdev(dev); return err; } lock_sock(sk); if (unlikely(sk->sk_user_data)) { err = -EBUSY; goto out_rel; } if (unlikely((1 << sk->sk_state & (TCPF_CLOSE|TCPF_LISTEN)) || sock_flag(sk, SOCK_DEAD))) { err = -EINVAL; goto out_rel; } sk->sk_user_data = gp; gp->old_state_change = sk->sk_state_change; gp->old_data_ready = sk->sk_data_ready; gp->old_write_space = sk->sk_write_space; sk->sk_state_change = gprs_state_change; sk->sk_data_ready = gprs_data_ready; sk->sk_write_space = gprs_write_space; release_sock(sk); sock_hold(sk); printk(KERN_DEBUG"%s: attached\n", dev->name); return dev->ifindex; out_rel: release_sock(sk); unregister_netdev(dev); return err; } void gprs_detach(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; struct net_device *dev = gp->dev; lock_sock(sk); sk->sk_user_data = NULL; sk->sk_state_change = gp->old_state_change; sk->sk_data_ready = gp->old_data_ready; sk->sk_write_space = gp->old_write_space; release_sock(sk); printk(KERN_DEBUG"%s: detached\n", dev->name); unregister_netdev(dev); sock_put(sk); } |
| 110 15 1 2 93 71 1 99 98 1 14 1 5 7 1 5 1 4 78 54 4 31 21 3 3 25 26 2 48 2 1 1 3 24 1 1 19 37 5 5 2 4 19 2 13 4 16 10 1 1 1 2 2 4 3 1 1 11 13 4 21 2 19 27 1 20 44 3 3 4 32 5 7 30 4 6 27 27 27 24 3 3 10 12 5 19 19 32 5 47 4 20 23 13 34 12 12 1 11 5 3 1 1 94 94 93 2 89 1 1 2 70 75 3 1 72 10 10 25 25 25 20 20 20 16 4 19 20 1 11 87 87 87 87 87 21 8 3 2 1 5 4 4 2 5 2 2 3 9 12 3 9 9 8 1 13 4 9 5 1 1 2 1 1 2 1 5 5 1 9 1 8 3 5 2 2 6 2 9 5 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * V4L2 controls framework uAPI implementation: * * Copyright (C) 2010-2021 Hans Verkuil <hverkuil@kernel.org> */ #define pr_fmt(fmt) "v4l2-ctrls: " fmt #include <linux/export.h> #include <linux/mm.h> #include <linux/slab.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-dev.h> #include <media/v4l2-device.h> #include <media/v4l2-event.h> #include <media/v4l2-ioctl.h> #include "v4l2-ctrls-priv.h" /* Internal temporary helper struct, one for each v4l2_ext_control */ struct v4l2_ctrl_helper { /* Pointer to the control reference of the master control */ struct v4l2_ctrl_ref *mref; /* The control ref corresponding to the v4l2_ext_control ID field. */ struct v4l2_ctrl_ref *ref; /* * v4l2_ext_control index of the next control belonging to the * same cluster, or 0 if there isn't any. */ u32 next; }; /* * Helper functions to copy control payload data from kernel space to * user space and vice versa. */ /* Helper function: copy the given control value back to the caller */ static int ptr_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr) { u32 len; if (ctrl->is_ptr && !ctrl->is_string) return copy_to_user(c->ptr, ptr.p_const, c->size) ? -EFAULT : 0; switch (ctrl->type) { case V4L2_CTRL_TYPE_STRING: len = strlen(ptr.p_char); if (c->size < len + 1) { c->size = ctrl->elem_size; return -ENOSPC; } return copy_to_user(c->string, ptr.p_char, len + 1) ? -EFAULT : 0; case V4L2_CTRL_TYPE_INTEGER64: c->value64 = *ptr.p_s64; break; default: c->value = *ptr.p_s32; break; } return 0; } /* Helper function: copy the current control value back to the caller */ static int cur_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) { return ptr_to_user(c, ctrl, ctrl->p_cur); } /* Helper function: copy the new control value back to the caller */ static int new_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) { return ptr_to_user(c, ctrl, ctrl->p_new); } /* Helper function: copy the request value back to the caller */ static int req_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl_ref *ref) { return ptr_to_user(c, ref->ctrl, ref->p_req); } /* Helper function: copy the initial control value back to the caller */ static int def_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) { ctrl->type_ops->init(ctrl, 0, ctrl->p_new); return ptr_to_user(c, ctrl, ctrl->p_new); } /* Helper function: copy the minimum control value back to the caller */ static int min_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) { ctrl->type_ops->minimum(ctrl, 0, ctrl->p_new); return ptr_to_user(c, ctrl, ctrl->p_new); } /* Helper function: copy the maximum control value back to the caller */ static int max_to_user(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) { ctrl->type_ops->maximum(ctrl, 0, ctrl->p_new); return ptr_to_user(c, ctrl, ctrl->p_new); } /* Helper function: copy the caller-provider value as the new control value */ static int user_to_new(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) { int ret; u32 size; ctrl->is_new = 0; if (ctrl->is_dyn_array && c->size > ctrl->p_array_alloc_elems * ctrl->elem_size) { void *old = ctrl->p_array; void *tmp = kvzalloc(2 * c->size, GFP_KERNEL); if (!tmp) return -ENOMEM; memcpy(tmp, ctrl->p_new.p, ctrl->elems * ctrl->elem_size); memcpy(tmp + c->size, ctrl->p_cur.p, ctrl->elems * ctrl->elem_size); ctrl->p_new.p = tmp; ctrl->p_cur.p = tmp + c->size; ctrl->p_array = tmp; ctrl->p_array_alloc_elems = c->size / ctrl->elem_size; kvfree(old); } if (ctrl->is_ptr && !ctrl->is_string) { unsigned int elems = c->size / ctrl->elem_size; if (copy_from_user(ctrl->p_new.p, c->ptr, c->size)) return -EFAULT; ctrl->is_new = 1; if (ctrl->is_dyn_array) ctrl->new_elems = elems; else if (ctrl->is_array) ctrl->type_ops->init(ctrl, elems, ctrl->p_new); return 0; } switch (ctrl->type) { case V4L2_CTRL_TYPE_INTEGER64: *ctrl->p_new.p_s64 = c->value64; break; case V4L2_CTRL_TYPE_STRING: size = c->size; if (size == 0) return -ERANGE; if (size > ctrl->maximum + 1) size = ctrl->maximum + 1; ret = copy_from_user(ctrl->p_new.p_char, c->string, size) ? -EFAULT : 0; if (!ret) { char last = ctrl->p_new.p_char[size - 1]; ctrl->p_new.p_char[size - 1] = 0; /* * If the string was longer than ctrl->maximum, * then return an error. */ if (strlen(ctrl->p_new.p_char) == ctrl->maximum && last) return -ERANGE; ctrl->is_new = 1; } return ret; default: *ctrl->p_new.p_s32 = c->value; break; } ctrl->is_new = 1; return 0; } /* * VIDIOC_G/TRY/S_EXT_CTRLS implementation */ /* * Some general notes on the atomic requirements of VIDIOC_G/TRY/S_EXT_CTRLS: * * It is not a fully atomic operation, just best-effort only. After all, if * multiple controls have to be set through multiple i2c writes (for example) * then some initial writes may succeed while others fail. Thus leaving the * system in an inconsistent state. The question is how much effort you are * willing to spend on trying to make something atomic that really isn't. * * From the point of view of an application the main requirement is that * when you call VIDIOC_S_EXT_CTRLS and some values are invalid then an * error should be returned without actually affecting any controls. * * If all the values are correct, then it is acceptable to just give up * in case of low-level errors. * * It is important though that the application can tell when only a partial * configuration was done. The way we do that is through the error_idx field * of struct v4l2_ext_controls: if that is equal to the count field then no * controls were affected. Otherwise all controls before that index were * successful in performing their 'get' or 'set' operation, the control at * the given index failed, and you don't know what happened with the controls * after the failed one. Since if they were part of a control cluster they * could have been successfully processed (if a cluster member was encountered * at index < error_idx), they could have failed (if a cluster member was at * error_idx), or they may not have been processed yet (if the first cluster * member appeared after error_idx). * * It is all fairly theoretical, though. In practice all you can do is to * bail out. If error_idx == count, then it is an application bug. If * error_idx < count then it is only an application bug if the error code was * EBUSY. That usually means that something started streaming just when you * tried to set the controls. In all other cases it is a driver/hardware * problem and all you can do is to retry or bail out. * * Note that these rules do not apply to VIDIOC_TRY_EXT_CTRLS: since that * never modifies controls the error_idx is just set to whatever control * has an invalid value. */ /* * Prepare for the extended g/s/try functions. * Find the controls in the control array and do some basic checks. */ static int prepare_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *cs, struct v4l2_ctrl_helper *helpers, struct video_device *vdev, bool get) { struct v4l2_ctrl_helper *h; bool have_clusters = false; u32 i; for (i = 0, h = helpers; i < cs->count; i++, h++) { struct v4l2_ext_control *c = &cs->controls[i]; struct v4l2_ctrl_ref *ref; struct v4l2_ctrl *ctrl; u32 id = c->id & V4L2_CTRL_ID_MASK; cs->error_idx = i; if (cs->which && (cs->which < V4L2_CTRL_WHICH_DEF_VAL || cs->which > V4L2_CTRL_WHICH_MAX_VAL) && V4L2_CTRL_ID2WHICH(id) != cs->which) { dprintk(vdev, "invalid which 0x%x or control id 0x%x\n", cs->which, id); return -EINVAL; } /* * Old-style private controls are not allowed for * extended controls. */ if (id >= V4L2_CID_PRIVATE_BASE) { dprintk(vdev, "old-style private controls not allowed\n"); return -EINVAL; } ref = find_ref_lock(hdl, id); if (!ref) { dprintk(vdev, "cannot find control id 0x%x\n", id); return -EINVAL; } h->ref = ref; ctrl = ref->ctrl; if (ctrl->flags & V4L2_CTRL_FLAG_DISABLED) { dprintk(vdev, "control id 0x%x is disabled\n", id); return -EINVAL; } if (!(ctrl->flags & V4L2_CTRL_FLAG_HAS_WHICH_MIN_MAX) && (cs->which == V4L2_CTRL_WHICH_MIN_VAL || cs->which == V4L2_CTRL_WHICH_MAX_VAL)) { dprintk(vdev, "invalid which 0x%x or control id 0x%x\n", cs->which, id); return -EINVAL; } if (ctrl->cluster[0]->ncontrols > 1) have_clusters = true; if (ctrl->cluster[0] != ctrl) ref = find_ref_lock(hdl, ctrl->cluster[0]->id); if (ctrl->is_dyn_array) { unsigned int max_size = ctrl->dims[0] * ctrl->elem_size; unsigned int tot_size = ctrl->elem_size; if (cs->which == V4L2_CTRL_WHICH_REQUEST_VAL) tot_size *= ref->p_req_elems; else tot_size *= ctrl->elems; c->size = ctrl->elem_size * (c->size / ctrl->elem_size); if (get) { if (c->size < tot_size) { c->size = tot_size; return -ENOSPC; } c->size = tot_size; } else { if (c->size > max_size) { c->size = max_size; return -ENOSPC; } if (!c->size) return -EFAULT; } } else if (ctrl->is_ptr && !ctrl->is_string) { unsigned int tot_size = ctrl->elems * ctrl->elem_size; if (c->size < tot_size) { /* * In the get case the application first * queries to obtain the size of the control. */ if (get) { c->size = tot_size; return -ENOSPC; } dprintk(vdev, "pointer control id 0x%x size too small, %d bytes but %d bytes needed\n", id, c->size, tot_size); return -EFAULT; } c->size = tot_size; } /* Store the ref to the master control of the cluster */ h->mref = ref; /* * Initially set next to 0, meaning that there is no other * control in this helper array belonging to the same * cluster. */ h->next = 0; } /* * We are done if there were no controls that belong to a multi- * control cluster. */ if (!have_clusters) return 0; /* * The code below figures out in O(n) time which controls in the list * belong to the same cluster. */ /* This has to be done with the handler lock taken. */ mutex_lock(hdl->lock); /* First zero the helper field in the master control references */ for (i = 0; i < cs->count; i++) helpers[i].mref->helper = NULL; for (i = 0, h = helpers; i < cs->count; i++, h++) { struct v4l2_ctrl_ref *mref = h->mref; /* * If the mref->helper is set, then it points to an earlier * helper that belongs to the same cluster. */ if (mref->helper) { /* * Set the next field of mref->helper to the current * index: this means that the earlier helper now * points to the next helper in the same cluster. */ mref->helper->next = i; /* * mref should be set only for the first helper in the * cluster, clear the others. */ h->mref = NULL; } /* Point the mref helper to the current helper struct. */ mref->helper = h; } mutex_unlock(hdl->lock); return 0; } /* * Handles the corner case where cs->count == 0. It checks whether the * specified control class exists. If that class ID is 0, then it checks * whether there are any controls at all. */ static int class_check(struct v4l2_ctrl_handler *hdl, u32 which) { if (which == 0 || (which >= V4L2_CTRL_WHICH_DEF_VAL && which <= V4L2_CTRL_WHICH_MAX_VAL)) return 0; return find_ref_lock(hdl, which | 1) ? 0 : -EINVAL; } /* * Get extended controls. Allocates the helpers array if needed. * * Note that v4l2_g_ext_ctrls_common() with 'which' set to * V4L2_CTRL_WHICH_REQUEST_VAL is only called if the request was * completed, and in that case p_req_valid is true for all controls. */ int v4l2_g_ext_ctrls_common(struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *cs, struct video_device *vdev) { struct v4l2_ctrl_helper helper[4]; struct v4l2_ctrl_helper *helpers = helper; int ret; int i, j; bool is_default, is_request, is_min, is_max; is_default = (cs->which == V4L2_CTRL_WHICH_DEF_VAL); is_request = (cs->which == V4L2_CTRL_WHICH_REQUEST_VAL); is_min = (cs->which == V4L2_CTRL_WHICH_MIN_VAL); is_max = (cs->which == V4L2_CTRL_WHICH_MAX_VAL); cs->error_idx = cs->count; cs->which = V4L2_CTRL_ID2WHICH(cs->which); if (!hdl) return -EINVAL; if (cs->count == 0) return class_check(hdl, cs->which); if (cs->count > ARRAY_SIZE(helper)) { helpers = kvmalloc_objs(helper[0], cs->count); if (!helpers) return -ENOMEM; } ret = prepare_ext_ctrls(hdl, cs, helpers, vdev, true); cs->error_idx = cs->count; for (i = 0; !ret && i < cs->count; i++) if (helpers[i].ref->ctrl->flags & V4L2_CTRL_FLAG_WRITE_ONLY) ret = -EACCES; for (i = 0; !ret && i < cs->count; i++) { struct v4l2_ctrl *master; bool is_volatile = false; u32 idx = i; if (!helpers[i].mref) continue; master = helpers[i].mref->ctrl; cs->error_idx = i; v4l2_ctrl_lock(master); /* * g_volatile_ctrl will update the new control values. * This makes no sense for V4L2_CTRL_WHICH_DEF_VAL, * V4L2_CTRL_WHICH_MIN_VAL, V4L2_CTRL_WHICH_MAX_VAL and * V4L2_CTRL_WHICH_REQUEST_VAL. In the case of requests * it is v4l2_ctrl_request_complete() that copies the * volatile controls at the time of request completion * to the request, so you don't want to do that again. */ if (!is_default && !is_request && !is_min && !is_max && ((master->flags & V4L2_CTRL_FLAG_VOLATILE) || (master->has_volatiles && !is_cur_manual(master)))) { for (j = 0; j < master->ncontrols; j++) cur_to_new(master->cluster[j]); ret = call_op(master, g_volatile_ctrl); is_volatile = true; } if (ret) { v4l2_ctrl_unlock(master); break; } /* * Copy the default value (if is_default is true), the * request value (if is_request is true and p_req is valid), * the new volatile value (if is_volatile is true) or the * current value. */ do { struct v4l2_ctrl_ref *ref = helpers[idx].ref; if (is_default) ret = def_to_user(cs->controls + idx, ref->ctrl); else if (is_request && ref->p_req_array_enomem) ret = -ENOMEM; else if (is_request && ref->p_req_valid) ret = req_to_user(cs->controls + idx, ref); else if (is_min) ret = min_to_user(cs->controls + idx, ref->ctrl); else if (is_max) ret = max_to_user(cs->controls + idx, ref->ctrl); else if (is_volatile) ret = new_to_user(cs->controls + idx, ref->ctrl); else ret = cur_to_user(cs->controls + idx, ref->ctrl); idx = helpers[idx].next; } while (!ret && idx); v4l2_ctrl_unlock(master); } if (cs->count > ARRAY_SIZE(helper)) kvfree(helpers); return ret; } int v4l2_g_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct video_device *vdev, struct media_device *mdev, struct v4l2_ext_controls *cs) { if (cs->which == V4L2_CTRL_WHICH_REQUEST_VAL) return v4l2_g_ext_ctrls_request(hdl, vdev, mdev, cs); return v4l2_g_ext_ctrls_common(hdl, cs, vdev); } EXPORT_SYMBOL(v4l2_g_ext_ctrls); /* Validate a new control */ static int validate_new(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr p_new) { return ctrl->type_ops->validate(ctrl, p_new); } /* Validate controls. */ static int validate_ctrls(struct v4l2_ext_controls *cs, struct v4l2_ctrl_helper *helpers, struct video_device *vdev, bool set) { unsigned int i; int ret = 0; cs->error_idx = cs->count; for (i = 0; i < cs->count; i++) { struct v4l2_ctrl *ctrl = helpers[i].ref->ctrl; union v4l2_ctrl_ptr p_new; cs->error_idx = i; if (ctrl->flags & V4L2_CTRL_FLAG_READ_ONLY) { dprintk(vdev, "control id 0x%x is read-only\n", ctrl->id); return -EACCES; } /* * This test is also done in try_set_control_cluster() which * is called in atomic context, so that has the final say, * but it makes sense to do an up-front check as well. Once * an error occurs in try_set_control_cluster() some other * controls may have been set already and we want to do a * best-effort to avoid that. */ if (set && (ctrl->flags & V4L2_CTRL_FLAG_GRABBED)) { dprintk(vdev, "control id 0x%x is grabbed, cannot set\n", ctrl->id); return -EBUSY; } /* * Skip validation for now if the payload needs to be copied * from userspace into kernelspace. We'll validate those later. */ if (ctrl->is_ptr) continue; if (ctrl->type == V4L2_CTRL_TYPE_INTEGER64) p_new.p_s64 = &cs->controls[i].value64; else p_new.p_s32 = &cs->controls[i].value; ret = validate_new(ctrl, p_new); if (ret) return ret; } return 0; } /* Try or try-and-set controls */ int try_set_ext_ctrls_common(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *cs, struct video_device *vdev, bool set) { struct v4l2_ctrl_helper helper[4]; struct v4l2_ctrl_helper *helpers = helper; unsigned int i, j; int ret; cs->error_idx = cs->count; /* Default/minimum/maximum values cannot be changed */ if (cs->which == V4L2_CTRL_WHICH_DEF_VAL || cs->which == V4L2_CTRL_WHICH_MIN_VAL || cs->which == V4L2_CTRL_WHICH_MAX_VAL) { dprintk(vdev, "%s: cannot change default/min/max value\n", video_device_node_name(vdev)); return -EINVAL; } cs->which = V4L2_CTRL_ID2WHICH(cs->which); if (!hdl) { dprintk(vdev, "%s: invalid null control handler\n", video_device_node_name(vdev)); return -EINVAL; } if (cs->count == 0) return class_check(hdl, cs->which); if (cs->count > ARRAY_SIZE(helper)) { helpers = kvmalloc_objs(helper[0], cs->count); if (!helpers) return -ENOMEM; } ret = prepare_ext_ctrls(hdl, cs, helpers, vdev, false); if (!ret) ret = validate_ctrls(cs, helpers, vdev, set); if (ret && set) cs->error_idx = cs->count; for (i = 0; !ret && i < cs->count; i++) { struct v4l2_ctrl *master; u32 idx = i; if (!helpers[i].mref) continue; cs->error_idx = i; master = helpers[i].mref->ctrl; v4l2_ctrl_lock(master); /* Reset the 'is_new' flags of the cluster */ for (j = 0; j < master->ncontrols; j++) if (master->cluster[j]) master->cluster[j]->is_new = 0; /* * For volatile autoclusters that are currently in auto mode * we need to discover if it will be set to manual mode. * If so, then we have to copy the current volatile values * first since those will become the new manual values (which * may be overwritten by explicit new values from this set * of controls). */ if (master->is_auto && master->has_volatiles && !is_cur_manual(master)) { /* Pick an initial non-manual value */ s32 new_auto_val = master->manual_mode_value + 1; u32 tmp_idx = idx; do { /* * Check if the auto control is part of the * list, and remember the new value. */ if (helpers[tmp_idx].ref->ctrl == master) new_auto_val = cs->controls[tmp_idx].value; tmp_idx = helpers[tmp_idx].next; } while (tmp_idx); /* * If the new value == the manual value, then copy * the current volatile values. */ if (new_auto_val == master->manual_mode_value) update_from_auto_cluster(master); } /* * Copy the new caller-supplied control values. * user_to_new() sets 'is_new' to 1. */ do { struct v4l2_ctrl *ctrl = helpers[idx].ref->ctrl; ret = user_to_new(cs->controls + idx, ctrl); if (!ret && ctrl->is_ptr) { ret = validate_new(ctrl, ctrl->p_new); if (ret) dprintk(vdev, "failed to validate control %s (%d)\n", v4l2_ctrl_get_name(ctrl->id), ret); } idx = helpers[idx].next; } while (!ret && idx); if (!ret) ret = try_or_set_cluster(fh, master, !hdl->req_obj.req && set, 0); if (!ret && hdl->req_obj.req && set) { for (j = 0; j < master->ncontrols; j++) { struct v4l2_ctrl_ref *ref = find_ref(hdl, master->cluster[j]->id); new_to_req(ref); } } /* Copy the new values back to userspace. */ if (!ret) { idx = i; do { ret = new_to_user(cs->controls + idx, helpers[idx].ref->ctrl); idx = helpers[idx].next; } while (!ret && idx); } v4l2_ctrl_unlock(master); } if (cs->count > ARRAY_SIZE(helper)) kvfree(helpers); return ret; } static int try_set_ext_ctrls(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl, struct video_device *vdev, struct media_device *mdev, struct v4l2_ext_controls *cs, bool set) { int ret; if (cs->which == V4L2_CTRL_WHICH_REQUEST_VAL) return try_set_ext_ctrls_request(fh, hdl, vdev, mdev, cs, set); ret = try_set_ext_ctrls_common(fh, hdl, cs, vdev, set); if (ret) dprintk(vdev, "%s: try_set_ext_ctrls_common failed (%d)\n", video_device_node_name(vdev), ret); return ret; } int v4l2_try_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct video_device *vdev, struct media_device *mdev, struct v4l2_ext_controls *cs) { return try_set_ext_ctrls(NULL, hdl, vdev, mdev, cs, false); } EXPORT_SYMBOL(v4l2_try_ext_ctrls); int v4l2_s_ext_ctrls(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl, struct video_device *vdev, struct media_device *mdev, struct v4l2_ext_controls *cs) { return try_set_ext_ctrls(fh, hdl, vdev, mdev, cs, true); } EXPORT_SYMBOL(v4l2_s_ext_ctrls); /* * VIDIOC_G/S_CTRL implementation */ /* Helper function to get a single control */ static int get_ctrl(struct v4l2_ctrl *ctrl, struct v4l2_ext_control *c) { struct v4l2_ctrl *master = ctrl->cluster[0]; int ret = 0; int i; /* Compound controls are not supported. The new_to_user() and * cur_to_user() calls below would need to be modified not to access * userspace memory when called from get_ctrl(). */ if (!ctrl->is_int && ctrl->type != V4L2_CTRL_TYPE_INTEGER64) return -EINVAL; if (ctrl->flags & V4L2_CTRL_FLAG_WRITE_ONLY) return -EACCES; v4l2_ctrl_lock(master); /* g_volatile_ctrl will update the current control values */ if (ctrl->flags & V4L2_CTRL_FLAG_VOLATILE) { for (i = 0; i < master->ncontrols; i++) cur_to_new(master->cluster[i]); ret = call_op(master, g_volatile_ctrl); if (!ret) ret = new_to_user(c, ctrl); } else { ret = cur_to_user(c, ctrl); } v4l2_ctrl_unlock(master); return ret; } int v4l2_g_ctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_control *control) { struct v4l2_ctrl *ctrl = v4l2_ctrl_find(hdl, control->id); struct v4l2_ext_control c; int ret; if (!ctrl || !ctrl->is_int) return -EINVAL; ret = get_ctrl(ctrl, &c); if (!ret) control->value = c.value; return ret; } EXPORT_SYMBOL(v4l2_g_ctrl); /* Helper function for VIDIOC_S_CTRL compatibility */ static int set_ctrl(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, u32 ch_flags) { struct v4l2_ctrl *master = ctrl->cluster[0]; int ret; int i; /* Reset the 'is_new' flags of the cluster */ for (i = 0; i < master->ncontrols; i++) if (master->cluster[i]) master->cluster[i]->is_new = 0; ret = validate_new(ctrl, ctrl->p_new); if (ret) return ret; /* * For autoclusters with volatiles that are switched from auto to * manual mode we have to update the current volatile values since * those will become the initial manual values after such a switch. */ if (master->is_auto && master->has_volatiles && ctrl == master && !is_cur_manual(master) && ctrl->val == master->manual_mode_value) update_from_auto_cluster(master); ctrl->is_new = 1; return try_or_set_cluster(fh, master, true, ch_flags); } /* Helper function for VIDIOC_S_CTRL compatibility */ static int set_ctrl_lock(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, struct v4l2_ext_control *c) { int ret; v4l2_ctrl_lock(ctrl); ret = user_to_new(c, ctrl); if (!ret) ret = set_ctrl(fh, ctrl, 0); if (!ret) ret = cur_to_user(c, ctrl); v4l2_ctrl_unlock(ctrl); return ret; } int v4l2_s_ctrl(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl, struct v4l2_control *control) { struct v4l2_ctrl *ctrl = v4l2_ctrl_find(hdl, control->id); struct v4l2_ext_control c = { control->id }; int ret; if (!ctrl || !ctrl->is_int) return -EINVAL; if (ctrl->flags & V4L2_CTRL_FLAG_READ_ONLY) return -EACCES; c.value = control->value; ret = set_ctrl_lock(fh, ctrl, &c); control->value = c.value; return ret; } EXPORT_SYMBOL(v4l2_s_ctrl); /* * Helper functions for drivers to get/set controls. */ s32 v4l2_ctrl_g_ctrl(struct v4l2_ctrl *ctrl) { struct v4l2_ext_control c; /* It's a driver bug if this happens. */ if (WARN_ON(!ctrl->is_int)) return 0; c.value = 0; get_ctrl(ctrl, &c); return c.value; } EXPORT_SYMBOL(v4l2_ctrl_g_ctrl); s64 v4l2_ctrl_g_ctrl_int64(struct v4l2_ctrl *ctrl) { struct v4l2_ext_control c; /* It's a driver bug if this happens. */ if (WARN_ON(ctrl->is_ptr || ctrl->type != V4L2_CTRL_TYPE_INTEGER64)) return 0; c.value64 = 0; get_ctrl(ctrl, &c); return c.value64; } EXPORT_SYMBOL(v4l2_ctrl_g_ctrl_int64); int __v4l2_ctrl_s_ctrl(struct v4l2_ctrl *ctrl, s32 val) { lockdep_assert_held(ctrl->handler->lock); /* It's a driver bug if this happens. */ if (WARN_ON(!ctrl->is_int)) return -EINVAL; ctrl->val = val; return set_ctrl(NULL, ctrl, 0); } EXPORT_SYMBOL(__v4l2_ctrl_s_ctrl); int __v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val) { lockdep_assert_held(ctrl->handler->lock); /* It's a driver bug if this happens. */ if (WARN_ON(ctrl->is_ptr || ctrl->type != V4L2_CTRL_TYPE_INTEGER64)) return -EINVAL; *ctrl->p_new.p_s64 = val; return set_ctrl(NULL, ctrl, 0); } EXPORT_SYMBOL(__v4l2_ctrl_s_ctrl_int64); int __v4l2_ctrl_s_ctrl_string(struct v4l2_ctrl *ctrl, const char *s) { lockdep_assert_held(ctrl->handler->lock); /* It's a driver bug if this happens. */ if (WARN_ON(ctrl->type != V4L2_CTRL_TYPE_STRING)) return -EINVAL; strscpy(ctrl->p_new.p_char, s, ctrl->maximum + 1); return set_ctrl(NULL, ctrl, 0); } EXPORT_SYMBOL(__v4l2_ctrl_s_ctrl_string); int __v4l2_ctrl_s_ctrl_compound(struct v4l2_ctrl *ctrl, enum v4l2_ctrl_type type, const void *p) { lockdep_assert_held(ctrl->handler->lock); /* It's a driver bug if this happens. */ if (WARN_ON(ctrl->type != type)) return -EINVAL; /* Setting dynamic arrays is not (yet?) supported. */ if (WARN_ON(ctrl->is_dyn_array)) return -EINVAL; memcpy(ctrl->p_new.p, p, ctrl->elems * ctrl->elem_size); return set_ctrl(NULL, ctrl, 0); } EXPORT_SYMBOL(__v4l2_ctrl_s_ctrl_compound); /* * Modify the range of a control. */ int __v4l2_ctrl_modify_range(struct v4l2_ctrl *ctrl, s64 min, s64 max, u64 step, s64 def) { bool value_changed; bool range_changed = false; int ret; lockdep_assert_held(ctrl->handler->lock); switch (ctrl->type) { case V4L2_CTRL_TYPE_INTEGER: case V4L2_CTRL_TYPE_INTEGER64: case V4L2_CTRL_TYPE_BOOLEAN: case V4L2_CTRL_TYPE_MENU: case V4L2_CTRL_TYPE_INTEGER_MENU: case V4L2_CTRL_TYPE_BITMASK: case V4L2_CTRL_TYPE_U8: case V4L2_CTRL_TYPE_U16: case V4L2_CTRL_TYPE_U32: if (ctrl->is_array) return -EINVAL; ret = check_range(ctrl->type, min, max, step, def); if (ret) return ret; break; default: return -EINVAL; } if (ctrl->minimum != min || ctrl->maximum != max || ctrl->step != step || ctrl->default_value != def) { range_changed = true; ctrl->minimum = min; ctrl->maximum = max; ctrl->step = step; ctrl->default_value = def; } cur_to_new(ctrl); if (validate_new(ctrl, ctrl->p_new)) { if (ctrl->type == V4L2_CTRL_TYPE_INTEGER64) *ctrl->p_new.p_s64 = def; else *ctrl->p_new.p_s32 = def; } if (ctrl->type == V4L2_CTRL_TYPE_INTEGER64) value_changed = *ctrl->p_new.p_s64 != *ctrl->p_cur.p_s64; else value_changed = *ctrl->p_new.p_s32 != *ctrl->p_cur.p_s32; if (value_changed) ret = set_ctrl(NULL, ctrl, V4L2_EVENT_CTRL_CH_RANGE); else if (range_changed) send_event(NULL, ctrl, V4L2_EVENT_CTRL_CH_RANGE); return ret; } EXPORT_SYMBOL(__v4l2_ctrl_modify_range); int __v4l2_ctrl_modify_dimensions(struct v4l2_ctrl *ctrl, u32 dims[V4L2_CTRL_MAX_DIMS]) { unsigned int elems = 1; unsigned int i; void *p_array; lockdep_assert_held(ctrl->handler->lock); if (!ctrl->is_array || ctrl->is_dyn_array) return -EINVAL; for (i = 0; i < ctrl->nr_of_dims; i++) elems *= dims[i]; if (elems == 0) return -EINVAL; p_array = kvzalloc(2 * elems * ctrl->elem_size, GFP_KERNEL); if (!p_array) return -ENOMEM; kvfree(ctrl->p_array); ctrl->p_array_alloc_elems = elems; ctrl->elems = elems; ctrl->new_elems = elems; ctrl->p_array = p_array; ctrl->p_new.p = p_array; ctrl->p_cur.p = p_array + elems * ctrl->elem_size; for (i = 0; i < ctrl->nr_of_dims; i++) ctrl->dims[i] = dims[i]; ctrl->type_ops->init(ctrl, 0, ctrl->p_cur); cur_to_new(ctrl); send_event(NULL, ctrl, V4L2_EVENT_CTRL_CH_VALUE | V4L2_EVENT_CTRL_CH_DIMENSIONS); return 0; } EXPORT_SYMBOL(__v4l2_ctrl_modify_dimensions); /* Implement VIDIOC_QUERY_EXT_CTRL */ int v4l2_query_ext_ctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_query_ext_ctrl *qc) { const unsigned int next_flags = V4L2_CTRL_FLAG_NEXT_CTRL | V4L2_CTRL_FLAG_NEXT_COMPOUND; u32 id = qc->id & V4L2_CTRL_ID_MASK; struct v4l2_ctrl_ref *ref; struct v4l2_ctrl *ctrl; if (!hdl) return -EINVAL; mutex_lock(hdl->lock); /* Try to find it */ ref = find_ref(hdl, id); if ((qc->id & next_flags) && !list_empty(&hdl->ctrl_refs)) { bool is_compound; /* Match any control that is not hidden */ unsigned int mask = 1; bool match = false; if ((qc->id & next_flags) == V4L2_CTRL_FLAG_NEXT_COMPOUND) { /* Match any hidden control */ match = true; } else if ((qc->id & next_flags) == next_flags) { /* Match any control, compound or not */ mask = 0; } /* Find the next control with ID > qc->id */ /* Did we reach the end of the control list? */ if (id >= node2id(hdl->ctrl_refs.prev)) { ref = NULL; /* Yes, so there is no next control */ } else if (ref) { struct v4l2_ctrl_ref *pos = ref; /* * We found a control with the given ID, so just get * the next valid one in the list. */ ref = NULL; list_for_each_entry_continue(pos, &hdl->ctrl_refs, node) { is_compound = pos->ctrl->is_array || pos->ctrl->type >= V4L2_CTRL_COMPOUND_TYPES; if (id < pos->ctrl->id && (is_compound & mask) == match) { ref = pos; break; } } } else { struct v4l2_ctrl_ref *pos; /* * No control with the given ID exists, so start * searching for the next largest ID. We know there * is one, otherwise the first 'if' above would have * been true. */ list_for_each_entry(pos, &hdl->ctrl_refs, node) { is_compound = pos->ctrl->is_array || pos->ctrl->type >= V4L2_CTRL_COMPOUND_TYPES; if (id < pos->ctrl->id && (is_compound & mask) == match) { ref = pos; break; } } } } mutex_unlock(hdl->lock); if (!ref) return -EINVAL; ctrl = ref->ctrl; memset(qc, 0, sizeof(*qc)); if (id >= V4L2_CID_PRIVATE_BASE) qc->id = id; else qc->id = ctrl->id; strscpy(qc->name, ctrl->name, sizeof(qc->name)); qc->flags = user_flags(ctrl); qc->type = ctrl->type; qc->elem_size = ctrl->elem_size; qc->elems = ctrl->elems; qc->nr_of_dims = ctrl->nr_of_dims; memcpy(qc->dims, ctrl->dims, qc->nr_of_dims * sizeof(qc->dims[0])); qc->minimum = ctrl->minimum; qc->maximum = ctrl->maximum; qc->default_value = ctrl->default_value; if (ctrl->type == V4L2_CTRL_TYPE_MENU || ctrl->type == V4L2_CTRL_TYPE_INTEGER_MENU) qc->step = 1; else qc->step = ctrl->step; return 0; } EXPORT_SYMBOL(v4l2_query_ext_ctrl); void v4l2_query_ext_ctrl_to_v4l2_queryctrl(struct v4l2_queryctrl *to, const struct v4l2_query_ext_ctrl *from) { to->id = from->id; to->type = from->type; to->flags = from->flags; strscpy(to->name, from->name, sizeof(to->name)); switch (from->type) { case V4L2_CTRL_TYPE_INTEGER: case V4L2_CTRL_TYPE_BOOLEAN: case V4L2_CTRL_TYPE_MENU: case V4L2_CTRL_TYPE_INTEGER_MENU: case V4L2_CTRL_TYPE_STRING: case V4L2_CTRL_TYPE_BITMASK: to->minimum = from->minimum; to->maximum = from->maximum; to->step = from->step; to->default_value = from->default_value; break; default: to->minimum = 0; to->maximum = 0; to->step = 0; to->default_value = 0; break; } } EXPORT_SYMBOL(v4l2_query_ext_ctrl_to_v4l2_queryctrl); /* Implement VIDIOC_QUERYCTRL */ int v4l2_queryctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_queryctrl *qc) { struct v4l2_query_ext_ctrl qec = { qc->id }; int rc; rc = v4l2_query_ext_ctrl(hdl, &qec); if (rc) return rc; v4l2_query_ext_ctrl_to_v4l2_queryctrl(qc, &qec); return 0; } EXPORT_SYMBOL(v4l2_queryctrl); /* Implement VIDIOC_QUERYMENU */ int v4l2_querymenu(struct v4l2_ctrl_handler *hdl, struct v4l2_querymenu *qm) { struct v4l2_ctrl *ctrl; u32 i = qm->index; ctrl = v4l2_ctrl_find(hdl, qm->id); if (!ctrl) return -EINVAL; qm->reserved = 0; /* Sanity checks */ switch (ctrl->type) { case V4L2_CTRL_TYPE_MENU: if (!ctrl->qmenu) return -EINVAL; break; case V4L2_CTRL_TYPE_INTEGER_MENU: if (!ctrl->qmenu_int) return -EINVAL; break; default: return -EINVAL; } if (i < ctrl->minimum || i > ctrl->maximum) return -EINVAL; /* Use mask to see if this menu item should be skipped */ if (i < BITS_PER_LONG_LONG && (ctrl->menu_skip_mask & BIT_ULL(i))) return -EINVAL; /* Empty menu items should also be skipped */ if (ctrl->type == V4L2_CTRL_TYPE_MENU) { if (!ctrl->qmenu[i] || ctrl->qmenu[i][0] == '\0') return -EINVAL; strscpy(qm->name, ctrl->qmenu[i], sizeof(qm->name)); } else { qm->value = ctrl->qmenu_int[i]; } return 0; } EXPORT_SYMBOL(v4l2_querymenu); /* * VIDIOC_LOG_STATUS helpers */ int v4l2_ctrl_log_status(struct file *file, void *priv) { struct video_device *vfd = video_devdata(file); if (vfd->v4l2_dev) { struct v4l2_fh *vfh = file_to_v4l2_fh(file); v4l2_ctrl_handler_log_status(vfh->ctrl_handler, vfd->v4l2_dev->name); } return 0; } EXPORT_SYMBOL(v4l2_ctrl_log_status); int v4l2_ctrl_subdev_log_status(struct v4l2_subdev *sd) { v4l2_ctrl_handler_log_status(sd->ctrl_handler, sd->name); return 0; } EXPORT_SYMBOL(v4l2_ctrl_subdev_log_status); /* * VIDIOC_(UN)SUBSCRIBE_EVENT implementation */ static int v4l2_ctrl_add_event(struct v4l2_subscribed_event *sev, unsigned int elems) { struct v4l2_ctrl *ctrl = v4l2_ctrl_find(sev->fh->ctrl_handler, sev->id); if (!ctrl) return -EINVAL; v4l2_ctrl_lock(ctrl); list_add_tail(&sev->node, &ctrl->ev_subs); if (ctrl->type != V4L2_CTRL_TYPE_CTRL_CLASS && (sev->flags & V4L2_EVENT_SUB_FL_SEND_INITIAL)) send_initial_event(sev->fh, ctrl); v4l2_ctrl_unlock(ctrl); return 0; } static void v4l2_ctrl_del_event(struct v4l2_subscribed_event *sev) { struct v4l2_ctrl *ctrl = v4l2_ctrl_find(sev->fh->ctrl_handler, sev->id); if (!ctrl) return; v4l2_ctrl_lock(ctrl); list_del(&sev->node); v4l2_ctrl_unlock(ctrl); } void v4l2_ctrl_replace(struct v4l2_event *old, const struct v4l2_event *new) { u32 old_changes = old->u.ctrl.changes; old->u.ctrl = new->u.ctrl; old->u.ctrl.changes |= old_changes; } EXPORT_SYMBOL(v4l2_ctrl_replace); void v4l2_ctrl_merge(const struct v4l2_event *old, struct v4l2_event *new) { new->u.ctrl.changes |= old->u.ctrl.changes; } EXPORT_SYMBOL(v4l2_ctrl_merge); const struct v4l2_subscribed_event_ops v4l2_ctrl_sub_ev_ops = { .add = v4l2_ctrl_add_event, .del = v4l2_ctrl_del_event, .replace = v4l2_ctrl_replace, .merge = v4l2_ctrl_merge, }; EXPORT_SYMBOL(v4l2_ctrl_sub_ev_ops); int v4l2_ctrl_subscribe_event(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub) { if (sub->type == V4L2_EVENT_CTRL) return v4l2_event_subscribe(fh, sub, 0, &v4l2_ctrl_sub_ev_ops); return -EINVAL; } EXPORT_SYMBOL(v4l2_ctrl_subscribe_event); int v4l2_ctrl_subdev_subscribe_event(struct v4l2_subdev *sd, struct v4l2_fh *fh, struct v4l2_event_subscription *sub) { if (!sd->ctrl_handler) return -EINVAL; return v4l2_ctrl_subscribe_event(fh, sub); } EXPORT_SYMBOL(v4l2_ctrl_subdev_subscribe_event); /* * poll helper */ __poll_t v4l2_ctrl_poll(struct file *file, struct poll_table_struct *wait) { struct v4l2_fh *fh = file_to_v4l2_fh(file); poll_wait(file, &fh->wait, wait); if (v4l2_event_pending(fh)) return EPOLLPRI; return 0; } EXPORT_SYMBOL(v4l2_ctrl_poll); |
| 5 2 2 2 2 2 2 3 3 3 3 2 2 2 2 2 2 2 2 1 1 3 1 2 2 1 1 1 2 2 1 1 2 4 4 8 1 7 1 1 1 1 1 1 4 4 4 5 5 4 4 4 4 4 4 4 4 4 2 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_qfq.c Quick Fair Queueing Plus Scheduler. * * Copyright (c) 2009 Fabio Checconi, Luigi Rizzo, and Paolo Valente. * Copyright (c) 2012 Paolo Valente. */ #include <linux/module.h> #include <linux/init.h> #include <linux/bitops.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/pkt_sched.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> /* Quick Fair Queueing Plus ======================== Sources: [1] Paolo Valente, "Reducing the Execution Time of Fair-Queueing Schedulers." http://algo.ing.unimo.it/people/paolo/agg-sched/agg-sched.pdf Sources for QFQ: [2] Fabio Checconi, Luigi Rizzo, and Paolo Valente: "QFQ: Efficient Packet Scheduling with Tight Bandwidth Distribution Guarantees." See also: http://retis.sssup.it/~fabio/linux/qfq/ */ /* QFQ+ divides classes into aggregates of at most MAX_AGG_CLASSES classes. Each aggregate is timestamped with a virtual start time S and a virtual finish time F, and scheduled according to its timestamps. S and F are computed as a function of a system virtual time function V. The classes within each aggregate are instead scheduled with DRR. To speed up operations, QFQ+ divides also aggregates into a limited number of groups. Which group a class belongs to depends on the ratio between the maximum packet length for the class and the weight of the class. Groups have their own S and F. In the end, QFQ+ schedules groups, then aggregates within groups, then classes within aggregates. See [1] and [2] for a full description. Virtual time computations. S, F and V are all computed in fixed point arithmetic with FRAC_BITS decimal bits. QFQ_MAX_INDEX is the maximum index allowed for a group. We need one bit per index. QFQ_MAX_WSHIFT is the maximum power of two supported as a weight. The layout of the bits is as below: [ MTU_SHIFT ][ FRAC_BITS ] [ MAX_INDEX ][ MIN_SLOT_SHIFT ] ^.__grp->index = 0 *.__grp->slot_shift where MIN_SLOT_SHIFT is derived by difference from the others. The max group index corresponds to Lmax/w_min, where Lmax=1<<MTU_SHIFT, w_min = 1 . From this, and knowing how many groups (MAX_INDEX) we want, we can derive the shift corresponding to each group. Because we often need to compute F = S + len/w_i and V = V + len/wsum instead of storing w_i store the value inv_w = (1<<FRAC_BITS)/w_i so we can do F = S + len * inv_w * wsum. We use W_TOT in the formulas so we can easily move between static and adaptive weight sum. The per-scheduler-instance data contain all the data structures for the scheduler: bitmaps and bucket lists. */ /* * Maximum number of consecutive slots occupied by backlogged classes * inside a group. */ #define QFQ_MAX_SLOTS 32 /* * Shifts used for aggregate<->group mapping. We allow class weights that are * in the range [1, 2^MAX_WSHIFT], and we try to map each aggregate i to the * group with the smallest index that can support the L_i / r_i configured * for the classes in the aggregate. * * grp->index is the index of the group; and grp->slot_shift * is the shift for the corresponding (scaled) sigma_i. */ #define QFQ_MAX_INDEX 24 #define QFQ_MAX_WSHIFT 10 #define QFQ_MAX_WEIGHT (1<<QFQ_MAX_WSHIFT) /* see qfq_slot_insert */ #define QFQ_MAX_WSUM (64*QFQ_MAX_WEIGHT) #define FRAC_BITS 30 /* fixed point arithmetic */ #define ONE_FP (1UL << FRAC_BITS) #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ #define QFQ_MAX_LMAX (1UL << QFQ_MTU_SHIFT) #define QFQ_MAX_AGG_CLASSES 8 /* max num classes per aggregate allowed */ /* * Possible group states. These values are used as indexes for the bitmaps * array of struct qfq_queue. */ enum qfq_state { ER, IR, EB, IB, QFQ_MAX_STATE }; struct qfq_group; struct qfq_aggregate; struct qfq_class { struct Qdisc_class_common common; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct Qdisc *qdisc; struct list_head alist; /* Link for active-classes list. */ struct qfq_aggregate *agg; /* Parent aggregate. */ int deficit; /* DRR deficit counter. */ }; struct qfq_aggregate { struct hlist_node next; /* Link for the slot list. */ u64 S, F; /* flow timestamps (exact) */ /* group we belong to. In principle we would need the index, * which is log_2(lmax/weight), but we never reference it * directly, only the group. */ struct qfq_group *grp; /* these are copied from the flowset. */ u32 class_weight; /* Weight of each class in this aggregate. */ /* Max pkt size for the classes in this aggregate, DRR quantum. */ int lmax; u32 inv_w; /* ONE_FP/(sum of weights of classes in aggr.). */ u32 budgetmax; /* Max budget for this aggregate. */ u32 initial_budget, budget; /* Initial and current budget. */ int num_classes; /* Number of classes in this aggr. */ struct list_head active; /* DRR queue of active classes. */ struct hlist_node nonfull_next; /* See nonfull_aggs in qfq_sched. */ }; struct qfq_group { u64 S, F; /* group timestamps (approx). */ unsigned int slot_shift; /* Slot shift. */ unsigned int index; /* Group index. */ unsigned int front; /* Index of the front slot. */ unsigned long full_slots; /* non-empty slots */ /* Array of RR lists of active aggregates. */ struct hlist_head slots[QFQ_MAX_SLOTS]; }; struct qfq_sched { struct tcf_proto __rcu *filter_list; struct tcf_block *block; struct Qdisc_class_hash clhash; u64 oldV, V; /* Precise virtual times. */ struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ u32 wsum; /* weight sum */ u32 iwsum; /* inverse weight sum */ unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */ struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */ u32 min_slot_shift; /* Index of the group-0 bit in the bitmaps. */ u32 max_agg_classes; /* Max number of classes per aggr. */ struct hlist_head nonfull_aggs; /* Aggs with room for more classes. */ }; /* * Possible reasons why the timestamps of an aggregate are updated * enqueue: the aggregate switches from idle to active and must scheduled * for service * requeue: the aggregate finishes its budget, so it stops being served and * must be rescheduled for service */ enum update_reason {enqueue, requeue}; static bool cl_is_active(struct qfq_class *cl) { return !list_empty(&cl->alist); } static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) { struct qfq_sched *q = qdisc_priv(sch); struct Qdisc_class_common *clc; clc = qdisc_class_find(&q->clhash, classid); if (clc == NULL) return NULL; return container_of(clc, struct qfq_class, common); } static const struct netlink_range_validation lmax_range = { .min = QFQ_MIN_LMAX, .max = QFQ_MAX_LMAX, }; static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { [TCA_QFQ_WEIGHT] = NLA_POLICY_RANGE(NLA_U32, 1, QFQ_MAX_WEIGHT), [TCA_QFQ_LMAX] = NLA_POLICY_FULL_RANGE(NLA_U32, &lmax_range), }; /* * Calculate a flow index, given its weight and maximum packet length. * index = log_2(maxlen/weight) but we need to apply the scaling. * This is used only once at flow creation. */ static int qfq_calc_index(u32 inv_w, unsigned int maxlen, u32 min_slot_shift) { u64 slot_size = (u64)maxlen * inv_w; unsigned long size_map; int index = 0; size_map = slot_size >> min_slot_shift; if (!size_map) goto out; index = __fls(size_map) + 1; /* basically a log_2 */ index -= !(slot_size - (1ULL << (index + min_slot_shift - 1))); if (index < 0) index = 0; out: pr_debug("qfq calc_index: W = %lu, L = %u, I = %d\n", (unsigned long) ONE_FP/inv_w, maxlen, index); return index; } static void qfq_deactivate_agg(struct qfq_sched *, struct qfq_aggregate *); static void qfq_activate_agg(struct qfq_sched *, struct qfq_aggregate *, enum update_reason); static void qfq_init_agg(struct qfq_sched *q, struct qfq_aggregate *agg, u32 lmax, u32 weight) { INIT_LIST_HEAD(&agg->active); hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs); agg->lmax = lmax; agg->class_weight = weight; } static struct qfq_aggregate *qfq_find_agg(struct qfq_sched *q, u32 lmax, u32 weight) { struct qfq_aggregate *agg; hlist_for_each_entry(agg, &q->nonfull_aggs, nonfull_next) if (agg->lmax == lmax && agg->class_weight == weight) return agg; return NULL; } /* Update aggregate as a function of the new number of classes. */ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg, int new_num_classes) { u32 new_agg_weight; if (new_num_classes == q->max_agg_classes) hlist_del_init(&agg->nonfull_next); if (agg->num_classes > new_num_classes && new_num_classes == q->max_agg_classes - 1) /* agg no more full */ hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs); /* The next assignment may let * agg->initial_budget > agg->budgetmax * hold, we will take it into account in charge_actual_service(). */ agg->budgetmax = new_num_classes * agg->lmax; new_agg_weight = agg->class_weight * new_num_classes; agg->inv_w = ONE_FP/new_agg_weight; if (agg->grp == NULL) { int i = qfq_calc_index(agg->inv_w, agg->budgetmax, q->min_slot_shift); agg->grp = &q->groups[i]; } q->wsum += (int) agg->class_weight * (new_num_classes - agg->num_classes); q->iwsum = ONE_FP / q->wsum; agg->num_classes = new_num_classes; } /* Add class to aggregate. */ static void qfq_add_to_agg(struct qfq_sched *q, struct qfq_aggregate *agg, struct qfq_class *cl) { cl->agg = agg; qfq_update_agg(q, agg, agg->num_classes+1); if (cl->qdisc->q.qlen > 0) { /* adding an active class */ list_add_tail(&cl->alist, &agg->active); if (list_first_entry(&agg->active, struct qfq_class, alist) == cl && q->in_serv_agg != agg) /* agg was inactive */ qfq_activate_agg(q, agg, enqueue); /* schedule agg */ } } static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *); static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { hlist_del_init(&agg->nonfull_next); q->wsum -= agg->class_weight; if (q->wsum != 0) q->iwsum = ONE_FP / q->wsum; if (q->in_serv_agg == agg) q->in_serv_agg = qfq_choose_next_agg(q); kfree(agg); } /* Deschedule class from within its parent aggregate. */ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) { struct qfq_aggregate *agg = cl->agg; list_del_init(&cl->alist); /* remove from RR queue of the aggregate */ if (list_empty(&agg->active)) /* agg is now inactive */ qfq_deactivate_agg(q, agg); } /* Remove class from its parent aggregate. */ static void qfq_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) { struct qfq_aggregate *agg = cl->agg; cl->agg = NULL; if (agg->num_classes == 1) { /* agg being emptied, destroy it */ qfq_destroy_agg(q, agg); return; } qfq_update_agg(q, agg, agg->num_classes-1); } /* Deschedule class and remove it from its parent aggregate. */ static void qfq_deact_rm_from_agg(struct qfq_sched *q, struct qfq_class *cl) { if (cl_is_active(cl)) /* class is active */ qfq_deactivate_class(q, cl); qfq_rm_from_agg(q, cl); } /* Move class to a new aggregate, matching the new class weight and/or lmax */ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, u32 lmax) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_aggregate *new_agg; /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */ if (lmax > QFQ_MAX_LMAX) return -EINVAL; new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ new_agg = kzalloc_obj(*new_agg, GFP_ATOMIC); if (new_agg == NULL) return -ENOBUFS; qfq_init_agg(q, new_agg, lmax, weight); } qfq_deact_rm_from_agg(q, cl); qfq_add_to_agg(q, new_agg, cl); return 0; } static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, unsigned long *arg, struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)*arg; bool existing = false; struct nlattr *tb[TCA_QFQ_MAX + 1]; struct qfq_aggregate *new_agg = NULL; u32 weight, lmax, inv_w, old_weight, old_lmax; int err; int delta_w; if (NL_REQ_ATTR_CHECK(extack, NULL, tca, TCA_OPTIONS)) { NL_SET_ERR_MSG_MOD(extack, "missing options"); return -EINVAL; } err = nla_parse_nested_deprecated(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy, extack); if (err < 0) return err; weight = nla_get_u32_default(tb[TCA_QFQ_WEIGHT], 1); if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); } else { /* MTU size is user controlled */ lmax = psched_mtu(qdisc_dev(sch)); if (lmax < QFQ_MIN_LMAX || lmax > QFQ_MAX_LMAX) { NL_SET_ERR_MSG_MOD(extack, "MTU size out of bounds for qfq"); return -EINVAL; } } inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; if (cl != NULL) { sch_tree_lock(sch); old_weight = cl->agg->class_weight; old_lmax = cl->agg->lmax; sch_tree_unlock(sch); if (lmax == old_lmax && weight == old_weight) return 0; /* nothing to change */ } delta_w = weight - (cl ? old_weight : 0); if (q->wsum + delta_w > QFQ_MAX_WSUM) { NL_SET_ERR_MSG_FMT_MOD(extack, "total weight out of range (%d + %u)", delta_w, q->wsum); return -EINVAL; } if (cl != NULL) { /* modify existing class */ if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, true, tca[TCA_RATE]); if (err) return err; } existing = true; goto set_change_agg; } /* create and init new class */ cl = kzalloc_obj(struct qfq_class); if (cl == NULL) return -ENOBUFS; gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->deficit = lmax; INIT_LIST_HEAD(&cl->alist); cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, NULL); if (cl->qdisc == NULL) cl->qdisc = &noop_qdisc; if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, true, tca[TCA_RATE]); if (err) goto destroy_class; } if (cl->qdisc != &noop_qdisc) qdisc_hash_add(cl->qdisc, true); set_change_agg: sch_tree_lock(sch); new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ sch_tree_unlock(sch); new_agg = kzalloc_obj(*new_agg); if (new_agg == NULL) { err = -ENOBUFS; gen_kill_estimator(&cl->rate_est); goto destroy_class; } sch_tree_lock(sch); qfq_init_agg(q, new_agg, lmax, weight); } if (existing) qfq_deact_rm_from_agg(q, cl); else qdisc_class_hash_insert(&q->clhash, &cl->common); qfq_add_to_agg(q, new_agg, cl); sch_tree_unlock(sch); qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; destroy_class: if (!existing) { qdisc_put(cl->qdisc); kfree(cl); } return err; } static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { gen_kill_estimator(&cl->rate_est); qdisc_put(cl->qdisc); kfree(cl); } static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; if (qdisc_class_in_use(&cl->common)) { NL_SET_ERR_MSG_MOD(extack, "QFQ class in use"); return -EBUSY; } sch_tree_lock(sch); qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); qfq_rm_from_agg(q, cl); sch_tree_unlock(sch); qfq_destroy_class(sch, cl); return 0; } static unsigned long qfq_search_class(struct Qdisc *sch, u32 classid) { return (unsigned long)qfq_find_class(sch, classid); } static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl, struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); if (cl) return NULL; return q->block; } static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent, u32 classid) { struct qfq_class *cl = qfq_find_class(sch, classid); if (cl) qdisc_class_get(&cl->common); return (unsigned long)cl; } static void qfq_unbind_tcf(struct Qdisc *sch, unsigned long arg) { struct qfq_class *cl = (struct qfq_class *)arg; qdisc_class_put(&cl->common); } static int qfq_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct qfq_class *cl = (struct qfq_class *)arg; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, cl->common.classid, NULL); if (new == NULL) new = &noop_qdisc; } *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } static struct Qdisc *qfq_class_leaf(struct Qdisc *sch, unsigned long arg) { struct qfq_class *cl = (struct qfq_class *)arg; return cl->qdisc; } static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct qfq_class *cl = (struct qfq_class *)arg; struct nlattr *nest; u32 class_weight, lmax; tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle = cl->common.classid; tcm->tcm_info = cl->qdisc->handle; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; sch_tree_lock(sch); class_weight = cl->agg->class_weight; lmax = cl->agg->lmax; sch_tree_unlock(sch); if (nla_put_u32(skb, TCA_QFQ_WEIGHT, class_weight) || nla_put_u32(skb, TCA_QFQ_LMAX, lmax)) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct qfq_class *cl = (struct qfq_class *)arg; struct tc_qfq_stats xstats; memset(&xstats, 0, sizeof(xstats)); sch_tree_lock(sch); xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; sch_tree_unlock(sch); if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || qdisc_qstats_copy(d, cl->qdisc) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); } static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg)) return; } } } static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; struct tcf_result res; struct tcf_proto *fl; int result; if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) { pr_debug("qfq_classify: found %d\n", skb->priority); cl = qfq_find_class(sch, skb->priority); if (cl != NULL) return cl; } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return NULL; } #endif cl = (struct qfq_class *)res.class; if (cl == NULL) cl = qfq_find_class(sch, res.classid); return cl; } return NULL; } /* Generic comparison function, handling wraparound. */ static inline int qfq_gt(u64 a, u64 b) { return (s64)(a - b) > 0; } /* Round a precise timestamp to its slotted value. */ static inline u64 qfq_round_down(u64 ts, unsigned int shift) { return ts & ~((1ULL << shift) - 1); } /* return the pointer to the group with lowest index in the bitmap */ static inline struct qfq_group *qfq_ffs(struct qfq_sched *q, unsigned long bitmap) { int index = __ffs(bitmap); return &q->groups[index]; } /* Calculate a mask to mimic what would be ffs_from(). */ static inline unsigned long mask_from(unsigned long bitmap, int from) { return bitmap & ~((1UL << from) - 1); } /* * The state computation relies on ER=0, IR=1, EB=2, IB=3 * First compute eligibility comparing grp->S, q->V, * then check if someone is blocking us and possibly add EB */ static int qfq_calc_state(struct qfq_sched *q, const struct qfq_group *grp) { /* if S > V we are not eligible */ unsigned int state = qfq_gt(grp->S, q->V); unsigned long mask = mask_from(q->bitmaps[ER], grp->index); struct qfq_group *next; if (mask) { next = qfq_ffs(q, mask); if (qfq_gt(grp->F, next->F)) state |= EB; } return state; } /* * In principle * q->bitmaps[dst] |= q->bitmaps[src] & mask; * q->bitmaps[src] &= ~mask; * but we should make sure that src != dst */ static inline void qfq_move_groups(struct qfq_sched *q, unsigned long mask, int src, int dst) { q->bitmaps[dst] |= q->bitmaps[src] & mask; q->bitmaps[src] &= ~mask; } static void qfq_unblock_groups(struct qfq_sched *q, int index, u64 old_F) { unsigned long mask = mask_from(q->bitmaps[ER], index + 1); struct qfq_group *next; if (mask) { next = qfq_ffs(q, mask); if (!qfq_gt(next->F, old_F)) return; } mask = (1UL << index) - 1; qfq_move_groups(q, mask, EB, ER); qfq_move_groups(q, mask, IB, IR); } /* * perhaps * old_V ^= q->V; old_V >>= q->min_slot_shift; if (old_V) { ... } * */ static void qfq_make_eligible(struct qfq_sched *q) { unsigned long vslot = q->V >> q->min_slot_shift; unsigned long old_vslot = q->oldV >> q->min_slot_shift; if (vslot != old_vslot) { unsigned long mask; int last_flip_pos = fls(vslot ^ old_vslot); if (last_flip_pos > 31) /* higher than the number of groups */ mask = ~0UL; /* make all groups eligible */ else mask = (1UL << last_flip_pos) - 1; qfq_move_groups(q, mask, IR, ER); qfq_move_groups(q, mask, IB, EB); } } /* * The index of the slot in which the input aggregate agg is to be * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2' * and not a '-1' because the start time of the group may be moved * backward by one slot after the aggregate has been inserted, and * this would cause non-empty slots to be right-shifted by one * position. * * QFQ+ fully satisfies this bound to the slot index if the parameters * of the classes are not changed dynamically, and if QFQ+ never * happens to postpone the service of agg unjustly, i.e., it never * happens that the aggregate becomes backlogged and eligible, or just * eligible, while an aggregate with a higher approximated finish time * is being served. In particular, in this case QFQ+ guarantees that * the timestamps of agg are low enough that the slot index is never * higher than 2. Unfortunately, QFQ+ cannot provide the same * guarantee if it happens to unjustly postpone the service of agg, or * if the parameters of some class are changed. * * As for the first event, i.e., an out-of-order service, the * upper bound to the slot index guaranteed by QFQ+ grows to * 2 + * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1. * * The following function deals with this problem by backward-shifting * the timestamps of agg, if needed, so as to guarantee that the slot * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may * cause the service of other aggregates to be postponed, yet the * worst-case guarantees of these aggregates are not violated. In * fact, in case of no out-of-order service, the timestamps of agg * would have been even lower than they are after the backward shift, * because QFQ+ would have guaranteed a maximum value equal to 2 for * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose * service is postponed because of the backward-shift would have * however waited for the service of agg before being served. * * The other event that may cause the slot index to be higher than 2 * for agg is a recent change of the parameters of some class. If the * weight of a class is increased or the lmax (max_pkt_size) of the * class is decreased, then a new aggregate with smaller slot size * than the original parent aggregate of the class may happen to be * activated. The activation of this aggregate should be properly * delayed to when the service of the class has finished in the ideal * system tracked by QFQ+. If the activation of the aggregate is not * delayed to this reference time instant, then this aggregate may be * unjustly served before other aggregates waiting for service. This * may cause the above bound to the slot index to be violated for some * of these unlucky aggregates. * * Instead of delaying the activation of the new aggregate, which is * quite complex, the above-discussed capping of the slot index is * used to handle also the consequences of a change of the parameters * of a class. */ static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg, u64 roundedS) { u64 slot = (roundedS - grp->S) >> grp->slot_shift; unsigned int i; /* slot index in the bucket list */ if (unlikely(slot > QFQ_MAX_SLOTS - 2)) { u64 deltaS = roundedS - grp->S - ((u64)(QFQ_MAX_SLOTS - 2)<<grp->slot_shift); agg->S -= deltaS; agg->F -= deltaS; slot = QFQ_MAX_SLOTS - 2; } i = (grp->front + slot) % QFQ_MAX_SLOTS; hlist_add_head(&agg->next, &grp->slots[i]); __set_bit(slot, &grp->full_slots); } /* Maybe introduce hlist_first_entry?? */ static struct qfq_aggregate *qfq_slot_head(struct qfq_group *grp) { return hlist_entry(grp->slots[grp->front].first, struct qfq_aggregate, next); } /* * remove the entry from the slot */ static void qfq_front_slot_remove(struct qfq_group *grp) { struct qfq_aggregate *agg = qfq_slot_head(grp); BUG_ON(!agg); hlist_del(&agg->next); if (hlist_empty(&grp->slots[grp->front])) __clear_bit(0, &grp->full_slots); } /* * Returns the first aggregate in the first non-empty bucket of the * group. As a side effect, adjusts the bucket list so the first * non-empty bucket is at position 0 in full_slots. */ static struct qfq_aggregate *qfq_slot_scan(struct qfq_group *grp) { unsigned int i; pr_debug("qfq slot_scan: grp %u full %#lx\n", grp->index, grp->full_slots); if (grp->full_slots == 0) return NULL; i = __ffs(grp->full_slots); /* zero based */ if (i > 0) { grp->front = (grp->front + i) % QFQ_MAX_SLOTS; grp->full_slots >>= i; } return qfq_slot_head(grp); } /* * adjust the bucket list. When the start time of a group decreases, * we move the index down (modulo QFQ_MAX_SLOTS) so we don't need to * move the objects. The mask of occupied slots must be shifted * because we use ffs() to find the first non-empty slot. * This covers decreases in the group's start time, but what about * increases of the start time ? * Here too we should make sure that i is less than 32 */ static void qfq_slot_rotate(struct qfq_group *grp, u64 roundedS) { unsigned int i = (grp->S - roundedS) >> grp->slot_shift; grp->full_slots <<= i; grp->front = (grp->front - i) % QFQ_MAX_SLOTS; } static void qfq_update_eligible(struct qfq_sched *q) { struct qfq_group *grp; unsigned long ineligible; ineligible = q->bitmaps[IR] | q->bitmaps[IB]; if (ineligible) { if (!q->bitmaps[ER]) { grp = qfq_ffs(q, ineligible); if (qfq_gt(grp->S, q->V)) q->V = grp->S; } qfq_make_eligible(q); } } /* Dequeue head packet of the head class in the DRR queue of the aggregate. */ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, struct qfq_class *cl, unsigned int len) { struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc); if (!skb) return NULL; cl->deficit -= (int) len; if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */ list_del_init(&cl->alist); else if (cl->deficit < qdisc_peek_len(cl->qdisc)) { cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } return skb; } static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, struct qfq_class **cl, unsigned int *len) { struct sk_buff *skb; *cl = list_first_entry(&agg->active, struct qfq_class, alist); skb = (*cl)->qdisc->ops->peek((*cl)->qdisc); if (skb == NULL) qdisc_warn_nonwc("qfq_dequeue", (*cl)->qdisc); else *len = qdisc_pkt_len(skb); return skb; } /* Update F according to the actual service received by the aggregate. */ static inline void charge_actual_service(struct qfq_aggregate *agg) { /* Compute the service received by the aggregate, taking into * account that, after decreasing the number of classes in * agg, it may happen that * agg->initial_budget - agg->budget > agg->bugdetmax */ u32 service_received = min(agg->budgetmax, agg->initial_budget - agg->budget); agg->F = agg->S + (u64)service_received * agg->inv_w; } /* Assign a reasonable start time for a new aggregate in group i. * Admissible values for \hat(F) are multiples of \sigma_i * no greater than V+\sigma_i . Larger values mean that * we had a wraparound so we consider the timestamp to be stale. * * If F is not stale and F >= V then we set S = F. * Otherwise we should assign S = V, but this may violate * the ordering in EB (see [2]). So, if we have groups in ER, * set S to the F_j of the first group j which would be blocking us. * We are guaranteed not to move S backward because * otherwise our group i would still be blocked. */ static void qfq_update_start(struct qfq_sched *q, struct qfq_aggregate *agg) { unsigned long mask; u64 limit, roundedF; int slot_shift = agg->grp->slot_shift; roundedF = qfq_round_down(agg->F, slot_shift); limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift); if (!qfq_gt(agg->F, q->V) || qfq_gt(roundedF, limit)) { /* timestamp was stale */ mask = mask_from(q->bitmaps[ER], agg->grp->index); if (mask) { struct qfq_group *next = qfq_ffs(q, mask); if (qfq_gt(roundedF, next->F)) { if (qfq_gt(limit, next->F)) agg->S = next->F; else /* preserve timestamp correctness */ agg->S = limit; return; } } agg->S = q->V; } else /* timestamp is not stale */ agg->S = agg->F; } /* Update the timestamps of agg before scheduling/rescheduling it for * service. In particular, assign to agg->F its maximum possible * value, i.e., the virtual finish time with which the aggregate * should be labeled if it used all its budget once in service. */ static inline void qfq_update_agg_ts(struct qfq_sched *q, struct qfq_aggregate *agg, enum update_reason reason) { if (reason != requeue) qfq_update_start(q, agg); else /* just charge agg for the service received */ agg->S = agg->F; agg->F = agg->S + (u64)agg->budgetmax * agg->inv_w; } static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg); static struct sk_buff *qfq_dequeue(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_aggregate *in_serv_agg = q->in_serv_agg; struct qfq_class *cl; struct sk_buff *skb = NULL; /* next-packet len, 0 means no more active classes in in-service agg */ unsigned int len = 0; if (in_serv_agg == NULL) return NULL; if (!list_empty(&in_serv_agg->active)) skb = qfq_peek_skb(in_serv_agg, &cl, &len); /* * If there are no active classes in the in-service aggregate, * or if the aggregate has not enough budget to serve its next * class, then choose the next aggregate to serve. */ if (len == 0 || in_serv_agg->budget < len) { charge_actual_service(in_serv_agg); /* recharge the budget of the aggregate */ in_serv_agg->initial_budget = in_serv_agg->budget = in_serv_agg->budgetmax; if (!list_empty(&in_serv_agg->active)) { /* * Still active: reschedule for * service. Possible optimization: if no other * aggregate is active, then there is no point * in rescheduling this aggregate, and we can * just keep it as the in-service one. This * should be however a corner case, and to * handle it, we would need to maintain an * extra num_active_aggs field. */ qfq_update_agg_ts(q, in_serv_agg, requeue); qfq_schedule_agg(q, in_serv_agg); } else if (sch->q.qlen == 0) { /* no aggregate to serve */ q->in_serv_agg = NULL; return NULL; } /* * If we get here, there are other aggregates queued: * choose the new aggregate to serve. */ in_serv_agg = q->in_serv_agg = qfq_choose_next_agg(q); skb = qfq_peek_skb(in_serv_agg, &cl, &len); } if (!skb) return NULL; sch->q.qlen--; skb = agg_dequeue(in_serv_agg, cl, len); if (!skb) { sch->q.qlen++; return NULL; } qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); /* If lmax is lowered, through qfq_change_class, for a class * owning pending packets with larger size than the new value * of lmax, then the following condition may hold. */ if (unlikely(in_serv_agg->budget < len)) in_serv_agg->budget = 0; else in_serv_agg->budget -= len; q->V += (u64)len * q->iwsum; pr_debug("qfq dequeue: len %u F %lld now %lld\n", len, (unsigned long long) in_serv_agg->F, (unsigned long long) q->V); return skb; } static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q) { struct qfq_group *grp; struct qfq_aggregate *agg, *new_front_agg; u64 old_F; qfq_update_eligible(q); q->oldV = q->V; if (!q->bitmaps[ER]) return NULL; grp = qfq_ffs(q, q->bitmaps[ER]); old_F = grp->F; agg = qfq_slot_head(grp); /* agg starts to be served, remove it from schedule */ qfq_front_slot_remove(grp); new_front_agg = qfq_slot_scan(grp); if (new_front_agg == NULL) /* group is now inactive, remove from ER */ __clear_bit(grp->index, &q->bitmaps[ER]); else { u64 roundedS = qfq_round_down(new_front_agg->S, grp->slot_shift); unsigned int s; if (grp->S == roundedS) return agg; grp->S = roundedS; grp->F = roundedS + (2ULL << grp->slot_shift); __clear_bit(grp->index, &q->bitmaps[ER]); s = qfq_calc_state(q, grp); __set_bit(grp->index, &q->bitmaps[s]); } qfq_unblock_groups(q, grp->index, old_F); return agg; } static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { unsigned int len = qdisc_pkt_len(skb), gso_segs; struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; struct qfq_aggregate *agg; int err = 0; cl = qfq_classify(skb, sch, &err); if (cl == NULL) { if (err & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return err; } pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); if (unlikely(cl->agg->lmax < len)) { pr_debug("qfq: increasing maxpkt from %u to %u for class %u", cl->agg->lmax, len, cl->common.classid); err = qfq_change_agg(sch, cl, cl->agg->class_weight, len); if (err) { cl->qstats.drops++; return qdisc_drop(skb, sch, to_free); } } gso_segs = qdisc_pkt_segs(skb); err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); if (net_xmit_drop_count(err)) { cl->qstats.drops++; qdisc_qstats_drop(sch); } return err; } _bstats_update(&cl->bstats, len, gso_segs); sch->qstats.backlog += len; ++sch->q.qlen; agg = cl->agg; /* if the class is active, then done here */ if (cl_is_active(cl)) { if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) && list_first_entry(&agg->active, struct qfq_class, alist) == cl && cl->deficit < len) list_move_tail(&cl->alist, &agg->active); return err; } /* schedule class for service within the aggregate */ cl->deficit = agg->lmax; list_add_tail(&cl->alist, &agg->active); if (list_first_entry(&agg->active, struct qfq_class, alist) != cl || q->in_serv_agg == agg) return err; /* non-empty or in service, nothing else to do */ qfq_activate_agg(q, agg, enqueue); return err; } /* * Schedule aggregate according to its timestamps. */ static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { struct qfq_group *grp = agg->grp; u64 roundedS; int s; roundedS = qfq_round_down(agg->S, grp->slot_shift); /* * Insert agg in the correct bucket. * If agg->S >= grp->S we don't need to adjust the * bucket list and simply go to the insertion phase. * Otherwise grp->S is decreasing, we must make room * in the bucket list, and also recompute the group state. * Finally, if there were no flows in this group and nobody * was in ER make sure to adjust V. */ if (grp->full_slots) { if (!qfq_gt(grp->S, agg->S)) goto skip_update; /* create a slot for this agg->S */ qfq_slot_rotate(grp, roundedS); /* group was surely ineligible, remove */ __clear_bit(grp->index, &q->bitmaps[IR]); __clear_bit(grp->index, &q->bitmaps[IB]); } else if (!q->bitmaps[ER] && qfq_gt(roundedS, q->V) && q->in_serv_agg == NULL) q->V = roundedS; grp->S = roundedS; grp->F = roundedS + (2ULL << grp->slot_shift); s = qfq_calc_state(q, grp); __set_bit(grp->index, &q->bitmaps[s]); pr_debug("qfq enqueue: new state %d %#lx S %lld F %lld V %lld\n", s, q->bitmaps[s], (unsigned long long) agg->S, (unsigned long long) agg->F, (unsigned long long) q->V); skip_update: qfq_slot_insert(grp, agg, roundedS); } /* Update agg ts and schedule agg for service */ static void qfq_activate_agg(struct qfq_sched *q, struct qfq_aggregate *agg, enum update_reason reason) { agg->initial_budget = agg->budget = agg->budgetmax; /* recharge budg. */ qfq_update_agg_ts(q, agg, reason); if (q->in_serv_agg == NULL) { /* no aggr. in service or scheduled */ q->in_serv_agg = agg; /* start serving this aggregate */ /* update V: to be in service, agg must be eligible */ q->oldV = q->V = agg->S; } else if (agg != q->in_serv_agg) qfq_schedule_agg(q, agg); } static void qfq_slot_remove(struct qfq_sched *q, struct qfq_group *grp, struct qfq_aggregate *agg) { unsigned int i, offset; u64 roundedS; roundedS = qfq_round_down(agg->S, grp->slot_shift); offset = (roundedS - grp->S) >> grp->slot_shift; i = (grp->front + offset) % QFQ_MAX_SLOTS; hlist_del(&agg->next); if (hlist_empty(&grp->slots[i])) __clear_bit(offset, &grp->full_slots); } /* * Called to forcibly deschedule an aggregate. If the aggregate is * not in the front bucket, or if the latter has other aggregates in * the front bucket, we can simply remove the aggregate with no other * side effects. * Otherwise we must propagate the event up. */ static void qfq_deactivate_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { struct qfq_group *grp = agg->grp; unsigned long mask; u64 roundedS; int s; if (agg == q->in_serv_agg) { charge_actual_service(agg); q->in_serv_agg = qfq_choose_next_agg(q); return; } agg->F = agg->S; qfq_slot_remove(q, grp, agg); if (!grp->full_slots) { __clear_bit(grp->index, &q->bitmaps[IR]); __clear_bit(grp->index, &q->bitmaps[EB]); __clear_bit(grp->index, &q->bitmaps[IB]); if (test_bit(grp->index, &q->bitmaps[ER]) && !(q->bitmaps[ER] & ~((1UL << grp->index) - 1))) { mask = q->bitmaps[ER] & ((1UL << grp->index) - 1); if (mask) mask = ~((1UL << __fls(mask)) - 1); else mask = ~0UL; qfq_move_groups(q, mask, EB, ER); qfq_move_groups(q, mask, IB, IR); } __clear_bit(grp->index, &q->bitmaps[ER]); } else if (hlist_empty(&grp->slots[grp->front])) { agg = qfq_slot_scan(grp); roundedS = qfq_round_down(agg->S, grp->slot_shift); if (grp->S != roundedS) { __clear_bit(grp->index, &q->bitmaps[ER]); __clear_bit(grp->index, &q->bitmaps[IR]); __clear_bit(grp->index, &q->bitmaps[EB]); __clear_bit(grp->index, &q->bitmaps[IB]); grp->S = roundedS; grp->F = roundedS + (2ULL << grp->slot_shift); s = qfq_calc_state(q, grp); __set_bit(grp->index, &q->bitmaps[s]); } } } static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; if (list_empty(&cl->alist)) return; qfq_deactivate_class(q, cl); } static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_group *grp; int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; max_classes = min_t(u64, (u64)qdisc_dev(sch)->tx_queue_len + 1, QFQ_MAX_AGG_CLASSES); /* max_cl_shift = floor(log_2(max_classes)) */ max_cl_shift = __fls(max_classes); q->max_agg_classes = 1<<max_cl_shift; /* maxbudg_shift = log2(max_len * max_classes_per_agg) */ maxbudg_shift = QFQ_MTU_SHIFT + max_cl_shift; q->min_slot_shift = FRAC_BITS + maxbudg_shift - QFQ_MAX_INDEX; for (i = 0; i <= QFQ_MAX_INDEX; i++) { grp = &q->groups[i]; grp->index = i; grp->slot_shift = q->min_slot_shift + i; for (j = 0; j < QFQ_MAX_SLOTS; j++) INIT_HLIST_HEAD(&grp->slots[j]); } INIT_HLIST_HEAD(&q->nonfull_aggs); return 0; } static void qfq_reset_qdisc(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl_is_active(cl)) qfq_deactivate_class(q, cl); qdisc_reset(cl->qdisc); } } } static void qfq_destroy_qdisc(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; struct hlist_node *next; unsigned int i; tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { qfq_rm_from_agg(q, cl); qfq_destroy_class(sch, cl); } } qdisc_class_hash_destroy(&q->clhash); } static const struct Qdisc_class_ops qfq_class_ops = { .change = qfq_change_class, .delete = qfq_delete_class, .find = qfq_search_class, .tcf_block = qfq_tcf_block, .bind_tcf = qfq_bind_tcf, .unbind_tcf = qfq_unbind_tcf, .graft = qfq_graft_class, .leaf = qfq_class_leaf, .qlen_notify = qfq_qlen_notify, .dump = qfq_dump_class, .dump_stats = qfq_dump_class_stats, .walk = qfq_walk, }; static struct Qdisc_ops qfq_qdisc_ops __read_mostly = { .cl_ops = &qfq_class_ops, .id = "qfq", .priv_size = sizeof(struct qfq_sched), .enqueue = qfq_enqueue, .dequeue = qfq_dequeue, .peek = qdisc_peek_dequeued, .init = qfq_init_qdisc, .reset = qfq_reset_qdisc, .destroy = qfq_destroy_qdisc, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("qfq"); static int __init qfq_init(void) { return register_qdisc(&qfq_qdisc_ops); } static void __exit qfq_exit(void) { unregister_qdisc(&qfq_qdisc_ops); } module_init(qfq_init); module_exit(qfq_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Quick Fair Queueing Plus qdisc"); |
| 201 201 93 1 42 32 39 93 93 93 8 85 53 41 51 2 40 93 32 32 32 32 32 32 32 35 35 16 19 4 32 15 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * open/close and reset interface * * Copyright (C) 1998-1999 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "seq_oss_writeq.h" #include "seq_oss_readq.h" #include "seq_oss_timer.h" #include "seq_oss_event.h" #include <linux/init.h> #include <linux/export.h> #include <linux/moduleparam.h> #include <linux/slab.h> #include <linux/workqueue.h> /* * common variables */ static int maxqlen = SNDRV_SEQ_OSS_MAX_QLEN; module_param(maxqlen, int, 0444); MODULE_PARM_DESC(maxqlen, "maximum queue length"); static int system_client = -1; /* ALSA sequencer client number */ static int system_port = -1; static int num_clients; static struct seq_oss_devinfo *client_table[SNDRV_SEQ_OSS_MAX_CLIENTS]; /* * prototypes */ static int receive_announce(struct snd_seq_event *ev, int direct, void *private, int atomic, int hop); static int translate_mode(struct file *file); static int create_port(struct seq_oss_devinfo *dp); static int delete_port(struct seq_oss_devinfo *dp); static int alloc_seq_queue(struct seq_oss_devinfo *dp); static int delete_seq_queue(int queue); static void free_devinfo(void *private); #define call_ctl(type,rec) snd_seq_kernel_client_ctl(system_client, type, rec) /* call snd_seq_oss_midi_lookup_ports() asynchronously */ static void async_call_lookup_ports(struct work_struct *work) { snd_seq_oss_midi_lookup_ports(system_client); } static DECLARE_WORK(async_lookup_work, async_call_lookup_ports); /* * create sequencer client for OSS sequencer */ int __init snd_seq_oss_create_client(void) { int rc; struct snd_seq_port_callback port_callback; struct snd_seq_port_info *port __free(kfree) = kzalloc_obj(*port); if (!port) return -ENOMEM; /* create ALSA client */ rc = snd_seq_create_kernel_client(NULL, SNDRV_SEQ_CLIENT_OSS, "OSS sequencer"); if (rc < 0) return rc; system_client = rc; /* create announcement receiver port */ strscpy(port->name, "Receiver"); port->addr.client = system_client; port->capability = SNDRV_SEQ_PORT_CAP_WRITE; /* receive only */ port->type = 0; memset(&port_callback, 0, sizeof(port_callback)); /* don't set port_callback.owner here. otherwise the module counter * is incremented and we can no longer release the module.. */ port_callback.event_input = receive_announce; port->kernel = &port_callback; if (call_ctl(SNDRV_SEQ_IOCTL_CREATE_PORT, port) >= 0) { struct snd_seq_port_subscribe subs; system_port = port->addr.port; memset(&subs, 0, sizeof(subs)); subs.sender.client = SNDRV_SEQ_CLIENT_SYSTEM; subs.sender.port = SNDRV_SEQ_PORT_SYSTEM_ANNOUNCE; subs.dest.client = system_client; subs.dest.port = system_port; call_ctl(SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs); } /* look up midi devices */ schedule_work(&async_lookup_work); return 0; } /* * receive announcement from system port, and check the midi device */ static int receive_announce(struct snd_seq_event *ev, int direct, void *private, int atomic, int hop) { struct snd_seq_port_info pinfo; if (atomic) return 0; /* it must not happen */ switch (ev->type) { case SNDRV_SEQ_EVENT_PORT_START: case SNDRV_SEQ_EVENT_PORT_CHANGE: if (ev->data.addr.client == system_client) break; /* ignore myself */ memset(&pinfo, 0, sizeof(pinfo)); pinfo.addr = ev->data.addr; if (call_ctl(SNDRV_SEQ_IOCTL_GET_PORT_INFO, &pinfo) >= 0) snd_seq_oss_midi_check_new_port(&pinfo); break; case SNDRV_SEQ_EVENT_PORT_EXIT: if (ev->data.addr.client == system_client) break; /* ignore myself */ snd_seq_oss_midi_check_exit_port(ev->data.addr.client, ev->data.addr.port); break; } return 0; } /* * delete OSS sequencer client */ int snd_seq_oss_delete_client(void) { cancel_work_sync(&async_lookup_work); if (system_client >= 0) snd_seq_delete_kernel_client(system_client); snd_seq_oss_midi_clear_all(); return 0; } /* * open sequencer device */ int snd_seq_oss_open(struct file *file, int level) { int i, rc; struct seq_oss_devinfo *dp; dp = kzalloc_obj(*dp); if (!dp) return -ENOMEM; dp->cseq = system_client; dp->port = -1; dp->queue = -1; for (i = 0; i < SNDRV_SEQ_OSS_MAX_CLIENTS; i++) { if (client_table[i] == NULL) break; } dp->index = i; if (i >= SNDRV_SEQ_OSS_MAX_CLIENTS) { pr_debug("ALSA: seq_oss: too many applications\n"); rc = -ENOMEM; goto _error; } /* look up synth and midi devices */ snd_seq_oss_synth_setup(dp); snd_seq_oss_midi_setup(dp); if (dp->synth_opened == 0 && dp->max_mididev == 0) { /* pr_err("ALSA: seq_oss: no device found\n"); */ rc = -ENODEV; goto _error; } /* create port */ rc = create_port(dp); if (rc < 0) { pr_err("ALSA: seq_oss: can't create port\n"); goto _error; } /* allocate queue */ rc = alloc_seq_queue(dp); if (rc < 0) goto _error; /* set address */ dp->addr.client = dp->cseq; dp->addr.port = dp->port; /*dp->addr.queue = dp->queue;*/ /*dp->addr.channel = 0;*/ dp->seq_mode = level; /* set up file mode */ dp->file_mode = translate_mode(file); /* initialize read queue */ if (is_read_mode(dp->file_mode)) { dp->readq = snd_seq_oss_readq_new(dp, maxqlen); if (!dp->readq) { rc = -ENOMEM; goto _error; } } /* initialize write queue */ if (is_write_mode(dp->file_mode)) { dp->writeq = snd_seq_oss_writeq_new(dp, maxqlen); if (!dp->writeq) { rc = -ENOMEM; goto _error; } } /* initialize timer */ dp->timer = snd_seq_oss_timer_new(dp); if (!dp->timer) { pr_err("ALSA: seq_oss: can't alloc timer\n"); rc = -ENOMEM; goto _error; } /* set private data pointer */ file->private_data = dp; /* set up for mode2 */ if (level == SNDRV_SEQ_OSS_MODE_MUSIC) snd_seq_oss_synth_setup_midi(dp); else if (is_read_mode(dp->file_mode)) snd_seq_oss_midi_open_all(dp, SNDRV_SEQ_OSS_FILE_READ); client_table[dp->index] = dp; num_clients++; return 0; _error: snd_seq_oss_synth_cleanup(dp); snd_seq_oss_midi_cleanup(dp); delete_seq_queue(dp->queue); delete_port(dp); return rc; } /* * translate file flags to private mode */ static int translate_mode(struct file *file) { int file_mode = 0; if ((file->f_flags & O_ACCMODE) != O_RDONLY) file_mode |= SNDRV_SEQ_OSS_FILE_WRITE; if ((file->f_flags & O_ACCMODE) != O_WRONLY) file_mode |= SNDRV_SEQ_OSS_FILE_READ; if (file->f_flags & O_NONBLOCK) file_mode |= SNDRV_SEQ_OSS_FILE_NONBLOCK; return file_mode; } /* * create sequencer port */ static int create_port(struct seq_oss_devinfo *dp) { int rc; struct snd_seq_port_info port; struct snd_seq_port_callback callback; memset(&port, 0, sizeof(port)); port.addr.client = dp->cseq; sprintf(port.name, "Sequencer-%d", dp->index); port.capability = SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_WRITE; /* no subscription */ port.type = SNDRV_SEQ_PORT_TYPE_SPECIFIC; port.midi_channels = 128; port.synth_voices = 128; memset(&callback, 0, sizeof(callback)); callback.owner = THIS_MODULE; callback.private_data = dp; callback.event_input = snd_seq_oss_event_input; callback.private_free = free_devinfo; port.kernel = &callback; rc = call_ctl(SNDRV_SEQ_IOCTL_CREATE_PORT, &port); if (rc < 0) return rc; dp->port = port.addr.port; return 0; } /* * delete ALSA port */ static int delete_port(struct seq_oss_devinfo *dp) { if (dp->port < 0) { kfree(dp); return 0; } return snd_seq_event_port_detach(dp->cseq, dp->port); } /* * allocate a queue */ static int alloc_seq_queue(struct seq_oss_devinfo *dp) { struct snd_seq_queue_info qinfo; int rc; memset(&qinfo, 0, sizeof(qinfo)); qinfo.owner = system_client; qinfo.locked = 1; strscpy(qinfo.name, "OSS Sequencer Emulation"); rc = call_ctl(SNDRV_SEQ_IOCTL_CREATE_QUEUE, &qinfo); if (rc < 0) return rc; dp->queue = qinfo.queue; return 0; } /* * release queue */ static int delete_seq_queue(int queue) { struct snd_seq_queue_info qinfo; int rc; if (queue < 0) return 0; memset(&qinfo, 0, sizeof(qinfo)); qinfo.queue = queue; rc = call_ctl(SNDRV_SEQ_IOCTL_DELETE_QUEUE, &qinfo); if (rc < 0) pr_err("ALSA: seq_oss: unable to delete queue %d (%d)\n", queue, rc); return rc; } /* * free device informations - private_free callback of port */ static void free_devinfo(void *private) { struct seq_oss_devinfo *dp = (struct seq_oss_devinfo *)private; snd_seq_oss_timer_delete(dp->timer); snd_seq_oss_writeq_delete(dp->writeq); snd_seq_oss_readq_delete(dp->readq); kfree(dp); } /* * close sequencer device */ void snd_seq_oss_release(struct seq_oss_devinfo *dp) { int queue; client_table[dp->index] = NULL; num_clients--; snd_seq_oss_reset(dp); snd_seq_oss_synth_cleanup(dp); snd_seq_oss_midi_cleanup(dp); /* clear slot */ queue = dp->queue; if (dp->port >= 0) delete_port(dp); delete_seq_queue(queue); } /* * reset sequencer devices */ void snd_seq_oss_reset(struct seq_oss_devinfo *dp) { int i; /* reset all synth devices */ for (i = 0; i < dp->max_synthdev; i++) snd_seq_oss_synth_reset(dp, i); /* reset all midi devices */ if (dp->seq_mode != SNDRV_SEQ_OSS_MODE_MUSIC) { for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_reset(dp, i); } /* remove queues */ if (dp->readq) snd_seq_oss_readq_clear(dp->readq); if (dp->writeq) snd_seq_oss_writeq_clear(dp->writeq); /* reset timer */ snd_seq_oss_timer_stop(dp->timer); } #ifdef CONFIG_SND_PROC_FS /* * misc. functions for proc interface */ static const char * filemode_str(int val) { static const char * const str[] = { "none", "read", "write", "read/write", }; return str[val & SNDRV_SEQ_OSS_FILE_ACMODE]; } /* * proc interface */ void snd_seq_oss_system_info_read(struct snd_info_buffer *buf) { int i; struct seq_oss_devinfo *dp; snd_iprintf(buf, "ALSA client number %d\n", system_client); snd_iprintf(buf, "ALSA receiver port %d\n", system_port); snd_iprintf(buf, "\nNumber of applications: %d\n", num_clients); for (i = 0; i < num_clients; i++) { snd_iprintf(buf, "\nApplication %d: ", i); dp = client_table[i]; if (!dp) { snd_iprintf(buf, "*empty*\n"); continue; } snd_iprintf(buf, "port %d : queue %d\n", dp->port, dp->queue); snd_iprintf(buf, " sequencer mode = %s : file open mode = %s\n", (dp->seq_mode ? "music" : "synth"), filemode_str(dp->file_mode)); if (dp->seq_mode) snd_iprintf(buf, " timer tempo = %d, timebase = %d\n", dp->timer->oss_tempo, dp->timer->oss_timebase); snd_iprintf(buf, " max queue length %d\n", maxqlen); if (is_read_mode(dp->file_mode) && dp->readq) snd_seq_oss_readq_info_read(dp->readq, buf); } } #endif /* CONFIG_SND_PROC_FS */ |
| 2121 2600 2600 2129 3420 3419 2160 3523 3449 3453 3087 3448 3515 2170 2165 283 2163 2167 2167 3510 3515 3518 3426 3420 3422 3378 3523 3515 3421 3475 3380 3500 3505 2598 2530 2553 2601 2555 2531 2626 2615 2557 3347 3346 3343 2529 2535 26 26 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/group.c - Operations for adding/removing multiple files at once. * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab * Copyright (c) 2013 Greg Kroah-Hartman * Copyright (c) 2013 The Linux Foundation */ #include <linux/kobject.h> #include <linux/module.h> #include <linux/dcache.h> #include <linux/namei.h> #include <linux/err.h> #include <linux/fs.h> #include "sysfs.h" static void remove_files(struct kernfs_node *parent, const struct attribute_group *grp) { struct attribute *const *attr; const struct bin_attribute *const *bin_attr; if (grp->attrs) for (attr = grp->attrs; *attr; attr++) kernfs_remove_by_name(parent, (*attr)->name); if (grp->bin_attrs) for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) kernfs_remove_by_name(parent, (*bin_attr)->attr.name); } static umode_t __first_visible(const struct attribute_group *grp, struct kobject *kobj) { if (grp->attrs && grp->attrs[0] && grp->is_visible) return grp->is_visible(kobj, grp->attrs[0], 0); if (grp->attrs && grp->attrs[0] && grp->is_visible_const) return grp->is_visible_const(kobj, grp->attrs[0], 0); if (grp->bin_attrs && grp->bin_attrs[0] && grp->is_bin_visible) return grp->is_bin_visible(kobj, grp->bin_attrs[0], 0); return 0; } static int create_files(struct kernfs_node *parent, struct kobject *kobj, kuid_t uid, kgid_t gid, const struct attribute_group *grp, int update) { struct attribute *const *attr; const struct bin_attribute *const *bin_attr; int error = 0, i; if (grp->attrs) { for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) { umode_t mode = (*attr)->mode; /* * In update mode, we're changing the permissions or * visibility. Do this by first removing then * re-adding (if required) the file. */ if (update) kernfs_remove_by_name(parent, (*attr)->name); if (grp->is_visible || grp->is_visible_const) { if (grp->is_visible) mode = grp->is_visible(kobj, *attr, i); else mode = grp->is_visible_const(kobj, *attr, i); mode &= ~SYSFS_GROUP_INVISIBLE; if (!mode) continue; } WARN(mode & ~(SYSFS_PREALLOC | 0664), "Attribute %s: Invalid permissions 0%o\n", (*attr)->name, mode); mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_file_mode_ns(parent, *attr, mode, uid, gid, NULL); if (unlikely(error)) break; } if (error) { remove_files(parent, grp); goto exit; } } if (grp->bin_attrs) { for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { umode_t mode = (*bin_attr)->attr.mode; size_t size = (*bin_attr)->size; if (update) kernfs_remove_by_name(parent, (*bin_attr)->attr.name); if (grp->is_bin_visible) { mode = grp->is_bin_visible(kobj, *bin_attr, i); mode &= ~SYSFS_GROUP_INVISIBLE; if (!mode) continue; } if (grp->bin_size) size = grp->bin_size(kobj, *bin_attr, i); WARN(mode & ~(SYSFS_PREALLOC | 0664), "Attribute %s: Invalid permissions 0%o\n", (*bin_attr)->attr.name, mode); mode &= SYSFS_PREALLOC | 0664; error = sysfs_add_bin_file_mode_ns(parent, *bin_attr, mode, size, uid, gid, NULL); if (error) break; } if (error) remove_files(parent, grp); } exit: return error; } static int internal_create_group(struct kobject *kobj, int update, const struct attribute_group *grp) { struct kernfs_node *kn; kuid_t uid; kgid_t gid; int error; if (WARN_ON(!kobj || (!update && !kobj->sd))) return -EINVAL; /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) return -EINVAL; if (!grp->attrs && !grp->bin_attrs) { pr_debug("sysfs: (bin_)attrs not set by subsystem for group: %s/%s, skipping\n", kobj->name, grp->name ?: ""); return 0; } kobject_get_ownership(kobj, &uid, &gid); if (grp->name) { umode_t mode = __first_visible(grp, kobj); if (mode & SYSFS_GROUP_INVISIBLE) mode = 0; else mode = S_IRWXU | S_IRUGO | S_IXUGO; if (update) { kn = kernfs_find_and_get(kobj->sd, grp->name); if (!kn) { pr_debug("attr grp %s/%s not created yet\n", kobj->name, grp->name); /* may have been invisible prior to this update */ update = 0; } else if (!mode) { sysfs_remove_group(kobj, grp); kernfs_put(kn); return 0; } } if (!update) { if (!mode) return 0; kn = kernfs_create_dir_ns(kobj->sd, grp->name, mode, uid, gid, kobj, NULL); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(kobj->sd, grp->name); return PTR_ERR(kn); } } } else { kn = kobj->sd; } kernfs_get(kn); error = create_files(kn, kobj, uid, gid, grp, update); if (error) { if (grp->name && !update) kernfs_remove(kn); } kernfs_put(kn); if (grp->name && update) kernfs_put(kn); return error; } /** * sysfs_create_group - given a directory kobject, create an attribute group * @kobj: The kobject to create the group on * @grp: The attribute group to create * * This function creates a group for the first time. It will explicitly * warn and error if any of the attribute files being created already exist. * * Returns 0 on success or error code on failure. */ int sysfs_create_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 0, grp); } EXPORT_SYMBOL_GPL(sysfs_create_group); static int internal_create_groups(struct kobject *kobj, int update, const struct attribute_group *const *groups) { int error = 0; int i; if (!groups) return 0; for (i = 0; groups[i]; i++) { error = internal_create_group(kobj, update, groups[i]); if (error) { while (--i >= 0) sysfs_remove_group(kobj, groups[i]); break; } } return error; } /** * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups * @kobj: The kobject to create the group on * @groups: The attribute groups to create, NULL terminated * * This function creates a bunch of attribute groups. If an error occurs when * creating a group, all previously created groups will be removed, unwinding * everything back to the original state when this function was called. * It will explicitly warn and error if any of the attribute files being * created already exist. * * Returns 0 on success or error code from sysfs_create_group on failure. */ int sysfs_create_groups(struct kobject *kobj, const struct attribute_group *const *groups) { return internal_create_groups(kobj, 0, groups); } EXPORT_SYMBOL_GPL(sysfs_create_groups); /** * sysfs_update_groups - given a directory kobject, create a bunch of attribute groups * @kobj: The kobject to update the group on * @groups: The attribute groups to update, NULL terminated * * This function update a bunch of attribute groups. If an error occurs when * updating a group, all previously updated groups will be removed together * with already existing (not updated) attributes. * * Returns 0 on success or error code from sysfs_update_group on failure. */ int sysfs_update_groups(struct kobject *kobj, const struct attribute_group *const *groups) { return internal_create_groups(kobj, 1, groups); } EXPORT_SYMBOL_GPL(sysfs_update_groups); /** * sysfs_update_group - given a directory kobject, update an attribute group * @kobj: The kobject to update the group on * @grp: The attribute group to update * * This function updates an attribute group. Unlike * sysfs_create_group(), it will explicitly not warn or error if any * of the attribute files being created already exist. Furthermore, * if the visibility of the files has changed through the is_visible() * callback, it will update the permissions and add or remove the * relevant files. Changing a group's name (subdirectory name under * kobj's directory in sysfs) is not allowed. * * The primary use for this function is to call it after making a change * that affects group visibility. * * Returns 0 on success or error code on failure. */ int sysfs_update_group(struct kobject *kobj, const struct attribute_group *grp) { return internal_create_group(kobj, 1, grp); } EXPORT_SYMBOL_GPL(sysfs_update_group); /** * sysfs_remove_group: remove a group from a kobject * @kobj: kobject to remove the group from * @grp: group to remove * * This function removes a group of attributes from a kobject. The attributes * previously have to have been created for this group, otherwise it will fail. */ void sysfs_remove_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent = kobj->sd; struct kernfs_node *kn; if (grp->name) { kn = kernfs_find_and_get(parent, grp->name); if (!kn) { pr_debug("sysfs group '%s' not found for kobject '%s'\n", grp->name, kobject_name(kobj)); return; } } else { kn = parent; kernfs_get(kn); } remove_files(kn, grp); if (grp->name) kernfs_remove(kn); kernfs_put(kn); } EXPORT_SYMBOL_GPL(sysfs_remove_group); /** * sysfs_remove_groups - remove a list of groups * * @kobj: The kobject for the groups to be removed from * @groups: NULL terminated list of groups to be removed * * If groups is not NULL, remove the specified groups from the kobject. */ void sysfs_remove_groups(struct kobject *kobj, const struct attribute_group *const *groups) { int i; if (!groups) return; for (i = 0; groups[i]; i++) sysfs_remove_group(kobj, groups[i]); } EXPORT_SYMBOL_GPL(sysfs_remove_groups); /** * sysfs_merge_group - merge files into a pre-existing named attribute group. * @kobj: The kobject containing the group. * @grp: The files to create and the attribute group they belong to. * * This function returns an error if the group doesn't exist, the .name field is * NULL or any of the files already exist in that group, in which case none of * the new files are created. */ int sysfs_merge_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent; kuid_t uid; kgid_t gid; int error = 0; struct attribute *const *attr; int i; parent = kernfs_find_and_get(kobj->sd, grp->name); if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr)) error = sysfs_add_file_mode_ns(parent, *attr, (*attr)->mode, uid, gid, NULL); if (error) { while (--i >= 0) kernfs_remove_by_name(parent, (*--attr)->name); } kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_merge_group); /** * sysfs_unmerge_group - remove files from a pre-existing named attribute group. * @kobj: The kobject containing the group. * @grp: The files to remove and the attribute group they belong to. */ void sysfs_unmerge_group(struct kobject *kobj, const struct attribute_group *grp) { struct kernfs_node *parent; struct attribute *const *attr; parent = kernfs_find_and_get(kobj->sd, grp->name); if (parent) { for (attr = grp->attrs; *attr; ++attr) kernfs_remove_by_name(parent, (*attr)->name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_unmerge_group); /** * sysfs_add_link_to_group - add a symlink to an attribute group. * @kobj: The kobject containing the group. * @group_name: The name of the group. * @target: The target kobject of the symlink to create. * @link_name: The name of the symlink to create. */ int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name, struct kobject *target, const char *link_name) { struct kernfs_node *parent; int error = 0; parent = kernfs_find_and_get(kobj->sd, group_name); if (!parent) return -ENOENT; error = sysfs_create_link_sd(parent, target, link_name); kernfs_put(parent); return error; } EXPORT_SYMBOL_GPL(sysfs_add_link_to_group); /** * sysfs_remove_link_from_group - remove a symlink from an attribute group. * @kobj: The kobject containing the group. * @group_name: The name of the group. * @link_name: The name of the symlink to remove. */ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name, const char *link_name) { struct kernfs_node *parent; parent = kernfs_find_and_get(kobj->sd, group_name); if (parent) { kernfs_remove_by_name(parent, link_name); kernfs_put(parent); } } EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group); /** * compat_only_sysfs_link_entry_to_kobj - add a symlink to a kobject pointing * to a group or an attribute * @kobj: The kobject containing the group. * @target_kobj: The target kobject. * @target_name: The name of the target group or attribute. * @symlink_name: The name of the symlink file (target_name will be * considered if symlink_name is NULL). */ int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, struct kobject *target_kobj, const char *target_name, const char *symlink_name) { struct kernfs_node *target; struct kernfs_node *entry; struct kernfs_node *link; /* * We don't own @target_kobj and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See sysfs_remove_dir() * for details. */ spin_lock(&sysfs_symlink_target_lock); target = target_kobj->sd; if (target) kernfs_get(target); spin_unlock(&sysfs_symlink_target_lock); if (!target) return -ENOENT; entry = kernfs_find_and_get(target, target_name); if (!entry) { kernfs_put(target); return -ENOENT; } if (!symlink_name) symlink_name = target_name; link = kernfs_create_link(kobj->sd, symlink_name, entry); if (PTR_ERR(link) == -EEXIST) sysfs_warn_dup(kobj->sd, symlink_name); kernfs_put(entry); kernfs_put(target); return PTR_ERR_OR_ZERO(link); } EXPORT_SYMBOL_GPL(compat_only_sysfs_link_entry_to_kobj); static int sysfs_group_attrs_change_owner(struct kobject *kobj, struct kernfs_node *grp_kn, const struct attribute_group *grp, struct iattr *newattrs) { struct kernfs_node *kn; int error, i; umode_t mode; if (grp->attrs) { struct attribute *const *attr; for (i = 0, attr = grp->attrs; *attr; i++, attr++) { if (grp->is_visible || grp->is_visible_const) { if (grp->is_visible) mode = grp->is_visible(kobj, *attr, i); else mode = grp->is_visible_const(kobj, *attr, i); if (mode & SYSFS_GROUP_INVISIBLE) break; if (!mode) continue; } kn = kernfs_find_and_get(grp_kn, (*attr)->name); if (!kn) return -ENOENT; error = kernfs_setattr(kn, newattrs); kernfs_put(kn); if (error) return error; } } if (grp->bin_attrs) { const struct bin_attribute *const *bin_attr; for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { if (grp->is_bin_visible) { mode = grp->is_bin_visible(kobj, *bin_attr, i); if (mode & SYSFS_GROUP_INVISIBLE) break; if (!mode) continue; } kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); if (!kn) return -ENOENT; error = kernfs_setattr(kn, newattrs); kernfs_put(kn); if (error) return error; } } return 0; } /** * sysfs_group_change_owner - change owner of an attribute group. * @kobj: The kobject containing the group. * @grp: The attribute group. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Returns 0 on success or error code on failure. */ int sysfs_group_change_owner(struct kobject *kobj, const struct attribute_group *grp, kuid_t kuid, kgid_t kgid) { struct kernfs_node *grp_kn; int error; struct iattr newattrs = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = kuid, .ia_gid = kgid, }; if (!kobj->state_in_sysfs) return -EINVAL; if (grp->name) { grp_kn = kernfs_find_and_get(kobj->sd, grp->name); } else { kernfs_get(kobj->sd); grp_kn = kobj->sd; } if (!grp_kn) return -ENOENT; error = kernfs_setattr(grp_kn, &newattrs); if (!error) error = sysfs_group_attrs_change_owner(kobj, grp_kn, grp, &newattrs); kernfs_put(grp_kn); return error; } EXPORT_SYMBOL_GPL(sysfs_group_change_owner); /** * sysfs_groups_change_owner - change owner of a set of attribute groups. * @kobj: The kobject containing the groups. * @groups: The attribute groups. * @kuid: new owner's kuid * @kgid: new owner's kgid * * Returns 0 on success or error code on failure. */ int sysfs_groups_change_owner(struct kobject *kobj, const struct attribute_group *const *groups, kuid_t kuid, kgid_t kgid) { int error = 0, i; if (!kobj->state_in_sysfs) return -EINVAL; if (!groups) return 0; for (i = 0; groups[i]; i++) { error = sysfs_group_change_owner(kobj, groups[i], kuid, kgid); if (error) break; } return error; } EXPORT_SYMBOL_GPL(sysfs_groups_change_owner); |
| 8 7 1 1 13 7 6 8 7 1 11 2 12 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <net/ip.h> #include <net/tcp.h> #include <net/route.h> #include <net/dst.h> #include <net/netfilter/ipv4/nf_reject.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, __u8 protocol, int ttl); static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth); static const struct tcphdr * nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook); static int nf_reject_iphdr_validate(struct sk_buff *skb) { struct iphdr *iph; u32 len; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return 0; iph = ip_hdr(skb); if (iph->ihl < 5 || iph->version != 4) return 0; len = ntohs(iph->tot_len); if (skb->len < len) return 0; else if (len < (iph->ihl*4)) return 0; if (!pskb_may_pull(skb, iph->ihl*4)) return 0; return 1; } struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, int hook) { const struct tcphdr *oth; struct sk_buff *nskb; struct iphdr *niph; struct tcphdr _oth; if (!nf_reject_iphdr_validate(oldskb)) return NULL; oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); if (!oth) return NULL; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) return NULL; nskb->dev = (struct net_device *)dev; skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); niph->tot_len = htons(nskb->len); ip_send_check(niph); return nskb; } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset); static bool nf_skb_is_icmp_unreach(const struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); u8 *tp, _type; int thoff; if (iph->protocol != IPPROTO_ICMP) return false; thoff = skb_network_offset(skb) + sizeof(*iph); tp = skb_header_pointer(skb, thoff + offsetof(struct icmphdr, type), sizeof(_type), &_type); if (!tp) return false; return *tp == ICMP_DEST_UNREACH; } struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, int hook, u8 code) { struct sk_buff *nskb; struct iphdr *niph; struct icmphdr *icmph; unsigned int len; int dataoff; __wsum csum; u8 proto; if (!nf_reject_iphdr_validate(oldskb)) return NULL; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return NULL; /* don't reply to ICMP_DEST_UNREACH with ICMP_DEST_UNREACH. */ if (nf_skb_is_icmp_unreach(oldskb)) return NULL; /* RFC says return as much as we can without exceeding 576 bytes. */ len = min_t(unsigned int, 536, oldskb->len); if (!pskb_may_pull(oldskb, len)) return NULL; if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len))) return NULL; dataoff = ip_hdrlen(oldskb); proto = ip_hdr(oldskb)->protocol; if (!skb_csum_unnecessary(oldskb) && nf_reject_verify_csum(oldskb, dataoff, proto) && nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto)) return NULL; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) + LL_MAX_HEADER + len, GFP_ATOMIC); if (!nskb) return NULL; nskb->dev = (struct net_device *)dev; skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); skb_reset_transport_header(nskb); icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); icmph->type = ICMP_DEST_UNREACH; icmph->code = code; skb_put_data(nskb, skb_network_header(oldskb), len); csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0); icmph->checksum = csum_fold(csum); niph->tot_len = htons(nskb->len); ip_send_check(niph); return nskb; } EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach); static const struct tcphdr * nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook) { const struct tcphdr *oth; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return NULL; if (ip_hdr(oldskb)->protocol != IPPROTO_TCP) return NULL; oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb), sizeof(struct tcphdr), _oth); if (oth == NULL) return NULL; /* No RST for RST. */ if (oth->rst) return NULL; /* Check checksum */ if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) return NULL; return oth; } static struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, __u8 protocol, int ttl) { struct iphdr *niph, *oiph = ip_hdr(oldskb); skb_reset_network_header(nskb); niph = skb_put(nskb, sizeof(struct iphdr)); niph->version = 4; niph->ihl = sizeof(struct iphdr) / 4; niph->tos = 0; niph->id = 0; niph->frag_off = htons(IP_DF); niph->protocol = protocol; niph->check = 0; niph->saddr = oiph->daddr; niph->daddr = oiph->saddr; niph->ttl = ttl; nskb->protocol = htons(ETH_P_IP); return niph; } static void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth) { struct iphdr *niph = ip_hdr(nskb); struct tcphdr *tcph; skb_reset_transport_header(nskb); tcph = skb_put_zero(nskb, sizeof(struct tcphdr)); tcph->source = oth->dest; tcph->dest = oth->source; tcph->doff = sizeof(struct tcphdr) / 4; if (oth->ack) { tcph->seq = oth->ack_seq; } else { tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin + oldskb->len - ip_hdrlen(oldskb) - (oth->doff << 2)); tcph->ack = 1; } tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)tcph - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); } static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) { struct dst_entry *dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(struct flowi)); fl.u.ip4.daddr = ip_hdr(skb_in)->saddr; nf_ip_route(dev_net(skb_in->dev), &dst, &fl, false); if (!dst) return -1; skb_dst_set(skb_in, dst); return 0; } /* Send RST reply */ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { const struct tcphdr *oth; struct sk_buff *nskb; struct tcphdr _oth; oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); if (!oth) return; if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return; nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) return; /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); nskb->mark = IP4_REPLY_MARK(net, oldskb->mark); skb_reserve(nskb, LL_MAX_HEADER); nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); if (ip_route_me_harder(net, sk, nskb, RTN_UNSPEC)) goto free_nskb; /* "Never happens" */ if (nskb->len > dst4_mtu(skb_dst(nskb))) goto free_nskb; nf_ct_attach(nskb, oldskb); nf_ct_set_closing(skb_nfct(oldskb)); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* If we use ip_local_out for bridged traffic, the MAC source on * the RST will be ours, instead of the destination's. This confuses * some routers/firewalls, and they drop the packet. So we need to * build the eth header using the original destination's MAC as the * source, and send the RST packet directly. */ if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); struct iphdr *niph = ip_hdr(nskb); struct net_device *br_indev; br_indev = nf_bridge_get_physindev(oldskb, net); if (!br_indev) goto free_nskb; nskb->dev = br_indev; niph->tot_len = htons(nskb->len); ip_send_check(niph); if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol), oeth->h_source, oeth->h_dest, nskb->len) < 0) goto free_nskb; dev_queue_xmit(nskb); } else #endif ip_local_out(net, nskb->sk, nskb); return; free_nskb: kfree_skb(nskb); } EXPORT_SYMBOL_GPL(nf_send_reset); void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) { struct iphdr *iph = ip_hdr(skb_in); int dataoff = ip_hdrlen(skb_in); u8 proto = iph->protocol; if (iph->frag_off & htons(IP_OFFSET)) return; if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(skb_in, dataoff, proto)) { icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); return; } if (nf_ip_checksum(skb_in, hook, dataoff, proto) == 0) icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); } EXPORT_SYMBOL_GPL(nf_send_unreach); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv4 packet rejection core"); |
| 1374 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 | // SPDX-License-Identifier: GPL-2.0 /* * Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h * * Copyright (c) 2011, Tom Herbert <therbert@google.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/dynamic_queue_limits.h> #include <linux/compiler.h> #include <linux/export.h> #include <trace/events/napi.h> #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) static void dql_check_stall(struct dql *dql, unsigned short stall_thrs) { unsigned long now; if (!stall_thrs) return; now = jiffies; /* Check for a potential stall */ if (time_after_eq(now, dql->last_reap + stall_thrs)) { unsigned long hist_head, t, start, end; /* We are trying to detect a period of at least @stall_thrs * jiffies without any Tx completions, but during first half * of which some Tx was posted. */ dqs_again: hist_head = READ_ONCE(dql->history_head); /* pairs with smp_wmb() in dql_queued() */ smp_rmb(); /* Get the previous entry in the ring buffer, which is the * oldest sample. */ start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; /* Advance start to continue from the last reap time */ if (time_before(start, dql->last_reap + 1)) start = dql->last_reap + 1; /* Newest sample we should have already seen a completion for */ end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); /* Shrink the search space to [start, (now - start_thrs/2)] if * `end` is beyond the stall zone */ if (time_before(now, end + stall_thrs / 2)) end = now - stall_thrs / 2; /* Search for the queued time in [t, end] */ for (t = start; time_before_eq(t, end); t++) if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), dql->history)) break; /* Variable t contains the time of the queue */ if (!time_before_eq(t, end)) goto no_stall; /* The ring buffer was modified in the meantime, retry */ if (hist_head != READ_ONCE(dql->history_head)) goto dqs_again; dql->stall_cnt++; dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); trace_dql_stall_detected(dql->stall_thrs, now - t, dql->last_reap, dql->history_head, now, dql->history); } no_stall: dql->last_reap = now; } /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { unsigned int inprogress, prev_inprogress, limit; unsigned int ovlimit, completed, num_queued; unsigned short stall_thrs; bool all_prev_completed; num_queued = READ_ONCE(dql->num_queued); /* Read stall_thrs in advance since it belongs to the same (first) * cache line as ->num_queued. This way, dql_check_stall() does not * need to touch the first cache line again later, reducing the window * of possible false sharing. */ stall_thrs = READ_ONCE(dql->stall_thrs); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); completed = dql->num_completed + count; limit = dql->limit; ovlimit = POSDIFF(num_queued - dql->num_completed, limit); inprogress = num_queued - completed; prev_inprogress = dql->prev_num_queued - dql->num_completed; all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued); if ((ovlimit && !inprogress) || (dql->prev_ovlimit && all_prev_completed)) { /* * Queue considered starved if: * - The queue was over-limit in the last interval, * and there is no more data in the queue. * OR * - The queue was over-limit in the previous interval and * when enqueuing it was possible that all queued data * had been consumed. This covers the case when queue * may have becomes starved between completion processing * running and next time enqueue was scheduled. * * When queue is starved increase the limit by the amount * of bytes both sent and completed in the last interval, * plus any previous over-limit. */ limit += POSDIFF(completed, dql->prev_num_queued) + dql->prev_ovlimit; dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } else if (inprogress && prev_inprogress && !all_prev_completed) { /* * Queue was not starved, check if the limit can be decreased. * A decrease is only considered if the queue has been busy in * the whole interval (the check above). * * If there is slack, the amount of excess data queued above * the amount needed to prevent starvation, the queue limit * can be decreased. To avoid hysteresis we consider the * minimum amount of slack found over several iterations of the * completion routine. */ unsigned int slack, slack_last_objs; /* * Slack is the maximum of * - The queue limit plus previous over-limit minus twice * the number of objects completed. Note that two times * number of completed bytes is a basis for an upper bound * of the limit. * - Portion of objects in the last queuing operation that * was not part of non-zero previous over-limit. That is * "round down" by non-overlimit portion of the last * queueing operation. */ slack = POSDIFF(limit + dql->prev_ovlimit, 2 * (completed - dql->num_completed)); slack_last_objs = dql->prev_ovlimit ? POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0; slack = max(slack, slack_last_objs); if (slack < dql->lowest_slack) dql->lowest_slack = slack; if (time_after(jiffies, dql->slack_start_time + dql->slack_hold_time)) { limit = POSDIFF(limit, dql->lowest_slack); dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } } /* Enforce bounds on limit */ limit = clamp(limit, dql->min_limit, dql->max_limit); if (limit != dql->limit) { dql->limit = limit; ovlimit = 0; } dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt); dql->num_completed = completed; dql->prev_num_queued = num_queued; dql_check_stall(dql, stall_thrs); } EXPORT_SYMBOL(dql_completed); void dql_reset(struct dql *dql) { /* Reset all dynamic values */ dql->limit = dql->min_limit; dql->num_queued = 0; dql->num_completed = 0; dql->last_obj_cnt = 0; dql->prev_num_queued = 0; dql->prev_last_obj_cnt = 0; dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; dql->last_reap = jiffies; dql->history_head = jiffies / BITS_PER_LONG; memset(dql->history, 0, sizeof(dql->history)); } EXPORT_SYMBOL(dql_reset); void dql_init(struct dql *dql, unsigned int hold_time) { dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; dql->stall_thrs = 0; dql_reset(dql); } EXPORT_SYMBOL(dql_init); |
| 3 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/bfs/inode.c * BFS superblock and inode operations. * Copyright (C) 1999-2018 Tigran Aivazian <aivazian.tigran@gmail.com> * From fs/minix, Copyright (C) 1991, 1992 Linus Torvalds. * Made endianness-clean by Andrew Stribblehill <ads@wompom.org>, 2005. */ #include <linux/module.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/writeback.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <linux/fs_context.h> #include "bfs.h" MODULE_AUTHOR("Tigran Aivazian <aivazian.tigran@gmail.com>"); MODULE_DESCRIPTION("SCO UnixWare BFS filesystem for Linux"); MODULE_LICENSE("GPL"); #undef DEBUG #ifdef DEBUG #define dprintf(x...) printf(x) #else #define dprintf(x...) #endif struct inode *bfs_iget(struct super_block *sb, unsigned long ino) { struct bfs_inode *di; struct inode *inode; struct buffer_head *bh; int block, off; inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode_state_read_once(inode) & I_NEW)) return inode; if ((ino < BFS_ROOT_INO) || (ino > BFS_SB(inode->i_sb)->si_lasti)) { printf("Bad inode number %s:%08lx\n", inode->i_sb->s_id, ino); goto error; } block = (ino - BFS_ROOT_INO) / BFS_INODES_PER_BLOCK + 1; bh = sb_bread(inode->i_sb, block); if (!bh) { printf("Unable to read inode %s:%08lx\n", inode->i_sb->s_id, ino); goto error; } off = (ino - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK; di = (struct bfs_inode *)bh->b_data + off; /* * https://martin.hinner.info/fs/bfs/bfs-structure.html explains that * BFS in SCO UnixWare environment used only lower 9 bits of di->i_mode * value. This means that, although bfs_write_inode() saves whole * inode->i_mode bits (which include S_IFMT bits and S_IS{UID,GID,VTX} * bits), middle 7 bits of di->i_mode value can be garbage when these * bits were not saved by bfs_write_inode(). * Since we can't tell whether middle 7 bits are garbage, use only * lower 12 bits (i.e. tolerate S_IS{UID,GID,VTX} bits possibly being * garbage) and reconstruct S_IFMT bits for Linux environment from * di->i_vtype value. */ inode->i_mode = 0x00000FFF & le32_to_cpu(di->i_mode); if (le32_to_cpu(di->i_vtype) == BFS_VDIR) { inode->i_mode |= S_IFDIR; inode->i_op = &bfs_dir_inops; inode->i_fop = &bfs_dir_operations; } else if (le32_to_cpu(di->i_vtype) == BFS_VREG) { inode->i_mode |= S_IFREG; inode->i_op = &bfs_file_inops; inode->i_fop = &bfs_file_operations; inode->i_mapping->a_ops = &bfs_aops; } else { brelse(bh); printf("Unknown vtype=%u %s:%08lx\n", le32_to_cpu(di->i_vtype), inode->i_sb->s_id, ino); goto error; } BFS_I(inode)->i_sblock = le32_to_cpu(di->i_sblock); BFS_I(inode)->i_eblock = le32_to_cpu(di->i_eblock); BFS_I(inode)->i_dsk_ino = le16_to_cpu(di->i_ino); i_uid_write(inode, le32_to_cpu(di->i_uid)); i_gid_write(inode, le32_to_cpu(di->i_gid)); set_nlink(inode, le32_to_cpu(di->i_nlink)); inode->i_size = BFS_FILESIZE(di); inode->i_blocks = BFS_FILEBLOCKS(di); inode_set_atime(inode, le32_to_cpu(di->i_atime), 0); inode_set_mtime(inode, le32_to_cpu(di->i_mtime), 0); inode_set_ctime(inode, le32_to_cpu(di->i_ctime), 0); brelse(bh); unlock_new_inode(inode); return inode; error: iget_failed(inode); return ERR_PTR(-EIO); } static struct bfs_inode *find_inode(struct super_block *sb, u16 ino, struct buffer_head **p) { if ((ino < BFS_ROOT_INO) || (ino > BFS_SB(sb)->si_lasti)) { printf("Bad inode number %s:%08x\n", sb->s_id, ino); return ERR_PTR(-EIO); } ino -= BFS_ROOT_INO; *p = sb_bread(sb, 1 + ino / BFS_INODES_PER_BLOCK); if (!*p) { printf("Unable to read inode %s:%08x\n", sb->s_id, ino); return ERR_PTR(-EIO); } return (struct bfs_inode *)(*p)->b_data + ino % BFS_INODES_PER_BLOCK; } static int bfs_write_inode(struct inode *inode, struct writeback_control *wbc) { struct bfs_sb_info *info = BFS_SB(inode->i_sb); unsigned int ino = (u16)inode->i_ino; unsigned long i_sblock; struct bfs_inode *di; struct buffer_head *bh; int err = 0; dprintf("ino=%08x\n", ino); di = find_inode(inode->i_sb, ino, &bh); if (IS_ERR(di)) return PTR_ERR(di); mutex_lock(&info->bfs_lock); if (ino == BFS_ROOT_INO) di->i_vtype = cpu_to_le32(BFS_VDIR); else di->i_vtype = cpu_to_le32(BFS_VREG); di->i_ino = cpu_to_le16(ino); di->i_mode = cpu_to_le32(inode->i_mode); di->i_uid = cpu_to_le32(i_uid_read(inode)); di->i_gid = cpu_to_le32(i_gid_read(inode)); di->i_nlink = cpu_to_le32(inode->i_nlink); di->i_atime = cpu_to_le32(inode_get_atime_sec(inode)); di->i_mtime = cpu_to_le32(inode_get_mtime_sec(inode)); di->i_ctime = cpu_to_le32(inode_get_ctime_sec(inode)); i_sblock = BFS_I(inode)->i_sblock; di->i_sblock = cpu_to_le32(i_sblock); di->i_eblock = cpu_to_le32(BFS_I(inode)->i_eblock); di->i_eoffset = cpu_to_le32(i_sblock * BFS_BSIZE + inode->i_size - 1); mark_buffer_dirty(bh); if (wbc->sync_mode == WB_SYNC_ALL) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) err = -EIO; } brelse(bh); mutex_unlock(&info->bfs_lock); return err; } static void bfs_evict_inode(struct inode *inode) { unsigned long ino = inode->i_ino; struct bfs_inode *di; struct buffer_head *bh; struct super_block *s = inode->i_sb; struct bfs_sb_info *info = BFS_SB(s); struct bfs_inode_info *bi = BFS_I(inode); dprintf("ino=%08lx\n", ino); truncate_inode_pages_final(&inode->i_data); if (inode->i_nlink) mmb_sync(&BFS_I(inode)->i_metadata_bhs); mmb_invalidate(&BFS_I(inode)->i_metadata_bhs); clear_inode(inode); if (inode->i_nlink) return; di = find_inode(s, inode->i_ino, &bh); if (IS_ERR(di)) return; mutex_lock(&info->bfs_lock); /* clear on-disk inode */ memset(di, 0, sizeof(struct bfs_inode)); mark_buffer_dirty(bh); brelse(bh); if (bi->i_dsk_ino) { if (bi->i_sblock) info->si_freeb += bi->i_eblock + 1 - bi->i_sblock; info->si_freei++; clear_bit(ino, info->si_imap); bfs_dump_imap("evict_inode", s); } /* * If this was the last file, make the previous block * "last block of the last file" even if there is no * real file there, saves us 1 gap. */ if (info->si_lf_eblk == bi->i_eblock) info->si_lf_eblk = bi->i_sblock - 1; mutex_unlock(&info->bfs_lock); } static void bfs_put_super(struct super_block *s) { struct bfs_sb_info *info = BFS_SB(s); if (!info) return; mutex_destroy(&info->bfs_lock); kfree(info); s->s_fs_info = NULL; } static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct bfs_sb_info *info = BFS_SB(s); u64 id = huge_encode_dev(s->s_bdev->bd_dev); buf->f_type = BFS_MAGIC; buf->f_bsize = s->s_blocksize; buf->f_blocks = info->si_blocks; buf->f_bfree = buf->f_bavail = info->si_freeb; buf->f_files = info->si_lasti + 1 - BFS_ROOT_INO; buf->f_ffree = info->si_freei; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = BFS_NAMELEN; return 0; } static struct kmem_cache *bfs_inode_cachep; static struct inode *bfs_alloc_inode(struct super_block *sb) { struct bfs_inode_info *bi; bi = alloc_inode_sb(sb, bfs_inode_cachep, GFP_KERNEL); if (!bi) return NULL; mmb_init(&bi->i_metadata_bhs, &bi->vfs_inode.i_data); return &bi->vfs_inode; } static void bfs_free_inode(struct inode *inode) { kmem_cache_free(bfs_inode_cachep, BFS_I(inode)); } static void init_once(void *foo) { struct bfs_inode_info *bi = foo; inode_init_once(&bi->vfs_inode); } static int __init init_inodecache(void) { bfs_inode_cachep = kmem_cache_create("bfs_inode_cache", sizeof(struct bfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (bfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(bfs_inode_cachep); } static const struct super_operations bfs_sops = { .alloc_inode = bfs_alloc_inode, .free_inode = bfs_free_inode, .write_inode = bfs_write_inode, .evict_inode = bfs_evict_inode, .put_super = bfs_put_super, .statfs = bfs_statfs, }; void bfs_dump_imap(const char *prefix, struct super_block *s) { #ifdef DEBUG int i; char *tmpbuf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!tmpbuf) return; for (i = BFS_SB(s)->si_lasti; i >= 0; i--) { if (i > PAGE_SIZE - 100) break; if (test_bit(i, BFS_SB(s)->si_imap)) strcat(tmpbuf, "1"); else strcat(tmpbuf, "0"); } printf("%s: lasti=%08lx <%s>\n", prefix, BFS_SB(s)->si_lasti, tmpbuf); kfree(tmpbuf); #endif } static int bfs_fill_super(struct super_block *s, struct fs_context *fc) { struct buffer_head *bh, *sbh; struct bfs_super_block *bfs_sb; struct inode *inode; unsigned i; struct bfs_sb_info *info; int ret = -EINVAL; unsigned long i_sblock, i_eblock, i_eoff, s_size; int silent = fc->sb_flags & SB_SILENT; info = kzalloc_obj(*info); if (!info) return -ENOMEM; mutex_init(&info->bfs_lock); s->s_fs_info = info; s->s_time_min = 0; s->s_time_max = U32_MAX; if (!sb_set_blocksize(s, BFS_BSIZE)) goto out; sbh = sb_bread(s, 0); if (!sbh) goto out; bfs_sb = (struct bfs_super_block *)sbh->b_data; if (le32_to_cpu(bfs_sb->s_magic) != BFS_MAGIC) { if (!silent) printf("No BFS filesystem on %s (magic=%08x)\n", s->s_id, le32_to_cpu(bfs_sb->s_magic)); goto out1; } if (BFS_UNCLEAN(bfs_sb, s) && !silent) printf("%s is unclean, continuing\n", s->s_id); s->s_magic = BFS_MAGIC; if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) || le32_to_cpu(bfs_sb->s_start) < sizeof(struct bfs_super_block) + sizeof(struct bfs_dirent)) { printf("Superblock is corrupted on %s\n", s->s_id); goto out1; } info->si_lasti = (le32_to_cpu(bfs_sb->s_start) - BFS_BSIZE) / sizeof(struct bfs_inode) + BFS_ROOT_INO - 1; if (info->si_lasti == BFS_MAX_LASTI) printf("NOTE: filesystem %s was created with 512 inodes, the real maximum is 511, mounting anyway\n", s->s_id); else if (info->si_lasti > BFS_MAX_LASTI) { printf("Impossible last inode number %lu > %d on %s\n", info->si_lasti, BFS_MAX_LASTI, s->s_id); goto out1; } for (i = 0; i < BFS_ROOT_INO; i++) set_bit(i, info->si_imap); s->s_op = &bfs_sops; inode = bfs_iget(s, BFS_ROOT_INO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto out1; } s->s_root = d_make_root(inode); if (!s->s_root) { ret = -ENOMEM; goto out1; } info->si_blocks = (le32_to_cpu(bfs_sb->s_end) + 1) >> BFS_BSIZE_BITS; info->si_freeb = (le32_to_cpu(bfs_sb->s_end) + 1 - le32_to_cpu(bfs_sb->s_start)) >> BFS_BSIZE_BITS; info->si_freei = 0; info->si_lf_eblk = 0; /* can we read the last block? */ bh = sb_bread(s, info->si_blocks - 1); if (!bh) { printf("Last block not available on %s: %lu\n", s->s_id, info->si_blocks - 1); ret = -EIO; goto out2; } brelse(bh); bh = NULL; for (i = BFS_ROOT_INO; i <= info->si_lasti; i++) { struct bfs_inode *di; int block = (i - BFS_ROOT_INO) / BFS_INODES_PER_BLOCK + 1; int off = (i - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK; unsigned long eblock; if (!off) { brelse(bh); bh = sb_bread(s, block); } if (!bh) continue; di = (struct bfs_inode *)bh->b_data + off; /* test if filesystem is not corrupted */ i_eoff = le32_to_cpu(di->i_eoffset); i_sblock = le32_to_cpu(di->i_sblock); i_eblock = le32_to_cpu(di->i_eblock); s_size = le32_to_cpu(bfs_sb->s_end); if (i_sblock > info->si_blocks || i_eblock > info->si_blocks || i_sblock > i_eblock || (i_eoff != le32_to_cpu(-1) && i_eoff > s_size) || i_sblock * BFS_BSIZE > i_eoff) { printf("Inode 0x%08x corrupted on %s\n", i, s->s_id); brelse(bh); ret = -EIO; goto out2; } if (!di->i_ino) { info->si_freei++; continue; } set_bit(i, info->si_imap); info->si_freeb -= BFS_FILEBLOCKS(di); eblock = le32_to_cpu(di->i_eblock); if (eblock > info->si_lf_eblk) info->si_lf_eblk = eblock; } brelse(bh); brelse(sbh); bfs_dump_imap("fill_super", s); return 0; out2: dput(s->s_root); s->s_root = NULL; out1: brelse(sbh); out: mutex_destroy(&info->bfs_lock); kfree(info); s->s_fs_info = NULL; return ret; } static int bfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, bfs_fill_super); } static const struct fs_context_operations bfs_context_ops = { .get_tree = bfs_get_tree, }; static int bfs_init_fs_context(struct fs_context *fc) { fc->ops = &bfs_context_ops; return 0; } static struct file_system_type bfs_fs_type = { .owner = THIS_MODULE, .name = "bfs", .init_fs_context = bfs_init_fs_context, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("bfs"); static int __init init_bfs_fs(void) { int err = init_inodecache(); if (err) goto out1; err = register_filesystem(&bfs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_bfs_fs(void) { unregister_filesystem(&bfs_fs_type); destroy_inodecache(); } module_init(init_bfs_fs) module_exit(exit_bfs_fs) |
| 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 | // SPDX-License-Identifier: GPL-2.0-or-later /* Linux driver for Philips webcam Decompression for chipset version 1 (C) 2004-2006 Luc Saillard (luc@saillard.org) NOTE: this version of pwc is an unofficial (modified) release of pwc & pcwx driver and thus may have bugs that are not present in the original version. Please send bug reports and support requests to <luc@saillard.org>. The decompression routines have been implemented by reverse-engineering the Nemosoft binary pwcx module. Caveat emptor. */ #include "pwc.h" void pwc_dec1_init(struct pwc_device *pdev, const unsigned char *cmd) { struct pwc_dec1_private *pdec = &pdev->dec1; pdec->version = pdev->release; } |
| 9 3 9 1 9 9 1 1 9 9 9 9 9 9 9 9 1 1 1 1 1 9 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 | // 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; unsigned long srcu_gp; bool ongoing; }; DEFINE_SRCU_FAST(tracepoint_srcu); EXPORT_SYMBOL_GPL(tracepoint_srcu); /* 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->srcu_gp = start_poll_synchronize_srcu(&tracepoint_srcu); 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); if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu_gp)) synchronize_srcu(&tracepoint_srcu); 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_flex(*p, probes, count); 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_srcu(&tracepoint_srcu, &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 : %pSb\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)) { if (tp->ext && tp->ext->unregfunc && !static_key_enabled(&tp->key)) tp->ext->unregfunc(); 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_obj(struct tp_module); 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 |
| 6 6 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/bug.h> #include <linux/err.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/ceph/messenger.h> #include <linux/ceph/decode.h> #include "mdsmap.h" #include "mds_client.h" #include "super.h" #define CEPH_MDS_IS_READY(i, ignore_laggy) \ (m->m_info[i].state > 0 && ignore_laggy ? true : !m->m_info[i].laggy) static int __mdsmap_get_random_mds(struct ceph_mdsmap *m, bool ignore_laggy) { int n = 0; int i, j; /* count */ for (i = 0; i < m->possible_max_rank; i++) if (CEPH_MDS_IS_READY(i, ignore_laggy)) n++; if (n == 0) return -1; /* pick */ n = get_random_u32_below(n); for (j = 0, i = 0; i < m->possible_max_rank; i++) { if (CEPH_MDS_IS_READY(i, ignore_laggy)) j++; if (j > n) break; } return i; } /* * choose a random mds that is "up" (i.e. has a state > 0), or -1. */ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m) { int mds; mds = __mdsmap_get_random_mds(m, false); if (mds == m->possible_max_rank || mds == -1) mds = __mdsmap_get_random_mds(m, true); return mds == m->possible_max_rank ? -1 : mds; } #define __decode_and_drop_type(p, end, type, bad) \ do { \ if (*p + sizeof(type) > end) \ goto bad; \ *p += sizeof(type); \ } while (0) #define __decode_and_drop_set(p, end, type, bad) \ do { \ u32 n; \ size_t need; \ ceph_decode_32_safe(p, end, n, bad); \ need = sizeof(type) * n; \ ceph_decode_need(p, end, need, bad); \ *p += need; \ } while (0) #define __decode_and_drop_map(p, end, ktype, vtype, bad) \ do { \ u32 n; \ size_t need; \ ceph_decode_32_safe(p, end, n, bad); \ need = (sizeof(ktype) + sizeof(vtype)) * n; \ ceph_decode_need(p, end, need, bad); \ *p += need; \ } while (0) static int __decode_and_drop_compat_set(void **p, void* end) { int i; /* compat, ro_compat, incompat*/ for (i = 0; i < 3; i++) { u32 n; ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad); /* mask */ *p += sizeof(u64); /* names (map<u64, string>) */ n = ceph_decode_32(p); while (n-- > 0) { u32 len; ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad); *p += sizeof(u64); len = ceph_decode_32(p); ceph_decode_need(p, end, len, bad); *p += len; } } return 0; bad: return -1; } /* * Decode an MDS map * * Ignore any fields we don't care about (there are quite a few of * them). */ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, void *end, bool msgr2) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_mdsmap *m; const void *start = *p; int i, j, n; int err; u8 mdsmap_v; u16 mdsmap_ev; u32 target; m = kzalloc_obj(*m, GFP_NOFS); if (!m) return ERR_PTR(-ENOMEM); ceph_decode_need(p, end, 1 + 1, bad); mdsmap_v = ceph_decode_8(p); *p += sizeof(u8); /* mdsmap_cv */ if (mdsmap_v >= 4) { u32 mdsmap_len; ceph_decode_32_safe(p, end, mdsmap_len, bad); if (end < *p + mdsmap_len) goto bad; end = *p + mdsmap_len; } ceph_decode_need(p, end, 8*sizeof(u32) + sizeof(u64), bad); m->m_epoch = ceph_decode_32(p); m->m_client_epoch = ceph_decode_32(p); m->m_last_failure = ceph_decode_32(p); m->m_root = ceph_decode_32(p); m->m_session_timeout = ceph_decode_32(p); m->m_session_autoclose = ceph_decode_32(p); m->m_max_file_size = ceph_decode_64(p); m->m_max_mds = ceph_decode_32(p); /* * pick out the active nodes as the m_num_active_mds, the * m_num_active_mds maybe larger than m_max_mds when decreasing * the max_mds in cluster side, in other case it should less * than or equal to m_max_mds. */ m->m_num_active_mds = n = ceph_decode_32(p); /* * the possible max rank, it maybe larger than the m_num_active_mds, * for example if the mds_max == 2 in the cluster, when the MDS(0) * was laggy and being replaced by a new MDS, we will temporarily * receive a new mds map with n_num_mds == 1 and the active MDS(1), * and the mds rank >= m_num_active_mds. */ m->possible_max_rank = max(m->m_num_active_mds, m->m_max_mds); m->m_info = kzalloc_objs(*m->m_info, m->possible_max_rank, GFP_NOFS); if (!m->m_info) goto nomem; /* pick out active nodes from mds_info (state > 0) */ for (i = 0; i < n; i++) { u64 global_id; u32 namelen; s32 mds, inc, state; u8 info_v; void *info_end = NULL; struct ceph_entity_addr addr; u32 num_export_targets; void *pexport_targets = NULL; struct ceph_timespec laggy_since; struct ceph_mds_info *info; bool laggy; ceph_decode_need(p, end, sizeof(u64) + 1, bad); global_id = ceph_decode_64(p); info_v= ceph_decode_8(p); if (info_v >= 4) { u32 info_len; ceph_decode_need(p, end, 1 + sizeof(u32), bad); *p += sizeof(u8); /* info_cv */ info_len = ceph_decode_32(p); info_end = *p + info_len; if (info_end > end) goto bad; } ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad); *p += sizeof(u64); namelen = ceph_decode_32(p); /* skip mds name */ *p += namelen; ceph_decode_32_safe(p, end, mds, bad); ceph_decode_32_safe(p, end, inc, bad); ceph_decode_32_safe(p, end, state, bad); *p += sizeof(u64); /* state_seq */ if (info_v >= 8) err = ceph_decode_entity_addrvec(p, end, msgr2, &addr); else err = ceph_decode_entity_addr(p, end, &addr); if (err) goto corrupt; ceph_decode_copy_safe(p, end, &laggy_since, sizeof(laggy_since), bad); laggy = laggy_since.tv_sec != 0 || laggy_since.tv_nsec != 0; *p += sizeof(u32); ceph_decode_32_safe(p, end, namelen, bad); *p += namelen; if (info_v >= 2) { ceph_decode_32_safe(p, end, num_export_targets, bad); pexport_targets = *p; *p += num_export_targets * sizeof(u32); } else { num_export_targets = 0; } if (info_end && *p != info_end) { if (*p > info_end) goto bad; *p = info_end; } doutc(cl, "%d/%d %lld mds%d.%d %s %s%s\n", i+1, n, global_id, mds, inc, ceph_pr_addr(&addr), ceph_mds_state_name(state), laggy ? "(laggy)" : ""); if (mds < 0 || mds >= m->possible_max_rank) { pr_warn_client(cl, "got incorrect mds(%d)\n", mds); continue; } if (state <= 0) { doutc(cl, "got incorrect state(%s)\n", ceph_mds_state_name(state)); continue; } info = &m->m_info[mds]; info->global_id = global_id; info->state = state; info->addr = addr; info->laggy = laggy; info->num_export_targets = num_export_targets; if (num_export_targets) { info->export_targets = kcalloc(num_export_targets, sizeof(u32), GFP_NOFS); if (!info->export_targets) goto nomem; for (j = 0; j < num_export_targets; j++) { target = ceph_decode_32(&pexport_targets); info->export_targets[j] = target; } } else { info->export_targets = NULL; } } /* pg_pools */ ceph_decode_32_safe(p, end, n, bad); m->m_num_data_pg_pools = n; m->m_data_pg_pools = kcalloc(n, sizeof(u64), GFP_NOFS); if (!m->m_data_pg_pools) goto nomem; ceph_decode_need(p, end, sizeof(u64)*(n+1), bad); for (i = 0; i < n; i++) m->m_data_pg_pools[i] = ceph_decode_64(p); m->m_cas_pg_pool = ceph_decode_64(p); m->m_enabled = m->m_epoch > 1; mdsmap_ev = 1; if (mdsmap_v >= 2) { ceph_decode_16_safe(p, end, mdsmap_ev, bad_ext); } if (mdsmap_ev >= 3) { if (__decode_and_drop_compat_set(p, end) < 0) goto bad_ext; } /* metadata_pool */ if (mdsmap_ev < 5) { __decode_and_drop_type(p, end, u32, bad_ext); } else { __decode_and_drop_type(p, end, u64, bad_ext); } /* created + modified + tableserver */ __decode_and_drop_type(p, end, struct ceph_timespec, bad_ext); __decode_and_drop_type(p, end, struct ceph_timespec, bad_ext); __decode_and_drop_type(p, end, u32, bad_ext); /* in */ { int num_laggy = 0; ceph_decode_32_safe(p, end, n, bad_ext); ceph_decode_need(p, end, sizeof(u32) * n, bad_ext); for (i = 0; i < n; i++) { s32 mds = ceph_decode_32(p); if (mds >= 0 && mds < m->possible_max_rank) { if (m->m_info[mds].laggy) num_laggy++; } } m->m_num_laggy = num_laggy; if (n > m->possible_max_rank) { void *new_m_info = krealloc(m->m_info, n * sizeof(*m->m_info), GFP_NOFS | __GFP_ZERO); if (!new_m_info) goto nomem; m->m_info = new_m_info; } m->possible_max_rank = n; } /* inc */ __decode_and_drop_map(p, end, u32, u32, bad_ext); /* up */ __decode_and_drop_map(p, end, u32, u64, bad_ext); /* failed */ __decode_and_drop_set(p, end, u32, bad_ext); /* stopped */ __decode_and_drop_set(p, end, u32, bad_ext); if (mdsmap_ev >= 4) { /* last_failure_osd_epoch */ __decode_and_drop_type(p, end, u32, bad_ext); } if (mdsmap_ev >= 6) { /* ever_allowed_snaps */ __decode_and_drop_type(p, end, u8, bad_ext); /* explicitly_allowed_snaps */ __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 7) { /* inline_data_enabled */ __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 8) { size_t fsname_len; /* enabled */ ceph_decode_8_safe(p, end, m->m_enabled, bad_ext); /* fs_name */ m->m_fs_name = ceph_extract_encoded_string(p, end, &fsname_len, GFP_NOFS); if (IS_ERR(m->m_fs_name)) { m->m_fs_name = NULL; goto nomem; } /* validate fsname against mds_namespace */ if (!namespace_equals(mdsc->fsc->mount_options, m->m_fs_name, fsname_len)) { pr_warn_client(cl, "fsname %s doesn't match mds_namespace %s\n", m->m_fs_name, mdsc->fsc->mount_options->mds_namespace); goto bad; } } else { m->m_enabled = false; m->m_fs_name = kstrdup(CEPH_OLD_FS_NAME, GFP_NOFS); if (!m->m_fs_name) goto nomem; } /* damaged */ if (mdsmap_ev >= 9) { size_t need; ceph_decode_32_safe(p, end, n, bad_ext); need = sizeof(u32) * n; ceph_decode_need(p, end, need, bad_ext); *p += need; m->m_damaged = n > 0; } else { m->m_damaged = false; } if (mdsmap_ev >= 17) { /* balancer */ ceph_decode_skip_string(p, end, bad_ext); /* standby_count_wanted */ ceph_decode_skip_32(p, end, bad_ext); /* old_max_mds */ ceph_decode_skip_32(p, end, bad_ext); /* min_compat_client */ ceph_decode_skip_8(p, end, bad_ext); /* required_client_features */ ceph_decode_skip_set(p, end, 64, bad_ext); /* bal_rank_mask */ ceph_decode_skip_string(p, end, bad_ext); } if (mdsmap_ev >= 18) { ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext); } bad_ext: doutc(cl, "m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n", !!m->m_enabled, !!m->m_damaged, m->m_num_laggy); *p = end; doutc(cl, "success epoch %u\n", m->m_epoch); return m; nomem: err = -ENOMEM; goto out_err; corrupt: pr_err_client(cl, "corrupt mdsmap\n"); print_hex_dump(KERN_DEBUG, "mdsmap: ", DUMP_PREFIX_OFFSET, 16, 1, start, end - start, true); out_err: ceph_mdsmap_destroy(m); return ERR_PTR(err); bad: err = -EINVAL; goto corrupt; } void ceph_mdsmap_destroy(struct ceph_mdsmap *m) { int i; if (m->m_info) { for (i = 0; i < m->possible_max_rank; i++) kfree(m->m_info[i].export_targets); kfree(m->m_info); } kfree(m->m_data_pg_pools); kfree(m->m_fs_name); kfree(m); } bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m) { int i, nr_active = 0; if (!m->m_enabled) return false; if (m->m_damaged) return false; if (m->m_num_laggy == m->m_num_active_mds) return false; for (i = 0; i < m->possible_max_rank; i++) { if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE) nr_active++; } return nr_active > 0; } |
| 2 2 5 2 4 3 2 1 4 4 4 4 4 3 3 9 9 2 2 2 3 4 1 1 3 1530 1525 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2013-2014 Intel Corp. */ #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/module.h> #include <linux/debugfs.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/netdev_lock.h> #include <net/pkt_sched.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/6lowpan.h> /* for the compression support */ #define VERSION "0.1" static struct dentry *lowpan_enable_debugfs; static struct dentry *lowpan_control_debugfs; #define IFACE_NAME_TEMPLATE "bt%d" struct skb_cb { struct in6_addr addr; struct in6_addr gw; struct l2cap_chan *chan; }; #define lowpan_cb(skb) ((struct skb_cb *)((skb)->cb)) /* The devices list contains those devices that we are acting * as a proxy. The BT 6LoWPAN device is a virtual device that * connects to the Bluetooth LE device. The real connection to * BT device is done via l2cap layer. There exists one * virtual device / one BT 6LoWPAN network (=hciX device). * The list contains struct lowpan_dev elements. */ static LIST_HEAD(bt_6lowpan_devices); static DEFINE_SPINLOCK(devices_lock); static bool enable_6lowpan; /* We are listening incoming connections via this channel */ static struct l2cap_chan *listen_chan; static DEFINE_MUTEX(set_lock); enum { LOWPAN_PEER_CLOSING, LOWPAN_PEER_MAXBITS }; struct lowpan_peer { struct list_head list; struct rcu_head rcu; struct l2cap_chan *chan; /* peer addresses in various formats */ unsigned char lladdr[ETH_ALEN]; struct in6_addr peer_addr; DECLARE_BITMAP(flags, LOWPAN_PEER_MAXBITS); }; struct lowpan_btle_dev { struct list_head list; struct hci_dev *hdev; struct net_device *netdev; struct list_head peers; atomic_t peer_count; /* number of items in peers list */ struct work_struct delete_netdev; struct delayed_work notify_peers; }; static inline struct lowpan_btle_dev * lowpan_btle_dev(const struct net_device *netdev) { return (struct lowpan_btle_dev *)lowpan_dev(netdev)->priv; } static inline void peer_add(struct lowpan_btle_dev *dev, struct lowpan_peer *peer) { list_add_rcu(&peer->list, &dev->peers); atomic_inc(&dev->peer_count); } static inline bool peer_del(struct lowpan_btle_dev *dev, struct lowpan_peer *peer) { list_del_rcu(&peer->list); kfree_rcu(peer, rcu); module_put(THIS_MODULE); if (atomic_dec_and_test(&dev->peer_count)) { BT_DBG("last peer"); return true; } return false; } static inline struct lowpan_peer * __peer_lookup_chan(struct lowpan_btle_dev *dev, struct l2cap_chan *chan) { struct lowpan_peer *peer; list_for_each_entry_rcu(peer, &dev->peers, list) { if (peer->chan == chan) return peer; } return NULL; } static inline struct lowpan_peer * __peer_lookup_conn(struct lowpan_btle_dev *dev, struct l2cap_conn *conn) { struct lowpan_peer *peer; list_for_each_entry_rcu(peer, &dev->peers, list) { if (peer->chan->conn == conn) return peer; } return NULL; } static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_btle_dev *dev, struct in6_addr *daddr, struct sk_buff *skb) { struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int count = atomic_read(&dev->peer_count); const struct in6_addr *nexthop; struct lowpan_peer *peer; struct neighbour *neigh; BT_DBG("peers %d addr %pI6c rt %p", count, daddr, rt); if (!rt) { if (ipv6_addr_any(&lowpan_cb(skb)->gw)) { /* There is neither route nor gateway, * probably the destination is a direct peer. */ nexthop = daddr; } else { /* There is a known gateway */ nexthop = &lowpan_cb(skb)->gw; } } else { nexthop = rt6_nexthop(rt, daddr); /* We need to remember the address because it is needed * by bt_xmit() when sending the packet. In bt_xmit(), the * destination routing info is not set. */ memcpy(&lowpan_cb(skb)->gw, nexthop, sizeof(struct in6_addr)); } BT_DBG("gw %pI6c", nexthop); rcu_read_lock(); list_for_each_entry_rcu(peer, &dev->peers, list) { BT_DBG("dst addr %pMR dst type %u ip %pI6c", &peer->chan->dst, peer->chan->dst_type, &peer->peer_addr); if (!ipv6_addr_cmp(&peer->peer_addr, nexthop)) { rcu_read_unlock(); return peer; } } /* use the neighbour cache for matching addresses assigned by SLAAC */ neigh = __ipv6_neigh_lookup(dev->netdev, nexthop); if (neigh) { list_for_each_entry_rcu(peer, &dev->peers, list) { if (!memcmp(neigh->ha, peer->lladdr, ETH_ALEN)) { neigh_release(neigh); rcu_read_unlock(); return peer; } } neigh_release(neigh); } rcu_read_unlock(); return NULL; } static struct lowpan_peer *lookup_peer(struct l2cap_conn *conn) { struct lowpan_btle_dev *entry; struct lowpan_peer *peer = NULL; rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { peer = __peer_lookup_conn(entry, conn); if (peer) break; } rcu_read_unlock(); return peer; } static struct lowpan_btle_dev *lookup_dev(struct l2cap_conn *conn) { struct lowpan_btle_dev *entry; struct lowpan_btle_dev *dev = NULL; rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { if (conn->hcon->hdev == entry->hdev) { dev = entry; break; } } rcu_read_unlock(); return dev; } static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *skb_cp; skb_cp = skb_copy(skb, GFP_ATOMIC); if (!skb_cp) return NET_RX_DROP; return netif_rx(skb_cp); } static int iphc_decompress(struct sk_buff *skb, struct net_device *netdev, struct lowpan_peer *peer) { const u8 *saddr; saddr = peer->lladdr; return lowpan_header_decompress(skb, netdev, netdev->dev_addr, saddr); } static int recv_pkt(struct sk_buff *skb, struct net_device *dev, struct lowpan_peer *peer) { struct sk_buff *local_skb; int ret; if (!netif_running(dev)) goto drop; if (dev->type != ARPHRD_6LOWPAN || !skb->len) goto drop; skb_reset_network_header(skb); skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto drop; /* check that it's our buffer */ if (lowpan_is_ipv6(*skb_network_header(skb))) { /* Pull off the 1-byte of 6lowpan header. */ skb_pull(skb, 1); /* Copy the packet so that the IPv6 header is * properly aligned. */ local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1, skb_tailroom(skb), GFP_ATOMIC); if (!local_skb) goto drop; local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; local_skb->dev = dev; skb_reset_mac_header(local_skb); skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { kfree_skb(local_skb); goto drop; } dev->stats.rx_bytes += skb->len; dev->stats.rx_packets++; consume_skb(local_skb); consume_skb(skb); } else if (lowpan_is_iphc(*skb_network_header(skb))) { local_skb = skb_clone(skb, GFP_ATOMIC); if (!local_skb) goto drop; local_skb->dev = dev; ret = iphc_decompress(local_skb, dev, peer); if (ret < 0) { BT_DBG("iphc_decompress failed: %d", ret); kfree_skb(local_skb); goto drop; } local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { kfree_skb(local_skb); goto drop; } dev->stats.rx_bytes += skb->len; dev->stats.rx_packets++; consume_skb(local_skb); consume_skb(skb); } else { BT_DBG("unknown packet type"); goto drop; } return NET_RX_SUCCESS; drop: dev->stats.rx_dropped++; return NET_RX_DROP; } /* Packet from BT LE device */ static int chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) { struct lowpan_btle_dev *dev; struct lowpan_peer *peer; int err; peer = lookup_peer(chan->conn); if (!peer) return -ENOENT; dev = lookup_dev(chan->conn); if (!dev || !dev->netdev) return -ENOENT; err = recv_pkt(skb, dev->netdev, peer); if (err) { BT_DBG("recv pkt %d", err); err = -EAGAIN; } return err; } static int setup_header(struct sk_buff *skb, struct net_device *netdev, bdaddr_t *peer_addr, u8 *peer_addr_type) { struct in6_addr ipv6_daddr; struct ipv6hdr *hdr; struct lowpan_btle_dev *dev; struct lowpan_peer *peer; u8 *daddr; int err, status = 0; hdr = ipv6_hdr(skb); dev = lowpan_btle_dev(netdev); memcpy(&ipv6_daddr, &hdr->daddr, sizeof(ipv6_daddr)); if (ipv6_addr_is_multicast(&ipv6_daddr)) { lowpan_cb(skb)->chan = NULL; daddr = NULL; } else { BT_DBG("dest IP %pI6c", &ipv6_daddr); /* The packet might be sent to 6lowpan interface * because of routing (either via default route * or user set route) so get peer according to * the destination address. */ peer = peer_lookup_dst(dev, &ipv6_daddr, skb); if (!peer) { BT_DBG("no such peer"); return -ENOENT; } daddr = peer->lladdr; *peer_addr = peer->chan->dst; *peer_addr_type = peer->chan->dst_type; lowpan_cb(skb)->chan = peer->chan; status = 1; } lowpan_header_compress(skb, netdev, daddr, dev->netdev->dev_addr); err = dev_hard_header(skb, netdev, ETH_P_IPV6, NULL, NULL, 0); if (err < 0) return err; return status; } static int header_create(struct sk_buff *skb, struct net_device *netdev, unsigned short type, const void *_daddr, const void *_saddr, unsigned int len) { if (type != ETH_P_IPV6) return -EINVAL; return 0; } /* Packet to BT LE device */ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb, struct net_device *netdev) { struct msghdr msg; struct kvec iv; int err; /* Remember the skb so that we can send EAGAIN to the caller if * we run out of credits. */ chan->data = skb; iv.iov_base = skb->data; iv.iov_len = skb->len; memset(&msg, 0, sizeof(msg)); iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iv, 1, skb->len); err = l2cap_chan_send(chan, &msg, skb->len, NULL); if (err > 0) { netdev->stats.tx_bytes += err; netdev->stats.tx_packets++; return 0; } if (err < 0) netdev->stats.tx_errors++; return err; } static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) { struct sk_buff *local_skb; struct lowpan_btle_dev *entry; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { struct lowpan_peer *pentry; struct lowpan_btle_dev *dev; if (entry->netdev != netdev) continue; dev = lowpan_btle_dev(entry->netdev); list_for_each_entry_rcu(pentry, &dev->peers, list) { int ret; local_skb = skb_clone(skb, GFP_ATOMIC); if (!local_skb) continue; BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &pentry->chan->dst, pentry->chan->dst_type, &pentry->peer_addr, pentry->chan); ret = send_pkt(pentry->chan, local_skb, netdev); if (ret < 0) err = ret; kfree_skb(local_skb); } } rcu_read_unlock(); return err; } static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) { int err = 0; bdaddr_t addr; u8 addr_type; /* We must take a copy of the skb before we modify/replace the ipv6 * header as the header could be used elsewhere */ skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) return NET_XMIT_DROP; /* Return values from setup_header() * <0 - error, packet is dropped * 0 - this is a multicast packet * 1 - this is unicast packet */ err = setup_header(skb, netdev, &addr, &addr_type); if (err < 0) { kfree_skb(skb); return NET_XMIT_DROP; } if (err) { if (lowpan_cb(skb)->chan) { BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &addr, addr_type, &lowpan_cb(skb)->addr, lowpan_cb(skb)->chan); err = send_pkt(lowpan_cb(skb)->chan, skb, netdev); } else { err = -ENOENT; } } else { /* We need to send the packet to every device behind this * interface. */ err = send_mcast_pkt(skb, netdev); } dev_kfree_skb(skb); if (err) BT_DBG("ERROR: xmit failed (%d)", err); return err < 0 ? NET_XMIT_DROP : err; } static int bt_dev_init(struct net_device *dev) { netdev_lockdep_set_classes(dev); return 0; } static const struct net_device_ops netdev_ops = { .ndo_init = bt_dev_init, .ndo_start_xmit = bt_xmit, }; static const struct header_ops header_ops = { .create = header_create, }; static void netdev_setup(struct net_device *dev) { dev->hard_header_len = 0; dev->needed_tailroom = 0; dev->flags = IFF_RUNNING | IFF_MULTICAST; dev->watchdog_timeo = 0; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->netdev_ops = &netdev_ops; dev->header_ops = &header_ops; dev->needs_free_netdev = true; } static const struct device_type bt_type = { .name = "bluetooth", }; static void ifup(struct net_device *netdev) { int err; rtnl_lock(); err = dev_open(netdev, NULL); if (err < 0) BT_INFO("iface %s cannot be opened (%d)", netdev->name, err); rtnl_unlock(); } static void ifdown(struct net_device *netdev) { rtnl_lock(); dev_close(netdev); rtnl_unlock(); } static void do_notify_peers(struct work_struct *work) { struct lowpan_btle_dev *dev = container_of(work, struct lowpan_btle_dev, notify_peers.work); netdev_notify_peers(dev->netdev); /* send neighbour adv at startup */ } static bool is_bt_6lowpan(struct hci_conn *hcon) { if (hcon->type != LE_LINK) return false; if (!enable_6lowpan) return false; return true; } static struct l2cap_chan *chan_create(void) { struct l2cap_chan *chan; chan = l2cap_chan_create(); if (!chan) return NULL; l2cap_chan_set_defaults(chan); chan->chan_type = L2CAP_CHAN_CONN_ORIENTED; chan->mode = L2CAP_MODE_LE_FLOWCTL; chan->imtu = 1280; return chan; } static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan, struct lowpan_btle_dev *dev, bool new_netdev) { struct lowpan_peer *peer; peer = kzalloc_obj(*peer, GFP_ATOMIC); if (!peer) return NULL; peer->chan = chan; baswap((void *)peer->lladdr, &chan->dst); lowpan_iphc_uncompress_eui48_lladdr(&peer->peer_addr, peer->lladdr); spin_lock(&devices_lock); INIT_LIST_HEAD(&peer->list); peer_add(dev, peer); spin_unlock(&devices_lock); /* Notifying peers about us needs to be done without locks held */ if (new_netdev) INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers); schedule_delayed_work(&dev->notify_peers, msecs_to_jiffies(100)); return peer->chan; } static int setup_netdev(struct l2cap_chan *chan, struct lowpan_btle_dev **dev) { struct net_device *netdev; bdaddr_t addr; int err; netdev = alloc_netdev(LOWPAN_PRIV_SIZE(sizeof(struct lowpan_btle_dev)), IFACE_NAME_TEMPLATE, NET_NAME_UNKNOWN, netdev_setup); if (!netdev) return -ENOMEM; netdev->addr_assign_type = NET_ADDR_PERM; baswap(&addr, &chan->src); __dev_addr_set(netdev, &addr, sizeof(addr)); netdev->netdev_ops = &netdev_ops; SET_NETDEV_DEV(netdev, &chan->conn->hcon->hdev->dev); SET_NETDEV_DEVTYPE(netdev, &bt_type); *dev = lowpan_btle_dev(netdev); (*dev)->netdev = netdev; (*dev)->hdev = chan->conn->hcon->hdev; INIT_LIST_HEAD(&(*dev)->peers); spin_lock(&devices_lock); INIT_LIST_HEAD(&(*dev)->list); list_add_rcu(&(*dev)->list, &bt_6lowpan_devices); spin_unlock(&devices_lock); err = lowpan_register_netdev(netdev, LOWPAN_LLTYPE_BTLE); if (err < 0) { BT_INFO("register_netdev failed %d", err); spin_lock(&devices_lock); list_del_rcu(&(*dev)->list); spin_unlock(&devices_lock); free_netdev(netdev); goto out; } BT_DBG("ifindex %d peer bdaddr %pMR type %d my addr %pMR type %d", netdev->ifindex, &chan->dst, chan->dst_type, &chan->src, chan->src_type); set_bit(__LINK_STATE_PRESENT, &netdev->state); return 0; out: return err; } static inline void chan_ready_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *dev; bool new_netdev = false; dev = lookup_dev(chan->conn); BT_DBG("chan %p conn %p dev %p", chan, chan->conn, dev); if (!dev) { if (setup_netdev(chan, &dev) < 0) { l2cap_chan_del(chan, -ENOENT); return; } new_netdev = true; } if (!try_module_get(THIS_MODULE)) return; add_peer_chan(chan, dev, new_netdev); ifup(dev->netdev); } static inline struct l2cap_chan *chan_new_conn_cb(struct l2cap_chan *pchan) { struct l2cap_chan *chan; chan = chan_create(); if (!chan) return NULL; chan->ops = pchan->ops; BT_DBG("chan %p pchan %p", chan, pchan); return chan; } static void delete_netdev(struct work_struct *work) { struct lowpan_btle_dev *entry = container_of(work, struct lowpan_btle_dev, delete_netdev); lowpan_unregister_netdev(entry->netdev); /* The entry pointer is deleted by the netdev destructor. */ } static void chan_close_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *entry; struct lowpan_btle_dev *dev = NULL; struct lowpan_peer *peer; int err = -ENOENT; bool last = false, remove = true; BT_DBG("chan %p conn %p", chan, chan->conn); if (chan->conn && chan->conn->hcon) { if (!is_bt_6lowpan(chan->conn->hcon)) return; /* If conn is set, then the netdev is also there and we should * not remove it. */ remove = false; } spin_lock(&devices_lock); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { dev = lowpan_btle_dev(entry->netdev); peer = __peer_lookup_chan(dev, chan); if (peer) { last = peer_del(dev, peer); err = 0; BT_DBG("dev %p removing %speer %p", dev, last ? "last " : "1 ", peer); BT_DBG("chan %p orig refcnt %u", chan, kref_read(&chan->kref)); l2cap_chan_put(chan); break; } } if (!err && last && dev && !atomic_read(&dev->peer_count)) { spin_unlock(&devices_lock); cancel_delayed_work_sync(&dev->notify_peers); ifdown(dev->netdev); if (remove) { INIT_WORK(&entry->delete_netdev, delete_netdev); schedule_work(&entry->delete_netdev); } } else { spin_unlock(&devices_lock); } } static void chan_state_change_cb(struct l2cap_chan *chan, int state, int err) { BT_DBG("chan %p conn %p state %s err %d", chan, chan->conn, state_to_string(state), err); } static struct sk_buff *chan_alloc_skb_cb(struct l2cap_chan *chan, unsigned long hdr_len, unsigned long len, int nb) { struct sk_buff *skb; /* Note that we must allocate using GFP_ATOMIC here as * this function is called originally from netdev hard xmit * function in atomic context. */ skb = bt_skb_alloc(hdr_len + len, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); return skb; } static void chan_suspend_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *dev; BT_DBG("chan %p suspend", chan); dev = lookup_dev(chan->conn); if (!dev || !dev->netdev) return; netif_stop_queue(dev->netdev); } static void chan_resume_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *dev; BT_DBG("chan %p resume", chan); dev = lookup_dev(chan->conn); if (!dev || !dev->netdev) return; netif_wake_queue(dev->netdev); } static long chan_get_sndtimeo_cb(struct l2cap_chan *chan) { return L2CAP_CONN_TIMEOUT; } static const struct l2cap_ops bt_6lowpan_chan_ops = { .name = "L2CAP 6LoWPAN channel", .new_connection = chan_new_conn_cb, .recv = chan_recv_cb, .close = chan_close_cb, .state_change = chan_state_change_cb, .ready = chan_ready_cb, .resume = chan_resume_cb, .suspend = chan_suspend_cb, .get_sndtimeo = chan_get_sndtimeo_cb, .alloc_skb = chan_alloc_skb_cb, .teardown = l2cap_chan_no_teardown, .defer = l2cap_chan_no_defer, .set_shutdown = l2cap_chan_no_set_shutdown, }; static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) { struct l2cap_chan *chan; int err; chan = chan_create(); if (!chan) return -EINVAL; chan->ops = &bt_6lowpan_chan_ops; err = l2cap_chan_connect(chan, cpu_to_le16(L2CAP_PSM_IPSP), 0, addr, dst_type, L2CAP_CONN_TIMEOUT); BT_DBG("chan %p err %d", chan, err); if (err < 0) l2cap_chan_put(chan); return err; } static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type) { struct lowpan_peer *peer; BT_DBG("conn %p dst type %u", conn, dst_type); peer = lookup_peer(conn); if (!peer) return -ENOENT; BT_DBG("peer %p chan %p", peer, peer->chan); l2cap_chan_lock(peer->chan); l2cap_chan_close(peer->chan, ENOENT); l2cap_chan_unlock(peer->chan); return 0; } static struct l2cap_chan *bt_6lowpan_listen(void) { bdaddr_t *addr = BDADDR_ANY; struct l2cap_chan *chan; int err; if (!enable_6lowpan) return NULL; chan = chan_create(); if (!chan) return NULL; chan->ops = &bt_6lowpan_chan_ops; chan->state = BT_LISTEN; chan->src_type = BDADDR_LE_PUBLIC; atomic_set(&chan->nesting, L2CAP_NESTING_PARENT); BT_DBG("chan %p src type %u", chan, chan->src_type); err = l2cap_add_psm(chan, addr, cpu_to_le16(L2CAP_PSM_IPSP)); if (err) { l2cap_chan_put(chan); BT_ERR("psm cannot be added err %d", err); return NULL; } return chan; } static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, struct l2cap_conn **conn, bool disconnect) { struct hci_conn *hcon; struct hci_dev *hdev; int le_addr_type; int n; n = sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", &addr->b[5], &addr->b[4], &addr->b[3], &addr->b[2], &addr->b[1], &addr->b[0], addr_type); if (n < 7) return -EINVAL; if (disconnect) { /* The "disconnect" debugfs command has used different address * type constants than "connect" since 2015. Let's retain that * for now even though it's obviously buggy... */ *addr_type += 1; } switch (*addr_type) { case BDADDR_LE_PUBLIC: le_addr_type = ADDR_LE_DEV_PUBLIC; break; case BDADDR_LE_RANDOM: le_addr_type = ADDR_LE_DEV_RANDOM; break; default: return -EINVAL; } /* The LE_PUBLIC address type is ignored because of BDADDR_ANY */ hdev = hci_get_route(addr, BDADDR_ANY, BDADDR_LE_PUBLIC); if (!hdev) return -ENOENT; hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_le(hdev, addr, le_addr_type); hci_dev_unlock(hdev); hci_dev_put(hdev); if (!hcon) return -ENOENT; *conn = (struct l2cap_conn *)hcon->l2cap_data; BT_DBG("conn %p dst %pMR type %u", *conn, &hcon->dst, hcon->dst_type); return 0; } static void disconnect_all_peers(void) { struct lowpan_btle_dev *entry; struct lowpan_peer *peer; int nchans; /* l2cap_chan_close() cannot be called from RCU, and lock ordering * chan->lock > devices_lock prevents taking write side lock, so copy * then close. */ rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) list_for_each_entry_rcu(peer, &entry->peers, list) clear_bit(LOWPAN_PEER_CLOSING, peer->flags); rcu_read_unlock(); do { struct l2cap_chan *chans[32]; int i; nchans = 0; spin_lock(&devices_lock); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { list_for_each_entry_rcu(peer, &entry->peers, list) { if (test_and_set_bit(LOWPAN_PEER_CLOSING, peer->flags)) continue; l2cap_chan_hold(peer->chan); chans[nchans++] = peer->chan; if (nchans >= ARRAY_SIZE(chans)) goto done; } } done: spin_unlock(&devices_lock); for (i = 0; i < nchans; ++i) { l2cap_chan_lock(chans[i]); l2cap_chan_close(chans[i], ENOENT); l2cap_chan_unlock(chans[i]); l2cap_chan_put(chans[i]); } } while (nchans); } struct set_enable { struct work_struct work; bool flag; }; static void do_enable_set(struct work_struct *work) { struct set_enable *set_enable = container_of(work, struct set_enable, work); if (!set_enable->flag || enable_6lowpan != set_enable->flag) /* Disconnect existing connections if 6lowpan is * disabled */ disconnect_all_peers(); enable_6lowpan = set_enable->flag; mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); } listen_chan = bt_6lowpan_listen(); mutex_unlock(&set_lock); kfree(set_enable); } static int lowpan_enable_set(void *data, u64 val) { struct set_enable *set_enable; set_enable = kzalloc_obj(*set_enable); if (!set_enable) return -ENOMEM; set_enable->flag = !!val; INIT_WORK(&set_enable->work, do_enable_set); schedule_work(&set_enable->work); return 0; } static int lowpan_enable_get(void *data, u64 *val) { *val = enable_6lowpan; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(lowpan_enable_fops, lowpan_enable_get, lowpan_enable_set, "%llu\n"); static ssize_t lowpan_control_write(struct file *fp, const char __user *user_buffer, size_t count, loff_t *position) { char buf[32]; size_t buf_size = min(count, sizeof(buf) - 1); int ret; bdaddr_t addr; u8 addr_type; struct l2cap_conn *conn = NULL; if (copy_from_user(buf, user_buffer, buf_size)) return -EFAULT; buf[buf_size] = '\0'; if (memcmp(buf, "connect ", 8) == 0) { ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn, false); if (ret == -EINVAL) return ret; mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); listen_chan = NULL; } mutex_unlock(&set_lock); if (conn) { struct lowpan_peer *peer; if (!is_bt_6lowpan(conn->hcon)) return -EINVAL; peer = lookup_peer(conn); if (peer) { BT_DBG("6LoWPAN connection already exists"); return -EALREADY; } BT_DBG("conn %p dst %pMR type %d user %u", conn, &conn->hcon->dst, conn->hcon->dst_type, addr_type); } ret = bt_6lowpan_connect(&addr, addr_type); if (ret < 0) return ret; return count; } if (memcmp(buf, "disconnect ", 11) == 0) { ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn, true); if (ret < 0) return ret; ret = bt_6lowpan_disconnect(conn, addr_type); if (ret < 0) return ret; return count; } return count; } static int lowpan_control_show(struct seq_file *f, void *ptr) { struct lowpan_btle_dev *entry; struct lowpan_peer *peer; spin_lock(&devices_lock); list_for_each_entry(entry, &bt_6lowpan_devices, list) { list_for_each_entry(peer, &entry->peers, list) seq_printf(f, "%pMR (type %u)\n", &peer->chan->dst, peer->chan->dst_type); } spin_unlock(&devices_lock); return 0; } static int lowpan_control_open(struct inode *inode, struct file *file) { return single_open(file, lowpan_control_show, inode->i_private); } static const struct file_operations lowpan_control_fops = { .open = lowpan_control_open, .read = seq_read, .write = lowpan_control_write, .llseek = seq_lseek, .release = single_release, }; static void disconnect_devices(void) { struct lowpan_btle_dev *entry, *tmp, *new_dev; struct list_head devices; INIT_LIST_HEAD(&devices); /* We make a separate list of devices because the unregister_netdev() * will call device_event() which will also want to modify the same * devices list. */ rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { new_dev = kmalloc_obj(*new_dev, GFP_ATOMIC); if (!new_dev) break; new_dev->netdev = entry->netdev; INIT_LIST_HEAD(&new_dev->list); list_add_rcu(&new_dev->list, &devices); } rcu_read_unlock(); list_for_each_entry_safe(entry, tmp, &devices, list) { ifdown(entry->netdev); BT_DBG("Unregistering netdev %s %p", entry->netdev->name, entry->netdev); lowpan_unregister_netdev(entry->netdev); kfree(entry); } } static int device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct lowpan_btle_dev *entry; if (netdev->type != ARPHRD_6LOWPAN) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: spin_lock(&devices_lock); list_for_each_entry(entry, &bt_6lowpan_devices, list) { if (entry->netdev == netdev) { BT_DBG("Unregistered netdev %s %p", netdev->name, netdev); list_del(&entry->list); break; } } spin_unlock(&devices_lock); break; } return NOTIFY_DONE; } static struct notifier_block bt_6lowpan_dev_notifier = { .notifier_call = device_event, }; static int __init bt_6lowpan_init(void) { lowpan_enable_debugfs = debugfs_create_file_unsafe("6lowpan_enable", 0644, bt_debugfs, NULL, &lowpan_enable_fops); lowpan_control_debugfs = debugfs_create_file("6lowpan_control", 0644, bt_debugfs, NULL, &lowpan_control_fops); return register_netdevice_notifier(&bt_6lowpan_dev_notifier); } static void __exit bt_6lowpan_exit(void) { debugfs_remove(lowpan_enable_debugfs); debugfs_remove(lowpan_control_debugfs); if (listen_chan) { l2cap_chan_lock(listen_chan); l2cap_chan_close(listen_chan, 0); l2cap_chan_unlock(listen_chan); l2cap_chan_put(listen_chan); } disconnect_devices(); unregister_netdevice_notifier(&bt_6lowpan_dev_notifier); } module_init(bt_6lowpan_init); module_exit(bt_6lowpan_exit); MODULE_AUTHOR("Jukka Rissanen <jukka.rissanen@linux.intel.com>"); MODULE_DESCRIPTION("Bluetooth 6LoWPAN"); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); |
| 7 6 45 409 5 15 1 1 14 103 7 272 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET Generic infrastructure for INET connection oriented protocols. * * Definitions for inet_connection_sock * * Authors: Many people, see the TCP sources * * From code originally in TCP */ #ifndef _INET_CONNECTION_SOCK_H #define _INET_CONNECTION_SOCK_H #include <linux/compiler.h> #include <linux/string.h> #include <linux/timer.h> #include <linux/poll.h> #include <linux/kernel.h> #include <linux/sockptr.h> #include <net/inet_sock.h> #include <net/request_sock.h> /* Cancel timers, when they are not required. */ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; struct inet_bind2_bucket; struct tcp_congestion_ops; /* * Pointers to address related TCP functions * (i.e. things that depend on the address family) */ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl); u16 net_header_len; int (*rebuild_header)(struct sock *sk); void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req, void (*opt_child_init)(struct sock *newsk, const struct sock *sk)); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); void (*mtu_reduced)(struct sock *sk); }; /** inet_connection_sock - INET connection oriented sock * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_delack_timer: Delayed ACK timer * @icsk_keepalive_timer: Keepalive timer * @mptcp_tout_timer: mptcp timer * @icsk_rto: Retransmit timeout * @icsk_pmtu_cookie Last pmtu seen by socket * @icsk_ca_ops Pluggable congestion control hook * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event * @icsk_backoff: Backoff * @icsk_syn_retries: Number of allowed SYN (or equivalent) retries * @icsk_probes_out: unanswered 0 window probes * @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options) * @icsk_ack: Delayed ACK control data * @icsk_mtup; MTU probing control data * @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack) * @icsk_user_timeout: TCP_USER_TIMEOUT value */ struct inet_connection_sock { /* inet_sock has to be the first member! */ struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; struct inet_bind2_bucket *icsk_bind2_hash; struct timer_list icsk_delack_timer; union { struct timer_list icsk_keepalive_timer; struct timer_list mptcp_tout_timer; }; __u32 icsk_rto; __u32 icsk_rto_min; u32 icsk_rto_max; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; __u8 icsk_pending; __u8 icsk_backoff; __u8 icsk_syn_retries; __u8 icsk_probes_out; __u16 icsk_ext_hdr_len; struct { __u8 pending; /* ACK is pending */ __u8 quick; /* Scheduled number of quick acks */ __u8 pingpong; /* The session is interactive */ __u8 retry; /* Number of attempts */ #define ATO_BITS 8 __u32 ato:ATO_BITS, /* Predicted tick of soft clock */ lrcv_flowlabel:20, /* last received ipv6 flowlabel */ dst_quick_ack:1, /* cache dst RTAX_QUICKACK */ unused:3; __u32 lrcvtime; /* timestamp of last received data packet */ __u16 last_seg_size; /* Size of last incoming segment */ __u16 rcv_mss; /* MSS used for delayed ACK decisions */ } icsk_ack; struct { /* Range of MTUs to search */ int search_high; int search_low; /* Information on the current probe. */ u32 probe_size:31, /* Is the MTUP feature enabled for this connection? */ enabled:1; u32 probe_timestamp; } icsk_mtup; u32 icsk_probes_tstamp; u32 icsk_user_timeout; u64 icsk_ca_priv[104 / sizeof(u64)]; #define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ #define ICSK_TIME_DACK 2 /* Delayed ack timer */ #define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ #define inet_csk(ptr) container_of_const(ptr, struct inet_connection_sock, icsk_inet.sk) static inline void *inet_csk_ca(const struct sock *sk) { return (void *)inet_csk(sk)->icsk_ca_priv; } struct sock *inet_csk_clone_lock(const struct sock *sk, const struct request_sock *req, const gfp_t priority); enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, ICSK_ACK_PUSHED2 = 8, ICSK_ACK_NOW = 16, /* Send the next ACK immediately (once) */ ICSK_ACK_NOMEM = 32, }; void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *), void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED; } static inline int inet_csk_ack_scheduled(const struct sock *sk) { return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED; } static inline void inet_csk_delack_init(struct sock *sk) { memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack)); } static inline unsigned long tcp_timeout_expires(const struct sock *sk) { return READ_ONCE(sk->tcp_retransmit_timer.expires); } static inline unsigned long icsk_delack_timeout(const struct inet_connection_sock *icsk) { return READ_ONCE(icsk->icsk_delack_timer.expires); } static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) { struct inet_connection_sock *icsk = inet_csk(sk); if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { smp_store_release(&icsk->icsk_pending, 0); #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &sk->tcp_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, 0); icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } /* * Reset the retransmission timer */ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { struct inet_connection_sock *icsk = inet_csk(sk); if (when > max_when) { pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, (void *)_THIS_IP_); when = max_when; } when += jiffies; if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { smp_store_release(&icsk->icsk_pending, what); sk_reset_timer(sk, &sk->tcp_retransmit_timer, when); } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_TIMER); sk_reset_timer(sk, &icsk->icsk_delack_timer, when); } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } static inline unsigned long inet_csk_rto_backoff(const struct inet_connection_sock *icsk, unsigned long max_when) { u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff; return (unsigned long)min_t(u64, when, max_when); } struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg); int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req); static inline void inet_csk_reqsk_queue_added(struct sock *sk) { reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_len(const struct sock *sk) { return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_for_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); /* * LISTEN is a special case for poll.. */ static inline __poll_t inet_csk_listen_poll(const struct sock *sk) { return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ? (EPOLLIN | EPOLLRDNORM) : 0; } int inet_csk_listen_start(struct sock *sk); void inet_csk_listen_stop(struct sock *sk); /* update the fast reuse flag when adding a socket */ void inet_csk_update_fastreuse(const struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2); struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); static inline void inet_csk_enter_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh); } static inline void inet_csk_exit_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = 0; } static inline bool inet_csk_in_pingpong_mode(struct sock *sk) { return inet_csk(sk)->icsk_ack.pingpong >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh); } static inline void inet_csk_inc_pingpong_cnt(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.pingpong < U8_MAX) icsk->icsk_ack.pingpong++; } static inline bool inet_csk_has_ulp(const struct sock *sk) { return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops; } static inline void inet_init_csk_locks(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); } #endif /* _INET_CONNECTION_SOCK_H */ |
| 15772 520 4950 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> #include <asm/processor.h> /* for cpu_relax() */ /* * For static context analysis, we need a unique token for each possible bit * that can be used as a bit_spinlock. The easiest way to do that is to create a * fake context that we can cast to with the __bitlock(bitnum, addr) macro * below, which will give us unique instances for each (bit, addr) pair that the * static analysis can use. */ context_lock_struct(__context_bitlock) { }; #define __bitlock(bitnum, addr) (struct __context_bitlock *)(bitnum + (addr)) /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static __always_inline void bit_spin_lock(int bitnum, unsigned long *addr) __acquires(__bitlock(bitnum, addr)) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(__bitlock(bitnum, addr)); } /* * Return true if it was acquired */ static __always_inline int bit_spin_trylock(int bitnum, unsigned long *addr) __cond_acquires(true, __bitlock(bitnum, addr)) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(__bitlock(bitnum, addr)); return 1; } /* * bit-based spin_unlock() */ static __always_inline void bit_spin_unlock(int bitnum, unsigned long *addr) __releases(__bitlock(bitnum, addr)) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(__bitlock(bitnum, addr)); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static __always_inline void __bit_spin_unlock(int bitnum, unsigned long *addr) __releases(__bitlock(bitnum, addr)) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(__bitlock(bitnum, addr)); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */ |
| 559 12 258 237 10 1022 1021 109 1022 1 945 944 809 237 6 878 878 878 112 100 12 73 61 61 12 9 9 14 14 11 11 10 11 11 11 57 56 1 56 9 14 14 9 9 1 47 47 41 41 41 41 41 1037 25 945 941 12 12 261 935 8260 8048 936 946 940 936 935 558 12 558 560 556 12 559 259 259 261 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #include "internal.h" #ifdef CONFIG_MEMCG static LIST_HEAD(memcg_list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static void list_lru_register(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_add(&lru->list, &memcg_list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { if (list_lru_memcg_aware(lru) && idx >= 0) { struct list_lru_memcg *mlru = xa_load(&lru->xa, idx); return mlru ? &mlru->node[nid] : NULL; } return &lru->node[nid].lru; } static inline bool lock_list_lru(struct list_lru_one *l, bool irq) { if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); if (unlikely(READ_ONCE(l->nr_items) == LONG_MIN)) { if (irq) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); return false; } return true; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l; rcu_read_lock(); again: l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); if (likely(l) && lock_list_lru(l, irq)) { rcu_read_unlock(); return l; } /* * Caller may simply bail out if raced with reparenting or * may iterate through the list_lru and expect empty slots. */ if (skip_empty) { rcu_read_unlock(); return NULL; } VM_WARN_ON(!css_is_dying(&memcg->css)); memcg = parent_mem_cgroup(memcg); goto again; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l = &lru->node[nid].lru; if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); return l; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #endif /* CONFIG_MEMCG */ /* The caller must ensure the memcg lifetime. */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (list_empty(item)) { list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); unlock_list_lru(l, false); atomic_long_inc(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_add(lru, item, nid, mem_cgroup_from_virt(item)); rcu_read_unlock(); } else { ret = list_lru_add(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_add_obj); /* The caller must ensure the memcg lifetime. */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (!list_empty(item)) { list_del_init(item); l->nr_items--; unlock_list_lru(l, false); atomic_long_dec(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_del(lru, item, nid, mem_cgroup_from_virt(item)); rcu_read_unlock(); } else { ret = list_lru_del(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_del_obj); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_one *l; long count; rcu_read_lock(); l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); count = l ? READ_ONCE(l->nr_items) : 0; rcu_read_unlock(); if (unlikely(count < 0)) count = 0; return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return atomic_long_read(&nlru->nr_items); } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk, bool irq_off) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l = NULL; struct list_head *item, *n; unsigned long isolated = 0; restart: l = lock_list_lru_of_memcg(lru, nid, memcg, irq_off, true); if (!l) return isolated; list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, cb_arg); switch (ret) { /* * LRU_RETRY, LRU_REMOVED_RETRY and LRU_STOP will drop the lru * lock. List traversal will have to restart from scratch. */ case LRU_RETRY: goto restart; case LRU_REMOVED_RETRY: fallthrough; case LRU_REMOVED: isolated++; atomic_long_dec(&nlru->nr_items); if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_STOP: goto out; default: BUG(); } } unlock_list_lru(l, irq_off); out: return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, true); } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); #ifdef CONFIG_MEMCG if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { struct list_lru_memcg *mlru; struct mem_cgroup *memcg; unsigned long index; xa_for_each(&lru->xa, index, mlru) { rcu_read_lock(); memcg = mem_cgroup_from_private_id(index); if (!mem_cgroup_tryget(memcg)) { rcu_read_unlock(); continue; } rcu_read_unlock(); isolated += __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); mem_cgroup_put(memcg); if (*nr_to_walk <= 0) break; } } #endif return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru *lru, struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); spin_lock_init(&l->lock); l->nr_items = 0; #ifdef CONFIG_LOCKDEP if (lru->key) lockdep_set_class(&l->lock, lru->key); #endif } #ifdef CONFIG_MEMCG static struct list_lru_memcg *memcg_init_list_lru_one(struct list_lru *lru, gfp_t gfp) { int nid; struct list_lru_memcg *mlru; mlru = kmalloc_flex(*mlru, node, nr_node_ids, gfp); if (!mlru) return NULL; for_each_node(nid) init_one_lru(lru, &mlru->node[nid]); return mlru; } static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ); lru->memcg_aware = memcg_aware; } static void memcg_destroy_list_lru(struct list_lru *lru) { XA_STATE(xas, &lru->xa, 0); struct list_lru_memcg *mlru; if (!list_lru_memcg_aware(lru)) return; xas_lock_irq(&xas); xas_for_each(&xas, mlru, ULONG_MAX) { kfree(mlru); xas_store(&xas, NULL); } xas_unlock_irq(&xas); } static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, struct list_lru_one *src, struct mem_cgroup *dst_memcg) { int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *dst; spin_lock_irq(&src->lock); dst = list_lru_from_memcg_idx(lru, nid, dst_idx); spin_lock_nested(&dst->lock, SINGLE_DEPTH_NESTING); list_splice_init(&src->list, &dst->list); if (src->nr_items) { WARN_ON(src->nr_items < 0); dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); } /* Mark the list_lru_one dead */ src->nr_items = LONG_MIN; spin_unlock(&dst->lock); spin_unlock_irq(&src->lock); } void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { struct list_lru *lru; int i; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &memcg_list_lrus, list) { struct list_lru_memcg *mlru; /* * css_is_dying() check in memcg_list_lru_alloc() avoids * allocating a new mlru since CSS_DYING is already set for this * memcg a rcu grace period ago. */ mlru = xa_load(&lru->xa, memcg->kmemcg_id); if (!mlru) continue; /* * Reparent each per-node list and mark the child dead * (LONG_MIN) before clearing xarray entry otherwise a * concurrent list_lru_del() may corrupt the list if it arrives * after xarray clear but before reparenting as * lock_list_lru_of_memcg will acquire parent's lock while the * item is still on child's list. */ for_each_node(i) memcg_reparent_list_lru_one(lru, i, &mlru->node[i], parent); xa_erase_irq(&lru->xa, memcg->kmemcg_id); /* * Here all list_lrus corresponding to the cgroup are guaranteed * to remain empty, we can safely free this lru, any further * memcg_list_lru_alloc() call will simply bail out. */ kvfree_rcu(mlru, rcu); } mutex_unlock(&list_lrus_mutex); } static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, struct list_lru *lru) { int idx = memcg->kmemcg_id; return idx < 0 || xa_load(&lru->xa, idx); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { unsigned long flags; struct list_lru_memcg *mlru = NULL; struct mem_cgroup *pos, *parent; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ do { /* * Keep finding the farest parent that wasn't populated * until found memcg itself. */ pos = memcg; parent = parent_mem_cgroup(pos); while (!memcg_list_lru_allocated(parent, lru)) { pos = parent; parent = parent_mem_cgroup(pos); } if (!mlru) { mlru = memcg_init_list_lru_one(lru, gfp); if (!mlru) return -ENOMEM; } xas_set(&xas, pos->kmemcg_id); do { xas_lock_irqsave(&xas, flags); if (!xas_load(&xas) && !css_is_dying(&pos->css)) { xas_store(&xas, mlru); if (!xas_error(&xas)) mlru = NULL; } xas_unlock_irqrestore(&xas, flags); } while (xas_nomem(&xas, gfp)); } while (pos != memcg && !css_is_dying(&pos->css)); if (unlikely(mlru)) kfree(mlru); return xas_error(&xas); } #else static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker) { int i; #ifdef CONFIG_MEMCG if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; if (mem_cgroup_kmem_disabled()) memcg_aware = false; #endif lru->node = kzalloc_objs(*lru->node, nr_node_ids); if (!lru->node) return -ENOMEM; for_each_node(i) init_one_lru(lru, &lru->node[i].lru); memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); return 0; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG lru->shrinker_id = -1; #endif } EXPORT_SYMBOL_GPL(list_lru_destroy); |
| 91 92 27 27 93 93 68 63 63 91 91 31 31 31 83 83 83 63 63 5 1 5 5 5 8 8 23 63 63 31 31 23 23 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 | /* * net/tipc/server.c: TIPC server infrastructure * * Copyright (c) 2012-2013, Wind River Systems * Copyright (c) 2017-2018, Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "subscr.h" #include "topsrv.h" #include "core.h" #include "socket.h" #include "addr.h" #include "msg.h" #include "bearer.h" #include <net/sock.h> #include <linux/module.h> #include <trace/events/sock.h> /* Number of messages to send before rescheduling */ #define MAX_SEND_MSG_COUNT 25 #define MAX_RECV_MSG_COUNT 25 #define CF_CONNECTED 1 #define TIPC_SERVER_NAME_LEN 32 /** * struct tipc_topsrv - TIPC server structure * @conn_idr: identifier set of connection * @idr_lock: protect the connection identifier set * @idr_in_use: amount of allocated identifier entry * @net: network namespace instance * @awork: accept work item * @rcv_wq: receive workqueue * @send_wq: send workqueue * @listener: topsrv listener socket * @name: server name */ struct tipc_topsrv { struct idr conn_idr; spinlock_t idr_lock; /* for idr list */ int idr_in_use; struct net *net; struct work_struct awork; struct workqueue_struct *rcv_wq; struct workqueue_struct *send_wq; struct socket *listener; char name[TIPC_SERVER_NAME_LEN]; }; /** * struct tipc_conn - TIPC connection structure * @kref: reference counter to connection object * @conid: connection identifier * @sock: socket handler associated with connection * @flags: indicates connection state * @server: pointer to connected server * @sub_list: list to all pertaining subscriptions * @sub_lock: lock protecting the subscription list * @rwork: receive work item * @outqueue: pointer to first outbound message in queue * @outqueue_lock: control access to the outqueue * @swork: send work item */ struct tipc_conn { struct kref kref; int conid; struct socket *sock; unsigned long flags; struct tipc_topsrv *server; struct list_head sub_list; spinlock_t sub_lock; /* for subscription list */ struct work_struct rwork; struct list_head outqueue; spinlock_t outqueue_lock; /* for outqueue */ struct work_struct swork; }; /* An entry waiting to be sent */ struct outqueue_entry { bool inactive; struct tipc_event evt; struct list_head list; }; static void tipc_conn_recv_work(struct work_struct *work); static void tipc_conn_send_work(struct work_struct *work); static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt); static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s); static bool connected(struct tipc_conn *con) { return con && test_bit(CF_CONNECTED, &con->flags); } static void tipc_conn_kref_release(struct kref *kref) { struct tipc_conn *con = container_of(kref, struct tipc_conn, kref); struct tipc_topsrv *s = con->server; struct outqueue_entry *e, *safe; spin_lock_bh(&s->idr_lock); idr_remove(&s->conn_idr, con->conid); s->idr_in_use--; spin_unlock_bh(&s->idr_lock); if (con->sock) sock_release(con->sock); spin_lock_bh(&con->outqueue_lock); list_for_each_entry_safe(e, safe, &con->outqueue, list) { list_del(&e->list); kfree(e); } spin_unlock_bh(&con->outqueue_lock); kfree(con); } static void conn_put(struct tipc_conn *con) { kref_put(&con->kref, tipc_conn_kref_release); } static void conn_get(struct tipc_conn *con) { kref_get(&con->kref); } static void tipc_conn_close(struct tipc_conn *con) { struct sock *sk = con->sock->sk; bool disconnect = false; write_lock_bh(&sk->sk_callback_lock); disconnect = test_and_clear_bit(CF_CONNECTED, &con->flags); if (disconnect) { sk->sk_user_data = NULL; tipc_conn_delete_sub(con, NULL); } write_unlock_bh(&sk->sk_callback_lock); /* Handle concurrent calls from sending and receiving threads */ if (!disconnect) return; /* Don't flush pending works, -just let them expire */ kernel_sock_shutdown(con->sock, SHUT_RDWR); conn_put(con); } static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; con = kzalloc_obj(*con, GFP_ATOMIC); if (!con) return ERR_PTR(-ENOMEM); kref_init(&con->kref); INIT_LIST_HEAD(&con->outqueue); INIT_LIST_HEAD(&con->sub_list); spin_lock_init(&con->outqueue_lock); spin_lock_init(&con->sub_lock); INIT_WORK(&con->swork, tipc_conn_send_work); INIT_WORK(&con->rwork, tipc_conn_recv_work); spin_lock_bh(&s->idr_lock); ret = idr_alloc(&s->conn_idr, con, 0, 0, GFP_ATOMIC); if (ret < 0) { kfree(con); spin_unlock_bh(&s->idr_lock); return ERR_PTR(-ENOMEM); } con->conid = ret; s->idr_in_use++; set_bit(CF_CONNECTED, &con->flags); con->server = s; con->sock = sock; conn_get(con); spin_unlock_bh(&s->idr_lock); return con; } static struct tipc_conn *tipc_conn_lookup(struct tipc_topsrv *s, int conid) { struct tipc_conn *con; spin_lock_bh(&s->idr_lock); con = idr_find(&s->conn_idr, conid); if (!connected(con) || !kref_get_unless_zero(&con->kref)) con = NULL; spin_unlock_bh(&s->idr_lock); return con; } /* tipc_conn_delete_sub - delete a specific or all subscriptions * for a given subscriber */ static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s) { struct tipc_net *tn = tipc_net(con->server->net); struct list_head *sub_list = &con->sub_list; struct tipc_subscription *sub, *tmp; spin_lock_bh(&con->sub_lock); list_for_each_entry_safe(sub, tmp, sub_list, sub_list) { if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) { tipc_sub_unsubscribe(sub); atomic_dec(&tn->subscription_count); if (s) break; } } spin_unlock_bh(&con->sub_lock); } static void tipc_conn_send_to_sock(struct tipc_conn *con) { struct list_head *queue = &con->outqueue; struct tipc_topsrv *srv = con->server; struct outqueue_entry *e; struct tipc_event *evt; struct msghdr msg; struct kvec iov; int count = 0; int ret; spin_lock_bh(&con->outqueue_lock); while (!list_empty(queue)) { e = list_first_entry(queue, struct outqueue_entry, list); evt = &e->evt; spin_unlock_bh(&con->outqueue_lock); if (e->inactive) tipc_conn_delete_sub(con, &evt->s); memset(&msg, 0, sizeof(msg)); msg.msg_flags = MSG_DONTWAIT; iov.iov_base = evt; iov.iov_len = sizeof(*evt); msg.msg_name = NULL; if (con->sock) { ret = kernel_sendmsg(con->sock, &msg, &iov, 1, sizeof(*evt)); if (ret == -EWOULDBLOCK || ret == 0) { cond_resched(); return; } else if (ret < 0) { return tipc_conn_close(con); } } else { tipc_topsrv_kern_evt(srv->net, evt); } /* Don't starve users filling buffers */ if (++count >= MAX_SEND_MSG_COUNT) { cond_resched(); count = 0; } spin_lock_bh(&con->outqueue_lock); list_del(&e->list); kfree(e); } spin_unlock_bh(&con->outqueue_lock); } static void tipc_conn_send_work(struct work_struct *work) { struct tipc_conn *con = container_of(work, struct tipc_conn, swork); if (connected(con)) tipc_conn_send_to_sock(con); conn_put(con); } /* tipc_topsrv_queue_evt() - interrupt level call from a subscription instance * The queued work is launched into tipc_conn_send_work()->tipc_conn_send_to_sock() */ void tipc_topsrv_queue_evt(struct net *net, int conid, u32 event, struct tipc_event *evt) { struct tipc_topsrv *srv = tipc_topsrv(net); struct outqueue_entry *e; struct tipc_conn *con; con = tipc_conn_lookup(srv, conid); if (!con) return; if (!connected(con)) goto err; e = kmalloc_obj(*e, GFP_ATOMIC); if (!e) goto err; e->inactive = (event == TIPC_SUBSCR_TIMEOUT); memcpy(&e->evt, evt, sizeof(*evt)); spin_lock_bh(&con->outqueue_lock); list_add_tail(&e->list, &con->outqueue); spin_unlock_bh(&con->outqueue_lock); if (queue_work(srv->send_wq, &con->swork)) return; err: conn_put(con); } /* tipc_conn_write_space - interrupt callback after a sendmsg EAGAIN * Indicates that there now is more space in the send buffer * The queued work is launched into tipc_send_work()->tipc_conn_send_to_sock() */ static void tipc_conn_write_space(struct sock *sk) { struct tipc_conn *con; read_lock_bh(&sk->sk_callback_lock); con = sk->sk_user_data; if (connected(con)) { conn_get(con); if (!queue_work(con->server->send_wq, &con->swork)) conn_put(con); } read_unlock_bh(&sk->sk_callback_lock); } static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, struct tipc_conn *con, struct tipc_subscr *s) { struct tipc_net *tn = tipc_net(srv->net); struct tipc_subscription *sub; u32 s_filter = tipc_sub_read(s, filter); if (s_filter & TIPC_SUB_CANCEL) { tipc_sub_write(s, filter, s_filter & ~TIPC_SUB_CANCEL); tipc_conn_delete_sub(con, s); return 0; } if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCR) { pr_warn("Subscription rejected, max (%u)\n", TIPC_MAX_SUBSCR); return -1; } sub = tipc_sub_subscribe(srv->net, s, con->conid); if (!sub) return -1; atomic_inc(&tn->subscription_count); spin_lock_bh(&con->sub_lock); list_add(&sub->sub_list, &con->sub_list); spin_unlock_bh(&con->sub_lock); return 0; } static int tipc_conn_rcv_from_sock(struct tipc_conn *con) { struct tipc_topsrv *srv = con->server; struct sock *sk = con->sock->sk; struct msghdr msg = {}; struct tipc_subscr s; struct kvec iov; int ret; iov.iov_base = &s; iov.iov_len = sizeof(s); msg.msg_name = NULL; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, iov.iov_len); ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); /* RACE: the connection can be closed in the meantime */ if (likely(connected(con))) ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); if (!ret) return 0; } tipc_conn_close(con); return ret; } static void tipc_conn_recv_work(struct work_struct *work) { struct tipc_conn *con = container_of(work, struct tipc_conn, rwork); int count = 0; while (connected(con)) { if (tipc_conn_rcv_from_sock(con)) break; /* Don't flood Rx machine */ if (++count >= MAX_RECV_MSG_COUNT) { cond_resched(); count = 0; } } conn_put(con); } /* tipc_conn_data_ready - interrupt callback indicating the socket has data * The queued work is launched into tipc_recv_work()->tipc_conn_rcv_from_sock() */ static void tipc_conn_data_ready(struct sock *sk) { struct tipc_conn *con; trace_sk_data_ready(sk); read_lock_bh(&sk->sk_callback_lock); con = sk->sk_user_data; if (connected(con)) { conn_get(con); if (!queue_work(con->server->rcv_wq, &con->rwork)) conn_put(con); } read_unlock_bh(&sk->sk_callback_lock); } static void tipc_topsrv_accept(struct work_struct *work) { struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork); struct socket *newsock, *lsock; struct tipc_conn *con; struct sock *newsk; int ret; spin_lock_bh(&srv->idr_lock); if (!srv->listener) { spin_unlock_bh(&srv->idr_lock); return; } lsock = srv->listener; spin_unlock_bh(&srv->idr_lock); while (1) { ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); return; } /* Register callbacks */ newsk = newsock->sk; write_lock_bh(&newsk->sk_callback_lock); newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); conn_put(con); } } /* tipc_topsrv_listener_data_ready - interrupt callback with connection request * The queued job is launched into tipc_topsrv_accept() */ static void tipc_topsrv_listener_data_ready(struct sock *sk) { struct tipc_topsrv *srv; trace_sk_data_ready(sk); read_lock_bh(&sk->sk_callback_lock); srv = sk->sk_user_data; if (srv) queue_work(srv->rcv_wq, &srv->awork); read_unlock_bh(&sk->sk_callback_lock); } static int tipc_topsrv_create_listener(struct tipc_topsrv *srv) { struct socket *lsock = NULL; struct sockaddr_tipc saddr; struct sock *sk; int rc; rc = sock_create_kern(srv->net, AF_TIPC, SOCK_SEQPACKET, 0, &lsock); if (rc < 0) return rc; srv->listener = lsock; sk = lsock->sk; write_lock_bh(&sk->sk_callback_lock); sk->sk_data_ready = tipc_topsrv_listener_data_ready; sk->sk_user_data = srv; write_unlock_bh(&sk->sk_callback_lock); lock_sock(sk); rc = tsk_set_importance(sk, TIPC_CRITICAL_IMPORTANCE); release_sock(sk); if (rc < 0) goto err; saddr.family = AF_TIPC; saddr.addrtype = TIPC_SERVICE_RANGE; saddr.addr.nameseq.type = TIPC_TOP_SRV; saddr.addr.nameseq.lower = TIPC_TOP_SRV; saddr.addr.nameseq.upper = TIPC_TOP_SRV; saddr.scope = TIPC_NODE_SCOPE; rc = tipc_sk_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr)); if (rc < 0) goto err; rc = kernel_listen(lsock, 0); if (rc < 0) goto err; /* As server's listening socket owner and creator is the same module, * we have to decrease TIPC module reference count to guarantee that * it remains zero after the server socket is created, otherwise, * executing "rmmod" command is unable to make TIPC module deleted * after TIPC module is inserted successfully. * * However, the reference count is ever increased twice in * sock_create_kern(): one is to increase the reference count of owner * of TIPC socket's proto_ops struct; another is to increment the * reference count of owner of TIPC proto struct. Therefore, we must * decrement the module reference count twice to ensure that it keeps * zero after server's listening socket is created. Of course, we * must bump the module reference count twice as well before the socket * is closed. */ module_put(lsock->ops->owner); module_put(sk->sk_prot_creator->owner); return 0; err: sock_release(lsock); return -EINVAL; } bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, u32 upper, u32 filter, int *conid) { struct tipc_subscr sub; struct tipc_conn *con; int rc; sub.seq.type = type; sub.seq.lower = lower; sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; *(u64 *)&sub.usr_handle = (u64)port; con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); if (rc) conn_put(con); conn_put(con); return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) { struct tipc_conn *con; con = tipc_conn_lookup(tipc_topsrv(net), conid); if (!con) return; test_and_clear_bit(CF_CONNECTED, &con->flags); tipc_conn_delete_sub(con, NULL); conn_put(con); conn_put(con); } static void tipc_topsrv_kern_evt(struct net *net, struct tipc_event *evt) { u32 port = *(u32 *)&evt->s.usr_handle; u32 self = tipc_own_addr(net); struct sk_buff_head evtq; struct sk_buff *skb; skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), self, self, port, port, 0); if (!skb) return; msg_set_dest_droppable(buf_msg(skb), true); memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); skb_queue_head_init(&evtq); __skb_queue_tail(&evtq, skb); tipc_loopback_trace(net, &evtq); tipc_sk_rcv(net, &evtq); } static int tipc_topsrv_work_start(struct tipc_topsrv *s) { s->rcv_wq = alloc_ordered_workqueue("tipc_rcv", 0); if (!s->rcv_wq) { pr_err("can't start tipc receive workqueue\n"); return -ENOMEM; } s->send_wq = alloc_ordered_workqueue("tipc_send", 0); if (!s->send_wq) { pr_err("can't start tipc send workqueue\n"); destroy_workqueue(s->rcv_wq); return -ENOMEM; } return 0; } static void tipc_topsrv_work_stop(struct tipc_topsrv *s) { destroy_workqueue(s->rcv_wq); destroy_workqueue(s->send_wq); } static int tipc_topsrv_start(struct net *net) { struct tipc_net *tn = tipc_net(net); const char name[] = "topology_server"; struct tipc_topsrv *srv; int ret; srv = kzalloc_obj(*srv, GFP_ATOMIC); if (!srv) return -ENOMEM; srv->net = net; INIT_WORK(&srv->awork, tipc_topsrv_accept); strscpy(srv->name, name, sizeof(srv->name)); tn->topsrv = srv; atomic_set(&tn->subscription_count, 0); spin_lock_init(&srv->idr_lock); idr_init(&srv->conn_idr); srv->idr_in_use = 0; ret = tipc_topsrv_work_start(srv); if (ret < 0) goto err_start; ret = tipc_topsrv_create_listener(srv); if (ret < 0) goto err_create; return 0; err_create: tipc_topsrv_work_stop(srv); err_start: kfree(srv); return ret; } static void tipc_topsrv_stop(struct net *net) { struct tipc_topsrv *srv = tipc_topsrv(net); struct socket *lsock = srv->listener; struct tipc_conn *con; int id; spin_lock_bh(&srv->idr_lock); for (id = 0; srv->idr_in_use; id++) { con = idr_find(&srv->conn_idr, id); if (con) { conn_get(con); spin_unlock_bh(&srv->idr_lock); tipc_conn_close(con); conn_put(con); spin_lock_bh(&srv->idr_lock); } } __module_get(lsock->ops->owner); __module_get(lsock->sk->sk_prot_creator->owner); srv->listener = NULL; spin_unlock_bh(&srv->idr_lock); tipc_topsrv_work_stop(srv); sock_release(lsock); idr_destroy(&srv->conn_idr); kfree(srv); } int __net_init tipc_topsrv_init_net(struct net *net) { return tipc_topsrv_start(net); } void __net_exit tipc_topsrv_exit_net(struct net *net) { tipc_topsrv_stop(net); } |
| 7 22 16 73 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mptcp #if !defined(_TRACE_MPTCP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MPTCP_H #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/tracepoint.h> #include <net/ipv6.h> #include <net/tcp.h> #include <linux/sock_diag.h> #include <net/rstreason.h> #define show_mapping_status(status) \ __print_symbolic(status, \ { 0, "MAPPING_OK" }, \ { 1, "MAPPING_INVALID" }, \ { 2, "MAPPING_EMPTY" }, \ { 3, "MAPPING_DATA_FIN" }, \ { 4, "MAPPING_DUMMY" }) TRACE_EVENT(mptcp_subflow_get_send, TP_PROTO(struct mptcp_subflow_context *subflow), TP_ARGS(subflow), TP_STRUCT__entry( __field(bool, active) __field(bool, free) __field(u32, snd_wnd) __field(u32, pace) __field(u8, backup) __field(u64, ratio) ), TP_fast_assign( struct sock *ssk; __entry->active = mptcp_subflow_active(subflow); __entry->backup = subflow->backup || subflow->request_bkup; if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock)) __entry->free = sk_stream_memory_free(subflow->tcp_sock); else __entry->free = 0; ssk = mptcp_subflow_tcp_sock(subflow); if (ssk && sk_fullsock(ssk)) { __entry->snd_wnd = tcp_sk(ssk)->snd_wnd; __entry->pace = READ_ONCE(ssk->sk_pacing_rate); } else { __entry->snd_wnd = 0; __entry->pace = 0; } if (ssk && sk_fullsock(ssk) && __entry->pace) __entry->ratio = div_u64((u64)ssk->sk_wmem_queued << 32, __entry->pace); else __entry->ratio = 0; ), TP_printk("active=%d free=%d snd_wnd=%u pace=%u backup=%u ratio=%llu", __entry->active, __entry->free, __entry->snd_wnd, __entry->pace, __entry->backup, __entry->ratio) ); DECLARE_EVENT_CLASS(mptcp_dump_mpext, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext), TP_STRUCT__entry( __field(u64, data_ack) __field(u64, data_seq) __field(u32, subflow_seq) __field(u16, data_len) __field(u16, csum) __field(u8, use_map) __field(u8, dsn64) __field(u8, data_fin) __field(u8, use_ack) __field(u8, ack64) __field(u8, mpc_map) __field(u8, frozen) __field(u8, reset_transient) __field(u8, reset_reason) __field(u8, csum_reqd) __field(u8, infinite_map) ), TP_fast_assign( __entry->data_ack = mpext->ack64 ? mpext->data_ack : mpext->data_ack32; __entry->data_seq = mpext->data_seq; __entry->subflow_seq = mpext->subflow_seq; __entry->data_len = mpext->data_len; __entry->csum = (__force u16)mpext->csum; __entry->use_map = mpext->use_map; __entry->dsn64 = mpext->dsn64; __entry->data_fin = mpext->data_fin; __entry->use_ack = mpext->use_ack; __entry->ack64 = mpext->ack64; __entry->mpc_map = mpext->mpc_map; __entry->frozen = mpext->frozen; __entry->reset_transient = mpext->reset_transient; __entry->reset_reason = mpext->reset_reason; __entry->csum_reqd = mpext->csum_reqd; __entry->infinite_map = mpext->infinite_map; ), TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u infinite_map=%u", __entry->data_ack, __entry->data_seq, __entry->subflow_seq, __entry->data_len, __entry->csum, __entry->use_map, __entry->dsn64, __entry->data_fin, __entry->use_ack, __entry->ack64, __entry->mpc_map, __entry->frozen, __entry->reset_transient, __entry->reset_reason, __entry->csum_reqd, __entry->infinite_map) ); DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext)); DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext)); TRACE_EVENT(ack_update_msk, TP_PROTO(u64 data_ack, u64 old_snd_una, u64 new_snd_una, u64 new_wnd_end, u64 msk_wnd_end), TP_ARGS(data_ack, old_snd_una, new_snd_una, new_wnd_end, msk_wnd_end), TP_STRUCT__entry( __field(u64, data_ack) __field(u64, old_snd_una) __field(u64, new_snd_una) __field(u64, new_wnd_end) __field(u64, msk_wnd_end) ), TP_fast_assign( __entry->data_ack = data_ack; __entry->old_snd_una = old_snd_una; __entry->new_snd_una = new_snd_una; __entry->new_wnd_end = new_wnd_end; __entry->msk_wnd_end = msk_wnd_end; ), TP_printk("data_ack=%llu old_snd_una=%llu new_snd_una=%llu new_wnd_end=%llu msk_wnd_end=%llu", __entry->data_ack, __entry->old_snd_una, __entry->new_snd_una, __entry->new_wnd_end, __entry->msk_wnd_end) ); TRACE_EVENT(subflow_check_data_avail, TP_PROTO(__u8 status, struct sk_buff *skb), TP_ARGS(status, skb), TP_STRUCT__entry( __field(u8, status) __field(const void *, skb) ), TP_fast_assign( __entry->status = status; __entry->skb = skb; ), TP_printk("mapping_status=%s, skb=%p", show_mapping_status(__entry->status), __entry->skb) ); #include <trace/events/net_probe_common.h> TRACE_EVENT(mptcp_rcvbuf_grow, TP_PROTO(struct sock *sk, int time), TP_ARGS(sk, time), TP_STRUCT__entry( __field(int, time) __field(__u32, rtt_us) __field(__u32, copied) __field(__u32, inq) __field(__u32, space) __field(__u32, ooo_space) __field(__u32, rcvbuf) __field(__u32, rcv_wnd) __field(__u8, scaling_ratio) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(const void *, skaddr) ), TP_fast_assign( struct mptcp_sock *msk = mptcp_sk(sk); struct inet_sock *inet = inet_sk(sk); bool ofo_empty; __be32 *p32; __entry->time = time; __entry->rtt_us = mptcp_rtt_us_est(msk) >> 3; __entry->copied = msk->rcvq_space.copied; __entry->inq = mptcp_inq_hint(sk); __entry->space = msk->rcvq_space.space; ofo_empty = RB_EMPTY_ROOT(&msk->out_of_order_queue); __entry->ooo_space = ofo_empty ? 0 : MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; __entry->rcvbuf = sk->sk_rcvbuf; __entry->rcv_wnd = atomic64_read(&msk->rcv_wnd_sent) - msk->ack_seq; __entry->scaling_ratio = msk->scaling_ratio; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->family = sk->sk_family; p32 = (__be32 *)__entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *)__entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); __entry->skaddr = sk; ), TP_printk("time=%u rtt_us=%u copied=%u inq=%u space=%u ooo=%u scaling_ratio=%u " "rcvbuf=%u rcv_wnd=%u family=%d sport=%hu dport=%hu saddr=%pI4 " "daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c skaddr=%p", __entry->time, __entry->rtt_us, __entry->copied, __entry->inq, __entry->space, __entry->ooo_space, __entry->scaling_ratio, __entry->rcvbuf, __entry->rcv_wnd, __entry->family, __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->skaddr) ); #endif /* _TRACE_MPTCP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DMA_MAPPING_H #define _LINUX_DMA_MAPPING_H #include <linux/device.h> #include <linux/err.h> #include <linux/dma-direction.h> #include <linux/scatterlist.h> #include <linux/bug.h> #include <linux/cache.h> /* * List of possible attributes associated with a DMA mapping. The semantics * of each attribute should be defined in Documentation/core-api/dma-attributes.rst. */ /* * DMA_ATTR_WEAK_ORDERING: Specifies that reads and writes to the mapping * may be weakly ordered, that is that reads and writes may pass each other. */ #define DMA_ATTR_WEAK_ORDERING (1UL << 1) /* * DMA_ATTR_WRITE_COMBINE: Specifies that writes to the mapping may be * buffered to improve performance. */ #define DMA_ATTR_WRITE_COMBINE (1UL << 2) /* * DMA_ATTR_NO_KERNEL_MAPPING: Lets the platform to avoid creating a kernel * virtual mapping for the allocated buffer. */ #define DMA_ATTR_NO_KERNEL_MAPPING (1UL << 4) /* * DMA_ATTR_SKIP_CPU_SYNC: Allows platform code to skip synchronization of * the CPU cache for the given buffer assuming that it has been already * transferred to 'device' domain. */ #define DMA_ATTR_SKIP_CPU_SYNC (1UL << 5) /* * DMA_ATTR_FORCE_CONTIGUOUS: Forces contiguous allocation of the buffer * in physical memory. */ #define DMA_ATTR_FORCE_CONTIGUOUS (1UL << 6) /* * DMA_ATTR_ALLOC_SINGLE_PAGES: This is a hint to the DMA-mapping subsystem * that it's probably not worth the time to try to allocate memory to in a way * that gives better TLB efficiency. */ #define DMA_ATTR_ALLOC_SINGLE_PAGES (1UL << 7) /* * DMA_ATTR_NO_WARN: This tells the DMA-mapping subsystem to suppress * allocation failure reports (similarly to __GFP_NOWARN). */ #define DMA_ATTR_NO_WARN (1UL << 8) /* * DMA_ATTR_PRIVILEGED: used to indicate that the buffer is fully * accessible at an elevated privilege level (and ideally inaccessible or * at least read-only at lesser-privileged levels). */ #define DMA_ATTR_PRIVILEGED (1UL << 9) /* * DMA_ATTR_MMIO - Indicates memory-mapped I/O (MMIO) region for DMA mapping * * This attribute indicates the physical address is not normal system * memory. It may not be used with kmap*()/phys_to_virt()/phys_to_page() * functions, it may not be cacheable, and access using CPU load/store * instructions may not be allowed. * * Usually this will be used to describe MMIO addresses, or other non-cacheable * register addresses. When DMA mapping this sort of address we call * the operation Peer to Peer as a one device is DMA'ing to another device. * For PCI devices the p2pdma APIs must be used to determine if DMA_ATTR_MMIO * is appropriate. * * For architectures that require cache flushing for DMA coherence * DMA_ATTR_MMIO will not perform any cache flushing. The address * provided must never be mapped cacheable into the CPU. */ #define DMA_ATTR_MMIO (1UL << 10) /* * DMA_ATTR_DEBUGGING_IGNORE_CACHELINES: Indicates the CPU cache line can be * overlapped. All mappings sharing a cacheline must have this attribute for * this to be considered safe. */ #define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES (1UL << 11) /* * DMA_ATTR_REQUIRE_COHERENT: Indicates that DMA coherency is required. * All mappings that carry this attribute can't work with SWIOTLB and cache * flushing. */ #define DMA_ATTR_REQUIRE_COHERENT (1UL << 12) /* * DMA_ATTR_CC_SHARED: Indicates the DMA mapping is shared (decrypted) for * confidential computing guests. For normal system memory the caller must have * called set_memory_decrypted(), and pgprot_decrypted must be used when * creating CPU PTEs for the mapping. The same shared semantic may be passed * to the vIOMMU when it sets up the IOPTE. For MMIO use together with * DMA_ATTR_MMIO to indicate shared MMIO. Unless DMA_ATTR_MMIO is provided * a struct page is required. */ #define DMA_ATTR_CC_SHARED (1UL << 13) /* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can * be given to a device to use as a DMA source or target. It is specific to a * given device and there may be a translation between the CPU physical address * space and the bus address space. * * DMA_MAPPING_ERROR is the magic error code if a mapping failed. It should not * be used directly in drivers, but checked for using dma_mapping_error() * instead. */ #define DMA_MAPPING_ERROR (~(dma_addr_t)0) #define DMA_BIT_MASK(n) GENMASK_ULL((n) - 1, 0) struct dma_iova_state { dma_addr_t addr; u64 __size; }; /* * Use the high bit to mark if we used swiotlb for one or more ranges. */ #define DMA_IOVA_USE_SWIOTLB (1ULL << 63) static inline size_t dma_iova_size(struct dma_iova_state *state) { /* Casting is needed for 32-bits systems */ return (size_t)(state->__size & ~DMA_IOVA_USE_SWIOTLB); } #ifdef CONFIG_DMA_API_DEBUG void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); void debug_dma_map_single(struct device *dev, const void *addr, unsigned long len); #else static inline void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { } static inline void debug_dma_map_single(struct device *dev, const void *addr, unsigned long len) { } #endif /* CONFIG_DMA_API_DEBUG */ #ifdef CONFIG_HAS_DMA static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { debug_dma_mapping_error(dev, dma_addr); if (unlikely(dma_addr == DMA_MAPPING_ERROR)) return -ENOMEM; return 0; } dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, size_t offset, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs); dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs); unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs); int dma_map_sgtable(struct device *dev, struct sg_table *sgt, enum dma_data_direction dir, unsigned long attrs); dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs); void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs); void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs); void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle); int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); bool dma_can_mmap(struct device *dev); bool dma_pci_p2pdma_supported(struct device *dev); int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); u64 dma_get_required_mask(struct device *dev); bool dma_addressing_limited(struct device *dev); size_t dma_max_mapping_size(struct device *dev); size_t dma_opt_mapping_size(struct device *dev); unsigned long dma_get_merge_boundary(struct device *dev); struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); void dma_free_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt, enum dma_data_direction dir); void *dma_vmap_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt); void dma_vunmap_noncontiguous(struct device *dev, void *vaddr); int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, size_t size, struct sg_table *sgt); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, size_t offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { return DMA_MAPPING_ERROR; } static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { } static inline dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs) { return DMA_MAPPING_ERROR; } static inline void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { } static inline unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { return 0; } static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { } static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt, enum dma_data_direction dir, unsigned long attrs) { return -EOPNOTSUPP; } static inline dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { return DMA_MAPPING_ERROR; } static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { } static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return -ENOMEM; } static inline void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs) { return NULL; } static inline void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) { } static inline void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { return NULL; } static inline void dmam_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle) { } static inline int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { return -ENXIO; } static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { return -ENXIO; } static inline bool dma_can_mmap(struct device *dev) { return false; } static inline bool dma_pci_p2pdma_supported(struct device *dev) { return false; } static inline int dma_set_mask(struct device *dev, u64 mask) { return -EIO; } static inline int dma_set_coherent_mask(struct device *dev, u64 mask) { return -EIO; } static inline u64 dma_get_required_mask(struct device *dev) { return 0; } static inline bool dma_addressing_limited(struct device *dev) { return false; } static inline size_t dma_max_mapping_size(struct device *dev) { return 0; } static inline size_t dma_opt_mapping_size(struct device *dev) { return 0; } static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; } static inline struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs) { return NULL; } static inline void dma_free_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt, enum dma_data_direction dir) { } static inline void *dma_vmap_noncontiguous(struct device *dev, size_t size, struct sg_table *sgt) { return NULL; } static inline void dma_vunmap_noncontiguous(struct device *dev, void *vaddr) { } static inline int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma, size_t size, struct sg_table *sgt) { return -EINVAL; } #endif /* CONFIG_HAS_DMA */ #ifdef CONFIG_IOMMU_DMA /** * dma_use_iova - check if the IOVA API is used for this state * @state: IOVA state * * Return %true if the DMA transfers uses the dma_iova_*() calls or %false if * they can't be used. */ static inline bool dma_use_iova(struct dma_iova_state *state) { return state->__size != 0; } bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state, phys_addr_t phys, size_t size); void dma_iova_free(struct device *dev, struct dma_iova_state *state); void dma_iova_destroy(struct device *dev, struct dma_iova_state *state, size_t mapped_len, enum dma_data_direction dir, unsigned long attrs); int dma_iova_sync(struct device *dev, struct dma_iova_state *state, size_t offset, size_t size); int dma_iova_link(struct device *dev, struct dma_iova_state *state, phys_addr_t phys, size_t offset, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_iova_unlink(struct device *dev, struct dma_iova_state *state, size_t offset, size_t size, enum dma_data_direction dir, unsigned long attrs); #else /* CONFIG_IOMMU_DMA */ static inline bool dma_use_iova(struct dma_iova_state *state) { return false; } static inline bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state, phys_addr_t phys, size_t size) { return false; } static inline void dma_iova_free(struct device *dev, struct dma_iova_state *state) { } static inline void dma_iova_destroy(struct device *dev, struct dma_iova_state *state, size_t mapped_len, enum dma_data_direction dir, unsigned long attrs) { } static inline int dma_iova_sync(struct device *dev, struct dma_iova_state *state, size_t offset, size_t size) { return -EOPNOTSUPP; } static inline int dma_iova_link(struct device *dev, struct dma_iova_state *state, phys_addr_t phys, size_t offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { return -EOPNOTSUPP; } static inline void dma_iova_unlink(struct device *dev, struct dma_iova_state *state, size_t offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { } #endif /* CONFIG_IOMMU_DMA */ #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir); void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir); void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr); static inline bool dma_dev_need_sync(const struct device *dev) { /* Always call DMA sync operations when debugging is enabled */ return !dev_dma_skip_sync(dev) || IS_ENABLED(CONFIG_DMA_API_DEBUG); } static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { if (dma_dev_need_sync(dev)) __dma_sync_single_for_cpu(dev, addr, size, dir); } static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { if (dma_dev_need_sync(dev)) __dma_sync_single_for_device(dev, addr, size, dir); } static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { if (dma_dev_need_sync(dev)) __dma_sync_sg_for_cpu(dev, sg, nelems, dir); } static inline void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { if (dma_dev_need_sync(dev)) __dma_sync_sg_for_device(dev, sg, nelems, dir); } static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) { return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false; } bool dma_need_unmap(struct device *dev); #else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ static inline bool dma_dev_need_sync(const struct device *dev) { return false; } static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { } static inline void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { } static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { } static inline void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir) { } static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) { return false; } static inline bool dma_need_unmap(struct device *dev) { return false; } #endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir); int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma, size_t size, struct page *page); static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) { struct page *page = dma_alloc_pages(dev, size, dma_handle, dir, gfp); return page ? page_address(page) : NULL; } static inline void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir) { dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir); } static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) { /* DMA must never operate on areas that might be remapped. */ if (dev_WARN_ONCE(dev, is_vmalloc_addr(ptr), "rejecting DMA map of vmalloc memory\n")) return DMA_MAPPING_ERROR; debug_dma_map_single(dev, ptr, size); return dma_map_page_attrs(dev, virt_to_page(ptr), offset_in_page(ptr), size, dir, attrs); } static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { return dma_unmap_page_attrs(dev, addr, size, dir, attrs); } static inline void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir) { return dma_sync_single_for_cpu(dev, addr + offset, size, dir); } static inline void dma_sync_single_range_for_device(struct device *dev, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir) { return dma_sync_single_for_device(dev, addr + offset, size, dir); } /** * dma_unmap_sgtable - Unmap the given buffer for DMA * @dev: The device for which to perform the DMA operation * @sgt: The sg_table object describing the buffer * @dir: DMA direction * @attrs: Optional DMA attributes for the unmap operation * * Unmaps a buffer described by a scatterlist stored in the given sg_table * object for the @dir DMA operation by the @dev device. After this function * the ownership of the buffer is transferred back to the CPU domain. */ static inline void dma_unmap_sgtable(struct device *dev, struct sg_table *sgt, enum dma_data_direction dir, unsigned long attrs) { dma_unmap_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs); } /** * dma_sync_sgtable_for_cpu - Synchronize the given buffer for CPU access * @dev: The device for which to perform the DMA operation * @sgt: The sg_table object describing the buffer * @dir: DMA direction * * Performs the needed cache synchronization and moves the ownership of the * buffer back to the CPU domain, so it is safe to perform any access to it * by the CPU. Before doing any further DMA operations, one has to transfer * the ownership of the buffer back to the DMA domain by calling the * dma_sync_sgtable_for_device(). */ static inline void dma_sync_sgtable_for_cpu(struct device *dev, struct sg_table *sgt, enum dma_data_direction dir) { dma_sync_sg_for_cpu(dev, sgt->sgl, sgt->orig_nents, dir); } /** * dma_sync_sgtable_for_device - Synchronize the given buffer for DMA * @dev: The device for which to perform the DMA operation * @sgt: The sg_table object describing the buffer * @dir: DMA direction * * Performs the needed cache synchronization and moves the ownership of the * buffer back to the DMA domain, so it is safe to perform the DMA operation. * Once finished, one has to call dma_sync_sgtable_for_cpu() or * dma_unmap_sgtable(). */ static inline void dma_sync_sgtable_for_device(struct device *dev, struct sg_table *sgt, enum dma_data_direction dir) { dma_sync_sg_for_device(dev, sgt->sgl, sgt->orig_nents, dir); } #define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0) #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0) #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0) #define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, 0) #define dma_map_page(d, p, o, s, r) dma_map_page_attrs(d, p, o, s, r, 0) #define dma_unmap_page(d, a, s, r) dma_unmap_page_attrs(d, a, s, r, 0) #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size); static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { return dma_alloc_attrs(dev, size, dma_handle, gfp, (gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0); } static inline void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) { return dma_free_attrs(dev, size, cpu_addr, dma_handle, 0); } static inline u64 dma_get_mask(struct device *dev) { if (dev->dma_mask && *dev->dma_mask) return *dev->dma_mask; return DMA_BIT_MASK(32); } /* * Set both the DMA mask and the coherent DMA mask to the same thing. * Note that we don't check the return value from dma_set_coherent_mask() * as the DMA API guarantees that the coherent DMA mask can be set to * the same or smaller than the streaming DMA mask. */ static inline int dma_set_mask_and_coherent(struct device *dev, u64 mask) { int rc = dma_set_mask(dev, mask); if (rc == 0) dma_set_coherent_mask(dev, mask); return rc; } /* * Similar to the above, except it deals with the case where the device * does not have dev->dma_mask appropriately setup. */ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) { dev->dma_mask = &dev->coherent_dma_mask; return dma_set_mask_and_coherent(dev, mask); } static inline unsigned int dma_get_max_seg_size(struct device *dev) { if (dev->dma_parms && dev->dma_parms->max_segment_size) return dev->dma_parms->max_segment_size; return SZ_64K; } static inline void dma_set_max_seg_size(struct device *dev, unsigned int size) { if (WARN_ON_ONCE(!dev->dma_parms)) return; dev->dma_parms->max_segment_size = size; } static inline unsigned long dma_get_seg_boundary(struct device *dev) { if (dev->dma_parms && dev->dma_parms->segment_boundary_mask) return dev->dma_parms->segment_boundary_mask; return ULONG_MAX; } /** * dma_get_seg_boundary_nr_pages - return the segment boundary in "page" units * @dev: device to guery the boundary for * @page_shift: ilog() of the IOMMU page size * * Return the segment boundary in IOMMU page units (which may be different from * the CPU page size) for the passed in device. * * If @dev is NULL a boundary of U32_MAX is assumed, this case is just for * non-DMA API callers. */ static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev, unsigned int page_shift) { if (!dev) return (U32_MAX >> page_shift) + 1; return (dma_get_seg_boundary(dev) >> page_shift) + 1; } static inline void dma_set_seg_boundary(struct device *dev, unsigned long mask) { if (WARN_ON_ONCE(!dev->dma_parms)) return; dev->dma_parms->segment_boundary_mask = mask; } static inline unsigned int dma_get_min_align_mask(struct device *dev) { if (dev->dma_parms) return dev->dma_parms->min_align_mask; return 0; } static inline void dma_set_min_align_mask(struct device *dev, unsigned int min_align_mask) { if (WARN_ON_ONCE(!dev->dma_parms)) return; dev->dma_parms->min_align_mask = min_align_mask; } #ifndef dma_get_cache_alignment static inline int dma_get_cache_alignment(void) { #ifdef ARCH_HAS_DMA_MINALIGN return ARCH_DMA_MINALIGN; #endif return 1; } #endif #ifdef ARCH_HAS_DMA_MINALIGN #define ____dma_from_device_aligned __aligned(ARCH_DMA_MINALIGN) #else #define ____dma_from_device_aligned #endif /* Mark start of DMA buffer */ #define __dma_from_device_group_begin(GROUP) \ __cacheline_group_begin(GROUP) ____dma_from_device_aligned /* Mark end of DMA buffer */ #define __dma_from_device_group_end(GROUP) \ __cacheline_group_end(GROUP) ____dma_from_device_aligned static inline void *dmam_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { return dmam_alloc_attrs(dev, size, dma_handle, gfp, (gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0); } static inline void *dma_alloc_wc(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t gfp) { unsigned long attrs = DMA_ATTR_WRITE_COMBINE; if (gfp & __GFP_NOWARN) attrs |= DMA_ATTR_NO_WARN; return dma_alloc_attrs(dev, size, dma_addr, gfp, attrs); } static inline void dma_free_wc(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr) { return dma_free_attrs(dev, size, cpu_addr, dma_addr, DMA_ATTR_WRITE_COMBINE); } static inline int dma_mmap_wc(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size) { return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, DMA_ATTR_WRITE_COMBINE); } #ifdef CONFIG_NEED_DMA_MAP_STATE #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME #define DEFINE_DMA_UNMAP_LEN(LEN_NAME) __u32 LEN_NAME #define dma_unmap_addr(PTR, ADDR_NAME) ((PTR)->ADDR_NAME) #define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) (((PTR)->ADDR_NAME) = (VAL)) #define dma_unmap_len(PTR, LEN_NAME) ((PTR)->LEN_NAME) #define dma_unmap_len_set(PTR, LEN_NAME, VAL) (((PTR)->LEN_NAME) = (VAL)) #else #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME) #define DEFINE_DMA_UNMAP_LEN(LEN_NAME) #define dma_unmap_addr(PTR, ADDR_NAME) \ ({ typeof(PTR) __p __maybe_unused = PTR; 0; }) #define dma_unmap_addr_set(PTR, ADDR_NAME, VAL) \ do { typeof(PTR) __p __maybe_unused = PTR; } while (0) #define dma_unmap_len(PTR, LEN_NAME) \ ({ typeof(PTR) __p __maybe_unused = PTR; 0; }) #define dma_unmap_len_set(PTR, LEN_NAME, VAL) \ do { typeof(PTR) __p __maybe_unused = PTR; } while (0) #endif #endif /* _LINUX_DMA_MAPPING_H */ |
| 3306 551 1480 1479 1480 201 163 358 159 650 571 571 176 175 148 148 1758 986 510 282 427 54 327 372 6 143 143 143 143 143 139 126 142 141 3254 1814 917 418 143 203 1272 785 745 37 29 18 11 1034 302 729 9 9 9 868 868 55 872 14 4 2 1 179 280 281 189 190 190 23 181 734 653 95 604 277 731 4 731 714 2 723 96 10 722 43 724 725 150 1 726 16 724 43 725 716 34 281 173 178 733 732 732 110 731 733 715 222 732 245 137 214 123 196 35 731 43 2 734 730 221 712 415 715 715 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/math64.h> #include <linux/string.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) { /* ubuf and len_total should both be specified (or not) together */ if (!!log->ubuf != !!log->len_total) return false; /* log buf without log_level is meaningless */ if (log->ubuf && log->level == 0) return false; if (log->level & ~BPF_LOG_MASK) return false; if (log->len_total > UINT_MAX >> 2) return false; return true; } int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, char __user *log_buf, u32 log_size) { log->level = log_level; log->ubuf = log_buf; log->len_total = log_size; /* log attributes have to be sane */ if (!bpf_verifier_log_attr_valid(log)) return -EINVAL; return 0; } static void bpf_vlog_update_len_max(struct bpf_verifier_log *log, u32 add_len) { /* add_len includes terminal \0, so no need for +1. */ u64 len = log->end_pos + add_len; /* log->len_max could be larger than our current len due to * bpf_vlog_reset() calls, so we maintain the max of any length at any * previous point */ if (len > UINT_MAX) log->len_max = UINT_MAX; else if (len > log->len_max) log->len_max = len; } void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args) { u64 cur_pos; u32 new_n, n; n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); if (log->level == BPF_LOG_KERNEL) { bool newline = n > 0 && log->kbuf[n - 1] == '\n'; pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); return; } n += 1; /* include terminating zero */ bpf_vlog_update_len_max(log, n); if (log->level & BPF_LOG_FIXED) { /* check if we have at least something to put into user buf */ new_n = 0; if (log->end_pos < log->len_total) { new_n = min_t(u32, log->len_total - log->end_pos, n); log->kbuf[new_n - 1] = '\0'; } cur_pos = log->end_pos; log->end_pos += n - 1; /* don't count terminating '\0' */ if (log->ubuf && new_n && copy_to_user(log->ubuf + cur_pos, log->kbuf, new_n)) goto fail; } else { u64 new_end, new_start; u32 buf_start, buf_end; new_end = log->end_pos + n; if (new_end - log->start_pos >= log->len_total) new_start = new_end - log->len_total; else new_start = log->start_pos; log->start_pos = new_start; log->end_pos = new_end - 1; /* don't count terminating '\0' */ if (!log->ubuf) return; new_n = min(n, log->len_total); cur_pos = new_end - new_n; div_u64_rem(cur_pos, log->len_total, &buf_start); div_u64_rem(new_end, log->len_total, &buf_end); /* new_end and buf_end are exclusive indices, so if buf_end is * exactly zero, then it actually points right to the end of * ubuf and there is no wrap around */ if (buf_end == 0) buf_end = log->len_total; /* if buf_start > buf_end, we wrapped around; * if buf_start == buf_end, then we fill ubuf completely; we * can't have buf_start == buf_end to mean that there is * nothing to write, because we always write at least * something, even if terminal '\0' */ if (buf_start < buf_end) { /* message fits within contiguous chunk of ubuf */ if (copy_to_user(log->ubuf + buf_start, log->kbuf + n - new_n, buf_end - buf_start)) goto fail; } else { /* message wraps around the end of ubuf, copy in two chunks */ if (copy_to_user(log->ubuf + buf_start, log->kbuf + n - new_n, log->len_total - buf_start)) goto fail; if (copy_to_user(log->ubuf, log->kbuf + n - buf_end, buf_end)) goto fail; } } return; fail: log->ubuf = NULL; } void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos) { char zero = 0; u32 pos; if (WARN_ON_ONCE(new_pos > log->end_pos)) return; if (!bpf_verifier_log_needed(log) || log->level == BPF_LOG_KERNEL) return; /* if position to which we reset is beyond current log window, * then we didn't preserve any useful content and should adjust * start_pos to end up with an empty log (start_pos == end_pos) */ log->end_pos = new_pos; if (log->end_pos < log->start_pos) log->start_pos = log->end_pos; if (!log->ubuf) return; if (log->level & BPF_LOG_FIXED) pos = log->end_pos + 1; else div_u64_rem(new_pos, log->len_total, &pos); if (pos < log->len_total && put_user(zero, log->ubuf + pos)) log->ubuf = NULL; } static void bpf_vlog_reverse_kbuf(char *buf, int len) { int i, j; for (i = 0, j = len - 1; i < j; i++, j--) swap(buf[i], buf[j]); } static int bpf_vlog_reverse_ubuf(struct bpf_verifier_log *log, int start, int end) { /* we split log->kbuf into two equal parts for both ends of array */ int n = sizeof(log->kbuf) / 2, nn; char *lbuf = log->kbuf, *rbuf = log->kbuf + n; /* Read ubuf's section [start, end) two chunks at a time, from left * and right side; within each chunk, swap all the bytes; after that * reverse the order of lbuf and rbuf and write result back to ubuf. * This way we'll end up with swapped contents of specified * [start, end) ubuf segment. */ while (end - start > 1) { nn = min(n, (end - start ) / 2); if (copy_from_user(lbuf, log->ubuf + start, nn)) return -EFAULT; if (copy_from_user(rbuf, log->ubuf + end - nn, nn)) return -EFAULT; bpf_vlog_reverse_kbuf(lbuf, nn); bpf_vlog_reverse_kbuf(rbuf, nn); /* we write lbuf to the right end of ubuf, while rbuf to the * left one to end up with properly reversed overall ubuf */ if (copy_to_user(log->ubuf + start, rbuf, nn)) return -EFAULT; if (copy_to_user(log->ubuf + end - nn, lbuf, nn)) return -EFAULT; start += nn; end -= nn; } return 0; } int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual) { u32 sublen; int err; *log_size_actual = 0; if (!log || log->level == 0 || log->level == BPF_LOG_KERNEL) return 0; if (!log->ubuf) goto skip_log_rotate; /* If we never truncated log, there is nothing to move around. */ if (log->start_pos == 0) goto skip_log_rotate; /* Otherwise we need to rotate log contents to make it start from the * buffer beginning and be a continuous zero-terminated string. Note * that if log->start_pos != 0 then we definitely filled up entire log * buffer with no gaps, and we just need to shift buffer contents to * the left by (log->start_pos % log->len_total) bytes. * * Unfortunately, user buffer could be huge and we don't want to * allocate temporary kernel memory of the same size just to shift * contents in a straightforward fashion. Instead, we'll be clever and * do in-place array rotation. This is a leetcode-style problem, which * could be solved by three rotations. * * Let's say we have log buffer that has to be shifted left by 7 bytes * (spaces and vertical bar is just for demonstrative purposes): * E F G H I J K | A B C D * * First, we reverse entire array: * D C B A | K J I H G F E * * Then we rotate first 4 bytes (DCBA) and separately last 7 bytes * (KJIHGFE), resulting in a properly rotated array: * A B C D | E F G H I J K * * We'll utilize log->kbuf to read user memory chunk by chunk, swap * bytes, and write them back. Doing it byte-by-byte would be * unnecessarily inefficient. Altogether we are going to read and * write each byte twice, for total 4 memory copies between kernel and * user space. */ /* length of the chopped off part that will be the beginning; * len(ABCD) in the example above */ div_u64_rem(log->start_pos, log->len_total, &sublen); sublen = log->len_total - sublen; err = bpf_vlog_reverse_ubuf(log, 0, log->len_total); err = err ?: bpf_vlog_reverse_ubuf(log, 0, sublen); err = err ?: bpf_vlog_reverse_ubuf(log, sublen, log->len_total); if (err) log->ubuf = NULL; skip_log_rotate: *log_size_actual = log->len_max; /* properly initialized log has either both ubuf!=NULL and len_total>0 * or ubuf==NULL and len_total==0, so if this condition doesn't hold, * we got a fault somewhere along the way, so report it back */ if (!!log->ubuf != !!log->len_total) return -EFAULT; /* did truncation actually happen? */ if (log->ubuf && log->len_max > log->len_total) return -ENOSPC; return 0; } /* log_level controls verbosity level of eBPF verifier. * bpf_verifier_log_write() is used to dump the verification trace to the log, * so the user can figure out what's wrong with the program */ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } EXPORT_SYMBOL_GPL(bpf_verifier_log_write); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(log)) return; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } EXPORT_SYMBOL_GPL(bpf_log); static const char *ltrim(const char *s) { while (isspace(*s)) s++; return s; } __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...) { const struct bpf_line_info *linfo, *prev_linfo; const struct btf *btf; const char *s, *fname; if (!bpf_verifier_log_needed(&env->log)) return; prev_linfo = env->prev_linfo; linfo = bpf_find_linfo(env->prog, insn_off); if (!linfo || linfo == prev_linfo) return; /* It often happens that two separate linfo records point to the same * source code line, but have differing column numbers. Given verifier * log doesn't emit column information, from user perspective we just * end up emitting the same source code line twice unnecessarily. * So instead check that previous and current linfo record point to * the same file (file_name_offs match) and the same line number, and * avoid emitting duplicated source code line in such case. */ if (prev_linfo && linfo->file_name_off == prev_linfo->file_name_off && BPF_LINE_INFO_LINE_NUM(linfo->line_col) == BPF_LINE_INFO_LINE_NUM(prev_linfo->line_col)) return; if (prefix_fmt) { va_list args; va_start(args, prefix_fmt); bpf_verifier_vlog(&env->log, prefix_fmt, args); va_end(args); } btf = env->prog->aux->btf; s = ltrim(btf_name_by_offset(btf, linfo->line_off)); verbose(env, "%s", s); /* source code line */ s = btf_name_by_offset(btf, linfo->file_name_off); /* leave only file name */ fname = strrchr(s, '/'); fname = fname ? fname + 1 : s; verbose(env, " @ %s:%u\n", fname, BPF_LINE_INFO_LINE_NUM(linfo->line_col)); env->prev_linfo = linfo; } static const char *btf_type_name(const struct btf *btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } /* string representation of 'enum bpf_reg_type' * * Note that reg_type_str() can not appear more than once in a single verbose() * statement. */ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) { char postfix[16] = {0}, prefix[64] = {0}; static const char * const str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "scalar", [PTR_TO_CTX] = "ctx", [CONST_PTR_TO_MAP] = "map_ptr", [PTR_TO_MAP_VALUE] = "map_value", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", [PTR_TO_SOCKET] = "sock", [PTR_TO_SOCK_COMMON] = "sock_common", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_MEM] = "mem", [PTR_TO_ARENA] = "arena", [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_INSN] = "insn", [PTR_TO_MAP_KEY] = "map_key", [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", }; if (type & PTR_MAYBE_NULL) { if (base_type(type) == PTR_TO_BTF_ID) strscpy(postfix, "or_null_"); else strscpy(postfix, "_or_null"); } snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", type & MEM_RDONLY ? "rdonly_" : "", type & MEM_RINGBUF ? "ringbuf_" : "", type & MEM_USER ? "user_" : "", type & MEM_PERCPU ? "percpu_" : "", type & MEM_RCU ? "rcu_" : "", type & PTR_UNTRUSTED ? "untrusted_" : "", type & PTR_TRUSTED ? "trusted_" : "" ); snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); return env->tmp_str_buf; } const char *dynptr_type_str(enum bpf_dynptr_type type) { switch (type) { case BPF_DYNPTR_TYPE_LOCAL: return "local"; case BPF_DYNPTR_TYPE_RINGBUF: return "ringbuf"; case BPF_DYNPTR_TYPE_SKB: return "skb"; case BPF_DYNPTR_TYPE_XDP: return "xdp"; case BPF_DYNPTR_TYPE_SKB_META: return "skb_meta"; case BPF_DYNPTR_TYPE_FILE: return "file"; case BPF_DYNPTR_TYPE_INVALID: return "<invalid>"; default: WARN_ONCE(1, "unknown dynptr type %d\n", type); return "<unknown>"; } } const char *iter_type_str(const struct btf *btf, u32 btf_id) { if (!btf || btf_id == 0) return "<invalid>"; /* we already validated that type is valid and has conforming name */ return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1; } const char *iter_state_str(enum bpf_iter_state state) { switch (state) { case BPF_ITER_STATE_ACTIVE: return "active"; case BPF_ITER_STATE_DRAINED: return "drained"; case BPF_ITER_STATE_INVALID: return "<invalid>"; default: WARN_ONCE(1, "unknown iter state %d\n", state); return "<unknown>"; } } static char slot_type_char[] = { [STACK_INVALID] = '?', [STACK_SPILL] = 'r', [STACK_MISC] = 'm', [STACK_ZERO] = '0', [STACK_DYNPTR] = 'd', [STACK_ITER] = 'i', [STACK_IRQ_FLAG] = 'f', [STACK_POISON] = 'p', }; #define UNUM_MAX_DECIMAL U16_MAX #define SNUM_MAX_DECIMAL S16_MAX #define SNUM_MIN_DECIMAL S16_MIN static bool is_unum_decimal(u64 num) { return num <= UNUM_MAX_DECIMAL; } static bool is_snum_decimal(s64 num) { return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL; } static void verbose_unum(struct bpf_verifier_env *env, u64 num) { if (is_unum_decimal(num)) verbose(env, "%llu", num); else verbose(env, "%#llx", num); } static void verbose_snum(struct bpf_verifier_env *env, s64 num) { if (is_snum_decimal(num)) verbose(env, "%lld", num); else verbose(env, "%#llx", num); } int tnum_strn(char *str, size_t size, struct tnum a) { /* print as a constant, if tnum is fully known */ if (a.mask == 0) { if (is_unum_decimal(a.value)) return snprintf(str, size, "%llu", a.value); if (is_snum_decimal(a.value)) return snprintf(str, size, "%lld", a.value); else return snprintf(str, size, "%#llx", a.value); } return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); } EXPORT_SYMBOL_GPL(tnum_strn); static void print_scalar_ranges(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char **sep) { /* For signed ranges, we want to unify 64-bit and 32-bit values in the * output as much as possible, but there is a bit of a complication. * If we choose to print values as decimals, this is natural to do, * because negative 64-bit and 32-bit values >= -S32_MIN have the same * representation due to sign extension. But if we choose to print * them in hex format (see is_snum_decimal()), then sign extension is * misleading. * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two * very different numbers. * So we avoid sign extension if we choose to print values in hex. */ struct { const char *name; u64 val; bool omit; } minmaxs[] = { {"smin", reg->smin_value, reg->smin_value == S64_MIN}, {"smax", reg->smax_value, reg->smax_value == S64_MAX}, {"umin", reg->umin_value, reg->umin_value == 0}, {"umax", reg->umax_value, reg->umax_value == U64_MAX}, {"smin32", is_snum_decimal((s64)reg->s32_min_value) ? (s64)reg->s32_min_value : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN}, {"smax32", is_snum_decimal((s64)reg->s32_max_value) ? (s64)reg->s32_max_value : (u32)reg->s32_max_value, reg->s32_max_value == S32_MAX}, {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; bool neg1, neg2; for (m1 = &minmaxs[0]; m1 < mend; m1++) { if (m1->omit) continue; neg1 = m1->name[0] == 's' && (s64)m1->val < 0; verbose(env, "%s%s=", *sep, m1->name); *sep = ","; for (m2 = m1 + 2; m2 < mend; m2 += 2) { if (m2->omit || m2->val != m1->val) continue; /* don't mix negatives with positives */ neg2 = m2->name[0] == 's' && (s64)m2->val < 0; if (neg2 != neg1) continue; m2->omit = true; verbose(env, "%s=", m2->name); } if (m1->name[0] == 's') verbose_snum(env, m1->val); else verbose_unum(env, m1->val); } } static bool type_is_map_ptr(enum bpf_reg_type t) { switch (base_type(t)) { case CONST_PTR_TO_MAP: case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: return true; default: return false; } } /* * _a stands for append, was shortened to avoid multiline statements below. * This macro is used to output a comma separated list of attributes. */ #define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) static void print_reg_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, const struct bpf_reg_state *reg) { enum bpf_reg_type t; const char *sep = ""; t = reg->type; if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) { verbose_snum(env, reg->var_off.value); return; } verbose(env, "%s", reg_type_str(env, t)); if (t == PTR_TO_ARENA) return; if (t == PTR_TO_STACK) { if (state->frameno != reg->frameno) verbose(env, "[%d]", reg->frameno); if (tnum_is_const(reg->var_off)) { verbose_snum(env, reg->var_off.value + reg->delta); return; } } if (base_type(t) == PTR_TO_BTF_ID) verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); verbose(env, "("); if (reg->id) verbose_a("id=%d", reg->id & ~BPF_ADD_CONST); if (reg->id & BPF_ADD_CONST) verbose(env, "%+d", reg->delta); if (reg->ref_obj_id) verbose_a("ref_obj_id=%d", reg->ref_obj_id); if (type_is_non_owning_ref(reg->type)) verbose_a("%s", "non_own_ref"); if (type_is_map_ptr(t)) { if (reg->map_ptr->name[0]) verbose_a("map=%s", reg->map_ptr->name); verbose_a("ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); } if (t != SCALAR_VALUE && reg->delta) { verbose_a("off="); verbose_snum(env, reg->delta); } if (type_is_pkt_pointer(t)) { verbose_a("r="); verbose_unum(env, reg->range); } if (base_type(t) == PTR_TO_MEM) { verbose_a("sz="); verbose_unum(env, reg->mem_size); } if (t == CONST_PTR_TO_DYNPTR) verbose_a("type=%s", dynptr_type_str(reg->dynptr.type)); if (tnum_is_const(reg->var_off)) { /* a pointer register with fixed offset */ if (reg->var_off.value) { verbose_a("imm="); verbose_snum(env, reg->var_off.value); } } else { print_scalar_ranges(env, reg, &sep); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose_a("var_off=%s", tn_buf); } } verbose(env, ")"); } void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno, bool print_all) { const struct bpf_func_state *state = vstate->frame[frameno]; const struct bpf_reg_state *reg; int i; if (state->frameno) verbose(env, " frame%d:", state->frameno); for (i = 0; i < MAX_BPF_REG; i++) { reg = &state->regs[i]; if (reg->type == NOT_INIT) continue; if (!print_all && !reg_scratched(env, i)) continue; verbose(env, " R%d", i); verbose(env, "="); print_reg_state(env, state, reg); } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { char types_buf[BPF_REG_SIZE + 1]; const char *sep = ""; bool valid = false; u8 slot_type; int j; if (!print_all && !stack_slot_scratched(env, i)) continue; for (j = 0; j < BPF_REG_SIZE; j++) { slot_type = state->stack[i].slot_type[j]; if (slot_type != STACK_INVALID && slot_type != STACK_POISON) valid = true; types_buf[j] = slot_type_char[slot_type]; } types_buf[BPF_REG_SIZE] = 0; if (!valid) continue; reg = &state->stack[i].spilled_ptr; switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { case STACK_SPILL: /* print MISC/ZERO/INVALID slots above subreg spill */ for (j = 0; j < BPF_REG_SIZE; j++) if (state->stack[i].slot_type[j] == STACK_SPILL) break; types_buf[j] = '\0'; verbose(env, " fp%d=%s", (-i - 1) * BPF_REG_SIZE, types_buf); print_reg_state(env, state, reg); break; case STACK_DYNPTR: /* skip to main dynptr slot */ i += BPF_DYNPTR_NR_SLOTS - 1; reg = &state->stack[i].spilled_ptr; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type)); if (reg->id) verbose_a("id=%d", reg->id); if (reg->ref_obj_id) verbose_a("ref_id=%d", reg->ref_obj_id); if (reg->dynptr_id) verbose_a("dynptr_id=%d", reg->dynptr_id); verbose(env, ")"); break; case STACK_ITER: /* only main slot has ref_obj_id set; skip others */ if (!reg->ref_obj_id) continue; verbose(env, " fp%d=iter_%s(ref_id=%d,state=%s,depth=%u)", (-i - 1) * BPF_REG_SIZE, iter_type_str(reg->iter.btf, reg->iter.btf_id), reg->ref_obj_id, iter_state_str(reg->iter.state), reg->iter.depth); break; case STACK_MISC: case STACK_ZERO: default: verbose(env, " fp%d=%s", (-i - 1) * BPF_REG_SIZE, types_buf); break; } } if (vstate->acquired_refs && vstate->refs[0].id) { verbose(env, " refs=%d", vstate->refs[0].id); for (i = 1; i < vstate->acquired_refs; i++) if (vstate->refs[i].id) verbose(env, ",%d", vstate->refs[i].id); } if (state->in_callback_fn) verbose(env, " cb"); if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); if (!print_all) mark_verifier_state_clean(env); } u32 bpf_vlog_alignment(u32 pos) { return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), BPF_LOG_MIN_ALIGNMENT) - pos - 1; } void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, u32 frameno) { if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { /* remove new line character */ bpf_vlog_reset(&env->log, env->prev_log_pos - 1); verbose(env, "%*c;", bpf_vlog_alignment(env->prev_insn_print_pos), ' '); } else { verbose(env, "%d:", env->insn_idx); } print_verifier_state(env, vstate, frameno, false); } |
| 5 1 1 5 5 7 2 5 102 101 32 33 32 31 1 1 32 1 12 3 31 89 17 2 71 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to io context handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/sched/task.h> #include "blk.h" #include "blk-mq-sched.h" /* * For io context allocations */ static struct kmem_cache *iocontext_cachep; #ifdef CONFIG_BLK_ICQ /** * get_io_context - increment reference count to io_context * @ioc: io_context to get * * Increment reference count to @ioc. */ static void get_io_context(struct io_context *ioc) { BUG_ON(atomic_long_read(&ioc->refcount) <= 0); atomic_long_inc(&ioc->refcount); } /* * Exit an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_exit_icq(struct io_cq *icq) { struct elevator_type *et = icq->q->elevator->type; if (icq->flags & ICQ_EXITED) return; if (et->ops.exit_icq) et->ops.exit_icq(icq); icq->flags |= ICQ_EXITED; } static void ioc_exit_icqs(struct io_context *ioc) { struct io_cq *icq; spin_lock_irq(&ioc->lock); hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) ioc_exit_icq(icq); spin_unlock_irq(&ioc->lock); } /* * Release an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_destroy_icq(struct io_cq *icq) { struct io_context *ioc = icq->ioc; struct request_queue *q = icq->q; struct elevator_type *et = q->elevator->type; lockdep_assert_held(&ioc->lock); lockdep_assert_held(&q->queue_lock); if (icq->flags & ICQ_DESTROYED) return; radix_tree_delete(&ioc->icq_tree, icq->q->id); hlist_del_init(&icq->ioc_node); list_del_init(&icq->q_node); /* * Both setting lookup hint to and clearing it from @icq are done * under queue_lock. If it's not pointing to @icq now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(ioc->icq_hint) == icq) rcu_assign_pointer(ioc->icq_hint, NULL); ioc_exit_icq(icq); /* * @icq->q might have gone away by the time RCU callback runs * making it impossible to determine icq_cache. Record it in @icq. */ icq->__rcu_icq_cache = et->icq_cache; icq->flags |= ICQ_DESTROYED; kfree_rcu(icq, __rcu_head); } /* * Slow path for ioc release in put_io_context(). Performs double-lock * dancing to unlink all icq's and then frees ioc. */ static void ioc_release_fn(struct work_struct *work) { struct io_context *ioc = container_of(work, struct io_context, release_work); spin_lock_irq(&ioc->lock); while (!hlist_empty(&ioc->icq_list)) { struct io_cq *icq = hlist_entry(ioc->icq_list.first, struct io_cq, ioc_node); struct request_queue *q = icq->q; if (spin_trylock(&q->queue_lock)) { ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); } else { /* Make sure q and icq cannot be freed. */ rcu_read_lock(); /* Re-acquire the locks in the correct order. */ spin_unlock(&ioc->lock); spin_lock(&q->queue_lock); spin_lock(&ioc->lock); ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); rcu_read_unlock(); } } spin_unlock_irq(&ioc->lock); kmem_cache_free(iocontext_cachep, ioc); } /* * Releasing icqs requires reverse order double locking and we may already be * holding a queue_lock. Do it asynchronously from a workqueue. */ static bool ioc_delay_free(struct io_context *ioc) { unsigned long flags; spin_lock_irqsave(&ioc->lock, flags); if (!hlist_empty(&ioc->icq_list)) { queue_work(system_power_efficient_wq, &ioc->release_work); spin_unlock_irqrestore(&ioc->lock, flags); return true; } spin_unlock_irqrestore(&ioc->lock, flags); return false; } /** * ioc_clear_queue - break any ioc association with the specified queue * @q: request_queue being cleared * * Walk @q->icq_list and exit all io_cq's. */ void ioc_clear_queue(struct request_queue *q) { spin_lock_irq(&q->queue_lock); while (!list_empty(&q->icq_list)) { struct io_cq *icq = list_first_entry(&q->icq_list, struct io_cq, q_node); /* * Other context won't hold ioc lock to wait for queue_lock, see * details in ioc_release_fn(). */ spin_lock(&icq->ioc->lock); ioc_destroy_icq(icq); spin_unlock(&icq->ioc->lock); } spin_unlock_irq(&q->queue_lock); } #else /* CONFIG_BLK_ICQ */ static inline void ioc_exit_icqs(struct io_context *ioc) { } static inline bool ioc_delay_free(struct io_context *ioc) { return false; } #endif /* CONFIG_BLK_ICQ */ /** * put_io_context - put a reference of io_context * @ioc: io_context to put * * Decrement reference count of @ioc and release it if the count reaches * zero. */ void put_io_context(struct io_context *ioc) { BUG_ON(atomic_long_read(&ioc->refcount) <= 0); if (atomic_long_dec_and_test(&ioc->refcount) && !ioc_delay_free(ioc)) kmem_cache_free(iocontext_cachep, ioc); } EXPORT_SYMBOL_GPL(put_io_context); /* Called by the exiting task */ void exit_io_context(struct task_struct *task) { struct io_context *ioc; task_lock(task); ioc = task->io_context; task->io_context = NULL; task_unlock(task); if (atomic_dec_and_test(&ioc->active_ref)) { ioc_exit_icqs(ioc); put_io_context(ioc); } } static struct io_context *alloc_io_context(gfp_t gfp_flags, int node) { struct io_context *ioc; ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO, node); if (unlikely(!ioc)) return NULL; atomic_long_set(&ioc->refcount, 1); atomic_set(&ioc->active_ref, 1); #ifdef CONFIG_BLK_ICQ spin_lock_init(&ioc->lock); INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&ioc->icq_list); INIT_WORK(&ioc->release_work, ioc_release_fn); #endif ioc->ioprio = IOPRIO_DEFAULT; return ioc; } int set_task_ioprio(struct task_struct *task, int ioprio) { int err; const struct cred *cred = current_cred(), *tcred; rcu_read_lock(); tcred = __task_cred(task); if (!uid_eq(tcred->uid, cred->euid) && !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); return -EPERM; } rcu_read_unlock(); err = security_task_setioprio(task, ioprio); if (err) return err; task_lock(task); if (unlikely(!task->io_context)) { struct io_context *ioc; task_unlock(task); ioc = alloc_io_context(GFP_ATOMIC, NUMA_NO_NODE); if (!ioc) return -ENOMEM; task_lock(task); if (task->flags & PF_EXITING) { kmem_cache_free(iocontext_cachep, ioc); goto out; } if (task->io_context) kmem_cache_free(iocontext_cachep, ioc); else task->io_context = ioc; } task->io_context->ioprio = ioprio; out: task_unlock(task); return 0; } EXPORT_SYMBOL_GPL(set_task_ioprio); int __copy_io(u64 clone_flags, struct task_struct *tsk) { struct io_context *ioc = current->io_context; /* * Share io context with parent, if CLONE_IO is set */ if (clone_flags & CLONE_IO) { atomic_inc(&ioc->active_ref); tsk->io_context = ioc; } else if (ioprio_valid(ioc->ioprio)) { tsk->io_context = alloc_io_context(GFP_KERNEL, NUMA_NO_NODE); if (!tsk->io_context) return -ENOMEM; tsk->io_context->ioprio = ioc->ioprio; } return 0; } #ifdef CONFIG_BLK_ICQ /** * ioc_lookup_icq - lookup io_cq from ioc in io issue path * @q: the associated request_queue * * Look up io_cq associated with @ioc - @q pair from @ioc. Must be called * from io issue path, either return NULL if current issue io to @q for the * first time, or return a valid icq. */ struct io_cq *ioc_lookup_icq(struct request_queue *q) { struct io_context *ioc = current->io_context; struct io_cq *icq; /* * icq's are indexed from @ioc using radix tree and hint pointer, * both of which are protected with RCU, io issue path ensures that * both request_queue and current task are valid, the found icq * is guaranteed to be valid until the io is done. */ rcu_read_lock(); icq = rcu_dereference(ioc->icq_hint); if (icq && icq->q == q) goto out; icq = radix_tree_lookup(&ioc->icq_tree, q->id); if (icq && icq->q == q) rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */ else icq = NULL; out: rcu_read_unlock(); return icq; } EXPORT_SYMBOL(ioc_lookup_icq); /** * ioc_create_icq - create and link io_cq * @q: request_queue of interest * * Make sure io_cq linking @ioc and @q exists. If icq doesn't exist, they * will be created using @gfp_mask. * * The caller is responsible for ensuring @ioc won't go away and @q is * alive and will stay alive until this function returns. */ static struct io_cq *ioc_create_icq(struct request_queue *q) { struct io_context *ioc = current->io_context; struct elevator_type *et = q->elevator->type; struct io_cq *icq; /* allocate stuff */ icq = kmem_cache_alloc_node(et->icq_cache, GFP_ATOMIC | __GFP_ZERO, q->node); if (!icq) return NULL; if (radix_tree_maybe_preload(GFP_ATOMIC) < 0) { kmem_cache_free(et->icq_cache, icq); return NULL; } icq->ioc = ioc; icq->q = q; INIT_LIST_HEAD(&icq->q_node); INIT_HLIST_NODE(&icq->ioc_node); /* lock both q and ioc and try to link @icq */ spin_lock_irq(&q->queue_lock); spin_lock(&ioc->lock); if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { hlist_add_head(&icq->ioc_node, &ioc->icq_list); list_add(&icq->q_node, &q->icq_list); if (et->ops.init_icq) et->ops.init_icq(icq); } else { kmem_cache_free(et->icq_cache, icq); icq = ioc_lookup_icq(q); if (!icq) printk(KERN_ERR "cfq: icq link failed!\n"); } spin_unlock(&ioc->lock); spin_unlock_irq(&q->queue_lock); radix_tree_preload_end(); return icq; } struct io_cq *ioc_find_get_icq(struct request_queue *q) { struct io_context *ioc = current->io_context; struct io_cq *icq = NULL; if (unlikely(!ioc)) { ioc = alloc_io_context(GFP_ATOMIC, q->node); if (!ioc) return NULL; task_lock(current); if (current->io_context) { kmem_cache_free(iocontext_cachep, ioc); ioc = current->io_context; } else { current->io_context = ioc; } get_io_context(ioc); task_unlock(current); } else { get_io_context(ioc); icq = ioc_lookup_icq(q); } if (!icq) { icq = ioc_create_icq(q); if (!icq) { put_io_context(ioc); return NULL; } } return icq; } EXPORT_SYMBOL_GPL(ioc_find_get_icq); #endif /* CONFIG_BLK_ICQ */ static int __init blk_ioc_init(void) { iocontext_cachep = kmem_cache_create("blkdev_ioc", sizeof(struct io_context), 0, SLAB_PANIC, NULL); return 0; } subsys_initcall(blk_ioc_init); |
| 9 9 9 9 9 9 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 | // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /****************************************************************************** * * Module Name: hwvalid - I/O request validation * * Copyright (C) 2000 - 2026, Intel Corp. * *****************************************************************************/ #include <acpi/acpi.h> #include "accommon.h" #define _COMPONENT ACPI_HARDWARE ACPI_MODULE_NAME("hwvalid") /* Local prototypes */ static acpi_status acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width); /* * Protected I/O ports. Some ports are always illegal, and some are * conditionally illegal. This table must remain ordered by port address. * * The table is used to implement the Microsoft port access rules that * first appeared in Windows XP. Some ports are always illegal, and some * ports are only illegal if the BIOS calls _OSI with nothing newer than * the specific _OSI strings. * * This provides ACPICA with the desired port protections and * Microsoft compatibility. * * Description of port entries: * DMA: DMA controller * PIC0: Programmable Interrupt Controller (8259A) * PIT1: System Timer 1 * PIT2: System Timer 2 failsafe * RTC: Real-time clock * CMOS: Extended CMOS * DMA1: DMA 1 page registers * DMA1L: DMA 1 Ch 0 low page * DMA2: DMA 2 page registers * DMA2L: DMA 2 low page refresh * ARBC: Arbitration control * SETUP: Reserved system board setup * POS: POS channel select * PIC1: Cascaded PIC * IDMA: ISA DMA * ELCR: PIC edge/level registers * PCI: PCI configuration space */ static const struct acpi_port_info acpi_protected_ports[] = { {"DMA", 0x0000, 0x000F, ACPI_OSI_WIN_XP}, {"PIC0", 0x0020, 0x0021, ACPI_ALWAYS_ILLEGAL}, {"PIT1", 0x0040, 0x0043, ACPI_OSI_WIN_XP}, {"PIT2", 0x0048, 0x004B, ACPI_OSI_WIN_XP}, {"RTC", 0x0070, 0x0071, ACPI_OSI_WIN_XP}, {"CMOS", 0x0074, 0x0076, ACPI_OSI_WIN_XP}, {"DMA1", 0x0081, 0x0083, ACPI_OSI_WIN_XP}, {"DMA1L", 0x0087, 0x0087, ACPI_OSI_WIN_XP}, {"DMA2", 0x0089, 0x008B, ACPI_OSI_WIN_XP}, {"DMA2L", 0x008F, 0x008F, ACPI_OSI_WIN_XP}, {"ARBC", 0x0090, 0x0091, ACPI_OSI_WIN_XP}, {"SETUP", 0x0093, 0x0094, ACPI_OSI_WIN_XP}, {"POS", 0x0096, 0x0097, ACPI_OSI_WIN_XP}, {"PIC1", 0x00A0, 0x00A1, ACPI_ALWAYS_ILLEGAL}, {"IDMA", 0x00C0, 0x00DF, ACPI_OSI_WIN_XP}, {"ELCR", 0x04D0, 0x04D1, ACPI_ALWAYS_ILLEGAL}, {"PCI", 0x0CF8, 0x0CFF, ACPI_OSI_WIN_XP} }; #define ACPI_PORT_INFO_ENTRIES ACPI_ARRAY_LENGTH (acpi_protected_ports) /****************************************************************************** * * FUNCTION: acpi_hw_validate_io_request * * PARAMETERS: Address Address of I/O port/register * bit_width Number of bits (8,16,32) * * RETURN: Status * * DESCRIPTION: Validates an I/O request (address/length). Certain ports are * always illegal and some ports are only illegal depending on * the requests the BIOS AML code makes to the predefined * _OSI method. * ******************************************************************************/ static acpi_status acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width) { u32 i; u32 byte_width; acpi_io_address last_address; const struct acpi_port_info *port_info; ACPI_FUNCTION_TRACE(hw_validate_io_request); /* Supported widths are 8/16/32 */ if ((bit_width != 8) && (bit_width != 16) && (bit_width != 32)) { ACPI_ERROR((AE_INFO, "Bad BitWidth parameter: %8.8X", bit_width)); return_ACPI_STATUS(AE_BAD_PARAMETER); } port_info = acpi_protected_ports; byte_width = ACPI_DIV_8(bit_width); last_address = address + byte_width - 1; ACPI_DEBUG_PRINT((ACPI_DB_IO, "Address %8.8X%8.8X LastAddress %8.8X%8.8X Length %X", ACPI_FORMAT_UINT64(address), ACPI_FORMAT_UINT64(last_address), byte_width)); /* Maximum 16-bit address in I/O space */ if (last_address > ACPI_UINT16_MAX) { ACPI_ERROR((AE_INFO, "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X", ACPI_FORMAT_UINT64(address), byte_width)); return_ACPI_STATUS(AE_LIMIT); } /* Exit if requested address is not within the protected port table */ if (address > acpi_protected_ports[ACPI_PORT_INFO_ENTRIES - 1].end) { return_ACPI_STATUS(AE_OK); } /* Check request against the list of protected I/O ports */ for (i = 0; i < ACPI_PORT_INFO_ENTRIES; i++, port_info++) { /* * Check if the requested address range will write to a reserved * port. There are four cases to consider: * * 1) Address range is contained completely in the port address range * 2) Address range overlaps port range at the port range start * 3) Address range overlaps port range at the port range end * 4) Address range completely encompasses the port range */ if ((address <= port_info->end) && (last_address >= port_info->start)) { /* Port illegality may depend on the _OSI calls made by the BIOS */ if (port_info->osi_dependency == ACPI_ALWAYS_ILLEGAL || acpi_gbl_osi_data == port_info->osi_dependency) { ACPI_DEBUG_PRINT((ACPI_DB_VALUES, "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)\n", ACPI_FORMAT_UINT64(address), byte_width, port_info->name, port_info->start, port_info->end)); return_ACPI_STATUS(AE_AML_ILLEGAL_ADDRESS); } } /* Finished if address range ends before the end of this port */ if (last_address <= port_info->end) { break; } } return_ACPI_STATUS(AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_read_port * * PARAMETERS: Address Address of I/O port/register to read * Value Where value (data) is returned * Width Number of bits * * RETURN: Status and value read from port * * DESCRIPTION: Read data from an I/O port or register. This is a front-end * to acpi_os_read_port that performs validation on both the port * address and the length. * *****************************************************************************/ acpi_status acpi_hw_read_port(acpi_io_address address, u32 *value, u32 width) { acpi_status status; u32 one_byte; u32 i; /* Truncate address to 16 bits if requested */ if (acpi_gbl_truncate_io_addresses) { address &= ACPI_UINT16_MAX; } /* Validate the entire request and perform the I/O */ status = acpi_hw_validate_io_request(address, width); if (ACPI_SUCCESS(status)) { status = acpi_os_read_port(address, value, width); return (status); } if (status != AE_AML_ILLEGAL_ADDRESS) { return (status); } /* * There has been a protection violation within the request. Fall * back to byte granularity port I/O and ignore the failing bytes. * This provides compatibility with other ACPI implementations. */ for (i = 0, *value = 0; i < width; i += 8) { /* Validate and read one byte */ if (acpi_hw_validate_io_request(address, 8) == AE_OK) { status = acpi_os_read_port(address, &one_byte, 8); if (ACPI_FAILURE(status)) { return (status); } *value |= (one_byte << i); } address++; } return (AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_write_port * * PARAMETERS: Address Address of I/O port/register to write * Value Value to write * Width Number of bits * * RETURN: Status * * DESCRIPTION: Write data to an I/O port or register. This is a front-end * to acpi_os_write_port that performs validation on both the port * address and the length. * *****************************************************************************/ acpi_status acpi_hw_write_port(acpi_io_address address, u32 value, u32 width) { acpi_status status; u32 i; /* Truncate address to 16 bits if requested */ if (acpi_gbl_truncate_io_addresses) { address &= ACPI_UINT16_MAX; } /* Validate the entire request and perform the I/O */ status = acpi_hw_validate_io_request(address, width); if (ACPI_SUCCESS(status)) { status = acpi_os_write_port(address, value, width); return (status); } if (status != AE_AML_ILLEGAL_ADDRESS) { return (status); } /* * There has been a protection violation within the request. Fall * back to byte granularity port I/O and ignore the failing bytes. * This provides compatibility with other ACPI implementations. */ for (i = 0; i < width; i += 8) { /* Validate and write one byte */ if (acpi_hw_validate_io_request(address, 8) == AE_OK) { status = acpi_os_write_port(address, (value >> i) & 0xFF, 8); if (ACPI_FAILURE(status)) { return (status); } } address++; } return (AE_OK); } /****************************************************************************** * * FUNCTION: acpi_hw_validate_io_block * * PARAMETERS: Address Address of I/O port/register blobk * bit_width Number of bits (8,16,32) in each register * count Number of registers in the block * * RETURN: Status * * DESCRIPTION: Validates a block of I/O ports/registers. * ******************************************************************************/ acpi_status acpi_hw_validate_io_block(u64 address, u32 bit_width, u32 count) { acpi_status status; while (count--) { status = acpi_hw_validate_io_request((acpi_io_address)address, bit_width); if (ACPI_FAILURE(status)) return_ACPI_STATUS(status); address += ACPI_DIV_8(bit_width); } return_ACPI_STATUS(AE_OK); } |
| 8 4 3 3 3 3 1 1 1 1 1 1 1 1 2 5 4 1 11 3 3 1 1 1 2 2 2 2 1 2 2 3 3 3 3 3 2 1 10 9 1 1 1 7 6 6 1 5 2 4 4 4 6 5 1 2 3 1 2 3 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/poll.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "opdef.h" #include "kbuf.h" #include "memmap.h" /* BIDs are addressed by a 16-bit field in a CQE */ #define MAX_BIDS_PER_BGID (1 << 16) /* Mapped buffer ring, return io_uring_buf from head */ #define io_ring_head_to_buf(br, head, mask) (&(br)->bufs[(head) & (mask)]) struct io_provide_buf { struct file *file; __u64 addr; __u32 len; __u32 bgid; __u32 nbufs; __u16 bid; }; static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len) { /* No data consumed, return false early to avoid consuming the buffer */ if (!len) return false; while (len) { struct io_uring_buf *buf; u32 buf_len, this_len; buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask); buf_len = READ_ONCE(buf->len); this_len = min_t(u32, len, buf_len); buf_len -= this_len; /* Stop looping for invalid buffer length of 0 */ if (buf_len > bl->min_left_sub_one || !this_len) { WRITE_ONCE(buf->addr, READ_ONCE(buf->addr) + this_len); WRITE_ONCE(buf->len, buf_len); return false; } WRITE_ONCE(buf->len, 0); bl->head++; len -= this_len; } return true; } bool io_kbuf_commit(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr) { if (unlikely(!(req->flags & REQ_F_BUFFERS_COMMIT))) return true; req->flags &= ~REQ_F_BUFFERS_COMMIT; if (unlikely(len < 0)) return true; if (bl->flags & IOBL_INC) return io_kbuf_inc_commit(bl, len); bl->head += nr; return true; } static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, unsigned int bgid) { lockdep_assert_held(&ctx->uring_lock); return xa_load(&ctx->io_bl_xa, bgid); } static int io_buffer_add_list(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned int bgid) { /* * Store buffer group ID and finally mark the list as visible. * The normal lookup doesn't care about the visibility as we're * always under the ->uring_lock, but lookups from mmap do. */ bl->bgid = bgid; guard(mutex)(&ctx->mmap_lock); return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } void io_kbuf_drop_legacy(struct io_kiocb *req) { if (WARN_ON_ONCE(!(req->flags & REQ_F_BUFFER_SELECTED))) return; req->flags &= ~REQ_F_BUFFER_SELECTED; kfree(req->kbuf); req->kbuf = NULL; } bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; struct io_buffer *buf; io_ring_submit_lock(ctx, issue_flags); buf = req->kbuf; bl = io_buffer_get_list(ctx, buf->bgid); /* * If the buffer list was upgraded to a ring-based one, or removed, * while the request was in-flight in io-wq, drop it. */ if (bl && !(bl->flags & IOBL_BUF_RING)) { list_add(&buf->list, &bl->buf_list); bl->nbufs++; } else { kfree(buf); } req->flags &= ~REQ_F_BUFFER_SELECTED; req->kbuf = NULL; io_ring_submit_unlock(ctx, issue_flags); return true; } static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len, struct io_buffer_list *bl) { if (!list_empty(&bl->buf_list)) { struct io_buffer *kbuf; kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list); list_del(&kbuf->list); bl->nbufs--; if (*len == 0 || *len > kbuf->len) *len = kbuf->len; if (list_empty(&bl->buf_list)) req->flags |= REQ_F_BL_EMPTY; req->flags |= REQ_F_BUFFER_SELECTED; req->kbuf = kbuf; req->buf_index = kbuf->bid; return u64_to_user_ptr(kbuf->addr); } return NULL; } static int io_provided_buffers_select(struct io_kiocb *req, size_t *len, struct io_buffer_list *bl, struct iovec *iov) { void __user *buf; buf = io_provided_buffer_select(req, len, bl); if (unlikely(!buf)) return -ENOBUFS; iov[0].iov_base = buf; iov[0].iov_len = *len; return 1; } static bool io_should_commit(struct io_kiocb *req, unsigned int issue_flags) { /* * If we came in unlocked, we have no choice but to consume the * buffer here, otherwise nothing ensures that the buffer won't * get used by others. This does mean it'll be pinned until the * IO completes, coming in unlocked means we're being called from * io-wq context and there may be further retries in async hybrid * mode. For the locked case, the caller must call commit when * the transfer completes (or if we get -EAGAIN and must poll of * retry). */ if (issue_flags & IO_URING_F_UNLOCKED) return true; /* uring_cmd commits kbuf upfront, no need to auto-commit */ if (!io_file_can_poll(req) && !io_is_uring_cmd(req)) return true; return false; } static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len, struct io_buffer_list *bl, unsigned int issue_flags) { struct io_uring_buf_ring *br = bl->buf_ring; __u16 tail, head = bl->head; struct io_br_sel sel = { }; struct io_uring_buf *buf; u32 buf_len; tail = smp_load_acquire(&br->tail); if (unlikely(tail == head)) return sel; if (head + 1 == tail) req->flags |= REQ_F_BL_EMPTY; buf = io_ring_head_to_buf(br, head, bl->mask); buf_len = READ_ONCE(buf->len); if (*len == 0 || *len > buf_len) *len = buf_len; sel.addr = u64_to_user_ptr(READ_ONCE(buf->addr)); if (unlikely(!access_ok(sel.addr, *len))) { sel.addr = NULL; return sel; } req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; req->buf_index = READ_ONCE(buf->bid); sel.buf_list = bl; if (io_should_commit(req, issue_flags)) { if (!io_kbuf_commit(req, sel.buf_list, *len, 1)) req->flags |= REQ_F_BUF_MORE; sel.buf_list = NULL; } return sel; } struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len, unsigned buf_group, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; struct io_br_sel sel = { }; struct io_buffer_list *bl; io_ring_submit_lock(ctx, issue_flags); bl = io_buffer_get_list(ctx, buf_group); if (likely(bl)) { if (bl->flags & IOBL_BUF_RING) sel = io_ring_buffer_select(req, len, bl, issue_flags); else sel.addr = io_provided_buffer_select(req, len, bl); } io_ring_submit_unlock(ctx, issue_flags); return sel; } /* cap it at a reasonable 256, will be one page even for 4K */ #define PEEK_MAX_IMPORT 256 static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_buffer_list *bl) { struct io_uring_buf_ring *br = bl->buf_ring; struct iovec *org_iovs = arg->iovs; struct iovec *iov = arg->iovs; int nr_iovs = arg->nr_iovs; __u16 nr_avail, tail, head; struct io_uring_buf *buf; tail = smp_load_acquire(&br->tail); head = bl->head; nr_avail = min_t(__u16, tail - head, UIO_MAXIOV); if (unlikely(!nr_avail)) return -ENOBUFS; buf = io_ring_head_to_buf(br, head, bl->mask); if (arg->max_len) { u32 len = READ_ONCE(buf->len); size_t needed; if (unlikely(!len)) return -ENOBUFS; needed = (arg->max_len + len - 1) / len; needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT); if (nr_avail > needed) nr_avail = needed; } /* * only alloc a bigger array if we know we have data to map, eg not * a speculative peek operation. */ if (arg->mode & KBUF_MODE_EXPAND && nr_avail > nr_iovs && arg->max_len) { iov = kmalloc_objs(struct iovec, nr_avail); if (unlikely(!iov)) return -ENOMEM; if (arg->mode & KBUF_MODE_FREE) kfree(arg->iovs); arg->iovs = iov; nr_iovs = nr_avail; } else if (nr_avail < nr_iovs) { nr_iovs = nr_avail; } /* set it to max, if not set, so we can use it unconditionally */ if (!arg->max_len) arg->max_len = INT_MAX; req->buf_index = READ_ONCE(buf->bid); do { u32 len = READ_ONCE(buf->len); /* truncate end piece, if needed, for non partial buffers */ if (len > arg->max_len) { len = arg->max_len; if (!(bl->flags & IOBL_INC)) { arg->partial_map = 1; if (iov != arg->iovs) break; } } iov->iov_base = u64_to_user_ptr(READ_ONCE(buf->addr)); iov->iov_len = len; if (unlikely(!access_ok(iov->iov_base, len))) { if (arg->iovs != org_iovs) kfree(arg->iovs); return -EFAULT; } iov++; arg->out_len += len; arg->max_len -= len; if (!arg->max_len) break; buf = io_ring_head_to_buf(br, ++head, bl->mask); } while (--nr_iovs); if (head == tail) req->flags |= REQ_F_BL_EMPTY; req->flags |= REQ_F_BUFFER_RING; return iov - arg->iovs; } int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; int ret = -ENOENT; io_ring_submit_lock(ctx, issue_flags); sel->buf_list = io_buffer_get_list(ctx, arg->buf_group); if (unlikely(!sel->buf_list)) goto out_unlock; if (sel->buf_list->flags & IOBL_BUF_RING) { ret = io_ring_buffers_peek(req, arg, sel->buf_list); /* * Don't recycle these buffers if we need to go through poll. * Nobody else can use them anyway, and holding on to provided * buffers for a send/write operation would happen on the app * side anyway with normal buffers. Besides, we already * committed them, they cannot be put back in the queue. */ if (ret > 0) { req->flags |= REQ_F_BUFFERS_COMMIT | REQ_F_BL_NO_RECYCLE; if (!io_kbuf_commit(req, sel->buf_list, arg->out_len, ret)) req->flags |= REQ_F_BUF_MORE; } } else { ret = io_provided_buffers_select(req, &arg->out_len, sel->buf_list, arg->iovs); } out_unlock: if (issue_flags & IO_URING_F_UNLOCKED) { sel->buf_list = NULL; mutex_unlock(&ctx->uring_lock); } return ret; } int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, struct io_br_sel *sel) { struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret; lockdep_assert_held(&ctx->uring_lock); bl = io_buffer_get_list(ctx, arg->buf_group); if (unlikely(!bl)) return -ENOENT; if (bl->flags & IOBL_BUF_RING) { ret = io_ring_buffers_peek(req, arg, bl); if (ret > 0) req->flags |= REQ_F_BUFFERS_COMMIT; sel->buf_list = bl; return ret; } /* don't support multiple buffer selections for legacy */ sel->buf_list = NULL; return io_provided_buffers_select(req, &arg->max_len, bl, arg->iovs); } static inline bool __io_put_kbuf_ring(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nr) { bool ret = true; if (bl) ret = io_kbuf_commit(req, bl, len, nr); if (ret && (req->flags & REQ_F_BUF_MORE)) ret = false; req->flags &= ~(REQ_F_BUFFER_RING | REQ_F_BUF_MORE); return ret; } unsigned int __io_put_kbufs(struct io_kiocb *req, struct io_buffer_list *bl, int len, int nbufs) { unsigned int ret; ret = IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT); if (unlikely(!(req->flags & REQ_F_BUFFER_RING))) { io_kbuf_drop_legacy(req); return ret; } if (!__io_put_kbuf_ring(req, bl, len, nbufs)) ret |= IORING_CQE_F_BUF_MORE; return ret; } static int io_remove_buffers_legacy(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned long nbufs) { unsigned long i = 0; struct io_buffer *nxt; /* protects io_buffers_cache */ lockdep_assert_held(&ctx->uring_lock); WARN_ON_ONCE(bl->flags & IOBL_BUF_RING); for (i = 0; i < nbufs && !list_empty(&bl->buf_list); i++) { nxt = list_first_entry(&bl->buf_list, struct io_buffer, list); list_del(&nxt->list); bl->nbufs--; kfree(nxt); cond_resched(); } return i; } static void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) { if (bl->flags & IOBL_BUF_RING) io_free_region(ctx->user, &bl->region); else io_remove_buffers_legacy(ctx, bl, -1U); kfree(bl); } void io_destroy_buffers(struct io_ring_ctx *ctx) { struct io_buffer_list *bl; while (1) { unsigned long index = 0; scoped_guard(mutex, &ctx->mmap_lock) { bl = xa_find(&ctx->io_bl_xa, &index, ULONG_MAX, XA_PRESENT); if (bl) xa_erase(&ctx->io_bl_xa, bl->bgid); } if (!bl) break; io_put_bl(ctx, bl); } } static void io_destroy_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) { scoped_guard(mutex, &ctx->mmap_lock) WARN_ON_ONCE(xa_erase(&ctx->io_bl_xa, bl->bgid) != bl); io_put_bl(ctx, bl); } int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); u64 tmp; if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off || sqe->splice_fd_in) return -EINVAL; tmp = READ_ONCE(sqe->fd); if (!tmp || tmp > MAX_BIDS_PER_BGID) return -EINVAL; memset(p, 0, sizeof(*p)); p->nbufs = tmp; p->bgid = READ_ONCE(sqe->buf_group); return 0; } int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { unsigned long size, tmp_check; struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); u64 tmp; if (sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; tmp = READ_ONCE(sqe->fd); if (!tmp || tmp > MAX_BIDS_PER_BGID) return -E2BIG; p->nbufs = tmp; p->addr = READ_ONCE(sqe->addr); p->len = READ_ONCE(sqe->len); if (!p->len) return -EINVAL; if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs, &size)) return -EOVERFLOW; if (check_add_overflow((unsigned long)p->addr, size, &tmp_check)) return -EOVERFLOW; if (!access_ok(u64_to_user_ptr(p->addr), size)) return -EFAULT; p->bgid = READ_ONCE(sqe->buf_group); tmp = READ_ONCE(sqe->off); if (tmp > USHRT_MAX) return -E2BIG; if (tmp + p->nbufs > MAX_BIDS_PER_BGID) return -EINVAL; p->bid = tmp; return 0; } static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf, struct io_buffer_list *bl) { struct io_buffer *buf; u64 addr = pbuf->addr; int ret = -ENOMEM, i, bid = pbuf->bid; for (i = 0; i < pbuf->nbufs; i++) { /* * Nonsensical to have more than MAX_BIDS_PER_BGID buffers in a * buffer list, as the application then has no way of knowing * which duplicate bid refers to what buffer. */ if (bl->nbufs == MAX_BIDS_PER_BGID) { ret = -EOVERFLOW; break; } buf = kmalloc_obj(*buf, GFP_KERNEL_ACCOUNT); if (!buf) break; list_add_tail(&buf->list, &bl->buf_list); bl->nbufs++; buf->addr = addr; buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT); buf->bid = bid; buf->bgid = pbuf->bgid; addr += pbuf->len; bid++; cond_resched(); } return i ? 0 : ret; } static int __io_manage_buffers_legacy(struct io_kiocb *req, struct io_buffer_list *bl) { struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); int ret; if (!bl) { if (req->opcode != IORING_OP_PROVIDE_BUFFERS) return -ENOENT; bl = kzalloc_obj(*bl, GFP_KERNEL_ACCOUNT); if (!bl) return -ENOMEM; INIT_LIST_HEAD(&bl->buf_list); ret = io_buffer_add_list(req->ctx, bl, p->bgid); if (ret) { kfree(bl); return ret; } } /* can't use provide/remove buffers command on mapped buffers */ if (bl->flags & IOBL_BUF_RING) return -EINVAL; if (req->opcode == IORING_OP_PROVIDE_BUFFERS) return io_add_buffers(req->ctx, p, bl); return io_remove_buffers_legacy(req->ctx, bl, p->nbufs); } int io_manage_buffers_legacy(struct io_kiocb *req, unsigned int issue_flags) { struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); struct io_ring_ctx *ctx = req->ctx; struct io_buffer_list *bl; int ret; io_ring_submit_lock(ctx, issue_flags); bl = io_buffer_get_list(ctx, p->bgid); ret = __io_manage_buffers_legacy(req, bl); io_ring_submit_unlock(ctx, issue_flags); if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); return IOU_COMPLETE; } int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) { struct io_uring_buf_reg reg; struct io_buffer_list *bl; struct io_uring_region_desc rd; struct io_uring_buf_ring *br; unsigned long mmap_offset; unsigned long ring_size; int ret; lockdep_assert_held(&ctx->uring_lock); if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; if (!mem_is_zero(reg.resv, sizeof(reg.resv))) return -EINVAL; if (reg.flags & ~(IOU_PBUF_RING_MMAP | IOU_PBUF_RING_INC)) return -EINVAL; if (!is_power_of_2(reg.ring_entries)) return -EINVAL; /* cannot disambiguate full vs empty due to head/tail size */ if (reg.ring_entries >= 65536) return -EINVAL; /* minimum left byte count is a property of incremental buffers */ if (!(reg.flags & IOU_PBUF_RING_INC) && reg.min_left) return -EINVAL; bl = io_buffer_get_list(ctx, reg.bgid); if (bl) { /* if mapped buffer ring OR classic exists, don't allow */ if (bl->flags & IOBL_BUF_RING || !list_empty(&bl->buf_list)) return -EEXIST; io_destroy_bl(ctx, bl); } bl = kzalloc_obj(*bl, GFP_KERNEL_ACCOUNT); if (!bl) return -ENOMEM; mmap_offset = (unsigned long)reg.bgid << IORING_OFF_PBUF_SHIFT; ring_size = flex_array_size(br, bufs, reg.ring_entries); memset(&rd, 0, sizeof(rd)); rd.size = PAGE_ALIGN(ring_size); if (!(reg.flags & IOU_PBUF_RING_MMAP)) { rd.user_addr = reg.ring_addr; rd.flags |= IORING_MEM_REGION_TYPE_USER; } ret = io_create_region(ctx, &bl->region, &rd, mmap_offset); if (ret) goto fail; br = io_region_get_ptr(&bl->region); #ifdef SHM_COLOUR /* * On platforms that have specific aliasing requirements, SHM_COLOUR * is set and we must guarantee that the kernel and user side align * nicely. We cannot do that if IOU_PBUF_RING_MMAP isn't set and * the application mmap's the provided ring buffer. Fail the request * if we, by chance, don't end up with aligned addresses. The app * should use IOU_PBUF_RING_MMAP instead, and liburing will handle * this transparently. */ if (!(reg.flags & IOU_PBUF_RING_MMAP) && ((reg.ring_addr | (unsigned long)br) & (SHM_COLOUR - 1))) { ret = -EINVAL; goto fail; } #endif bl->mask = reg.ring_entries - 1; bl->flags |= IOBL_BUF_RING; bl->buf_ring = br; if (reg.min_left) bl->min_left_sub_one = reg.min_left - 1; if (reg.flags & IOU_PBUF_RING_INC) bl->flags |= IOBL_INC; ret = io_buffer_add_list(ctx, bl, reg.bgid); if (!ret) return 0; fail: io_free_region(ctx->user, &bl->region); kfree(bl); return ret; } int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) { struct io_uring_buf_reg reg; struct io_buffer_list *bl; lockdep_assert_held(&ctx->uring_lock); if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; if (!mem_is_zero(reg.resv, sizeof(reg.resv)) || reg.flags) return -EINVAL; bl = io_buffer_get_list(ctx, reg.bgid); if (!bl) return -ENOENT; if (!(bl->flags & IOBL_BUF_RING)) return -EINVAL; scoped_guard(mutex, &ctx->mmap_lock) xa_erase(&ctx->io_bl_xa, bl->bgid); io_put_bl(ctx, bl); return 0; } int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg) { struct io_uring_buf_status buf_status; struct io_buffer_list *bl; if (copy_from_user(&buf_status, arg, sizeof(buf_status))) return -EFAULT; if (!mem_is_zero(buf_status.resv, sizeof(buf_status.resv))) return -EINVAL; bl = io_buffer_get_list(ctx, buf_status.buf_group); if (!bl) return -ENOENT; if (!(bl->flags & IOBL_BUF_RING)) return -EINVAL; buf_status.head = bl->head; if (copy_to_user(arg, &buf_status, sizeof(buf_status))) return -EFAULT; return 0; } struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx, unsigned int bgid) { struct io_buffer_list *bl; lockdep_assert_held(&ctx->mmap_lock); bl = xa_load(&ctx->io_bl_xa, bgid); if (!bl || !(bl->flags & IOBL_BUF_RING)) return NULL; return &bl->region; } |
| 106 26 13 68 260 1 1 74 68 262 2 2 148 75 75 75 73 22 4 102 113 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_H #define BLK_MQ_H #include <linux/blkdev.h> #include <linux/sbitmap.h> #include <linux/lockdep.h> #include <linux/scatterlist.h> #include <linux/prefetch.h> #include <linux/srcu.h> #include <linux/rw_hint.h> #include <linux/rwsem.h> struct blk_mq_tags; struct blk_flush_queue; struct io_comp_batch; #define BLKDEV_MIN_RQ 4 #define BLKDEV_DEFAULT_RQ 128 enum rq_end_io_ret { RQ_END_IO_NONE, RQ_END_IO_FREE, }; typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t, const struct io_comp_batch *); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* Keep rqf_name[] in sync with the definitions below */ enum rqf_flags { /* drive already may have started this one */ __RQF_STARTED, /* request for flush sequence */ __RQF_FLUSH_SEQ, /* merge of different types, fail separately */ __RQF_MIXED_MERGE, /* don't call prep for this one */ __RQF_DONTPREP, /* use hctx->sched_tags */ __RQF_SCHED_TAGS, /* use an I/O scheduler for this request */ __RQF_USE_SCHED, /* vaguely specified driver internal error. Ignored by block layer */ __RQF_FAILED, /* don't warn about errors */ __RQF_QUIET, /* account into disk and partition IO statistics */ __RQF_IO_STAT, /* runtime pm request */ __RQF_PM, /* on IO scheduler merge hash */ __RQF_HASHED, /* track IO completion time */ __RQF_STATS, /* Look at ->special_vec for the actual data payload instead of the bio chain. */ __RQF_SPECIAL_PAYLOAD, /* request completion needs to be signaled to zone write plugging. */ __RQF_ZONE_WRITE_PLUGGING, /* ->timeout has been called, don't expire again */ __RQF_TIMED_OUT, __RQF_RESV, __RQF_BITS }; #define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED)) #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ)) #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE)) #define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP)) #define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS)) #define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED)) #define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED)) #define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET)) #define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT)) #define RQF_PM ((__force req_flags_t)(1 << __RQF_PM)) #define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED)) #define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS)) #define RQF_SPECIAL_PAYLOAD \ ((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD)) #define RQF_ZONE_WRITE_PLUGGING \ ((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING)) #define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT)) #define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, MQ_RQ_IN_FLIGHT = 1, MQ_RQ_COMPLETE = 2, }; /* * Try to put the fields that are referenced together in the same cacheline. * * If you modify this structure, make sure to update blk_rq_init() and * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; struct blk_mq_hw_ctx *mq_hctx; blk_opf_t cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; unsigned int timeout; /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; union { struct list_head queuelist; struct request *rq_next; }; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; #endif /* Time that this request was allocated for this IO. */ u64 start_time_ns; /* Time that I/O was submitted to the device. */ u64 io_start_time_ns; #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; #endif /* * rq sectors used for blk stats. It has the same value * with blk_rq_sectors(rq), except that it never be zeroed * by completion. */ unsigned short stats_sectors; /* * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; unsigned short nr_integrity_segments; /* * The lowest set bit for address gaps between physical segments. This * provides information necessary for dma optimization opprotunities, * like for testing if the segments can be coalesced against the * device's iommu granule. */ unsigned char phys_gap_bit; #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_crypto_keyslot *crypt_keyslot; #endif enum mq_rq_state state; atomic_t ref; unsigned long deadline; /* * The hash is used inside the scheduler, and killed once the * request reaches the dispatch list. The ipi_list is only used * to queue the request for softirq completion, which is long * after the request has been unhashed (and even removed from * the dispatch list). */ union { struct hlist_node hash; /* merge hash */ struct llist_node ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. special_vec must * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be * insert into an IO scheduler. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. */ struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; rq_end_io_fn *saved_end_io; } flush; u64 fifo_time; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; }; /* * Returns a mask with all bits starting at req->phys_gap_bit set to 1. */ static inline unsigned long req_phys_gap_mask(const struct request *req) { return ~(((1 << req->phys_gap_bit) >> 1) - 1); } static inline enum req_op req_op(const struct request *req) { return req->cmd_flags & REQ_OP_MASK; } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) { if (req->bio) return req->bio->bi_ioprio; return 0; } #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) static inline int rq_list_empty(const struct rq_list *rl) { return rl->head == NULL; } static inline void rq_list_init(struct rq_list *rl) { rl->head = NULL; rl->tail = NULL; } static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq) { rq->rq_next = NULL; if (rl->tail) rl->tail->rq_next = rq; else rl->head = rq; rl->tail = rq; } static inline void rq_list_add_head(struct rq_list *rl, struct request *rq) { rq->rq_next = rl->head; rl->head = rq; if (!rl->tail) rl->tail = rq; } static inline struct request *rq_list_pop(struct rq_list *rl) { struct request *rq = rl->head; if (rq) { rl->head = rl->head->rq_next; if (!rl->head) rl->tail = NULL; rq->rq_next = NULL; } return rq; } static inline struct request *rq_list_peek(struct rq_list *rl) { return rl->head; } #define rq_list_for_each(rl, pos) \ for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next) #define rq_list_for_each_safe(rl, pos, nxt) \ for (pos = rq_list_peek((rl)), nxt = pos->rq_next; \ pos; pos = nxt, nxt = pos ? pos->rq_next : NULL) /** * enum blk_eh_timer_return - How the timeout handler should proceed * @BLK_EH_DONE: The block driver completed the command or will complete it at * a later time. * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the * request to complete. */ enum blk_eh_timer_return { BLK_EH_DONE, BLK_EH_RESET_TIMER, }; /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device */ struct blk_mq_hw_ctx { struct { /** @lock: Protects the dispatch list. */ spinlock_t lock; /** * @dispatch: Used for requests that are ready to be * dispatched to the hardware but for some reason (e.g. lack of * resources) could not be sent to the hardware. As soon as the * driver can send new requests, requests at this list will * be sent first for a fairer dispatch. */ struct list_head dispatch; /** * @state: BLK_MQ_S_* flags. Defines the state of the hw * queue (active, scheduled to restart, stopped). */ unsigned long state; } ____cacheline_aligned_in_smp; /** * @run_work: Used for scheduling a hardware queue run at a later time. */ struct delayed_work run_work; /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; /** * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU * selection from @cpumask. */ int next_cpu; /** * @next_cpu_batch: Counter of how many works left in the batch before * changing to the next CPU. */ int next_cpu_batch; /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ unsigned long flags; /** * @sched_data: Pointer owned by the IO scheduler attached to a request * queue. It's up to the IO scheduler how to use this pointer. */ void *sched_data; /** * @queue: Pointer to the request queue that owns this hardware context. */ struct request_queue *queue; /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; /** * @driver_data: Pointer to data owned by the block driver that created * this hctx */ void *driver_data; /** * @ctx_map: Bitmap for each software queue. If bit is on, there is a * pending request in that software queue. */ struct sbitmap ctx_map; /** * @dispatch_from: Software queue to be used when no scheduler was * selected. */ struct blk_mq_ctx *dispatch_from; /** * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to * decide if the hw_queue is busy using Exponential Weighted Moving * Average algorithm. */ unsigned int dispatch_busy; /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; /** * @dispatch_wait: Waitqueue to put requests when there is no tag * available at the moment, to wait for another try in the future. */ wait_queue_entry_t dispatch_wait; /** * @wait_index: Index of next available dispatch_wait queue to insert * requests. */ atomic_t wait_index; /** * @tags: Tags owned by the block driver. A tag at this set is only * assigned when a request is dispatched from a hardware queue. */ struct blk_mq_tags *tags; /** * @sched_tags: Tags owned by I/O scheduler. If there is an I/O * scheduler associated with a request queue, a tag is assigned when * that request is allocated. Else, this member is not used. */ struct blk_mq_tags *sched_tags; /** @numa_node: NUMA node the storage adapter has been connected to. */ int numa_node; /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; /** * @nr_active: Number of active requests. Only used when a tag set is * shared across request queues. */ atomic_t nr_active; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; /** @kobj: Kernel object for sysfs. */ struct kobject kobj; #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named * as cpu<cpu_number>. */ struct dentry *debugfs_dir; /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif /** * @hctx_list: if this hctx is not in use, this is an entry in * q->unused_hctx_list. */ struct list_head hctx_list; }; /** * struct blk_mq_queue_map - Map software queues to hardware queues * @mq_map: CPU ID to hardware queue index map. This is an array * with nr_cpu_ids elements. Each element has a value in the range * [@queue_offset, @queue_offset + @nr_queues). * @nr_queues: Number of hardware queues to map CPU IDs onto. * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe * driver to map each hardware queue type (enum hctx_type) onto a distinct * set of hardware queues. */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; /** * enum hctx_type - Type of hardware queue * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. * @HCTX_TYPE_READ: Just for READ I/O. * @HCTX_TYPE_POLL: Polled I/O of any kind. * @HCTX_MAX_TYPES: Number of types of hctx. */ enum hctx_type { HCTX_TYPE_DEFAULT, HCTX_TYPE_READ, HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; /** * struct blk_mq_tag_set - tag set that can be shared between request queues * @ops: Pointers to functions that implement block driver behavior. * @map: One or more ctx -> hctx mappings. One map exists for each * hardware queue type (enum hctx_type) that the driver wishes * to support. There are no restrictions on maps being of the * same size, and it's perfectly legal to share maps between * types. * @nr_maps: Number of elements in the @map array. A number in the range * [1, HCTX_MAX_TYPES]. * @nr_hw_queues: Number of hardware queues supported by the block driver that * owns this data structure. * @queue_depth: Number of tags per hardware queue, reserved tags included. * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag * allocations. * @cmd_size: Number of additional bytes to allocate per request. The block * driver owns these additional bytes. * @numa_node: NUMA node the storage adapter has been connected to. * @timeout: Request processing timeout in jiffies. * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @shared_tags: * Shared set of tags. Has @nr_hw_queues elements. If set, * shared by all @tags. * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. * @srcu: Use as lock when type of the request queue is blocking * (BLK_MQ_F_BLOCKING). * @tags_srcu: SRCU used to defer freeing of tags page_list to prevent * use-after-free when iterating tags. * @update_nr_hwq_lock: * Synchronize updating nr_hw_queues with add/del disk & * switching elevator. */ struct blk_mq_tag_set { const struct blk_mq_ops *ops; struct blk_mq_queue_map map[HCTX_MAX_TYPES]; unsigned int nr_maps; unsigned int nr_hw_queues; unsigned int queue_depth; unsigned int reserved_tags; unsigned int cmd_size; int numa_node; unsigned int timeout; unsigned int flags; void *driver_data; struct blk_mq_tags **tags; struct blk_mq_tags *shared_tags; struct mutex tag_list_lock; struct list_head tag_list; struct srcu_struct *srcu; struct srcu_struct tags_srcu; struct rw_semaphore update_nr_hwq_lock; }; /** * struct blk_mq_queue_data - Data about a request inserted in a queue * * @rq: Request pointer. * @last: If it is the last request in the queue. */ struct blk_mq_queue_data { struct request *rq; bool last; }; typedef bool (busy_tag_iter_fn)(struct request *, void *); /** * struct blk_mq_ops - Callback functions that implements block driver * behaviour. */ struct blk_mq_ops { /** * @queue_rq: Queue a new request from block IO. */ blk_status_t (*queue_rq)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); /** * @commit_rqs: If a driver uses bd->last to judge when to submit * requests to hardware, it must define this function. In case of errors * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ void (*commit_rqs)(struct blk_mq_hw_ctx *); /** * @queue_rqs: Queue a list of new requests. Driver is guaranteed * that each request belongs to the same queue. If the driver doesn't * empty the @rqlist completely, then the rest will be queued * individually by the block layer upon return. */ void (*queue_rqs)(struct rq_list *rqlist); /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ int (*get_budget)(struct request_queue *); /** * @put_budget: Release the reserved budget. */ void (*put_budget)(struct request_queue *, int); /** * @set_rq_budget_token: store rq's budget token */ void (*set_rq_budget_token)(struct request *, int); /** * @get_rq_budget_token: retrieve rq's budget token */ int (*get_rq_budget_token)(struct request *); /** * @timeout: Called on request timeout. */ enum blk_eh_timer_return (*timeout)(struct request *); /** * @poll: Called to poll for completion of a specific tag. */ int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *); /** * @complete: Mark the request as complete. */ void (*complete)(struct request *); /** * @init_hctx: Called when the block layer side of a hardware queue has * been set up, allowing the driver to allocate/init matching * structures. */ int (*init_hctx)(struct blk_mq_hw_ctx *, void *, unsigned int); /** * @exit_hctx: Ditto for exit/teardown. */ void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); /** * @init_request: Called for every command allocated by the block layer * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. */ int (*init_request)(struct blk_mq_tag_set *set, struct request *, unsigned int, int); /** * @exit_request: Ditto for exit/teardown. */ void (*exit_request)(struct blk_mq_tag_set *set, struct request *, unsigned int); /** * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. */ void (*cleanup_rq)(struct request *); /** * @busy: If set, returns whether or not this queue currently is busy. */ bool (*busy)(struct request_queue *); /** * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); #endif }; /* Keep hctx_flag_name[] in sync with the definitions below */ enum { BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, /* * Set when this device requires underlying blk-mq device for * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 4, /* * Alloc tags on a round-robin base instead of the first available one. */ BLK_MQ_F_TAG_RR = 1 << 5, /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6, BLK_MQ_F_MAX = 1 << 7, }; #define BLK_MQ_MAX_DEPTH (10240) #define BLK_MQ_NO_HCTX_IDX (-1U) enum { /* Keep hctx_state_name[] in sync with the definitions below */ BLK_MQ_S_STOPPED, BLK_MQ_S_TAG_ACTIVE, BLK_MQ_S_SCHED_RESTART, /* hw queue is inactive after all its CPUs become offline */ BLK_MQ_S_INACTIVE, BLK_MQ_S_MAX }; struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass); #define blk_mq_alloc_disk(set, lim, queuedata) \ ({ \ static struct lock_class_key __key; \ \ __blk_mq_alloc_disk(set, lim, queuedata, &__key); \ }) struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass); struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata); int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q); void blk_mq_destroy_queue(struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_free_request(struct request *rq); int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, unsigned int poll_flags); bool blk_mq_queue_inflight(struct request_queue *q); enum { /* return when out of requests */ BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), /* set RQF_PM */ BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2), }; struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx); /* * Tag address space map. */ struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; unsigned int active_queues; struct sbitmap_queue bitmap_tags; struct sbitmap_queue breserved_tags; struct request **rqs; struct request **static_rqs; struct list_head page_list; /* * used to clear request reference in rqs[] before freeing one * request pool */ spinlock_t lock; struct rcu_head rcu_head; }; static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) { if (tag < tags->nr_tags) { prefetch(tags->rqs[tag]); return tags->rqs[tag]; } return NULL; } enum { BLK_MQ_UNIQUE_TAG_BITS = 16, BLK_MQ_UNIQUE_TAG_MASK = (1 << BLK_MQ_UNIQUE_TAG_BITS) - 1, }; u32 blk_mq_unique_tag(struct request *rq); static inline u16 blk_mq_unique_tag_to_hwq(u32 unique_tag) { return unique_tag >> BLK_MQ_UNIQUE_TAG_BITS; } static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) { return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } /** * blk_mq_rq_state() - read the current MQ_RQ_* state of a request * @rq: target request. */ static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) { return READ_ONCE(rq->state); } static inline int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; } static inline int blk_mq_request_completed(struct request *rq) { return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } /* * * Set the state to complete when completing a request from inside ->queue_rq. * This is used by drivers that want to ensure special complete actions that * need access to the request are called on failure, e.g. by nvme for * multipathing. */ static inline void blk_mq_set_request_complete(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); } /* * Complete the request directly instead of deferring it to softirq or * completing it another CPU. Useful in preemptible instead of an interrupt. */ static inline void blk_mq_complete_request_direct(struct request *rq, void (*complete)(struct request *rq)) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); complete(rq); } void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_end_request_batch(struct io_comp_batch *ib); /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. */ static inline bool blk_mq_need_time_stamp(struct request *rq) { return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } static inline bool blk_mq_is_reserved_rq(struct request *rq) { return rq->rq_flags & RQF_RESV; } /** * blk_mq_add_to_batch() - add a request to the completion batch * @req: The request to add to batch * @iob: The batch to add the request * @is_error: Specify true if the request failed with an error * @complete: The completaion handler for the request * * Batched completions only work when there is no I/O error and no special * ->end_io handler. * * Return: true when the request was added to the batch, otherwise false */ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, bool is_error, void (*complete)(struct io_comp_batch *)) { /* * Check various conditions that exclude batch processing: * 1) No batch container * 2) Has scheduler data attached * 3) Not a passthrough request and end_io set * 4) Not a passthrough request and failed with an error */ if (!iob) return false; if (req->rq_flags & RQF_SCHED_TAGS) return false; if (!blk_rq_is_passthrough(req)) { if (req->end_io) return false; if (is_error) return false; } if (!iob->complete) iob->complete = complete; else if (iob->complete != complete) return false; iob->need_ts |= blk_mq_need_time_stamp(req); rq_list_add_tail(&iob->req_list, req); return true; } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); bool blk_mq_complete_request_remote(struct request *rq); void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set); void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set); void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); void blk_mq_freeze_queue_nomemsave(struct request_queue *q); void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q); static inline unsigned int __must_check blk_mq_freeze_queue(struct request_queue *q) { unsigned int memflags = memalloc_noio_save(); blk_mq_freeze_queue_nomemsave(q); return memflags; } static inline void blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags) { blk_mq_unfreeze_queue_nomemrestore(q); memalloc_noio_restore(memflags); } void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); void blk_mq_unfreeze_queue_non_owner(struct request_queue *q); void blk_freeze_queue_start_non_owner(struct request_queue *q); unsigned int blk_mq_num_possible_queues(unsigned int max_queues); unsigned int blk_mq_num_online_queues(unsigned int max_queues); void blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, struct device *dev, unsigned int offset); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); bool __blk_should_fake_timeout(struct request_queue *q); static inline bool blk_should_fake_timeout(struct request_queue *q) { if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) return __blk_should_fake_timeout(q); return false; } /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted * * Return: request * * Driver command data is immediately after the request. So subtract request * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } /** * blk_mq_rq_to_pdu - cast a request to a PDU * @rq: the request to be casted * * Return: pointer to the PDU * * Driver command data is immediately after the request. So add request to get * the PDU. */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; } static inline struct blk_mq_hw_ctx *queue_hctx(struct request_queue *q, int id) { struct blk_mq_hw_ctx *hctx; rcu_read_lock(); hctx = rcu_dereference(q->queue_hw_ctx)[id]; rcu_read_unlock(); return hctx; } #define queue_for_each_hw_ctx(q, hctx, i) \ for ((i) = 0; (i) < (q)->nr_hw_queues && \ ({ hctx = queue_hctx((q), i); 1; }); (i)++) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) static inline void blk_mq_cleanup_rq(struct request *rq) { if (rq->q->mq_ops->cleanup_rq) rq->q->mq_ops->cleanup_rq(rq); } void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); static inline bool rq_is_sync(struct request *rq) { return op_is_sync(rq->cmd_flags); } void blk_rq_init(struct request_queue *q, struct request *rq); int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); void blk_rq_unprep_clone(struct request *rq); blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; unsigned long offset; unsigned short page_order; unsigned short nr_entries; bool null_mapped; bool from_user; }; int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); int blk_rq_map_user_io(struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t, bool, int, bool, int); int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len, gfp_t gfp); int blk_rq_append_bio(struct request *rq, struct bio *bio); void blk_execute_rq_nowait(struct request *rq, bool at_head); blk_status_t blk_execute_rq(struct request *rq, bool at_head); bool blk_rq_is_poll(struct request *rq); struct req_iterator { struct bvec_iter iter; struct bio *bio; }; #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_for_each_bvec(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_bvec(bvl, _iter.bio, _iter.iter) #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_has_data() : whether the request carries data * blk_rq_cur_bytes() : bytes left in the current segment * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats */ static inline sector_t blk_rq_pos(const struct request *rq) { return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { return rq->__data_len; } static inline bool blk_rq_has_data(const struct request *rq) { return blk_rq_bytes(rq) && req_op(rq) != REQ_OP_DISCARD && req_op(rq) != REQ_OP_SECURE_ERASE && req_op(rq) != REQ_OP_WRITE_ZEROES; } static inline int blk_rq_cur_bytes(const struct request *rq) { if (!rq->bio) return 0; if (!bio_has_data(rq->bio)) /* dataless requests such as discard */ return rq->bio->bi_iter.bi_size; return bio_iovec(rq->bio).bv_len; } static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_stats_sectors(const struct request *rq) { return rq->stats_sectors; } /* * Some commands like WRITE SAME have a payload or data transfer size which * is different from the size of the request. Any driver that supports such * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to * calculate the data transfer size. */ static inline unsigned int blk_rq_payload_bytes(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec.bv_len; return blk_rq_bytes(rq); } /* * Return the first full biovec in the request. The caller needs to check that * there are any bvecs before calling this helper. */ static inline struct bio_vec req_bvec(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec; return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); } static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; struct bio *bio; __rq_for_each_bio(bio, rq) nr_bios++; return nr_bios; } void blk_steal_bios(struct bio_list *list, struct request *rq); /* * Request completion related functions. * * blk_update_request() completes given number of bytes and updates * the request without completing it. */ bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); void blk_abort_request(struct request *); /* * Number of physical segments as sent to the device. * * Normally this is the number of discontiguous data segments sent by the * submitter. But for data-less command like discard we might have no * actual data segments submitted, but the driver might have to add it's * own special payload. In that case we still return 1 here so that this * special payload will be mapped. */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return 1; return rq->nr_phys_segments; } /* * Number of discard segments (or ranges) the driver needs to fill in. * Each discard bio merged into a request is counted as one segment. */ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) { return max_t(unsigned short, rq->nr_phys_segments, 1); } /** * blk_rq_nr_bvec - return number of bvecs in a request * @rq: request to calculate bvecs for * * Returns the number of bvecs. */ static inline unsigned int blk_rq_nr_bvec(struct request *rq) { struct req_iterator rq_iter; struct bio_vec bv; unsigned int nr_bvec = 0; rq_for_each_bvec(bv, rq, rq_iter) nr_bvec++; return nr_bvec; } int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg); static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist) { struct scatterlist *last_sg = NULL; return __blk_rq_map_sg(rq, sglist, &last_sg); } void blk_dump_rq_flags(struct request *, char *); /** * blk_rq_passthrough_stats - check if this request should account stats * @rq: request to check * @q: the queue accumulating the stats * * Note, @q does not necessarily need to be the request_queue that provides * @rq. * * Return: true if stats should be accounted. */ static inline bool blk_rq_passthrough_stats(struct request *rq, struct request_queue *q) { struct bio *bio = rq->bio; if (!blk_queue_passthrough_stat(q)) return false; /* Requests without a bio do not transfer data. */ if (!bio) return false; /* * Stats are accumulated in the bdev, so must have one attached to a * bio to track stats. Most drivers do not set the bdev for passthrough * requests, but nvme is one that will set it. */ if (!bio->bi_bdev) return false; /* * We don't know what a passthrough command does, but we know the * payload size and data direction. Ensuring the size is aligned to the * block size filters out most commands with payloads that don't * represent sector access. */ if (blk_rq_bytes(rq) & (bdev_logical_block_size(bio->bi_bdev) - 1)) return false; return true; } #endif /* BLK_MQ_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Definitions for IB environment * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <Ursula Braun@linux.vnet.ibm.com> */ #ifndef _SMC_IB_H #define _SMC_IB_H #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/mutex.h> #include <linux/wait.h> #include <rdma/ib_verbs.h> #include <net/smc.h> #define SMC_MAX_PORTS 2 /* Max # of ports */ #define SMC_GID_SIZE sizeof(union ib_gid) #define SMC_IB_MAX_SEND_SGE 2 struct smc_ib_devices { /* list of smc ib devices definition */ struct list_head list; struct mutex mutex; /* protects list of smc ib devices */ }; extern struct smc_ib_devices smc_ib_devices; /* list of smc ib devices */ extern struct smc_lgr_list smc_lgr_list; /* list of linkgroups */ struct smc_ib_device { /* ib-device infos for smc */ struct list_head list; struct ib_device *ibdev; struct ib_port_attr pattr[SMC_MAX_PORTS]; /* ib dev. port attrs */ struct ib_event_handler event_handler; /* global ib_event handler */ struct ib_cq *roce_cq_send; /* send completion queue */ struct ib_cq *roce_cq_recv; /* recv completion queue */ struct tasklet_struct send_tasklet; /* called by send cq handler */ struct tasklet_struct recv_tasklet; /* called by recv cq handler */ char mac[SMC_MAX_PORTS][ETH_ALEN]; /* mac address per port*/ u8 pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN]; /* pnetid per port */ bool pnetid_by_user[SMC_MAX_PORTS]; /* pnetid defined by user? */ u8 initialized : 1; /* ib dev CQ, evthdl done */ struct work_struct port_event_work; unsigned long port_event_mask; DECLARE_BITMAP(ports_going_away, SMC_MAX_PORTS); atomic_t lnk_cnt; /* number of links on ibdev */ wait_queue_head_t lnks_deleted; /* wait 4 removal of all links*/ struct mutex mutex; /* protect dev setup+cleanup */ atomic_t lnk_cnt_by_port[SMC_MAX_PORTS]; /* number of links per port */ int ndev_ifidx[SMC_MAX_PORTS]; /* ndev if indexes */ }; static inline __be32 smc_ib_gid_to_ipv4(u8 gid[SMC_GID_SIZE]) { struct in6_addr *addr6 = (struct in6_addr *)gid; if (ipv6_addr_v4mapped(addr6) || !(addr6->s6_addr32[0] | addr6->s6_addr32[1] | addr6->s6_addr32[2])) return addr6->s6_addr32[3]; return cpu_to_be32(INADDR_NONE); } static inline struct net *smc_ib_net(struct smc_ib_device *smcibdev) { if (smcibdev && smcibdev->ibdev) return read_pnet(&smcibdev->ibdev->coredev.rdma_net); return NULL; } struct smc_init_info_smcrv2; struct smc_buf_desc; struct smc_link; void smc_ib_ndev_change(struct net_device *ndev, unsigned long event); int smc_ib_register_client(void) __init; void smc_ib_unregister_client(void); bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport); int smc_ib_buf_map_sg(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); void smc_ib_buf_unmap_sg(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); void smc_ib_dealloc_protection_domain(struct smc_link *lnk); int smc_ib_create_protection_domain(struct smc_link *lnk); void smc_ib_destroy_queue_pair(struct smc_link *lnk); int smc_ib_create_queue_pair(struct smc_link *lnk); int smc_ib_ready_link(struct smc_link *lnk); int smc_ib_modify_qp_rts(struct smc_link *lnk); int smc_ib_modify_qp_error(struct smc_link *lnk); long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev); int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags, struct smc_buf_desc *buf_slot, u8 link_idx); void smc_ib_put_memory_region(struct ib_mr *mr); bool smc_ib_is_sg_need_sync(struct smc_link *lnk, struct smc_buf_desc *buf_slot); void smc_ib_sync_sg_for_cpu(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); void smc_ib_sync_sg_for_device(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index, struct smc_init_info_smcrv2 *smcrv2); int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway); bool smc_ib_is_valid_local_systemid(void); int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); #endif |
| 12 12 2 1 5 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> * Copyright (c) 2013 Eric Leblond <eric@regit.org> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_reject.h> #include <linux/icmp.h> #include <linux/icmpv6.h> const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { [NFTA_REJECT_TYPE] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 }, }; EXPORT_SYMBOL_GPL(nft_reject_policy); int nft_reject_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_PRE_ROUTING)); } EXPORT_SYMBOL_GPL(nft_reject_validate); int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); int icmp_code; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: case NFT_REJECT_ICMPX_UNREACH: if (tb[NFTA_REJECT_ICMP_CODE] == NULL) return -EINVAL; icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); if (priv->type == NFT_REJECT_ICMPX_UNREACH && icmp_code > NFT_REJECT_ICMPX_MAX) return -EINVAL; priv->icmp_code = icmp_code; break; case NFT_REJECT_TCP_RST: break; default: return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(nft_reject_init); int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_reject *priv = nft_expr_priv(expr); if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) goto nla_put_failure; switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: case NFT_REJECT_ICMPX_UNREACH: if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; default: break; } return 0; nla_put_failure: return -1; } EXPORT_SYMBOL_GPL(nft_reject_dump); static u8 icmp_code_v4[NFT_REJECT_ICMPX_MAX + 1] = { [NFT_REJECT_ICMPX_NO_ROUTE] = ICMP_NET_UNREACH, [NFT_REJECT_ICMPX_PORT_UNREACH] = ICMP_PORT_UNREACH, [NFT_REJECT_ICMPX_HOST_UNREACH] = ICMP_HOST_UNREACH, [NFT_REJECT_ICMPX_ADMIN_PROHIBITED] = ICMP_PKT_FILTERED, }; int nft_reject_icmp_code(u8 code) { if (WARN_ON_ONCE(code > NFT_REJECT_ICMPX_MAX)) return ICMP_NET_UNREACH; return icmp_code_v4[code]; } EXPORT_SYMBOL_GPL(nft_reject_icmp_code); static u8 icmp_code_v6[NFT_REJECT_ICMPX_MAX + 1] = { [NFT_REJECT_ICMPX_NO_ROUTE] = ICMPV6_NOROUTE, [NFT_REJECT_ICMPX_PORT_UNREACH] = ICMPV6_PORT_UNREACH, [NFT_REJECT_ICMPX_HOST_UNREACH] = ICMPV6_ADDR_UNREACH, [NFT_REJECT_ICMPX_ADMIN_PROHIBITED] = ICMPV6_ADM_PROHIBITED, }; int nft_reject_icmpv6_code(u8 code) { if (WARN_ON_ONCE(code > NFT_REJECT_ICMPX_MAX)) return ICMPV6_NOROUTE; return icmp_code_v6[code]; } EXPORT_SYMBOL_GPL(nft_reject_icmpv6_code); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Netfilter x_tables over nftables module"); |
| 9 8 8 7 2 1 2 2 8 10 8 2 2 2 1 1 13 13 2 2 10 10 10 10 10 9 9 9 5 9 9 9 9 6 9 3 3 4 4 3 3 1 2 1 10 5 6 6 3 3 2 1 2 1 2 2 1 1 1 2 2 2 1 2 2 2 2 3 11 11 6 11 11 2 2 2 2 2 2 2 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/super.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/module.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/parser.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/vfs.h> #include <linux/random.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/ctype.h> #include <linux/log2.h> #include <linux/crc16.h> #include <linux/dax.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include <linux/unicode.h> #include <linux/part_stat.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/fsnotify.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/fserror.h> #include "ext4.h" #include "ext4_extents.h" /* Needed for trace points definition */ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "mballoc.h" #include "fsmap.h" #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> static struct ext4_lazy_init *ext4_li_info; static DEFINE_MUTEX(ext4_li_mtx); static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static void ext4_update_super(struct super_block *sb); static int ext4_commit_super(struct super_block *sb); static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); static int ext4_freeze(struct super_block *sb); static inline int ext2_feature_set_ok(struct super_block *sb); static inline int ext3_feature_set_ok(struct super_block *sb); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum); static int ext4_validate_options(struct fs_context *fc); static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb); static void ext4_apply_options(struct fs_context *fc, struct super_block *sb); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param); static int ext4_get_tree(struct fs_context *fc); static int ext4_reconfigure(struct fs_context *fc); static void ext4_fc_free(struct fs_context *fc); static int ext4_init_fs_context(struct fs_context *fc); static void ext4_kill_sb(struct super_block *sb); static const struct fs_parameter_spec ext4_param_specs[]; /* * Lock ordering * * page fault path: * mmap_lock -> sb_start_pagefault -> invalidate_lock (r) -> transaction start * -> page lock -> i_data_sem (rw) * * buffered write path: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> page lock -> * i_data_sem (rw) * * truncate: * sb_start_write -> i_mutex -> invalidate_lock (w) -> i_mmap_rwsem (w) -> * page lock * sb_start_write -> i_mutex -> invalidate_lock (w) -> transaction start -> * i_data_sem (rw) * * direct IO: * sb_start_write -> i_mutex -> mmap_lock * sb_start_write -> i_mutex -> transaction start -> i_data_sem (rw) * * writepages: * transaction start -> page lock(s) -> i_data_sem (rw) */ static const struct fs_context_operations ext4_context_ops = { .parse_param = ext4_parse_param, .get_tree = ext4_get_tree, .reconfigure = ext4_reconfigure, .free = ext4_fc_free, }; #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static struct file_system_type ext2_fs_type = { .owner = THIS_MODULE, .name = "ext2", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext2"); MODULE_ALIAS("ext2"); #define IS_EXT2_SB(sb) ((sb)->s_type == &ext2_fs_type) #else #define IS_EXT2_SB(sb) (0) #endif static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("ext3"); MODULE_ALIAS("ext3"); #define IS_EXT3_SB(sb) ((sb)->s_type == &ext3_fs_type) static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bio_end_io_t end_io, bool simu_fail) { if (simu_fail) { clear_buffer_uptodate(bh); unlock_buffer(bh); return; } /* * buffer's verified bit is no longer valid after reading from * disk again due to write out error, clear it to make sure we * recheck the buffer contents. */ clear_buffer_verified(bh); if (!end_io) end_io = bh_end_read; bh_submit(bh, REQ_OP_READ | op_flags, end_io); } void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags, bio_end_io_t end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return; } __ext4_read_bh(bh, op_flags, end_io, simu_fail); } int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bio_end_io_t end_io, bool simu_fail) { BUG_ON(!buffer_locked(bh)); if (ext4_buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } __ext4_read_bh(bh, op_flags, end_io, simu_fail); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { lock_buffer(bh); if (!wait) { ext4_read_bh_nowait(bh, op_flags, NULL, false); return 0; } return ext4_read_bh(bh, op_flags, NULL, false); } /* * This works like __bread_gfp() except it uses ERR_PTR for error * returns. Currently with sb_bread it's impossible to distinguish * between ENOMEM and EIO situations (since both result in a NULL * return. */ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb, sector_t block, blk_opf_t op_flags, gfp_t gfp) { struct buffer_head *bh; int ret; bh = sb_getblk_gfp(sb, block, gfp); if (bh == NULL) return ERR_PTR(-ENOMEM); if (ext4_buffer_uptodate(bh)) return bh; ret = ext4_read_bh_lock(bh, REQ_META | op_flags, true); if (ret) { put_bh(bh); return ERR_PTR(ret); } return bh; } struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block, blk_opf_t op_flags) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS) | __GFP_MOVABLE; return __ext4_sb_bread_gfp(sb, block, op_flags, gfp); } struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, sector_t block) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS); return __ext4_sb_bread_gfp(sb, block, 0, gfp); } struct buffer_head *ext4_sb_bread_nofail(struct super_block *sb, sector_t block) { gfp_t gfp = mapping_gfp_constraint(sb->s_bdev->bd_mapping, ~__GFP_FS) | __GFP_MOVABLE | __GFP_NOFAIL; return __ext4_sb_bread_gfp(sb, block, 0, gfp); } void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, sb->s_blocksize, GFP_NOWAIT); if (likely(bh)) { if (trylock_buffer(bh)) ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL, false); brelse(bh); } } static int ext4_verify_csum_type(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_feature_metadata_csum(sb)) return 1; return es->s_checksum_type == EXT4_CRC32C_CHKSUM; } __le32 ext4_superblock_csum(struct ext4_super_block *es) { int offset = offsetof(struct ext4_super_block, s_checksum); __u32 csum; csum = ext4_chksum(~0, (char *)es, offset); return cpu_to_le32(csum); } static int ext4_superblock_csum_verify(struct super_block *sb, struct ext4_super_block *es) { if (!ext4_has_feature_metadata_csum(sb)) return 1; return es->s_checksum == ext4_superblock_csum(es); } void ext4_superblock_csum_set(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (!ext4_has_feature_metadata_csum(sb)) return; es->s_checksum = ext4_superblock_csum(es); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_block_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_bitmap_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0); } ext4_fsblk_t ext4_inode_table(struct super_block *sb, struct ext4_group_desc *bg) { return le32_to_cpu(bg->bg_inode_table_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0); } __u32 ext4_free_group_clusters(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_free_blocks_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_free_blocks_count_hi) << 16 : 0); } __u32 ext4_free_inodes_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0); } __u32 ext4_used_dirs_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_used_dirs_count_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_used_dirs_count_hi) << 16 : 0); } __u32 ext4_itable_unused_count(struct super_block *sb, struct ext4_group_desc *bg) { return le16_to_cpu(bg->bg_itable_unused_lo) | (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ? (__u32)le16_to_cpu(bg->bg_itable_unused_hi) << 16 : 0); } void ext4_block_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_block_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_bitmap_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_bitmap_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32); } void ext4_inode_table_set(struct super_block *sb, struct ext4_group_desc *bg, ext4_fsblk_t blk) { bg->bg_inode_table_lo = cpu_to_le32((u32)blk); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_inode_table_hi = cpu_to_le32(blk >> 32); } void ext4_free_group_clusters_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_free_blocks_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_free_blocks_count_hi = cpu_to_le16(count >> 16); } void ext4_free_inodes_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count)); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16)); } void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_used_dirs_count_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_used_dirs_count_hi = cpu_to_le16(count >> 16); } void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count) { bg->bg_itable_unused_lo = cpu_to_le16((__u16)count); if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT) bg->bg_itable_unused_hi = cpu_to_le16(count >> 16); } static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now) { now = clamp_val(now, 0, (1ull << 40) - 1); *lo = cpu_to_le32(lower_32_bits(now)); *hi = upper_32_bits(now); } static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) { return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo); } #define ext4_update_tstamp(es, tstamp) \ __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \ ktime_get_real_seconds()) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) /* * The ext4_maybe_update_superblock() function checks and updates the * superblock if needed. * * This function is designed to update the on-disk superblock only under * certain conditions to prevent excessive disk writes and unnecessary * waking of the disk from sleep. The superblock will be updated if: * 1. More than sbi->s_sb_update_sec (def: 1 hour) has passed since the last * superblock update * 2. More than sbi->s_sb_update_kb (def: 16MB) kbs have been written since the * last superblock update. * * @sb: The superblock */ static void ext4_maybe_update_superblock(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; journal_t *journal = sbi->s_journal; time64_t now; __u64 last_update; __u64 lifetime_write_kbytes; __u64 diff_size; if (ext4_emergency_state(sb) || sb_rdonly(sb) || !(sb->s_flags & SB_ACTIVE) || !journal || journal->j_flags & JBD2_UNMOUNT) return; now = ktime_get_real_seconds(); last_update = ext4_get_tstamp(es, s_wtime); if (likely(now - last_update < sbi->s_sb_update_sec)) return; lifetime_write_kbytes = sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); /* Get the number of kilobytes not written to disk to account * for statistics and compare with a multiple of 16 MB. This * is used to determine when the next superblock commit should * occur (i.e. not more often than once per 16MB if there was * less written in an hour). */ diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written); if (diff_size > sbi->s_sb_update_kb) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) { struct super_block *sb = journal->j_private; BUG_ON(txn->t_state == T_FINISHED); ext4_process_freed_data(sb, txn->t_tid); ext4_maybe_update_superblock(sb); } static bool ext4_journalled_writepage_needs_redirty(struct jbd2_inode *jinode, struct folio *folio) { struct buffer_head *bh, *head; struct journal_head *jh; transaction_t *trans = READ_ONCE(jinode->i_transaction); bh = head = folio_buffers(folio); do { /* * We have to redirty a page in these cases: * 1) If buffer is dirty, it means the page was dirty because it * contains a buffer that needs checkpointing. So the dirty bit * needs to be preserved so that checkpointing writes the buffer * properly. * 2) If buffer is not part of the committing transaction * (we may have just accidentally come across this buffer because * inode range tracking is not exact) or if the currently running * transaction already contains this buffer as well, dirty bit * needs to be preserved so that the buffer gets writeprotected * properly on running transaction's commit. */ jh = bh2jh(bh); if (buffer_dirty(bh) || (jh && (jh->b_transaction != trans || jh->b_next_transaction))) return true; } while ((bh = bh->b_this_page) != head); return false; } static int ext4_journalled_submit_inode_data_buffers(struct jbd2_inode *jinode) { struct address_space *mapping = jinode->i_vfs_inode->i_mapping; loff_t range_start, range_end; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, }; struct folio *folio = NULL; int error; if (!jbd2_jinode_get_dirty_range(jinode, &range_start, &range_end)) return 0; wbc.range_start = range_start; wbc.range_end = range_end; /* * writeback_iter() already checks for dirty pages and calls * folio_clear_dirty_for_io(), which we want to write protect the * folios. * * However, we may have to redirty a folio sometimes. */ while ((folio = writeback_iter(mapping, &wbc, folio, &error))) { if (ext4_journalled_writepage_needs_redirty(jinode, folio)) folio_redirty_for_writepage(&wbc, folio); folio_unlock(folio); } return error; } static int ext4_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) { int ret; if (ext4_should_journal_data(jinode->i_vfs_inode)) ret = ext4_journalled_submit_inode_data_buffers(jinode); else ret = ext4_normal_submit_inode_data_buffers(jinode); return ret; } static int ext4_journal_finish_inode_data_buffers(struct jbd2_inode *jinode) { int ret = 0; if (!ext4_should_journal_data(jinode->i_vfs_inode)) ret = jbd2_journal_finish_inode_data_buffers(jinode); return ret; } static bool system_going_down(void) { return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART; } struct ext4_err_translation { int code; int errno; }; #define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err } static struct ext4_err_translation err_translation[] = { EXT4_ERR_TRANSLATE(EIO), EXT4_ERR_TRANSLATE(ENOMEM), EXT4_ERR_TRANSLATE(EFSBADCRC), EXT4_ERR_TRANSLATE(EFSCORRUPTED), EXT4_ERR_TRANSLATE(ENOSPC), EXT4_ERR_TRANSLATE(ENOKEY), EXT4_ERR_TRANSLATE(EROFS), EXT4_ERR_TRANSLATE(EFBIG), EXT4_ERR_TRANSLATE(EEXIST), EXT4_ERR_TRANSLATE(ERANGE), EXT4_ERR_TRANSLATE(EOVERFLOW), EXT4_ERR_TRANSLATE(EBUSY), EXT4_ERR_TRANSLATE(ENOTDIR), EXT4_ERR_TRANSLATE(ENOTEMPTY), EXT4_ERR_TRANSLATE(ESHUTDOWN), EXT4_ERR_TRANSLATE(EFAULT), }; static int ext4_errno_to_code(int errno) { int i; for (i = 0; i < ARRAY_SIZE(err_translation); i++) if (err_translation[i].errno == errno) return err_translation[i].code; return EXT4_ERR_UNKNOWN; } static void save_error_info(struct super_block *sb, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* We default to EFSCORRUPTED error... */ if (error == 0) error = EFSCORRUPTED; spin_lock(&sbi->s_error_lock); sbi->s_add_error_count++; sbi->s_last_error_code = error; sbi->s_last_error_line = line; sbi->s_last_error_ino = ino; sbi->s_last_error_block = block; sbi->s_last_error_func = func; sbi->s_last_error_time = ktime_get_real_seconds(); if (!sbi->s_first_error_time) { sbi->s_first_error_code = error; sbi->s_first_error_line = line; sbi->s_first_error_ino = ino; sbi->s_first_error_block = block; sbi->s_first_error_func = func; sbi->s_first_error_time = sbi->s_last_error_time; } spin_unlock(&sbi->s_error_lock); } /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * * On ext2, we can store the error state of the filesystem in the * superblock. That is not possible on ext4, because we may have other * write ordering constraints on the superblock which prevent us from * writing it out straight away; and given that the journal is about to * be aborted, we can't rely on the current, or future, transactions to * write out the superblock safely. * * We'll just use the jbd2_journal_abort() error code to record an error in * the journal instead. On recovery, the journal will complain about * that error until we've noted it down and cleared it. * * If force_ro is set, we unconditionally force the filesystem into an * ABORT|READONLY state, unless the error response on the fs has been set to * panic in which case we take the easy way out and panic immediately. This is * used to deal with unrecoverable failures such as journal IO errors or ENOMEM * at a critical moment in log management. */ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, __u32 ino, __u64 block, const char *func, unsigned int line) { journal_t *journal = EXT4_SB(sb)->s_journal; bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); if (!continue_fs && !ext4_emergency_ro(sb) && journal) jbd2_journal_abort(journal, -error); if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, error, ino, block, func, line); /* * In case the fs should keep running, we need to writeout * superblock through the journal. Due to lock ordering * constraints, it may not be safe to do it right here so we * defer superblock flushing to a workqueue. We just need to be * careful when the journal is already shutting down. If we get * here in that case, just update the sb directly as the last * transaction won't commit anyway. */ if (continue_fs && journal && !ext4_test_mount_flag(sb, EXT4_MF_JOURNAL_DESTROY)) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); else ext4_commit_super(sb); } /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already * disabled. */ if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); } if (ext4_emergency_ro(sb) || continue_fs) return; ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * We don't set SB_RDONLY because that requires sb->s_umount * semaphore and setting it without proper remount procedure is * confusing code such as freeze_super() leading to deadlocks * and other problems. */ set_bit(EXT4_FLAGS_EMERGENCY_RO, &EXT4_SB(sb)->s_ext4_flags); } static void update_super_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_sb_upd_work); journal_t *journal = sbi->s_journal; handle_t *handle; /* * If the journal is still running, we have to write out superblock * through the journal to avoid collisions of other journalled sb * updates. * * We use directly jbd2 functions here to avoid recursing back into * ext4 error handling code during handling of previous errors. */ if (!ext4_emergency_state(sbi->s_sb) && !sb_rdonly(sbi->s_sb) && journal) { struct buffer_head *sbh = sbi->s_sbh; bool call_notify_err = false; handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; if (jbd2_journal_get_write_access(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } if (sbi->s_add_error_count > 0) call_notify_err = true; ext4_update_super(sbi->s_sb); if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } if (jbd2_journal_dirty_metadata(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } jbd2_journal_stop(handle); if (call_notify_err) ext4_notify_error_sysfs(sbi); return; } write_directly: /* * Write through journal failed. Write sb directly to get error info * out and hope for the best. */ ext4_commit_super(sbi->s_sb); ext4_notify_error_sysfs(sbi); } #define ext4_error_ratelimit(sb) \ ___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \ "EXT4-fs error") void __ext4_error(struct super_block *sb, const char *function, unsigned int line, bool force_ro, int error, __u64 block, const char *fmt, ...) { struct va_format vaf; va_list args; if (unlikely(ext4_emergency_state(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n", sb->s_id, function, line, current->comm, &vaf); va_end(args); } fserror_report_metadata(sb, error ? -abs(error) : -EFSCORRUPTED, GFP_ATOMIC); ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, unsigned int line, ext4_fsblk_t block, int error, const char *fmt, ...) { va_list args; struct va_format vaf; if (unlikely(ext4_emergency_state(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%llu: block %llu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: " "inode #%llu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } fserror_report_file_metadata(inode, error ? -abs(error) : -EFSCORRUPTED, GFP_ATOMIC); ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, function, line); } void __ext4_error_file(struct file *file, const char *function, unsigned int line, ext4_fsblk_t block, const char *fmt, ...) { va_list args; struct va_format vaf; struct inode *inode = file_inode(file); char pathname[80], *path; if (unlikely(ext4_emergency_state(inode->i_sb))) return; trace_ext4_error(inode->i_sb, function, line); if (ext4_error_ratelimit(inode->i_sb)) { path = file_path(file, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (block) printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%llu: " "block %llu: comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, block, current->comm, path, &vaf); else printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%llu: " "comm %s: path %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, path, &vaf); va_end(args); } fserror_report_file_metadata(inode, -EFSCORRUPTED, GFP_ATOMIC); ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, char nbuf[16]) { char *errstr = NULL; switch (errno) { case -EFSCORRUPTED: errstr = "Corrupt filesystem"; break; case -EFSBADCRC: errstr = "Filesystem failed CRC"; break; case -EIO: errstr = "IO failure"; break; case -ENOMEM: errstr = "Out of memory"; break; case -EROFS: if (!sb || (EXT4_SB(sb)->s_journal && EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)) errstr = "Journal has aborted"; else errstr = "Readonly filesystem"; break; default: /* If the caller passed in an extra buffer for unknown * errors, textualise them now. Else we just return * NULL. */ if (nbuf) { /* Check for truncated error codes... */ if (snprintf(nbuf, 16, "error %d", -errno) >= 0) errstr = nbuf; } break; } return errstr; } /* __ext4_std_error decodes expected errors from journaling functions * automatically and invokes the appropriate error response. */ void __ext4_std_error(struct super_block *sb, const char *function, unsigned int line, int errno) { char nbuf[16]; const char *errstr; if (unlikely(ext4_emergency_state(sb))) return; /* Special case: if the error is EROFS, and we're not already * inside a transaction, then there's really no point in logging * an error. */ if (errno == -EROFS && journal_current_handle() == NULL && sb_rdonly(sb)) return; if (ext4_error_ratelimit(sb)) { errstr = ext4_decode_error(sb, errno, nbuf); printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n", sb->s_id, function, line, errstr); } fserror_report_metadata(sb, errno ? -abs(errno) : -EFSCORRUPTED, GFP_ATOMIC); ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) { struct va_format vaf; va_list args; if (sb) { atomic_inc(&EXT4_SB(sb)->s_msg_count); if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) return; } va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (sb) printk("%sEXT4-fs (%s): %pV\n", prefix, sb->s_id, &vaf); else printk("%sEXT4-fs: %pV\n", prefix, &vaf); va_end(args); } static int ext4_warning_ratelimit(struct super_block *sb) { atomic_inc(&EXT4_SB(sb)->s_warning_count); return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), "EXT4-fs warning"); } void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: %pV\n", sb->s_id, function, line, &vaf); va_end(args); } void __ext4_warning_inode(const struct inode *inode, const char *function, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (!ext4_warning_ratelimit(inode->i_sb)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: " "inode #%llu: comm %s: %pV\n", inode->i_sb->s_id, function, line, inode->i_ino, current->comm, &vaf); va_end(args); } void __ext4_grp_locked_error(const char *function, unsigned int line, struct super_block *sb, ext4_group_t grp, u64 ino, ext4_fsblk_t block, const char *fmt, ...) __releases(bitlock) __acquires(bitlock) { struct va_format vaf; va_list args; if (unlikely(ext4_emergency_state(sb))) return; trace_ext4_error(sb, function, line); if (ext4_error_ratelimit(sb)) { va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ", sb->s_id, function, line, grp); if (ino) printk(KERN_CONT "inode %llu: ", ino); if (block) printk(KERN_CONT "block %llu:", (unsigned long long) block); printk(KERN_CONT "%pV\n", &vaf); va_end(args); } if (test_opt(sb, ERRORS_CONT)) { if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (!bdev_read_only(sb->s_bdev)) { save_error_info(sb, EFSCORRUPTED, ino, block, function, line); schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } return; } ext4_unlock_group(sb, grp); ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the * filesystem will have already been marked read/only and the * journal has been aborted. We return 1 as a hint to callers * who might what to use the return value from * ext4_grp_locked_error() to distinguish between the * ERRORS_CONT and ERRORS_RO case, and perhaps return more * aggressively from the ext4 function in question, with a * more appropriate error code. */ ext4_lock_group(sb, grp); return; } void ext4_mark_group_bitmap_corrupted(struct super_block *sb, ext4_group_t group, unsigned int flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; if (!grp || !gdp) return; if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret) percpu_counter_sub(&sbi->s_freeclusters_counter, grp->bb_free); } if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); if (!ret && gdp) { int count; count = ext4_free_inodes_count(sb, gdp); percpu_counter_sub(&sbi->s_freeinodes_counter, count); } } } void ext4_update_dynamic_rev(struct super_block *sb) { struct ext4_super_block *es = EXT4_SB(sb)->s_es; if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV) return; ext4_warning(sb, "updating to rev %d because of new feature flag, " "running e2fsck is recommended", EXT4_DYNAMIC_REV); es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO); es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE); es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV); /* leave es->s_feature_*compat flags alone */ /* es->s_uuid will be set by e2fsck if empty */ /* * The rest of the superblock fields should be zero, and if not it * means they are likely already in use, so leave them alone. We * can leave it up to e2fsck to clean up any inconsistencies there. */ } static inline struct inode *orphan_list_entry(struct list_head *l) { return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode; } static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi) { struct list_head *l; ext4_msg(sb, KERN_ERR, "sb orphan head is %d", le32_to_cpu(sbi->s_es->s_last_orphan)); printk(KERN_ERR "sb_info orphan list:\n"); list_for_each(l, &sbi->s_orphan) { struct inode *inode = orphan_list_entry(l); printk(KERN_ERR " " "inode %s:%llu at %p: mode %o, nlink %d, next %d\n", inode->i_sb->s_id, inode->i_ino, inode, inode->i_mode, inode->i_nlink, NEXT_ORPHAN(inode)); } } #ifdef CONFIG_QUOTA static int ext4_quota_off(struct super_block *sb, int type); static inline void ext4_quotas_off(struct super_block *sb, int type) { BUG_ON(type > EXT4_MAXQUOTAS); /* Use our quota_off function to clear inode flags etc. */ for (type--; type >= 0; type--) ext4_quota_off(sb, type); } /* * This is a helper function which is used in the mount/remount * codepaths (which holds s_umount) to fetch the quota file name. */ static inline char *get_qf_name(struct super_block *sb, struct ext4_sb_info *sbi, int type) { return rcu_dereference_protected(sbi->s_qf_names[type], lockdep_is_held(&sb->s_umount)); } #else static inline void ext4_quotas_off(struct super_block *sb, int type) { } #endif static int ext4_percpu_param_init(struct ext4_sb_info *sbi) { ext4_fsblk_t block; int err; block = ext4_count_free_clusters(sbi->s_sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sbi->s_sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } if (!err) err = percpu_counter_init(&sbi->s_dirs_counter, ext4_count_dirs(sbi->s_sb), GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0, GFP_KERNEL); if (!err) err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) ext4_msg(sbi->s_sb, KERN_ERR, "insufficient memory"); return err; } static void ext4_percpu_param_destroy(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); } static void ext4_group_desc_free(struct ext4_sb_info *sbi) { struct buffer_head **group_desc; int i; group_desc = rcu_access_pointer(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) brelse(group_desc[i]); kvfree(group_desc); } static void ext4_flex_groups_free(struct ext4_sb_info *sbi) { struct flex_groups **flex_groups; int i; flex_groups = rcu_access_pointer(sbi->s_flex_groups); if (flex_groups) { for (i = 0; i < sbi->s_flex_groups_allocated; i++) kvfree(flex_groups[i]); kvfree(flex_groups); } } static void ext4_put_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int aborted = 0; int err; /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL * Unregister sysfs before flush sbi->s_sb_upd_work. * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If * read metadata verify failed then will queue error work. * update_super_work will call start_this_handle may trigger * BUG_ON. */ ext4_unregister_sysfs(sb); if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs unmount")) ext4_msg(sb, KERN_INFO, "unmounting filesystem %pU.", &sb->s_uuid); ext4_unregister_li_request(sb); ext4_quotas_off(sb, EXT4_MAXQUOTAS); destroy_workqueue(sbi->rsv_conversion_wq); ext4_release_orphan_info(sb); if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = ext4_journal_destroy(sbi, sbi->s_journal); if ((err < 0) && !aborted) { ext4_abort(sb, -err, "Couldn't clean up the journal"); } } else flush_work(&sbi->s_sb_upd_work); ext4_es_unregister_shrinker(sbi); timer_shutdown_sync(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); if (!ext4_emergency_state(sb) && !sb_rdonly(sb)) { if (!aborted) { ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); es->s_state = cpu_to_le16(sbi->s_mount_state); } ext4_commit_super(sb); } ext4_group_desc_free(sbi); ext4_flex_groups_free(sbi); WARN_ON_ONCE(!(sbi->s_mount_state & EXT4_ERROR_FS) && percpu_counter_sum(&sbi->s_dirtyclusters_counter)); ext4_percpu_param_destroy(sbi); #ifdef CONFIG_QUOTA for (int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif /* Debugging code just in case the in-memory inode orphan list * isn't empty. The on-disk one can be non-empty if we've * detected an error and taken the fs readonly, but the * in-memory list had better be clean by this point. */ if (!list_empty(&sbi->s_orphan)) dump_orphan_list(sb, sbi); ASSERT(list_empty(&sbi->s_orphan)); sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->s_journal_bdev_file) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ sync_blockdev(file_bdev(sbi->s_journal_bdev_file)); invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; ext4_stop_mmpd(sbi); brelse(sbi->s_sbh); sb->s_fs_info = NULL; /* * Now that we are completely done shutting down the * superblock, we need to actually destroy the kobject. */ kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); } static struct kmem_cache *ext4_inode_cachep; /* * Called inside transaction, so use GFP_NOFS */ static struct inode *ext4_alloc_inode(struct super_block *sb) { struct ext4_inode_info *ei; ei = alloc_inode_sb(sb, ext4_inode_cachep, GFP_NOFS); if (!ei) return NULL; inode_set_iversion(&ei->vfs_inode, 1); ei->i_flags = 0; ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ spin_lock_init(&ei->i_raw_lock); ei->i_prealloc_node = RB_ROOT; atomic_set(&ei->i_prealloc_active, 0); rwlock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); INIT_LIST_HEAD(&ei->i_es_list); ei->i_es_all_nr = 0; ei->i_es_shk_nr = 0; ei->i_es_shrink_lblk = 0; ei->i_es_seq = 0; ei->i_reserved_data_blocks = 0; spin_lock_init(&(ei->i_block_reservation_lock)); ext4_init_pending_tree(&ei->i_pending_tree); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); #endif ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_rsv_conversion_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); ext4_fc_init_inode(&ei->vfs_inode); spin_lock_init(&ei->i_fc_lock); mmb_init(&ei->i_metadata_bhs, &ei->vfs_inode.i_data); return &ei->vfs_inode; } static int ext4_drop_inode(struct inode *inode) { int drop = inode_generic_drop(inode); if (!drop) drop = fscrypt_drop_inode(inode); trace_ext4_drop_inode(inode, drop); return drop; } static void ext4_free_in_core_inode(struct inode *inode) { fscrypt_free_inode(inode); if (!list_empty(&(EXT4_I(inode)->i_fc_list))) { pr_warn("%s: inode %llu still in fc list", __func__, inode->i_ino); } kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } static void ext4_destroy_inode(struct inode *inode) { if (ext4_inode_orphan_tracked(inode)) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %llu (%p): inode tracked as orphan!", inode->i_ino, EXT4_I(inode)); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4, EXT4_I(inode), sizeof(struct ext4_inode_info), true); dump_stack(); } if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ERROR_FS) && WARN_ON_ONCE(EXT4_I(inode)->i_reserved_data_blocks)) ext4_msg(inode->i_sb, KERN_ERR, "Inode %llu (%p): i_reserved_data_blocks (%u) not cleared!", inode->i_ino, EXT4_I(inode), EXT4_I(inode)->i_reserved_data_blocks); } static void ext4_shutdown(struct super_block *sb) { ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH); } static void init_once(void *foo) { struct ext4_inode_info *ei = foo; INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); inode_init_once(&ei->vfs_inode); ext4_fc_init_inode(&ei->vfs_inode); #ifdef CONFIG_FS_ENCRYPTION ei->i_crypt_info = NULL; #endif } static int __init init_inodecache(void) { struct kmem_cache_args args = { .useroffset = offsetof(struct ext4_inode_info, i_data), .usersize = sizeof_field(struct ext4_inode_info, i_data), .use_freeptr_offset = true, .freeptr_offset = offsetof(struct ext4_inode_info, i_flags), .ctor = init_once, }; ext4_inode_cachep = kmem_cache_create("ext4_inode_cache", sizeof(struct ext4_inode_info), &args, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT); if (ext4_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(ext4_inode_cachep); } void ext4_clear_inode(struct inode *inode) { ext4_fc_del(inode); if (!EXT4_SB(inode->i_sb)->s_journal) mmb_invalidate(&EXT4_I(inode)->i_metadata_bhs); clear_inode(inode); ext4_discard_preallocations(inode); /* * We must remove the inode from the hash before ext4_free_inode() * clears the bit in inode bitmap as otherwise another process reusing * the inode will block in insert_inode_hash() waiting for inode * eviction to complete while holding transaction handle open, but * ext4_evict_inode() still running for that inode could block waiting * for transaction commit if the inode is marked as IS_SYNC => deadlock. * * Removing the inode from the hash here is safe. There are two cases * to consider: * 1) The inode still has references to it (i_nlink > 0). In that case * we are keeping the inode and once we remove the inode from the hash, * iget() can create the new inode structure for the same inode number * and we are fine with that as all IO on behalf of the inode is * finished. * 2) We are deleting the inode (i_nlink == 0). In that case inode * number cannot be reused until ext4_free_inode() clears the bit in * the inode bitmap, at which point all IO is done and reuse is fine * again. */ remove_inode_hash(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode); jbd2_free_inode(EXT4_I(inode)->jinode); EXT4_I(inode)->jinode = NULL; } fscrypt_put_encryption_info(inode); } static struct inode *ext4_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation) { struct inode *inode; /* * Currently we don't know the generation for parent directory, so * a generation of 0 means "accept any" */ inode = ext4_iget(sb, ino, EXT4_IGET_HANDLE); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { iput(inode); return ERR_PTR(-ESTALE); } return inode; } static struct dentry *ext4_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { return generic_fh_to_parent(sb, fid, fh_len, fh_type, ext4_nfs_get_inode); } static int ext4_nfs_commit_metadata(struct inode *inode) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL }; trace_ext4_nfs_commit_metadata(inode); return ext4_write_inode(inode, &wbc); } #ifdef CONFIG_QUOTA static const char * const quotatypes[] = INITQFNAMES; #define QTYPE2NAME(t) (quotatypes[t]) static int ext4_write_dquot(struct dquot *dquot); static int ext4_acquire_dquot(struct dquot *dquot); static int ext4_release_dquot(struct dquot *dquot); static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); static struct dquot __rcu **ext4_get_dquots(struct inode *inode) { return EXT4_I(inode)->i_dquot; } static const struct dquot_operations ext4_quota_operations = { .get_reserved_space = ext4_get_reserved_space, .write_dquot = ext4_write_dquot, .acquire_dquot = ext4_acquire_dquot, .release_dquot = ext4_release_dquot, .mark_dirty = ext4_mark_dquot_dirty, .write_info = ext4_write_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = ext4_get_projid, .get_inode_usage = ext4_get_inode_usage, .get_next_id = dquot_get_next_id, }; static const struct quotactl_ops ext4_qctl_operations = { .quota_on = ext4_quota_on, .quota_off = ext4_quota_off, .quota_sync = dquot_quota_sync, .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk, .get_nextdqblk = dquot_get_next_dqblk, }; #endif static const struct super_operations ext4_sops = { .alloc_inode = ext4_alloc_inode, .free_inode = ext4_free_in_core_inode, .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .sync_fs = ext4_sync_fs, .freeze_fs = ext4_freeze, .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .show_options = ext4_show_options, .shutdown = ext4_shutdown, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, .get_dquots = ext4_get_dquots, #endif }; static const struct export_operations ext4_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, .commit_metadata = ext4_nfs_commit_metadata, }; enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, Opt_resgid, Opt_resuid, Opt_sb, Opt_nouid32, Opt_debug, Opt_removed, Opt_user_xattr, Opt_acl, Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload, Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev, Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit, Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_inlinecrypt, Opt_usrjquota, Opt_grpjquota, Opt_quota, Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, Opt_nowarn_on_error, Opt_mblk_io_submit, Opt_debug_want_extra_isize, Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, Opt_no_prefetch_block_bitmaps, Opt_mb_optimize_scan, Opt_errors, Opt_data, Opt_data_err, Opt_jqfmt, Opt_dax_type, #ifdef CONFIG_EXT4_DEBUG Opt_fc_debug_max_replay, Opt_fc_debug_force #endif }; static const struct constant_table ext4_param_errors[] = { {"continue", EXT4_MOUNT_ERRORS_CONT}, {"panic", EXT4_MOUNT_ERRORS_PANIC}, {"remount-ro", EXT4_MOUNT_ERRORS_RO}, {} }; static const struct constant_table ext4_param_data[] = { {"journal", EXT4_MOUNT_JOURNAL_DATA}, {"ordered", EXT4_MOUNT_ORDERED_DATA}, {"writeback", EXT4_MOUNT_WRITEBACK_DATA}, {} }; static const struct constant_table ext4_param_data_err[] = { {"abort", Opt_data_err_abort}, {"ignore", Opt_data_err_ignore}, {} }; static const struct constant_table ext4_param_jqfmt[] = { {"vfsold", QFMT_VFS_OLD}, {"vfsv0", QFMT_VFS_V0}, {"vfsv1", QFMT_VFS_V1}, {} }; static const struct constant_table ext4_param_dax[] = { {"always", Opt_dax_always}, {"inode", Opt_dax_inode}, {"never", Opt_dax_never}, {} }; /* * Mount option specification * We don't use fsparam_flag_no because of the way we set the * options and the way we show them in _ext4_show_options(). To * keep the changes to a minimum, let's keep the negative options * separate for now. */ static const struct fs_parameter_spec ext4_param_specs[] = { fsparam_flag ("bsddf", Opt_bsd_df), fsparam_flag ("minixdf", Opt_minix_df), fsparam_flag ("grpid", Opt_grpid), fsparam_flag ("bsdgroups", Opt_grpid), fsparam_flag ("nogrpid", Opt_nogrpid), fsparam_flag ("sysvgroups", Opt_nogrpid), fsparam_gid ("resgid", Opt_resgid), fsparam_uid ("resuid", Opt_resuid), fsparam_u32 ("sb", Opt_sb), fsparam_enum ("errors", Opt_errors, ext4_param_errors), fsparam_flag ("nouid32", Opt_nouid32), fsparam_flag ("debug", Opt_debug), fsparam_flag ("oldalloc", Opt_removed), fsparam_flag ("orlov", Opt_removed), fsparam_flag ("user_xattr", Opt_user_xattr), fsparam_flag ("acl", Opt_acl), fsparam_flag ("norecovery", Opt_noload), fsparam_flag ("noload", Opt_noload), fsparam_flag ("bh", Opt_removed), fsparam_flag ("nobh", Opt_removed), fsparam_u32 ("commit", Opt_commit), fsparam_u32 ("min_batch_time", Opt_min_batch_time), fsparam_u32 ("max_batch_time", Opt_max_batch_time), fsparam_u32 ("journal_dev", Opt_journal_dev), fsparam_bdev ("journal_path", Opt_journal_path), fsparam_flag ("journal_checksum", Opt_journal_checksum), fsparam_flag ("nojournal_checksum", Opt_nojournal_checksum), fsparam_flag ("journal_async_commit",Opt_journal_async_commit), fsparam_flag ("abort", Opt_abort), fsparam_enum ("data", Opt_data, ext4_param_data), fsparam_enum ("data_err", Opt_data_err, ext4_param_data_err), fsparam_string_empty ("usrjquota", Opt_usrjquota), fsparam_string_empty ("grpjquota", Opt_grpjquota), fsparam_enum ("jqfmt", Opt_jqfmt, ext4_param_jqfmt), fsparam_flag ("grpquota", Opt_grpquota), fsparam_flag ("quota", Opt_quota), fsparam_flag ("noquota", Opt_noquota), fsparam_flag ("usrquota", Opt_usrquota), fsparam_flag ("prjquota", Opt_prjquota), fsparam_flag ("barrier", Opt_barrier), fsparam_u32 ("barrier", Opt_barrier), fsparam_flag ("nobarrier", Opt_nobarrier), fsparam_flag ("i_version", Opt_removed), fsparam_flag ("dax", Opt_dax), fsparam_enum ("dax", Opt_dax_type, ext4_param_dax), fsparam_u32 ("stripe", Opt_stripe), fsparam_flag ("delalloc", Opt_delalloc), fsparam_flag ("nodelalloc", Opt_nodelalloc), fsparam_flag ("warn_on_error", Opt_warn_on_error), fsparam_flag ("nowarn_on_error", Opt_nowarn_on_error), fsparam_u32 ("debug_want_extra_isize", Opt_debug_want_extra_isize), fsparam_flag ("mblk_io_submit", Opt_removed), fsparam_flag ("nomblk_io_submit", Opt_removed), fsparam_flag ("block_validity", Opt_block_validity), fsparam_flag ("noblock_validity", Opt_noblock_validity), fsparam_u32 ("inode_readahead_blks", Opt_inode_readahead_blks), fsparam_u32 ("journal_ioprio", Opt_journal_ioprio), fsparam_u32 ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("auto_da_alloc", Opt_auto_da_alloc), fsparam_flag ("noauto_da_alloc", Opt_noauto_da_alloc), fsparam_flag ("dioread_nolock", Opt_dioread_nolock), fsparam_flag ("nodioread_nolock", Opt_dioread_lock), fsparam_flag ("dioread_lock", Opt_dioread_lock), fsparam_flag ("discard", Opt_discard), fsparam_flag ("nodiscard", Opt_nodiscard), fsparam_u32 ("init_itable", Opt_init_itable), fsparam_flag ("init_itable", Opt_init_itable), fsparam_flag ("noinit_itable", Opt_noinit_itable), #ifdef CONFIG_EXT4_DEBUG fsparam_flag ("fc_debug_force", Opt_fc_debug_force), fsparam_u32 ("fc_debug_max_replay", Opt_fc_debug_max_replay), #endif fsparam_u32 ("max_dir_size_kb", Opt_max_dir_size_kb), fsparam_flag ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_string ("test_dummy_encryption", Opt_test_dummy_encryption), fsparam_flag ("inlinecrypt", Opt_inlinecrypt), fsparam_flag ("nombcache", Opt_nombcache), fsparam_flag ("no_mbcache", Opt_nombcache), /* for backward compatibility */ fsparam_flag ("prefetch_block_bitmaps", Opt_removed), fsparam_flag ("no_prefetch_block_bitmaps", Opt_no_prefetch_block_bitmaps), fsparam_s32 ("mb_optimize_scan", Opt_mb_optimize_scan), fsparam_string ("check", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("nocheck", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("reservation", Opt_removed), /* mount option from ext2/3 */ fsparam_flag ("noreservation", Opt_removed), /* mount option from ext2/3 */ fsparam_u32 ("journal", Opt_removed), /* mount option from ext2/3 */ {} }; #define MOPT_SET 0x0001 #define MOPT_CLEAR 0x0002 #define MOPT_NOSUPPORT 0x0004 #define MOPT_EXPLICIT 0x0008 #ifdef CONFIG_QUOTA #define MOPT_Q 0 #define MOPT_QFMT 0x0010 #else #define MOPT_Q MOPT_NOSUPPORT #define MOPT_QFMT MOPT_NOSUPPORT #endif #define MOPT_NO_EXT2 0x0020 #define MOPT_NO_EXT3 0x0040 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3) #define MOPT_SKIP 0x0080 #define MOPT_2 0x0100 static const struct mount_opts { int token; int mount_opt; int flags; } ext4_mount_opts[] = { {Opt_minix_df, EXT4_MOUNT_MINIX_DF, MOPT_SET}, {Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR}, {Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET}, {Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR}, {Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET}, {Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR}, {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET}, {Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR}, {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET}, {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR}, {Opt_commit, 0, MOPT_NO_EXT2}, {Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET}, {Opt_data_err, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_NO_EXT2}, {Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET}, {Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR}, {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, {Opt_dax_type, 0, MOPT_EXT4_ONLY}, {Opt_journal_dev, 0, MOPT_NO_EXT2}, {Opt_journal_path, 0, MOPT_NO_EXT2}, {Opt_journal_ioprio, 0, MOPT_NO_EXT2}, {Opt_data, 0, MOPT_NO_EXT2}, {Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET}, #ifdef CONFIG_EXT4_FS_POSIX_ACL {Opt_acl, EXT4_MOUNT_POSIX_ACL, MOPT_SET}, #else {Opt_acl, 0, MOPT_NOSUPPORT}, #endif {Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET}, {Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET}, {Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q}, {Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA, MOPT_SET | MOPT_Q}, {Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA, MOPT_SET | MOPT_Q}, {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, {Opt_usrjquota, 0, MOPT_Q}, {Opt_grpjquota, 0, MOPT_Q}, {Opt_jqfmt, 0, MOPT_QFMT}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, #ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, #endif {Opt_abort, EXT4_MOUNT2_ABORT, MOPT_SET | MOPT_2}, {Opt_err, 0, 0} }; #if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; unsigned int version; } ext4_sb_encoding_map[] = { {EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; static const struct ext4_sb_encodings * ext4_sb_read_encoding(const struct ext4_super_block *es) { __u16 magic = le16_to_cpu(es->s_encoding); int i; for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++) if (magic == ext4_sb_encoding_map[i].magic) return &ext4_sb_encoding_map[i]; return NULL; } #endif #define EXT4_SPEC_JQUOTA (1 << 0) #define EXT4_SPEC_JQFMT (1 << 1) #define EXT4_SPEC_DATAJ (1 << 2) #define EXT4_SPEC_SB_BLOCK (1 << 3) #define EXT4_SPEC_JOURNAL_DEV (1 << 4) #define EXT4_SPEC_JOURNAL_IOPRIO (1 << 5) #define EXT4_SPEC_s_want_extra_isize (1 << 7) #define EXT4_SPEC_s_max_batch_time (1 << 8) #define EXT4_SPEC_s_min_batch_time (1 << 9) #define EXT4_SPEC_s_inode_readahead_blks (1 << 10) #define EXT4_SPEC_s_li_wait_mult (1 << 11) #define EXT4_SPEC_s_max_dir_size_kb (1 << 12) #define EXT4_SPEC_s_stripe (1 << 13) #define EXT4_SPEC_s_resuid (1 << 14) #define EXT4_SPEC_s_resgid (1 << 15) #define EXT4_SPEC_s_commit_interval (1 << 16) #define EXT4_SPEC_s_fc_debug_max_replay (1 << 17) #define EXT4_SPEC_s_sb_block (1 << 18) #define EXT4_SPEC_mb_optimize_scan (1 << 19) struct ext4_fs_context { char *s_qf_names[EXT4_MAXQUOTAS]; struct fscrypt_dummy_policy dummy_enc_policy; int s_jquota_fmt; /* Format of quota to use */ #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif unsigned short qname_spec; unsigned long vals_s_flags; /* Bits to set in s_flags */ unsigned long mask_s_flags; /* Bits changed in s_flags */ unsigned long journal_devnum; unsigned long s_commit_interval; unsigned long s_stripe; unsigned int s_inode_readahead_blks; unsigned int s_want_extra_isize; unsigned int s_li_wait_mult; unsigned int s_max_dir_size_kb; unsigned int journal_ioprio; unsigned int vals_s_mount_opt; unsigned int mask_s_mount_opt; unsigned int vals_s_mount_opt2; unsigned int mask_s_mount_opt2; unsigned int opt_flags; /* MOPT flags */ unsigned int spec; u32 s_max_batch_time; u32 s_min_batch_time; kuid_t s_resuid; kgid_t s_resgid; ext4_fsblk_t s_sb_block; }; static void ext4_fc_free(struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; int i; if (!ctx) return; for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(ctx->s_qf_names[i]); fscrypt_free_dummy_policy(&ctx->dummy_enc_policy); kfree(ctx); } int ext4_init_fs_context(struct fs_context *fc) { struct ext4_fs_context *ctx; ctx = kzalloc_obj(struct ext4_fs_context); if (!ctx) return -ENOMEM; fc->fs_private = ctx; fc->ops = &ext4_context_ops; /* i_version is always enabled now */ fc->sb_flags |= SB_I_VERSION; return 0; } #ifdef CONFIG_QUOTA /* * Note the name of the specified quota file. */ static int note_qf_name(struct fs_context *fc, int qtype, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; char *qname; if (param->size < 1) { ext4_msg(NULL, KERN_ERR, "Missing quota name"); return -EINVAL; } if (strchr(param->string, '/')) { ext4_msg(NULL, KERN_ERR, "quotafile must be on filesystem root"); return -EINVAL; } if (ctx->s_qf_names[qtype]) { if (strcmp(ctx->s_qf_names[qtype], param->string) != 0) { ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(qtype)); return -EINVAL; } return 0; } qname = kmemdup_nul(param->string, param->size, GFP_KERNEL); if (!qname) { ext4_msg(NULL, KERN_ERR, "Not enough memory for storing quotafile name"); return -ENOMEM; } ctx->s_qf_names[qtype] = qname; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } /* * Clear the name of the specified quota file. */ static int unnote_qf_name(struct fs_context *fc, int qtype) { struct ext4_fs_context *ctx = fc->fs_private; kfree(ctx->s_qf_names[qtype]); ctx->s_qf_names[qtype] = NULL; ctx->qname_spec |= 1 << qtype; ctx->spec |= EXT4_SPEC_JQUOTA; return 0; } #endif static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param, struct ext4_fs_context *ctx) { int err; if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption option not supported"); return -EINVAL; } err = fscrypt_parse_test_dummy_encryption(param, &ctx->dummy_enc_policy); if (err == -EINVAL) { ext4_msg(NULL, KERN_WARNING, "Value of option \"%s\" is unrecognized", param->key); } else if (err == -EEXIST) { ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return err; } #define EXT4_SET_CTX(name) \ static inline __maybe_unused \ void ctx_set_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name |= flag; \ } #define EXT4_CLEAR_CTX(name) \ static inline __maybe_unused \ void ctx_clear_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ ctx->mask_s_##name |= flag; \ ctx->vals_s_##name &= ~flag; \ } #define EXT4_TEST_CTX(name) \ static inline unsigned long \ ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \ { \ return (ctx->vals_s_##name & flag); \ } EXT4_SET_CTX(flags); /* set only */ EXT4_SET_CTX(mount_opt); EXT4_CLEAR_CTX(mount_opt); EXT4_TEST_CTX(mount_opt); EXT4_SET_CTX(mount_opt2); EXT4_CLEAR_CTX(mount_opt2); EXT4_TEST_CTX(mount_opt2); static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct ext4_fs_context *ctx = fc->fs_private; struct fs_parse_result result; const struct mount_opts *m; int is_remount; int token; token = fs_parse(fc, ext4_param_specs, param, &result); if (token < 0) return token; is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; for (m = ext4_mount_opts; m->token != Opt_err; m++) if (token == m->token) break; ctx->opt_flags |= m->flags; if (m->flags & MOPT_EXPLICIT) { if (m->mount_opt & EXT4_MOUNT_DELALLOC) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_DELALLOC); } else if (m->mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM); } else return -EINVAL; } if (m->flags & MOPT_NOSUPPORT) { ext4_msg(NULL, KERN_ERR, "%s option not supported", param->key); return 0; } switch (token) { #ifdef CONFIG_QUOTA case Opt_usrjquota: if (!*param->string) return unnote_qf_name(fc, USRQUOTA); else return note_qf_name(fc, USRQUOTA, param); case Opt_grpjquota: if (!*param->string) return unnote_qf_name(fc, GRPQUOTA); else return note_qf_name(fc, GRPQUOTA, param); #endif case Opt_sb: if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { ext4_msg(NULL, KERN_WARNING, "Ignoring %s option on remount", param->key); } else { ctx->s_sb_block = result.uint_32; ctx->spec |= EXT4_SPEC_s_sb_block; } return 0; case Opt_removed: ext4_msg(NULL, KERN_WARNING, "Ignoring removed %s option", param->key); return 0; case Opt_inlinecrypt: #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT ctx_set_flags(ctx, SB_INLINECRYPT); #else ext4_msg(NULL, KERN_ERR, "inline encryption not supported"); #endif return 0; case Opt_errors: ctx_clear_mount_opt(ctx, EXT4_MOUNT_ERRORS_MASK); ctx_set_mount_opt(ctx, result.uint_32); return 0; #ifdef CONFIG_QUOTA case Opt_jqfmt: ctx->s_jquota_fmt = result.uint_32; ctx->spec |= EXT4_SPEC_JQFMT; return 0; #endif case Opt_data: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); ctx_set_mount_opt(ctx, result.uint_32); ctx->spec |= EXT4_SPEC_DATAJ; return 0; case Opt_commit: if (result.uint_32 == 0) result.uint_32 = JBD2_DEFAULT_MAX_COMMIT_AGE; else if (result.uint_32 > INT_MAX / HZ) { ext4_msg(NULL, KERN_ERR, "Invalid commit interval %d, " "must be smaller than %d", result.uint_32, INT_MAX / HZ); return -EINVAL; } ctx->s_commit_interval = HZ * result.uint_32; ctx->spec |= EXT4_SPEC_s_commit_interval; return 0; case Opt_debug_want_extra_isize: if ((result.uint_32 & 1) || (result.uint_32 < 4)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", result.uint_32); return -EINVAL; } ctx->s_want_extra_isize = result.uint_32; ctx->spec |= EXT4_SPEC_s_want_extra_isize; return 0; case Opt_max_batch_time: ctx->s_max_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_batch_time; return 0; case Opt_min_batch_time: ctx->s_min_batch_time = result.uint_32; ctx->spec |= EXT4_SPEC_s_min_batch_time; return 0; case Opt_inode_readahead_blks: if (result.uint_32 && (result.uint_32 > (1 << 30) || !is_power_of_2(result.uint_32))) { ext4_msg(NULL, KERN_ERR, "EXT4-fs: inode_readahead_blks must be " "0 or a power of 2 smaller than 2^31"); return -EINVAL; } ctx->s_inode_readahead_blks = result.uint_32; ctx->spec |= EXT4_SPEC_s_inode_readahead_blks; return 0; case Opt_init_itable: ctx_set_mount_opt(ctx, EXT4_MOUNT_INIT_INODE_TABLE); ctx->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; if (param->type == fs_value_is_string) ctx->s_li_wait_mult = result.uint_32; ctx->spec |= EXT4_SPEC_s_li_wait_mult; return 0; case Opt_max_dir_size_kb: ctx->s_max_dir_size_kb = result.uint_32; ctx->spec |= EXT4_SPEC_s_max_dir_size_kb; return 0; #ifdef CONFIG_EXT4_DEBUG case Opt_fc_debug_max_replay: ctx->s_fc_debug_max_replay = result.uint_32; ctx->spec |= EXT4_SPEC_s_fc_debug_max_replay; return 0; #endif case Opt_stripe: ctx->s_stripe = result.uint_32; ctx->spec |= EXT4_SPEC_s_stripe; return 0; case Opt_resuid: ctx->s_resuid = result.uid; ctx->spec |= EXT4_SPEC_s_resuid; return 0; case Opt_resgid: ctx->s_resgid = result.gid; ctx->spec |= EXT4_SPEC_s_resgid; return 0; case Opt_journal_dev: if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } ctx->journal_devnum = result.uint_32; ctx->spec |= EXT4_SPEC_JOURNAL_DEV; return 0; case Opt_journal_path: { struct inode *journal_inode; struct path path; int error; if (is_remount) { ext4_msg(NULL, KERN_ERR, "Cannot specify journal on remount"); return -EINVAL; } error = fs_lookup_param(fc, param, 1, LOOKUP_FOLLOW, &path); if (error) { ext4_msg(NULL, KERN_ERR, "error: could not find " "journal device path"); return -EINVAL; } journal_inode = d_inode(path.dentry); ctx->journal_devnum = new_encode_dev(journal_inode->i_rdev); ctx->spec |= EXT4_SPEC_JOURNAL_DEV; path_put(&path); return 0; } case Opt_journal_ioprio: if (result.uint_32 > 7) { ext4_msg(NULL, KERN_ERR, "Invalid journal IO priority" " (must be 0-7)"); return -EINVAL; } ctx->journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, result.uint_32); ctx->spec |= EXT4_SPEC_JOURNAL_IOPRIO; return 0; case Opt_test_dummy_encryption: return ext4_parse_test_dummy_encryption(param, ctx); case Opt_dax: case Opt_dax_type: #ifdef CONFIG_FS_DAX { int type = (token == Opt_dax) ? Opt_dax : result.uint_32; switch (type) { case Opt_dax: case Opt_dax_always: ctx_set_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); break; case Opt_dax_never: ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); break; case Opt_dax_inode: ctx_clear_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS); ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER); /* Strictly for printing options */ ctx_set_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE); break; } return 0; } #else ext4_msg(NULL, KERN_INFO, "dax option not supported"); return -EINVAL; #endif case Opt_data_err: if (result.uint_32 == Opt_data_err_abort) ctx_set_mount_opt(ctx, m->mount_opt); else if (result.uint_32 == Opt_data_err_ignore) ctx_clear_mount_opt(ctx, m->mount_opt); return 0; case Opt_mb_optimize_scan: if (result.int_32 == 1) { ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else if (result.int_32 == 0) { ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN); ctx->spec |= EXT4_SPEC_mb_optimize_scan; } else { ext4_msg(NULL, KERN_WARNING, "mb_optimize_scan should be set to 0 or 1."); return -EINVAL; } return 0; } /* * At this point we should only be getting options requiring MOPT_SET, * or MOPT_CLEAR. Anything else is a bug */ if (m->token == Opt_err) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } else { unsigned int set = 0; if ((param->type == fs_value_is_flag) || result.uint_32 > 0) set = 1; if (m->flags & MOPT_CLEAR) set = !set; else if (unlikely(!(m->flags & MOPT_SET))) { ext4_msg(NULL, KERN_WARNING, "buggy handling of option %s", param->key); WARN_ON(1); return -EINVAL; } if (m->flags & MOPT_2) { if (set != 0) ctx_set_mount_opt2(ctx, m->mount_opt); else ctx_clear_mount_opt2(ctx, m->mount_opt); } else { if (set != 0) ctx_set_mount_opt(ctx, m->mount_opt); else ctx_clear_mount_opt(ctx, m->mount_opt); } } return 0; } static int parse_options(struct fs_context *fc, char *options) { struct fs_parameter param; int ret; char *key; if (!options) return 0; while ((key = strsep(&options, ",")) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); param.type = fs_value_is_flag; param.string = NULL; if (value) { if (value == key) continue; *value++ = 0; v_len = strlen(value); param.string = kmemdup_nul(value, v_len, GFP_KERNEL); if (!param.string) return -ENOMEM; param.type = fs_value_is_string; } param.key = key; param.size = v_len; ret = ext4_parse_param(fc, ¶m); kfree(param.string); if (ret < 0) return ret; } } ret = ext4_validate_options(fc); if (ret < 0) return ret; return 0; } static int parse_apply_sb_mount_options(struct super_block *sb, struct ext4_fs_context *m_ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); char s_mount_opts[64]; struct ext4_fs_context *s_ctx = NULL; struct fs_context *fc = NULL; int ret = -ENOMEM; if (!sbi->s_es->s_mount_opts[0]) return 0; if (strscpy_pad(s_mount_opts, sbi->s_es->s_mount_opts) < 0) return -E2BIG; fc = kzalloc_obj(struct fs_context); if (!fc) return -ENOMEM; s_ctx = kzalloc_obj(struct ext4_fs_context); if (!s_ctx) goto out_free; fc->fs_private = s_ctx; fc->s_fs_info = sbi; ret = parse_options(fc, s_mount_opts); if (ret < 0) goto parse_failed; ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) { parse_failed: ext4_msg(sb, KERN_WARNING, "failed to parse options in superblock: %s", s_mount_opts); ret = 0; goto out_free; } if (s_ctx->spec & EXT4_SPEC_JOURNAL_DEV) m_ctx->journal_devnum = s_ctx->journal_devnum; if (s_ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO) m_ctx->journal_ioprio = s_ctx->journal_ioprio; ext4_apply_options(fc, sb); ret = 0; out_free: ext4_fc_free(fc); kfree(fc); return ret; } static void ext4_apply_quota_options(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA bool quota_feature = ext4_has_feature_quota(sb); struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); char *qname; int i; if (quota_feature) return; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; qname = ctx->s_qf_names[i]; /* May be NULL */ if (qname) set_opt(sb, QUOTA); ctx->s_qf_names[i] = NULL; qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, lockdep_is_held(&sb->s_umount)); if (qname) kfree_rcu_mightsleep(qname); } } if (ctx->spec & EXT4_SPEC_JQFMT) sbi->s_jquota_fmt = ctx->s_jquota_fmt; #endif } /* * Check quota settings consistency. */ static int ext4_check_quota_consistency(struct fs_context *fc, struct super_block *sb) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = EXT4_SB(sb); bool quota_feature = ext4_has_feature_quota(sb); bool quota_loaded = sb_any_quota_loaded(sb); bool usr_qf_name, grp_qf_name, usrquota, grpquota; int quota_flags, i; /* * We do the test below only for project quotas. 'usrquota' and * 'grpquota' mount options are allowed even without quota feature * to support legacy quotas in quota files. */ if (ctx_test_mount_opt(ctx, EXT4_MOUNT_PRJQUOTA) && !ext4_has_feature_project(sb)) { ext4_msg(NULL, KERN_ERR, "Project quota feature not enabled. " "Cannot enable project quota enforcement."); return -EINVAL; } quota_flags = EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA; if (quota_loaded && ctx->mask_s_mount_opt & quota_flags && !ctx_test_mount_opt(ctx, quota_flags)) goto err_quota_change; if (ctx->spec & EXT4_SPEC_JQUOTA) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (!(ctx->qname_spec & (1 << i))) continue; if (quota_loaded && !!sbi->s_qf_names[i] != !!ctx->s_qf_names[i]) goto err_jquota_change; if (sbi->s_qf_names[i] && ctx->s_qf_names[i] && strcmp(get_qf_name(sb, sbi, i), ctx->s_qf_names[i]) != 0) goto err_jquota_specified; } if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Journaled quota options ignored when " "QUOTA feature is enabled"); return 0; } } if (ctx->spec & EXT4_SPEC_JQFMT) { if (sbi->s_jquota_fmt != ctx->s_jquota_fmt && quota_loaded) goto err_jquota_change; if (quota_feature) { ext4_msg(NULL, KERN_INFO, "Quota format mount options " "ignored when QUOTA feature is enabled"); return 0; } } /* Make sure we don't mix old and new quota format */ usr_qf_name = (get_qf_name(sb, sbi, USRQUOTA) || ctx->s_qf_names[USRQUOTA]); grp_qf_name = (get_qf_name(sb, sbi, GRPQUOTA) || ctx->s_qf_names[GRPQUOTA]); usrquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || test_opt(sb, USRQUOTA)); grpquota = (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) || test_opt(sb, GRPQUOTA)); if (usr_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); usrquota = false; } if (grp_qf_name) { ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); grpquota = false; } if (usr_qf_name || grp_qf_name) { if (usrquota || grpquota) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } if (!(ctx->spec & EXT4_SPEC_JQFMT || sbi->s_jquota_fmt)) { ext4_msg(NULL, KERN_ERR, "journaled quota format " "not specified"); return -EINVAL; } } return 0; err_quota_change: ext4_msg(NULL, KERN_ERR, "Cannot change quota options when quota turned on"); return -EINVAL; err_jquota_change: ext4_msg(NULL, KERN_ERR, "Cannot change journaled quota " "options when quota turned on"); return -EINVAL; err_jquota_specified: ext4_msg(NULL, KERN_ERR, "%s quota file already specified", QTYPE2NAME(i)); return -EINVAL; #else return 0; #endif } static int ext4_check_test_dummy_encryption(const struct fs_context *fc, struct super_block *sb) { const struct ext4_fs_context *ctx = fc->fs_private; const struct ext4_sb_info *sbi = EXT4_SB(sb); if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy)) return 0; if (!ext4_has_feature_encrypt(sb)) { ext4_msg(NULL, KERN_WARNING, "test_dummy_encryption requires encrypt feature"); return -EINVAL; } /* * This mount option is just for testing, and it's not worthwhile to * implement the extra complexity (e.g. RCU protection) that would be * needed to allow it to be set or changed during remount. We do allow * it to be specified during remount, but only if there is no change. */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Can't set or change test_dummy_encryption on remount"); return -EINVAL; } /* Also make sure s_mount_opts didn't contain a conflicting value. */ if (fscrypt_is_dummy_policy_set(&sbi->s_dummy_enc_policy)) { if (fscrypt_dummy_policies_equal(&sbi->s_dummy_enc_policy, &ctx->dummy_enc_policy)) return 0; ext4_msg(NULL, KERN_WARNING, "Conflicting test_dummy_encryption options"); return -EINVAL; } return 0; } static void ext4_apply_test_dummy_encryption(struct ext4_fs_context *ctx, struct super_block *sb) { if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy) || /* if already set, it was already verified to be the same */ fscrypt_is_dummy_policy_set(&EXT4_SB(sb)->s_dummy_enc_policy)) return; EXT4_SB(sb)->s_dummy_enc_policy = ctx->dummy_enc_policy; memset(&ctx->dummy_enc_policy, 0, sizeof(ctx->dummy_enc_policy)); ext4_msg(sb, KERN_WARNING, "Test dummy encryption mode enabled"); } static int ext4_check_opt_consistency(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; int err; if ((ctx->opt_flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext2"); return -EINVAL; } if ((ctx->opt_flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) { ext4_msg(NULL, KERN_ERR, "Mount option(s) incompatible with ext3"); return -EINVAL; } if (ctx->s_want_extra_isize > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE)) { ext4_msg(NULL, KERN_ERR, "Invalid want_extra_isize %d", ctx->s_want_extra_isize); return -EINVAL; } err = ext4_check_test_dummy_encryption(fc, sb); if (err) return err; if ((ctx->spec & EXT4_SPEC_DATAJ) && is_remount) { if (!sbi->s_journal) { ext4_msg(NULL, KERN_WARNING, "Remounting file system with no journal " "so ignoring journalled data option"); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS); } else if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_FLAGS) != test_opt(sb, DATA_FLAGS)) { ext4_msg(NULL, KERN_ERR, "Cannot change data mode " "on remount"); return -EINVAL; } } if (is_remount) { if (!sbi->s_journal && ctx_test_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT)) { ext4_msg(NULL, KERN_WARNING, "Remounting fs w/o journal so ignoring data_err option"); ctx_clear_mount_opt(ctx, EXT4_MOUNT_DATA_ERR_ABORT); } if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)) { ext4_msg(NULL, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DAX_ALWAYS) && (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) { fail_dax_change_remount: ext4_msg(NULL, KERN_ERR, "can't change " "dax mount option while remounting"); return -EINVAL; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_NEVER) && (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS))) { goto fail_dax_change_remount; } else if (ctx_test_mount_opt2(ctx, EXT4_MOUNT2_DAX_INODE) && ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) || (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) || !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE))) { goto fail_dax_change_remount; } } return ext4_check_quota_consistency(fc, sb); } static void ext4_apply_options(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi = fc->s_fs_info; sbi->s_mount_opt &= ~ctx->mask_s_mount_opt; sbi->s_mount_opt |= ctx->vals_s_mount_opt; sbi->s_mount_opt2 &= ~ctx->mask_s_mount_opt2; sbi->s_mount_opt2 |= ctx->vals_s_mount_opt2; sb->s_flags &= ~ctx->mask_s_flags; sb->s_flags |= ctx->vals_s_flags; #define APPLY(X) ({ if (ctx->spec & EXT4_SPEC_##X) sbi->X = ctx->X; }) APPLY(s_commit_interval); APPLY(s_stripe); APPLY(s_max_batch_time); APPLY(s_min_batch_time); APPLY(s_want_extra_isize); APPLY(s_inode_readahead_blks); APPLY(s_max_dir_size_kb); APPLY(s_li_wait_mult); APPLY(s_resgid); APPLY(s_resuid); #ifdef CONFIG_EXT4_DEBUG APPLY(s_fc_debug_max_replay); #endif ext4_apply_quota_options(fc, sb); ext4_apply_test_dummy_encryption(ctx, sb); } static int ext4_validate_options(struct fs_context *fc) { #ifdef CONFIG_QUOTA struct ext4_fs_context *ctx = fc->fs_private; char *usr_qf_name, *grp_qf_name; usr_qf_name = ctx->s_qf_names[USRQUOTA]; grp_qf_name = ctx->s_qf_names[GRPQUOTA]; if (usr_qf_name || grp_qf_name) { if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) && usr_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_USRQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA) && grp_qf_name) ctx_clear_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA); if (ctx_test_mount_opt(ctx, EXT4_MOUNT_USRQUOTA) || ctx_test_mount_opt(ctx, EXT4_MOUNT_GRPQUOTA)) { ext4_msg(NULL, KERN_ERR, "old and new quota " "format mixing"); return -EINVAL; } } #endif return 1; } static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb) { #if defined(CONFIG_QUOTA) struct ext4_sb_info *sbi = EXT4_SB(sb); char *usr_qf_name, *grp_qf_name; if (sbi->s_jquota_fmt) { char *fmtname = ""; switch (sbi->s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; case QFMT_VFS_V0: fmtname = "vfsv0"; break; case QFMT_VFS_V1: fmtname = "vfsv1"; break; } seq_printf(seq, ",jqfmt=%s", fmtname); } rcu_read_lock(); usr_qf_name = rcu_dereference(sbi->s_qf_names[USRQUOTA]); grp_qf_name = rcu_dereference(sbi->s_qf_names[GRPQUOTA]); if (usr_qf_name) seq_show_option(seq, "usrjquota", usr_qf_name); if (grp_qf_name) seq_show_option(seq, "grpjquota", grp_qf_name); rcu_read_unlock(); #endif } static const char *token2str(int token) { const struct fs_parameter_spec *spec; for (spec = ext4_param_specs; spec->name != NULL; spec++) if (spec->opt == token && !spec->type) break; return spec->name; } /* * Show an option if * - it's set to a non-default value OR * - if the per-sb default is different from the global default */ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, int nodefs) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int def_errors; const struct mount_opts *m; char sep = nodefs ? '\n' : ','; #define SEQ_OPTS_PUTS(str) seq_printf(seq, "%c" str, sep) #define SEQ_OPTS_PRINT(str, arg) seq_printf(seq, "%c" str, sep, arg) if (sbi->s_sb_block != 1) SEQ_OPTS_PRINT("sb=%llu", sbi->s_sb_block); for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; int opt_2 = m->flags & MOPT_2; unsigned int mount_opt, def_mount_opt; if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || m->flags & MOPT_SKIP) continue; if (opt_2) { mount_opt = sbi->s_mount_opt2; def_mount_opt = sbi->s_def_mount_opt2; } else { mount_opt = sbi->s_mount_opt; def_mount_opt = sbi->s_def_mount_opt; } /* skip if same as the default */ if (!nodefs && !(m->mount_opt & (mount_opt ^ def_mount_opt))) continue; /* select Opt_noFoo vs Opt_Foo */ if ((want_set && (mount_opt & m->mount_opt) != m->mount_opt) || (!want_set && (mount_opt & m->mount_opt))) continue; SEQ_OPTS_PRINT("%s", token2str(m->token)); } if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) || ext4_get_resuid(es) != EXT4_DEF_RESUID) SEQ_OPTS_PRINT("resuid=%u", from_kuid_munged(&init_user_ns, sbi->s_resuid)); if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) || ext4_get_resgid(es) != EXT4_DEF_RESGID) SEQ_OPTS_PRINT("resgid=%u", from_kgid_munged(&init_user_ns, sbi->s_resgid)); def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors); if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO) SEQ_OPTS_PUTS("errors=remount-ro"); if (test_opt(sb, ERRORS_CONT) && def_errors != EXT4_ERRORS_CONTINUE) SEQ_OPTS_PUTS("errors=continue"); if (test_opt(sb, ERRORS_PANIC) && def_errors != EXT4_ERRORS_PANIC) SEQ_OPTS_PUTS("errors=panic"); if (nodefs || sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) SEQ_OPTS_PRINT("commit=%lu", sbi->s_commit_interval / HZ); if (nodefs || sbi->s_min_batch_time != EXT4_DEF_MIN_BATCH_TIME) SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); if (nodefs && sb->s_flags & SB_I_VERSION) SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) SEQ_OPTS_PUTS("data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) SEQ_OPTS_PUTS("data=ordered"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) SEQ_OPTS_PUTS("data=writeback"); } if (nodefs || sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS) SEQ_OPTS_PRINT("inode_readahead_blks=%u", sbi->s_inode_readahead_blks); if (test_opt(sb, INIT_INODE_TABLE) && (nodefs || (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT))) SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult); if (nodefs || sbi->s_max_dir_size_kb) SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); fscrypt_show_test_dummy_encryption(seq, sep, sb); if (sb->s_flags & SB_INLINECRYPT) SEQ_OPTS_PUTS("inlinecrypt"); if (test_opt(sb, DAX_ALWAYS)) { if (IS_EXT2_SB(sb)) SEQ_OPTS_PUTS("dax"); else SEQ_OPTS_PUTS("dax=always"); } else if (test_opt2(sb, DAX_NEVER)) { SEQ_OPTS_PUTS("dax=never"); } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD && !test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=0"); } else if (sbi->s_groups_count < MB_DEFAULT_LINEAR_SCAN_THRESHOLD && test_opt2(sb, MB_OPTIMIZE_SCAN)) { SEQ_OPTS_PUTS("mb_optimize_scan=1"); } if (nodefs && !test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) SEQ_OPTS_PUTS("prefetch_block_bitmaps"); if (ext4_emergency_ro(sb)) SEQ_OPTS_PUTS("emergency_ro"); if (ext4_forced_shutdown(sb)) SEQ_OPTS_PUTS("shutdown"); ext4_show_quota_options(seq, sb); return 0; } static int ext4_show_options(struct seq_file *seq, struct dentry *root) { return _ext4_show_options(seq, root->d_sb, 0); } int ext4_seq_options_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; int rc; seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw"); rc = _ext4_show_options(seq, sb, 1); seq_putc(seq, '\n'); return rc; } static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, int read_only) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err = 0; if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) { ext4_msg(sb, KERN_ERR, "revision level too high, " "forcing read-only mode"); err = -EROFS; goto done; } if (read_only) goto done; if (!(sbi->s_mount_state & EXT4_VALID_FS)) ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, " "running e2fsck is recommended"); else if (sbi->s_mount_state & EXT4_ERROR_FS) ext4_msg(sb, KERN_WARNING, "warning: mounting fs with errors, " "running e2fsck is recommended"); else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 && le16_to_cpu(es->s_mnt_count) >= (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) ext4_msg(sb, KERN_WARNING, "warning: maximal mount count reached, " "running e2fsck is recommended"); else if (le32_to_cpu(es->s_checkinterval) && (ext4_get_tstamp(es, s_lastcheck) + le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds())) ext4_msg(sb, KERN_WARNING, "warning: checktime reached, " "running e2fsck is recommended"); if (!sbi->s_journal) es->s_state &= cpu_to_le16(~EXT4_VALID_FS); if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); ext4_update_tstamp(es, s_mtime); if (sbi->s_journal) { ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } err = ext4_commit_super(sb); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " "bpg=%lu, ipg=%lu, mo=%04x, mo2=%04x]\n", sb->s_blocksize, sbi->s_groups_count, EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); return err; } int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct flex_groups **old_groups, **new_groups; int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; size = ext4_flex_group(sbi, ngroup - 1) + 1; if (size <= sbi->s_flex_groups_allocated) return 0; new_groups = kvzalloc(roundup_pow_of_two(size * sizeof(*sbi->s_flex_groups)), GFP_KERNEL); if (!new_groups) { ext4_msg(sb, KERN_ERR, "not enough memory for %d flex group pointers", size); return -ENOMEM; } for (i = sbi->s_flex_groups_allocated; i < size; i++) { new_groups[i] = kvzalloc(roundup_pow_of_two( sizeof(struct flex_groups)), GFP_KERNEL); if (!new_groups[i]) { for (j = sbi->s_flex_groups_allocated; j < i; j++) kvfree(new_groups[j]); kvfree(new_groups); ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", size); return -ENOMEM; } } rcu_read_lock(); old_groups = rcu_dereference(sbi->s_flex_groups); if (old_groups) memcpy(new_groups, old_groups, (sbi->s_flex_groups_allocated * sizeof(struct flex_groups *))); rcu_read_unlock(); rcu_assign_pointer(sbi->s_flex_groups, new_groups); sbi->s_flex_groups_allocated = size; if (old_groups) ext4_kvfree_array_rcu(old_groups); return 0; } static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; struct flex_groups *fg; ext4_group_t flex_group; int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) { sbi->s_log_groups_per_flex = 0; return 1; } err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); if (err) goto failed; for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext4_get_group_desc(sb, i, NULL); flex_group = ext4_flex_group(sbi, i); fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); atomic_add(ext4_free_inodes_count(sb, gdp), &fg->free_inodes); atomic64_add(ext4_free_group_clusters(sb, gdp), &fg->free_clusters); atomic_add(ext4_used_dirs_count(sb, gdp), &fg->used_dirs); } return 1; failed: return 0; } static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { int offset = offsetof(struct ext4_group_desc, bg_checksum); __u16 crc = 0; __le32 le_group = cpu_to_le32(block_group); struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_feature_metadata_csum(sbi->s_sb)) { /* Use new metadata_csum algorithm */ __u32 csum32; __u16 dummy_csum = 0; csum32 = ext4_chksum(sbi->s_csum_seed, (__u8 *)&le_group, sizeof(le_group)); csum32 = ext4_chksum(csum32, (__u8 *)gdp, offset); csum32 = ext4_chksum(csum32, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); if (offset < sbi->s_desc_size) csum32 = ext4_chksum(csum32, (__u8 *)gdp + offset, sbi->s_desc_size - offset); crc = csum32 & 0xFFFF; goto out; } /* old crc16 code */ if (!ext4_has_feature_gdt_csum(sb)) return 0; crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, sbi->s_desc_size - offset); out: return cpu_to_le16(crc); } int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (ext4_has_group_desc_csum(sb) && (gdp->bg_checksum != ext4_group_desc_csum(sb, block_group, gdp))) return 0; return 1; } void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { if (!ext4_has_group_desc_csum(sb)) return; gdp->bg_checksum = ext4_group_desc_csum(sb, block_group, gdp); } /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, ext4_fsblk_t sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; int flexbg_flag = 0; ext4_group_t i, grp = sbi->s_groups_count; if (ext4_has_feature_flex_bg(sb)) flexbg_flag = 1; ext4_debug("Checking group descriptors"); for (i = 0; i < sbi->s_groups_count; i++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL); if (i == sbi->s_groups_count - 1 || flexbg_flag) last_block = ext4_blocks_count(sbi->s_es) - 1; else last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); if ((grp == sbi->s_groups_count) && !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap >= sb_block + 1 && block_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " "(block %llu)!", i, block_bitmap); return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); if (inode_bitmap == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap >= sb_block + 1 && inode_bitmap <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " "(block %llu)!", i, inode_bitmap); return 0; } inode_table = ext4_inode_table(sb, gdp); if (inode_table == sb_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "superblock", i); if (!sb_rdonly(sb)) return 0; } if (inode_table >= sb_block + 1 && inode_table <= last_bg_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u overlaps " "block group descriptors", i); if (!sb_rdonly(sb)) return 0; } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode table for group %u not in group " "(block %llu)!", i, inode_table); return 0; } ext4_lock_group(sb, i); if (!ext4_group_desc_csum_verify(sb, i, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)", i, le16_to_cpu(ext4_group_desc_csum(sb, i, gdp)), le16_to_cpu(gdp->bg_checksum)); if (!sb_rdonly(sb)) { ext4_unlock_group(sb, i); return 0; } } ext4_unlock_group(sb, i); if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } if (NULL != first_not_zeroed) *first_not_zeroed = grp; return 1; } /* * Maximal extent format file size. * Resulting logical blkno at s_maxbytes must fit in our on-disk * extent format containers, within a sector_t, and within i_blocks * in the vfs. ext4 inode has 48 bits of i_block in fsblock units, * so that won't be a limiting factor. * * However there is other limiting factor. We do store extents in the form * of starting block and length, hence the resulting length of the extent * covering maximum file size must fit into on-disk format containers as * well. Given that length is always by 1 unit bigger than max unit (because * we count 0 as well) we have to lower the s_maxbytes by one fs block. * * Note, this does *not* consider any metadata overhead for vfs i_blocks. */ static loff_t ext4_max_size(int blkbits, int has_huge_files) { loff_t res; loff_t upper_limit = MAX_LFS_FILESIZE; BUILD_BUG_ON(sizeof(blkcnt_t) < sizeof(u64)); if (!has_huge_files) { upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (blkbits - 9); upper_limit <<= blkbits; } /* * 32-bit extent-start container, ee_block. We lower the maxbytes * by one fs block, so ee_len can cover the extent of maximum file * size */ res = (1LL << 32) - 1; res <<= blkbits; /* Sanity check against vm- & vfs- imposed limits */ if (res > upper_limit) res = upper_limit; return res; } /* * Maximal bitmap file size. There is a direct, and {,double-,triple-}indirect * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks. * We need to be 1 filesystem block less than the 2^48 sector limit. */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { loff_t upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; unsigned int ppb = 1 << (bits - 2); /* * This is calculated to be the largest file size for a dense, block * mapped file such that the file's total number of 512-byte sectors, * including data and all indirect blocks, does not exceed (2^48 - 1). * * __u32 i_blocks_lo and _u16 i_blocks_high represent the total * number of 512-byte sectors of the file. */ if (!has_huge_files) { /* * !has_huge_files or implies that the inode i_block field * represents total file blocks in 2^32 512-byte sectors == * size of vfs inode i_blocks * 8 */ upper_limit = (1LL << 32) - 1; /* total blocks in file system block size */ upper_limit >>= (bits - 9); } else { /* * We use 48 bit ext4_inode i_blocks * With EXT4_HUGE_FILE_FL set the i_blocks * represent total number of blocks in * file system block size */ upper_limit = (1LL << 48) - 1; } /* Compute how many blocks we can address by block tree */ res += ppb; res += ppb * ppb; res += ((loff_t)ppb) * ppb * ppb; /* Compute how many metadata blocks are needed */ meta_blocks = 1; meta_blocks += 1 + ppb; meta_blocks += 1 + ppb + ppb * ppb; /* Does block tree limit file size? */ if (res + meta_blocks <= upper_limit) goto check_lfs; res = upper_limit; /* How many metadata blocks are needed for addressing upper_limit? */ upper_limit -= EXT4_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; upper_limit -= ppb; /* double indirect blocks */ if (upper_limit < ppb * ppb) { meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb); res -= meta_blocks; goto check_lfs; } meta_blocks += 1 + ppb; upper_limit -= ppb * ppb; /* tripple indirect blocks for the rest */ meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb) + DIV_ROUND_UP_ULL(upper_limit, ppb*ppb); res -= meta_blocks; check_lfs: res <<= bits; if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; return res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, ext4_fsblk_t logical_sb_block, int nr) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t bg, first_meta_bg; int has_super = 0; first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); if (!ext4_has_feature_meta_bg(sb) || nr < first_meta_bg) return logical_sb_block + nr + 1; bg = sbi->s_desc_per_block * nr; if (ext4_bg_has_super(sb, bg)) has_super = 1; /* * If we have a meta_bg fs with 1k blocks, group 0's GDT is at * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled * on modern mke2fs or blksize > 1k on older mke2fs) then we must * compensate. */ if (sb->s_blocksize == 1024 && nr == 0 && le32_to_cpu(sbi->s_es->s_first_data_block) == 0) has_super++; return (has_super + ext4_group_first_block_no(sb, bg)); } /** * ext4_get_stripe_size: Get the stripe size. * @sbi: In memory super block info * * If we have specified it via mount option, then * use the mount option value. If the value specified at mount time is * greater than the blocks per group use the super block value. * If the super block value is greater than blocks per group return 0. * Allocator needs it be less than blocks per group. * */ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) { unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride); unsigned long stripe_width = le32_to_cpu(sbi->s_es->s_raid_stripe_width); int ret; if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group) ret = sbi->s_stripe; else if (stripe_width && stripe_width <= sbi->s_blocks_per_group) ret = stripe_width; else if (stride && stride <= sbi->s_blocks_per_group) ret = stride; else ret = 0; /* * If the stripe width is 1, this makes no sense and * we set it to 0 to turn off stripe handling code. */ if (ret <= 1) ret = 0; return ret; } /* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. * Returns 1 if this filesystem can be mounted as requested, * 0 if it cannot be. */ int ext4_feature_set_ok(struct super_block *sb, int readonly) { if (ext4_has_unknown_ext4_incompat_features(sb)) { ext4_msg(sb, KERN_ERR, "Couldn't mount because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_incompat) & ~EXT4_FEATURE_INCOMPAT_SUPP)); return 0; } if (!IS_ENABLED(CONFIG_UNICODE) && ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " "mounted without CONFIG_UNICODE"); return 0; } if (readonly) return 1; if (ext4_has_feature_readonly(sb)) { ext4_msg(sb, KERN_INFO, "filesystem is read-only"); sb->s_flags |= SB_RDONLY; return 1; } /* Check that feature set is OK for a read-write mount */ if (ext4_has_unknown_ext4_ro_compat_features(sb)) { ext4_msg(sb, KERN_ERR, "couldn't mount RDWR because of " "unsupported optional features (%x)", (le32_to_cpu(EXT4_SB(sb)->s_es->s_feature_ro_compat) & ~EXT4_FEATURE_RO_COMPAT_SUPP)); return 0; } if (ext4_has_feature_bigalloc(sb) && !ext4_has_feature_extents(sb)) { ext4_msg(sb, KERN_ERR, "Can't support bigalloc feature without " "extents feature\n"); return 0; } if (ext4_has_feature_bigalloc(sb) && le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { ext4_msg(sb, KERN_WARNING, "bad geometry: bigalloc file system with non-zero " "first_data_block\n"); return 0; } #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) if (!readonly && (ext4_has_feature_quota(sb) || ext4_has_feature_project(sb))) { ext4_msg(sb, KERN_ERR, "The kernel was not built with CONFIG_QUOTA and CONFIG_QFMT_V2"); return 0; } #endif /* CONFIG_QUOTA */ return 1; } /* * This function is called once a day by default if we have errors logged * on the file system. * Use the err_report_sec sysfs attribute to disable or adjust its call * freequency. */ void print_daily_error_info(struct timer_list *t) { struct ext4_sb_info *sbi = timer_container_of(sbi, t, s_err_report); struct super_block *sb = sbi->s_sb; struct ext4_super_block *es = sbi->s_es; if (es->s_error_count) /* fsck newer than v1.41.13 is needed to clean this condition. */ ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u", le32_to_cpu(es->s_error_count)); if (es->s_first_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_first_error_time), (int) sizeof(es->s_first_error_func), es->s_first_error_func, le32_to_cpu(es->s_first_error_line)); if (es->s_first_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_first_error_ino)); if (es->s_first_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_first_error_block)); printk(KERN_CONT "\n"); } if (es->s_last_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d", sb->s_id, ext4_get_tstamp(es, s_last_error_time), (int) sizeof(es->s_last_error_func), es->s_last_error_func, le32_to_cpu(es->s_last_error_line)); if (es->s_last_error_ino) printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_last_error_ino)); if (es->s_last_error_block) printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_last_error_block)); printk(KERN_CONT "\n"); } if (sbi->s_err_report_sec) mod_timer(&sbi->s_err_report, jiffies + secs_to_jiffies(sbi->s_err_report_sec)); } /* Find next suitable group and run ext4_init_inode_table */ static int ext4_run_li_request(struct ext4_li_request *elr) { struct ext4_group_desc *gdp = NULL; struct super_block *sb = elr->lr_super; ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; ext4_group_t group = elr->lr_next_group; unsigned int prefetch_ios = 0; int ret = 0; int nr = EXT4_SB(sb)->s_mb_prefetch; u64 start_time; if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { elr->lr_next_group = ext4_mb_prefetch(sb, group, nr, &prefetch_ios); ext4_mb_prefetch_fini(sb, elr->lr_next_group, nr); trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group, nr); if (group >= elr->lr_next_group) { ret = 1; if (elr->lr_first_not_zeroed != ngroups && !ext4_emergency_state(sb) && !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { elr->lr_next_group = elr->lr_first_not_zeroed; elr->lr_mode = EXT4_LI_MODE_ITABLE; ret = 0; } } return ret; } for (; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { ret = 1; break; } if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } if (group >= ngroups) ret = 1; if (!ret) { start_time = ktime_get_ns(); ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { elr->lr_timeout = nsecs_to_jiffies((ktime_get_ns() - start_time) * EXT4_SB(elr->lr_super)->s_li_wait_mult); } elr->lr_next_sched = jiffies + elr->lr_timeout; elr->lr_next_group = group + 1; } return ret; } /* * Remove lr_request from the list_request and free the * request structure. Should be called with li_list_mtx held */ static void ext4_remove_li_request(struct ext4_li_request *elr) { if (!elr) return; list_del(&elr->lr_request); EXT4_SB(elr->lr_super)->s_li_request = NULL; kfree(elr); } static void ext4_unregister_li_request(struct super_block *sb) { mutex_lock(&ext4_li_mtx); if (!ext4_li_info) { mutex_unlock(&ext4_li_mtx); return; } mutex_lock(&ext4_li_info->li_list_mtx); ext4_remove_li_request(EXT4_SB(sb)->s_li_request); mutex_unlock(&ext4_li_info->li_list_mtx); mutex_unlock(&ext4_li_mtx); } static struct task_struct *ext4_lazyinit_task; /* * This is the function where ext4lazyinit thread lives. It walks * through the request list searching for next scheduled filesystem. * When such a fs is found, run the lazy initialization request * (ext4_rn_li_request) and keep track of the time spend in this * function. Based on that time we compute next schedule time of * the request. When walking through the list is complete, compute * next waking time and put itself into sleep. */ static int ext4_lazyinit_thread(void *arg) { struct ext4_lazy_init *eli = arg; struct list_head *pos, *n; struct ext4_li_request *elr; unsigned long next_wakeup, cur; BUG_ON(NULL == eli); set_freezable(); cont_thread: while (true) { bool next_wakeup_initialized = false; next_wakeup = 0; mutex_lock(&eli->li_list_mtx); if (list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); goto exit_thread; } list_for_each_safe(pos, n, &eli->li_request_list) { int err = 0; int progress = 0; elr = list_entry(pos, struct ext4_li_request, lr_request); if (time_before(jiffies, elr->lr_next_sched)) { if (!next_wakeup_initialized || time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; next_wakeup_initialized = true; } continue; } if (down_read_trylock(&elr->lr_super->s_umount)) { if (sb_start_write_trylock(elr->lr_super)) { progress = 1; /* * We hold sb->s_umount, sb can not * be removed from the list, it is * now safe to drop li_list_mtx */ mutex_unlock(&eli->li_list_mtx); err = ext4_run_li_request(elr); sb_end_write(elr->lr_super); mutex_lock(&eli->li_list_mtx); n = pos->next; } up_read((&elr->lr_super->s_umount)); } /* error, remove the lazy_init job */ if (err) { ext4_remove_li_request(elr); continue; } if (!progress) { elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); } if (!next_wakeup_initialized || time_before(elr->lr_next_sched, next_wakeup)) { next_wakeup = elr->lr_next_sched; next_wakeup_initialized = true; } } mutex_unlock(&eli->li_list_mtx); try_to_freeze(); cur = jiffies; if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) { cond_resched(); continue; } schedule_timeout_interruptible(next_wakeup - cur); if (kthread_should_stop()) { ext4_clear_request_list(); goto exit_thread; } } exit_thread: /* * It looks like the request list is empty, but we need * to check it under the li_list_mtx lock, to prevent any * additions into it, and of course we should lock ext4_li_mtx * to atomically free the list and ext4_li_info, because at * this point another ext4 filesystem could be registering * new one. */ mutex_lock(&ext4_li_mtx); mutex_lock(&eli->li_list_mtx); if (!list_empty(&eli->li_request_list)) { mutex_unlock(&eli->li_list_mtx); mutex_unlock(&ext4_li_mtx); goto cont_thread; } mutex_unlock(&eli->li_list_mtx); kfree(ext4_li_info); ext4_li_info = NULL; mutex_unlock(&ext4_li_mtx); return 0; } static void ext4_clear_request_list(void) { struct list_head *pos, *n; struct ext4_li_request *elr; mutex_lock(&ext4_li_info->li_list_mtx); list_for_each_safe(pos, n, &ext4_li_info->li_request_list) { elr = list_entry(pos, struct ext4_li_request, lr_request); ext4_remove_li_request(elr); } mutex_unlock(&ext4_li_info->li_list_mtx); } static int ext4_run_lazyinit_thread(void) { ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit"); if (IS_ERR(ext4_lazyinit_task)) { int err = PTR_ERR(ext4_lazyinit_task); ext4_clear_request_list(); kfree(ext4_li_info); ext4_li_info = NULL; printk(KERN_CRIT "EXT4-fs: error %d creating inode table " "initialization thread\n", err); return err; } ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING; return 0; } /* * Check whether it make sense to run itable init. thread or not. * If there is at least one uninitialized inode table, return * corresponding group number, else the loop goes through all * groups and return total number of groups. */ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) { ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count; struct ext4_group_desc *gdp = NULL; if (!ext4_has_group_desc_csum(sb)) return ngroups; for (group = 0; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) continue; if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; } return group; } static int ext4_li_info_new(void) { struct ext4_lazy_init *eli = NULL; eli = kzalloc_obj(*eli); if (!eli) return -ENOMEM; INIT_LIST_HEAD(&eli->li_request_list); mutex_init(&eli->li_list_mtx); eli->li_state |= EXT4_LAZYINIT_QUIT; ext4_li_info = eli; return 0; } static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, ext4_group_t start) { struct ext4_li_request *elr; elr = kzalloc_obj(*elr); if (!elr) return NULL; elr->lr_super = sb; elr->lr_first_not_zeroed = start; if (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS)) { elr->lr_mode = EXT4_LI_MODE_ITABLE; elr->lr_next_group = start; } else { elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; } /* * Randomize first schedule time of the request to * spread the inode table initialization requests * better. */ elr->lr_next_sched = jiffies + get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ); return elr; } int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_li_request *elr = NULL; ext4_group_t ngroups = sbi->s_groups_count; int ret = 0; mutex_lock(&ext4_li_mtx); if (sbi->s_li_request != NULL) { /* * Reset timeout so it can be computed again, because * s_li_wait_mult might have changed. */ sbi->s_li_request->lr_timeout = 0; goto out; } if (ext4_emergency_state(sb) || sb_rdonly(sb) || (test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS) && (first_not_zeroed == ngroups || !test_opt(sb, INIT_INODE_TABLE)))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); if (!elr) { ret = -ENOMEM; goto out; } if (NULL == ext4_li_info) { ret = ext4_li_info_new(); if (ret) goto out; } mutex_lock(&ext4_li_info->li_list_mtx); list_add(&elr->lr_request, &ext4_li_info->li_request_list); mutex_unlock(&ext4_li_info->li_list_mtx); sbi->s_li_request = elr; /* * set elr to NULL here since it has been inserted to * the request_list and the removal and free of it is * handled by ext4_clear_request_list from now on. */ elr = NULL; if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { ret = ext4_run_lazyinit_thread(); if (ret) goto out; } out: mutex_unlock(&ext4_li_mtx); if (ret) kfree(elr); return ret; } /* * We do not need to lock anything since this is called on * module unload. */ static void ext4_destroy_lazyinit_thread(void) { /* * If thread exited earlier * there's nothing to be done. */ if (!ext4_li_info || !ext4_lazyinit_task) return; kthread_stop(ext4_lazyinit_task); } static int set_journal_csum_feature_set(struct super_block *sb) { int ret = 1; int compat, incompat; struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_has_feature_metadata_csum(sb)) { /* journal checksum v3 */ compat = 0; incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3; } else { /* journal checksum v1 */ compat = JBD2_FEATURE_COMPAT_CHECKSUM; incompat = 0; } jbd2_journal_clear_features(sbi->s_journal, JBD2_FEATURE_COMPAT_CHECKSUM, 0, JBD2_FEATURE_INCOMPAT_CSUM_V3 | JBD2_FEATURE_INCOMPAT_CSUM_V2); if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | incompat); } else if (test_opt(sb, JOURNAL_CHECKSUM)) { ret = jbd2_journal_set_features(sbi->s_journal, compat, 0, incompat); jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } else { jbd2_journal_clear_features(sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); } return ret; } /* * Note: calculating the overhead so we can be compatible with * historical BSD practice is quite difficult in the face of * clusters/bigalloc. This is because multiple metadata blocks from * different block group can end up in the same allocation cluster. * Calculating the exact overhead in the face of clustered allocation * requires either O(all block bitmaps) in memory or O(number of block * groups**2) in time. We will still calculate the superblock for * older file systems --- and if we come across with a bigalloc file * system with zero in s_overhead_clusters the estimate will be close to * correct especially for very large cluster sizes --- but for newer * file systems, it's better to calculate this figure once at mkfs * time, and store it in the superblock. If the superblock value is * present (even for non-bigalloc file systems), we will use it. */ static int count_overhead(struct super_block *sb, ext4_group_t grp, char *buf) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp; ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) return (has_super + ext4_bg_num_gdb(sb, grp) + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + (grp * EXT4_BLOCKS_PER_GROUP(sb)); last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; for (i = 0; i < ngroups; i++) { gdp = ext4_get_group_desc(sb, i, NULL); b = ext4_block_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_bitmap(sb, gdp); if (b >= first_block && b <= last_block) { ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf); count++; } b = ext4_inode_table(sb, gdp); if (b >= first_block && b + sbi->s_itb_per_group <= last_block) for (j = 0; j < sbi->s_itb_per_group; j++, b++) { int c = EXT4_B2C(sbi, b - first_block); ext4_set_bit(c, buf); count++; } if (i != grp) continue; s = 0; if (ext4_bg_has_super(sb, grp)) { ext4_set_bit(s++, buf); count++; } j = ext4_bg_num_gdb(sb, grp); if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) { ext4_error(sb, "Invalid number of block group " "descriptor blocks: %d", j); j = EXT4_BLOCKS_PER_GROUP(sb) - s; } count += j; for (; j > 0; j--) ext4_set_bit(EXT4_B2C(sbi, s++), buf); } if (!count) return 0; return EXT4_CLUSTERS_PER_GROUP(sb) - ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8); } /* * Compute the overhead and stash it in sbi->s_overhead */ int ext4_calculate_overhead(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct inode *j_inode; unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum); ext4_group_t i, ngroups = ext4_get_groups_count(sb); ext4_fsblk_t overhead = 0; char *buf = kvmalloc(sb->s_blocksize, GFP_NOFS | __GFP_ZERO); if (!buf) return -ENOMEM; /* * Compute the overhead (FS structures). This is constant * for a given filesystem unless the number of block groups * changes so we cache the previous value until it does. */ /* * All of the blocks before first_data_block are overhead */ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block)); /* * Add the overhead found in each block group */ for (i = 0; i < ngroups; i++) { int blks; blks = count_overhead(sb, i, buf); overhead += blks; if (blks) memset(buf, 0, sb->s_blocksize); cond_resched(); } /* * Add the internal journal blocks whether the journal has been * loaded or not */ if (sbi->s_journal && !sbi->s_journal_bdev_file) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); if (!IS_ERR(j_inode)) { j_blocks = j_inode->i_size >> sb->s_blocksize_bits; overhead += EXT4_NUM_B2C(sbi, j_blocks); iput(j_inode); } else { ext4_msg(sb, KERN_ERR, "can't get journal size"); } } sbi->s_overhead = overhead; smp_wmb(); kvfree(buf); return 0; } static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * There's no need to reserve anything when we aren't using extents. * The space estimates are exact, there are no unwritten extents, * hole punching doesn't need new metadata... This is needed especially * to keep ext2/3 backward compatibility. */ if (!ext4_has_feature_extents(sb)) return; /* * By default we reserve 2% or 4096 clusters, whichever is smaller. * This should cover the situations where we can not afford to run * out of space like for example punch hole, or converting * unwritten extents in delalloc path. In most cases such * allocation would require 1, or 2 blocks, higher numbers are * very rare. */ resv_clusters = (ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits); do_div(resv_clusters, 50); resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); atomic64_set(&sbi->s_resv_clusters, resv_clusters); } static const char *ext4_quota_mode(struct super_block *sb) { #ifdef CONFIG_QUOTA if (!ext4_quota_capable(sb)) return "none"; if (EXT4_SB(sb)->s_journal && ext4_is_quota_journalled(sb)) return "journalled"; else return "writeback"; #else return "disabled"; #endif } static void ext4_setup_csum_trigger(struct super_block *sb, enum ext4_journal_trigger_type type, void (*trigger)( struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size)) { struct ext4_sb_info *sbi = EXT4_SB(sb); sbi->s_journal_triggers[type].sb = sb; sbi->s_journal_triggers[type].tr_triggers.t_frozen = trigger; } static void ext4_free_sbi(struct ext4_sb_info *sbi) { if (!sbi) return; kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); } static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb) { struct ext4_sb_info *sbi; sbi = kzalloc_obj(*sbi); if (!sbi) return NULL; sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off, NULL, NULL); sbi->s_blockgroup_lock = kzalloc_obj(struct blockgroup_lock); if (!sbi->s_blockgroup_lock) goto err_out; sb->s_fs_info = sbi; sbi->s_sb = sb; return sbi; err_out: fs_put_dax(sbi->s_daxdev, NULL); kfree(sbi); return NULL; } static void ext4_set_def_opts(struct super_block *sb, struct ext4_super_block *es) { unsigned long def_mount_opts; /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); set_opt(sb, INIT_INODE_TABLE); if (def_mount_opts & EXT4_DEFM_DEBUG) set_opt(sb, DEBUG); if (def_mount_opts & EXT4_DEFM_BSDGROUPS) set_opt(sb, GRPID); if (def_mount_opts & EXT4_DEFM_UID16) set_opt(sb, NO_UID32); /* xattr user namespace & acls are now defaulted on */ set_opt(sb, XATTR_USER); #ifdef CONFIG_EXT4_FS_POSIX_ACL set_opt(sb, POSIX_ACL); #endif if (ext4_has_feature_fast_commit(sb)) set_opt2(sb, JOURNAL_FAST_COMMIT); /* don't forget to enable journal_csum when metadata_csum is enabled. */ if (ext4_has_feature_metadata_csum(sb)) set_opt(sb, JOURNAL_CHECKSUM); if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA) set_opt(sb, JOURNAL_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED) set_opt(sb, ORDERED_DATA); else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK) set_opt(sb, WRITEBACK_DATA); if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_PANIC) set_opt(sb, ERRORS_PANIC); else if (le16_to_cpu(es->s_errors) == EXT4_ERRORS_CONTINUE) set_opt(sb, ERRORS_CONT); else set_opt(sb, ERRORS_RO); /* block_validity enabled by default; disable with noblock_validity */ set_opt(sb, BLOCK_VALIDITY); if (def_mount_opts & EXT4_DEFM_DISCARD) set_opt(sb, DISCARD); if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0) set_opt(sb, BARRIER); /* * enable delayed allocation by default * Use -o nodelalloc to turn it off */ if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) && ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); set_opt(sb, DIOREAD_NOLOCK); } static int ext4_handle_clustersize(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int clustersize; /* Handle clustersize */ clustersize = BLOCK_SIZE << le32_to_cpu(es->s_log_cluster_size); if (ext4_has_feature_bigalloc(sb)) { if (clustersize < sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "cluster size (%d) smaller than " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); } else { if (clustersize != sb->s_blocksize) { ext4_msg(sb, KERN_ERR, "fragment/cluster size (%d) != " "block size (%lu)", clustersize, sb->s_blocksize); return -EINVAL; } if (sbi->s_blocks_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#blocks per group too big: %lu", sbi->s_blocks_per_group); return -EINVAL; } sbi->s_cluster_bits = 0; } sbi->s_clusters_per_group = le32_to_cpu(es->s_clusters_per_group); if (sbi->s_clusters_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "#clusters per group too big: %lu", sbi->s_clusters_per_group); return -EINVAL; } if (sbi->s_blocks_per_group != (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) { ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and clusters per group (%lu) inconsistent", sbi->s_blocks_per_group, sbi->s_clusters_per_group); return -EINVAL; } sbi->s_cluster_ratio = clustersize / sb->s_blocksize; /* Do we have standard group size of clustersize * 8 blocks ? */ if (sbi->s_blocks_per_group == clustersize << 3) set_opt2(sb, STD_GROUP_SIZE); return 0; } /* * ext4_atomic_write_init: Initializes filesystem min & max atomic write units. * With non-bigalloc filesystem awu will be based upon filesystem blocksize * & bdev awu units. * With bigalloc it will be based upon bigalloc cluster size & bdev awu units. * @sb: super block */ static void ext4_atomic_write_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct block_device *bdev = sb->s_bdev; unsigned int clustersize = EXT4_CLUSTER_SIZE(sb); if (!bdev_can_atomic_write(bdev)) return; if (!ext4_has_feature_extents(sb)) return; sbi->s_awu_min = max(sb->s_blocksize, bdev_atomic_write_unit_min_bytes(bdev)); sbi->s_awu_max = min(clustersize, bdev_atomic_write_unit_max_bytes(bdev)); if (sbi->s_awu_min && sbi->s_awu_max && sbi->s_awu_min <= sbi->s_awu_max) { ext4_msg(sb, KERN_NOTICE, "Supports (experimental) DIO atomic writes awu_min: %u, awu_max: %u", sbi->s_awu_min, sbi->s_awu_max); } else { sbi->s_awu_min = 0; sbi->s_awu_max = 0; } } static void ext4_fast_commit_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Initialize fast commit stuff */ atomic_set(&sbi->s_fc_subtid, 0); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); sbi->s_fc_ineligible_tid = 0; mutex_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; sbi->s_fc_replay_state.fc_regions_size = 0; sbi->s_fc_replay_state.fc_regions_used = 0; sbi->s_fc_replay_state.fc_regions_valid = 0; sbi->s_fc_replay_state.fc_modified_inodes = NULL; sbi->s_fc_replay_state.fc_modified_inodes_size = 0; sbi->s_fc_replay_state.fc_modified_inodes_used = 0; } static int ext4_inode_info_init(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) { sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE; sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO; } else { sbi->s_inode_size = le16_to_cpu(es->s_inode_size); sbi->s_first_ino = le32_to_cpu(es->s_first_ino); if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) { ext4_msg(sb, KERN_ERR, "invalid first ino: %u", sbi->s_first_ino); return -EINVAL; } if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) || (!is_power_of_2(sbi->s_inode_size)) || (sbi->s_inode_size > sb->s_blocksize)) { ext4_msg(sb, KERN_ERR, "unsupported inode size: %d", sbi->s_inode_size); ext4_msg(sb, KERN_ERR, "blocksize: %lu", sb->s_blocksize); return -EINVAL; } /* * i_atime_extra is the last extra field available for * [acm]times in struct ext4_inode. Checking for that * field should suffice to ensure we have extra space * for all three. */ if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) + sizeof(((struct ext4_inode *)0)->i_atime_extra)) { sb->s_time_gran = 1; sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; } else { sb->s_time_gran = NSEC_PER_SEC; sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; } sb->s_time_min = EXT4_TIMESTAMP_MIN; } if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { sbi->s_want_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; if (ext4_has_feature_extra_isize(sb)) { unsigned v, max = (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE); v = le16_to_cpu(es->s_want_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_want_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; v = le16_to_cpu(es->s_min_extra_isize); if (v > max) { ext4_msg(sb, KERN_ERR, "bad s_min_extra_isize: %d", v); return -EINVAL; } if (sbi->s_want_extra_isize < v) sbi->s_want_extra_isize = v; } } return 0; } #if IS_ENABLED(CONFIG_UNICODE) static int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { const struct ext4_sb_encodings *encoding_info; struct unicode_map *encoding; __u16 encoding_flags = le16_to_cpu(es->s_encoding_flags); if (!ext4_has_feature_casefold(sb) || sb->s_encoding) return 0; encoding_info = ext4_sb_read_encoding(es); if (!encoding_info) { ext4_msg(sb, KERN_ERR, "Encoding requested by superblock is unknown"); return -EINVAL; } encoding = utf8_load(encoding_info->version); if (IS_ERR(encoding)) { ext4_msg(sb, KERN_ERR, "can't mount with superblock charset: %s-%u.%u.%u " "not supported by the kernel. flags: 0x%x.", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); return -EINVAL; } ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, unicode_major(encoding_info->version), unicode_minor(encoding_info->version), unicode_rev(encoding_info->version), encoding_flags); sb->s_encoding = encoding; sb->s_encoding_flags = encoding_flags; return 0; } #else static inline int ext4_encoding_init(struct super_block *sb, struct ext4_super_block *es) { return 0; } #endif static int ext4_init_metadata_csum(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); /* Warn if metadata_csum and gdt_csum are both set. */ if (ext4_has_feature_metadata_csum(sb) && ext4_has_feature_gdt_csum(sb)) ext4_warning(sb, "metadata_csum and uninit_bg are " "redundant flags; please run fsck."); /* Check for a known checksum algorithm */ if (!ext4_verify_csum_type(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "unknown checksum algorithm."); return -EINVAL; } ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE, ext4_orphan_file_block_trigger); /* Check superblock checksum */ if (!ext4_superblock_csum_verify(sb, es)) { ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " "invalid superblock checksum. Run e2fsck?"); return -EFSBADCRC; } /* Precompute checksum seed for all metadata */ if (ext4_has_feature_csum_seed(sb)) sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); else if (ext4_has_feature_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) sbi->s_csum_seed = ext4_chksum(~0, es->s_uuid, sizeof(es->s_uuid)); return 0; } static int ext4_check_feature_compatibility(struct super_block *sb, struct ext4_super_block *es, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV && (ext4_has_compat_features(sb) || ext4_has_ro_compat_features(sb) || ext4_has_incompat_features(sb))) ext4_msg(sb, KERN_WARNING, "feature flags set on rev 0 fs, " "running e2fsck is recommended"); if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) { set_opt2(sb, HURD_COMPAT); if (ext4_has_feature_64bit(sb)) { ext4_msg(sb, KERN_ERR, "The Hurd can't support 64-bit file systems"); return -EINVAL; } /* * ea_inode feature uses l_i_version field which is not * available in HURD_COMPAT mode. */ if (ext4_has_feature_ea_inode(sb)) { ext4_msg(sb, KERN_ERR, "ea_inode feature is not supported for Hurd"); return -EINVAL; } } if (IS_EXT2_SB(sb)) { if (ext2_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext2 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext[34] filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due " "to feature incompatibilities"); return -EINVAL; } } if (IS_EXT3_SB(sb)) { if (ext3_feature_set_ok(sb)) ext4_msg(sb, KERN_INFO, "mounting ext3 file system " "using the ext4 subsystem"); else { /* * If we're probing be silent, if this looks like * it's actually an ext4 filesystem. */ if (silent && ext4_feature_set_ok(sb, sb_rdonly(sb))) return -EINVAL; ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due " "to feature incompatibilities"); return -EINVAL; } } /* * Check feature flags regardless of the revision level, since we * previously didn't change the revision level when setting the flags, * so there is a chance incompat flags are set on a rev 0 filesystem. */ if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) return -EINVAL; if (sbi->s_daxdev) { if (sb->s_blocksize == PAGE_SIZE) set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); else ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); } if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem" " that may contain inline data"); return -EINVAL; } if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "DAX unsupported by block device."); return -EINVAL; } } if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) { ext4_msg(sb, KERN_ERR, "Unsupported encryption level %d", es->s_encryption_level); return -EINVAL; } return 0; } static int ext4_check_geometry(struct super_block *sb, struct ext4_super_block *es) { struct ext4_sb_info *sbi = EXT4_SB(sb); __u64 blocks_count; int err; if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (sb->s_blocksize / 4)) { ext4_msg(sb, KERN_ERR, "Number of reserved GDT blocks insanely large: %d", le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks)); return -EINVAL; } /* * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. */ err = generic_check_addressable(sb->s_blocksize_bits, ext4_blocks_count(es)); if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); return err; } /* check blocks count against device size */ blocks_count = sb_bdev_nr_blocks(sb); if (blocks_count && ext4_blocks_count(es) > blocks_count) { ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " "exceeds size of device (%llu blocks)", ext4_blocks_count(es), blocks_count); return -EINVAL; } /* * It makes no sense for the first data block to be beyond the end * of the filesystem. */ if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block %u is beyond end of filesystem (%llu)", le32_to_cpu(es->s_first_data_block), ext4_blocks_count(es)); return -EINVAL; } if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) && (sbi->s_cluster_ratio == 1)) { ext4_msg(sb, KERN_WARNING, "bad geometry: first data " "block is 0 with a 1k block and cluster size"); return -EINVAL; } blocks_count = (ext4_blocks_count(es) - le32_to_cpu(es->s_first_data_block) + EXT4_BLOCKS_PER_GROUP(sb) - 1); do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb)); if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) { ext4_msg(sb, KERN_WARNING, "groups count too large: %llu " "(block count %llu, first data block %u, " "blocks per group %lu)", blocks_count, ext4_blocks_count(es), le32_to_cpu(es->s_first_data_block), EXT4_BLOCKS_PER_GROUP(sb)); return -EINVAL; } sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min(sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != le32_to_cpu(es->s_inodes_count)) { ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", le32_to_cpu(es->s_inodes_count), ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); return -EINVAL; } return 0; } static int ext4_group_desc_init(struct super_block *sb, struct ext4_super_block *es, ext4_fsblk_t logical_sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int db_count; ext4_fsblk_t block; int i; db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { if (le32_to_cpu(es->s_first_meta_bg) > db_count) { ext4_msg(sb, KERN_WARNING, "first meta block group too large: %u " "(group descriptor block count %u)", le32_to_cpu(es->s_first_meta_bg), db_count); return -EINVAL; } } rcu_assign_pointer(sbi->s_group_desc, kvmalloc_objs(struct buffer_head *, db_count)); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); return -ENOMEM; } bgl_lock_init(sbi->s_blockgroup_lock); /* Pre-read the descriptors into the buffer cache */ for (i = 0; i < db_count; i++) { block = descriptor_loc(sb, logical_sb_block, i); ext4_sb_breadahead_unmovable(sb, block); } for (i = 0; i < db_count; i++) { struct buffer_head *bh; block = descriptor_loc(sb, logical_sb_block, i); bh = ext4_sb_bread_unmovable(sb, block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "can't read group descriptor %d", i); sbi->s_gdb_count = i; return PTR_ERR(bh); } rcu_read_lock(); rcu_dereference(sbi->s_group_desc)[i] = bh; rcu_read_unlock(); } sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); return -EFSCORRUPTED; } return 0; } static int ext4_load_and_init_journal(struct super_block *sb, struct ext4_super_block *es, struct ext4_fs_context *ctx) { struct ext4_sb_info *sbi = EXT4_SB(sb); int err; err = ext4_load_journal(sb, es, ctx->journal_devnum); if (err) return err; if (ext4_has_feature_64bit(sb) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); goto out; } if (!set_journal_csum_feature_set(sb)) { ext4_msg(sb, KERN_ERR, "Failed to set journal checksum " "feature set"); goto out; } if (test_opt2(sb, JOURNAL_FAST_COMMIT) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { ext4_msg(sb, KERN_ERR, "Failed to set fast commit journal feature"); goto out; } /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { case 0: /* No mode set, assume a default based on the journal * capabilities: ORDERED_DATA if the journal can * cope, else JOURNAL_DATA */ if (jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { set_opt(sb, ORDERED_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_ORDERED_DATA; } else { set_opt(sb, JOURNAL_DATA); sbi->s_def_mount_opt |= EXT4_MOUNT_JOURNAL_DATA; } break; case EXT4_MOUNT_ORDERED_DATA: case EXT4_MOUNT_WRITEBACK_DATA: if (!jbd2_journal_check_available_features (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) { ext4_msg(sb, KERN_ERR, "Journal does not support " "requested data journaling mode"); goto out; } break; default: break; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA && test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); goto out; } set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); sbi->s_journal->j_submit_inode_data_buffers = ext4_journal_submit_inode_data_buffers; sbi->s_journal->j_finish_inode_data_buffers = ext4_journal_finish_inode_data_buffers; return 0; out: ext4_journal_destroy(sbi, sbi->s_journal); return -EINVAL; } static int ext4_check_journal_data_mode(struct super_block *sb) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with " "data=journal disables delayed allocation, " "dioread_nolock, O_DIRECT and fast_commit support!\n"); /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); clear_opt2(sb, JOURNAL_FAST_COMMIT); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); return -EINVAL; } if (test_opt(sb, DAX_ALWAYS)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dax"); return -EINVAL; } if (ext4_has_feature_encrypt(sb)) { ext4_msg(sb, KERN_WARNING, "encrypted files will use data=ordered " "instead of data journaling mode"); } if (test_opt(sb, DELALLOC)) clear_opt(sb, DELALLOC); } else { sb->s_iflags |= SB_I_CGROUPWB; } return 0; } static const char *ext4_has_journal_option(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) return "journal_async_commit"; if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) return "journal_checksum"; if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) return "commit="; if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) return "data="; if (test_opt(sb, DATA_ERR_ABORT)) return "data_err=abort"; return NULL; } /* * Limit the maximum folio order to 2048 blocks to prevent overestimation * of reserve handle credits during the folio writeback in environments * where the PAGE_SIZE exceeds 4KB. */ #define EXT4_MAX_PAGECACHE_ORDER(sb) \ umin(MAX_PAGECACHE_ORDER, (11 + (sb)->s_blocksize_bits - PAGE_SHIFT)) static void ext4_set_max_mapping_order(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) sbi->s_max_folio_order = sbi->s_min_folio_order; else sbi->s_max_folio_order = EXT4_MAX_PAGECACHE_ORDER(sb); } static int ext4_check_large_folio(struct super_block *sb) { const char *err_str = NULL; if (ext4_has_feature_encrypt(sb)) err_str = "encrypt"; if (!err_str) { ext4_set_max_mapping_order(sb); } else if (sb->s_blocksize > PAGE_SIZE) { ext4_msg(sb, KERN_ERR, "bs(%lu) > ps(%lu) unsupported for %s", sb->s_blocksize, PAGE_SIZE, err_str); return -EINVAL; } return 0; } static int ext4_load_super(struct super_block *sb, ext4_fsblk_t *lsb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es; ext4_fsblk_t logical_sb_block; unsigned long offset = 0; struct buffer_head *bh; int ret = -EINVAL; int blocksize; blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE); if (!blocksize) { ext4_msg(sb, KERN_ERR, "unable to set blocksize"); return -EINVAL; } /* * The ext4 superblock will not be buffer aligned for other than 1kB * block sizes. We need to calculate the offset from buffer start. */ if (blocksize != EXT4_MIN_BLOCK_SIZE) { logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); } else { logical_sb_block = sbi->s_sb_block; } bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "unable to read superblock"); return PTR_ERR(bh); } /* * Note: s_es must be initialized as soon as possible because * some ext4 macro-instructions depend on its value */ es = (struct ext4_super_block *) (bh->b_data + offset); sbi->s_es = es; sb->s_magic = le16_to_cpu(es->s_magic); if (sb->s_magic != EXT4_SUPER_MAGIC) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto out; } if (le32_to_cpu(es->s_log_block_size) > (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log block size: %u", le32_to_cpu(es->s_log_block_size)); goto out; } if (le32_to_cpu(es->s_log_cluster_size) > (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { ext4_msg(sb, KERN_ERR, "Invalid log cluster size: %u", le32_to_cpu(es->s_log_cluster_size)); goto out; } blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); /* * If the default block size is not the same as the real block size, * we need to reload it. */ if (sb->s_blocksize == blocksize) goto success; /* * bh must be released before kill_bdev(), otherwise * it won't be freed and its page also. kill_bdev() * is called by sb_set_blocksize(). */ brelse(bh); /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); bh = NULL; goto out; } logical_sb_block = sbi->s_sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = ext4_sb_bread_unmovable(sb, logical_sb_block); if (IS_ERR(bh)) { ext4_msg(sb, KERN_ERR, "Can't read superblock on 2nd try"); ret = PTR_ERR(bh); bh = NULL; goto out; } es = (struct ext4_super_block *)(bh->b_data + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { ext4_msg(sb, KERN_ERR, "Magic mismatch, very weird!"); goto out; } success: sbi->s_min_folio_order = get_order(blocksize); *lsb = logical_sb_block; sbi->s_sbh = bh; return 0; out: brelse(bh); return ret; } static int ext4_hash_info_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; unsigned int i; sbi->s_def_hash_version = es->s_def_hash_version; if (sbi->s_def_hash_version > DX_HASH_LAST) { ext4_msg(sb, KERN_ERR, "Invalid default hash set in the superblock"); return -EINVAL; } else if (sbi->s_def_hash_version == DX_HASH_SIPHASH) { ext4_msg(sb, KERN_ERR, "SIPHASH is not a valid default hash value"); return -EINVAL; } for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); if (ext4_has_feature_dir_index(sb)) { i = le32_to_cpu(es->s_flags); if (i & EXT2_FLAGS_UNSIGNED_HASH) sbi->s_hash_unsigned = 3; else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { #ifdef __CHAR_UNSIGNED__ if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); sbi->s_hash_unsigned = 3; #else if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); #endif } } return 0; } static int ext4_block_group_meta_init(struct super_block *sb, int silent) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int has_huge_files; has_huge_files = ext4_has_feature_huge_file(sb); sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits, has_huge_files); sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files); sbi->s_desc_size = le16_to_cpu(es->s_desc_size); if (ext4_has_feature_64bit(sb)) { if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT || sbi->s_desc_size > EXT4_MAX_DESC_SIZE || !is_power_of_2(sbi->s_desc_size)) { ext4_msg(sb, KERN_ERR, "unsupported descriptor size %lu", sbi->s_desc_size); return -EINVAL; } } else sbi->s_desc_size = EXT4_MIN_DESC_SIZE; sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); sbi->s_inodes_per_block = sb->s_blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0 || sbi->s_blocks_per_group == 0) { if (!silent) ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); return -EINVAL; } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", sbi->s_inodes_per_group); return -EINVAL; } sbi->s_itb_per_group = sbi->s_inodes_per_group / sbi->s_inodes_per_block; sbi->s_desc_per_block = sb->s_blocksize / EXT4_DESC_SIZE(sb); sbi->s_mount_state = le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY; sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); return 0; } /* * It's hard to get stripe aligned blocks if stripe is not aligned with * cluster, just disable stripe and alert user to simplify code and avoid * stripe aligned allocation which will rarely succeed. */ static bool ext4_is_stripe_incompatible(struct super_block *sb, unsigned long stripe) { struct ext4_sb_info *sbi = EXT4_SB(sb); return (stripe > 0 && sbi->s_cluster_ratio > 1 && stripe % sbi->s_cluster_ratio != 0); } static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) { struct ext4_super_block *es = NULL; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t logical_sb_block; struct inode *root; int needs_recovery; int err; ext4_group_t first_not_zeroed; struct ext4_fs_context *ctx = fc->fs_private; int silent = fc->sb_flags & SB_SILENT; /* Set defaults for the variables that will be set during parsing */ if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) ctx->journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sectors_written_start = part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); err = ext4_load_super(sb, &logical_sb_block, silent); if (err) goto out_fail; es = sbi->s_es; sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); err = ext4_init_metadata_csum(sb, es); if (err) goto failed_mount; ext4_set_def_opts(sb, es); sbi->s_resuid = make_kuid(&init_user_ns, ext4_get_resuid(es)); sbi->s_resgid = make_kgid(&init_user_ns, ext4_get_resuid(es)); sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; sbi->s_sb_update_kb = EXT4_DEF_SB_UPDATE_INTERVAL_KB; sbi->s_sb_update_sec = EXT4_DEF_SB_UPDATE_INTERVAL_SEC; /* * set default s_li_wait_mult for lazyinit, for the case there is * no mount option specified. */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; err = ext4_inode_info_init(sb, es); if (err) goto failed_mount; err = parse_apply_sb_mount_options(sb, ctx); if (err < 0) goto failed_mount; sbi->s_def_mount_opt = sbi->s_mount_opt; sbi->s_def_mount_opt2 = sbi->s_mount_opt2; err = ext4_check_opt_consistency(fc, sb); if (err < 0) goto failed_mount; ext4_apply_options(fc, sb); err = ext4_check_large_folio(sb); if (err < 0) goto failed_mount; err = ext4_encoding_init(sb, es); if (err) goto failed_mount; err = ext4_check_journal_data_mode(sb); if (err) goto failed_mount; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); /* HSM events are allowed by default. */ sb->s_iflags |= SB_I_ALLOW_HSM; err = ext4_check_feature_compatibility(sb, es, silent); if (err) goto failed_mount; err = ext4_block_group_meta_init(sb, silent); if (err) goto failed_mount; err = ext4_hash_info_init(sb); if (err) goto failed_mount; err = ext4_handle_clustersize(sb); if (err) goto failed_mount; err = ext4_check_geometry(sb, es); if (err) goto failed_mount; timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); mutex_init(&sbi->s_error_notify_mutex); INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); if (err) goto failed_mount3; err = ext4_es_register_shrinker(sbi); if (err) goto failed_mount3; sbi->s_stripe = ext4_get_stripe_size(sbi); if (ext4_is_stripe_incompatible(sb, sbi->s_stripe)) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", sbi->s_stripe, sbi->s_cluster_ratio); sbi->s_stripe = 0; } sbi->s_extent_max_zeroout_kb = 32; /* * set up enough so that it can read an inode */ sb->s_op = &ext4_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_FS_ENCRYPTION sb->s_cop = &ext4_cryptops; #endif #ifdef CONFIG_FS_VERITY sb->s_vop = &ext4_verityops; #endif #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (ext4_has_feature_quota(sb)) sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif super_set_uuid(sb, es->s_uuid, sizeof(es->s_uuid)); super_set_sysfs_name_bdev(sb); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); spin_lock_init(&sbi->s_bdev_wb_lock); ext4_atomic_write_init(sb); ext4_fast_commit_init(sb); sb->s_root = NULL; needs_recovery = (es->s_last_orphan != 0 || ext4_has_feature_orphan_present(sb) || ext4_has_feature_journal_needs_recovery(sb)); if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto failed_mount3a; } err = -EINVAL; /* * The first inode we look at is the journal inode. Don't try * root first: it may be modified in the journal! */ if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) { err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; if (bdev_read_only(sb->s_bdev)) needs_recovery = 0; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); goto failed_mount3a; } else { const char *journal_option; /* Nojournal mode, all journal mount options are illegal */ journal_option = ext4_has_journal_option(sb); if (journal_option != NULL) { ext4_msg(sb, KERN_ERR, "can't mount with %s, fs mounted w/o journal", journal_option); goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); clear_opt2(sb, JOURNAL_FAST_COMMIT); sbi->s_journal = NULL; needs_recovery = 0; } if (!test_opt(sb, NO_MBCACHE)) { sbi->s_ea_block_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_block_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); err = -EINVAL; goto failed_mount_wq; } if (ext4_has_feature_ea_inode(sb)) { sbi->s_ea_inode_cache = ext4_xattr_create_cache(); if (!sbi->s_ea_inode_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_inode_cache"); err = -EINVAL; goto failed_mount_wq; } } } /* * Get the # of file system overhead blocks from the * superblock if present. */ sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); /* ignore the precalculated value if it is ridiculous */ if (sbi->s_overhead > ext4_blocks_count(es)) sbi->s_overhead = 0; /* * If the bigalloc feature is not enabled recalculating the * overhead doesn't take long, so we might as well just redo * it to make sure we are using the correct value. */ if (!ext4_has_feature_bigalloc(sb)) sbi->s_overhead = 0; if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; } /* * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ EXT4_SB(sb)->rsv_conversion_wq = alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->rsv_conversion_wq) { printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); err = -ENOMEM; goto failed_mount4; } /* * The jbd2_journal_load will have done any necessary log recovery, * so we can safely mount the rest of the filesystem now. */ root = ext4_iget(sb, EXT4_ROOT_INO, EXT4_IGET_SPECIAL); if (IS_ERR(root)) { ext4_msg(sb, KERN_ERR, "get root inode failed"); err = PTR_ERR(root); root = NULL; goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); iput(root); err = -EFSCORRUPTED; goto failed_mount4; } generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); err = -ENOMEM; goto failed_mount4; } err = ext4_setup_super(sb, es, sb_rdonly(sb)); if (err == -EROFS) { sb->s_flags |= SB_RDONLY; } else if (err) goto failed_mount4a; ext4_set_resv_clusters(sb); if (test_opt(sb, BLOCK_VALIDITY)) { err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " "zone (%d)", err); goto failed_mount4a; } } ext4_fc_replay_cleanup(sb); ext4_ext_init(sb); /* * Enable optimize_scan if number of groups is > threshold. This can be * turned off by passing "mb_optimize_scan=0". This can also be * turned on forcefully by passing "mb_optimize_scan=1". */ if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) { if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD) set_opt2(sb, MB_OPTIMIZE_SCAN); else clear_opt2(sb, MB_OPTIMIZE_SCAN); } err = ext4_percpu_param_init(sbi); if (err) goto failed_mount5; err = ext4_mb_init(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", err); goto failed_mount5; } /* * We can only set up the journal commit callback once * mballoc is initialized */ if (sbi->s_journal) sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; if (ext4_has_feature_flex_bg(sb)) if (!ext4_fill_flex_info(sb)) { ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); err = -ENOMEM; goto failed_mount6; } err = ext4_register_li_request(sb, first_not_zeroed); if (err) goto failed_mount6; err = ext4_init_orphan_info(sb); if (err) goto failed_mount7; #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) { err = ext4_enable_quotas(sb); if (err) goto failed_mount8; } #endif /* CONFIG_QUOTA */ /* * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err, &sbi->s_bdev_wb_err); EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; /* * Update the checksum after updating free space/inode counters and * ext4_orphan_cleanup. Otherwise the superblock can have an incorrect * checksum in the buffer cache until it is written out and * e2fsprogs programs trying to open a file system immediately * after it is mounted can fail. */ ext4_superblock_csum_set(sb); if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); err = ext4_mark_recovery_complete(sb, es); if (err) goto failed_mount9; } if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev)) { ext4_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but the device does not support discard"); clear_opt(sb, DISCARD); } if (es->s_error_count) { sbi->s_err_report_sec = 5*60; /* first time 5 minutes */ mod_timer(&sbi->s_err_report, jiffies + secs_to_jiffies(sbi->s_err_report_sec)); } sbi->s_err_report_sec = 24*60*60; /* Once a day */ /* Enable message ratelimiting. Default is 10 messages per 5 secs. */ ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); atomic_set(&sbi->s_warning_count, 0); atomic_set(&sbi->s_msg_count, 0); /* Register sysfs after all initializations are complete. */ err = ext4_register_sysfs(sb); if (err) goto failed_mount9; return 0; failed_mount9: ext4_quotas_off(sb, EXT4_MAXQUOTAS); failed_mount8: __maybe_unused ext4_release_orphan_info(sb); failed_mount7: ext4_unregister_li_request(sb); failed_mount6: ext4_mb_release(sb); ext4_flex_groups_free(sbi); failed_mount5: ext4_percpu_param_destroy(sbi); ext4_ext_release(sb); ext4_release_system_zone(sb); failed_mount4a: dput(sb->s_root); sb->s_root = NULL; failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); failed_mount_wq: ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); sbi->s_ea_inode_cache = NULL; ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { ext4_journal_destroy(sbi, sbi->s_journal); } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: /* flush s_sb_upd_work before sbi destroy */ flush_work(&sbi->s_sb_upd_work); ext4_stop_mmpd(sbi); timer_delete_sync(&sbi->s_err_report); ext4_group_desc_free(sbi); failed_mount: #if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif #ifdef CONFIG_QUOTA for (unsigned int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); if (sbi->s_journal_bdev_file) { invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); bdev_fput(sbi->s_journal_bdev_file); } out_fail: invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; return err; } static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_sb_info *sbi; const char *descr; int ret; sbi = ext4_alloc_sbi(sb); if (!sbi) return -ENOMEM; fc->s_fs_info = sbi; /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); sbi->s_sb_block = 1; /* Default super block location */ if (ctx->spec & EXT4_SPEC_s_sb_block) sbi->s_sb_block = ctx->s_sb_block; ret = __ext4_fill_super(fc, sb); if (ret < 0) goto free_sbi; if (sbi->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) descr = " journalled data mode"; else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) descr = " ordered data mode"; else descr = " writeback data mode"; } else descr = "out journal"; if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) ext4_msg(sb, KERN_INFO, "mounted filesystem %pU %s with%s. " "Quota mode: %s.", &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", descr, ext4_quota_mode(sb)); /* Update the s_overhead_clusters if necessary */ ext4_update_overhead(sb, false); return 0; free_sbi: ext4_free_sbi(sbi); fc->s_fs_info = NULL; return ret; } static int ext4_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, ext4_fill_super); } /* * Setup any per-fs journal parameters now. We'll do this both on * initial mount, once the journal has been initialised but before we've * done any recovery; and again on any subsequent remount. */ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal) { struct ext4_sb_info *sbi = EXT4_SB(sb); journal->j_commit_interval = sbi->s_commit_interval; journal->j_min_batch_time = sbi->s_min_batch_time; journal->j_max_batch_time = sbi->s_max_batch_time; ext4_fc_init(sb, journal); write_lock(&journal->j_state_lock); if (test_opt(sb, BARRIER)) journal->j_flags |= JBD2_BARRIER; else journal->j_flags &= ~JBD2_BARRIER; /* * Always enable journal cycle record option, letting the journal * records log transactions continuously between each mount. */ journal->j_flags |= JBD2_CYCLE_RECORD; write_unlock(&journal->j_state_lock); } static struct inode *ext4_get_journal_inode(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; /* * Test for the existence of a valid inode on disk. Bad things * happen if we iget() an unused inode, as the subsequent iput() * will try to delete it. */ journal_inode = ext4_iget(sb, journal_inum, EXT4_IGET_SPECIAL); if (IS_ERR(journal_inode)) { ext4_msg(sb, KERN_ERR, "no journal found"); return ERR_CAST(journal_inode); } if (!journal_inode->i_nlink) { make_bad_inode(journal_inode); iput(journal_inode); ext4_msg(sb, KERN_ERR, "journal inode is deleted"); return ERR_PTR(-EFSCORRUPTED); } if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return ERR_PTR(-EFSCORRUPTED); } ext4_debug("Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); return journal_inode; } static int ext4_journal_bmap(journal_t *journal, sector_t *block) { struct ext4_map_blocks map; int ret; if (journal->j_inode == NULL) return 0; map.m_lblk = *block; map.m_len = 1; ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0); if (ret <= 0) { ext4_msg(journal->j_inode->i_sb, KERN_CRIT, "journal bmap failed: block %llu ret %d\n", *block, ret); jbd2_journal_abort(journal, ret ? ret : -EFSCORRUPTED); return ret; } *block = map.m_pblk; return 0; } static journal_t *ext4_open_inode_journal(struct super_block *sb, unsigned int journal_inum) { struct inode *journal_inode; journal_t *journal; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (IS_ERR(journal_inode)) return ERR_CAST(journal_inode); journal = jbd2_journal_init_inode(journal_inode); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "Could not load journal inode"); iput(journal_inode); return ERR_CAST(journal); } journal->j_private = sb; journal->j_bmap = ext4_journal_bmap; ext4_init_journal_params(sb, journal); return journal; } static struct file *ext4_get_journal_blkdev(struct super_block *sb, dev_t j_dev, ext4_fsblk_t *j_start, ext4_fsblk_t *j_len) { struct buffer_head *bh; struct block_device *bdev; struct file *bdev_file; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; struct ext4_super_block *es; int errno; bdev_file = bdev_file_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES, sb, &fs_holder_ops); if (IS_ERR(bdev_file)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_file)); return bdev_file; } bdev = file_bdev(bdev_file); blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { ext4_msg(sb, KERN_ERR, "blocksize too small for journal device"); errno = -EINVAL; goto out_bdev; } sb_block = EXT4_MIN_BLOCK_SIZE / blocksize; offset = EXT4_MIN_BLOCK_SIZE % blocksize; set_blocksize(bdev_file, blocksize); bh = __bread(bdev, sb_block, blocksize); if (!bh) { ext4_msg(sb, KERN_ERR, "couldn't read superblock of " "external journal"); errno = -EINVAL; goto out_bdev; } es = (struct ext4_super_block *) (bh->b_data + offset); if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { ext4_msg(sb, KERN_ERR, "external journal has bad superblock"); errno = -EFSCORRUPTED; goto out_bh; } if ((le32_to_cpu(es->s_feature_ro_compat) & EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && es->s_checksum != ext4_superblock_csum(es)) { ext4_msg(sb, KERN_ERR, "external journal has corrupt superblock"); errno = -EFSCORRUPTED; goto out_bh; } if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) { ext4_msg(sb, KERN_ERR, "journal UUID does not match"); errno = -EFSCORRUPTED; goto out_bh; } *j_start = sb_block + 1; *j_len = ext4_blocks_count(es); brelse(bh); return bdev_file; out_bh: brelse(bh); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static journal_t *ext4_open_dev_journal(struct super_block *sb, dev_t j_dev) { journal_t *journal; ext4_fsblk_t j_start; ext4_fsblk_t j_len; struct file *bdev_file; int errno = 0; bdev_file = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); if (IS_ERR(bdev_file)) return ERR_CAST(bdev_file); journal = jbd2_journal_init_dev(file_bdev(bdev_file), sb->s_bdev, j_start, j_len, sb->s_blocksize); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); errno = PTR_ERR(journal); goto out_bdev; } if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) { ext4_msg(sb, KERN_ERR, "External journal has more than one " "user (unsupported) - %d", be32_to_cpu(journal->j_superblock->s_nr_users)); errno = -EINVAL; goto out_journal; } journal->j_private = sb; EXT4_SB(sb)->s_journal_bdev_file = bdev_file; ext4_init_journal_params(sb, journal); return journal; out_journal: ext4_journal_destroy(EXT4_SB(sb), journal); out_bdev: bdev_fput(bdev_file); return ERR_PTR(errno); } static int ext4_load_journal(struct super_block *sb, struct ext4_super_block *es, unsigned long journal_devnum) { journal_t *journal; unsigned int journal_inum = le32_to_cpu(es->s_journal_inum); dev_t journal_dev; int err = 0; int really_read_only; int journal_dev_ro; if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { ext4_msg(sb, KERN_INFO, "external journal device major/minor " "numbers have changed"); journal_dev = new_decode_dev(journal_devnum); } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); if (journal_inum && journal_dev) { ext4_msg(sb, KERN_ERR, "filesystem has both journal inode and journal device!"); return -EINVAL; } if (journal_inum) { journal = ext4_open_inode_journal(sb, journal_inum); if (IS_ERR(journal)) return PTR_ERR(journal); } else { journal = ext4_open_dev_journal(sb, journal_dev); if (IS_ERR(journal)) return PTR_ERR(journal); } journal_dev_ro = bdev_read_only(journal->j_dev); really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; if (journal_dev_ro && !sb_rdonly(sb)) { ext4_msg(sb, KERN_ERR, "journal device read-only, try mounting with '-o ro'"); err = -EROFS; goto err_out; } /* * Are we loading a blank journal or performing recovery after a * crash? For recovery, we need to check in advance whether we * can get read-write access to the device. */ if (ext4_has_feature_journal_needs_recovery(sb)) { if (sb_rdonly(sb)) { ext4_msg(sb, KERN_INFO, "INFO: recovery " "required on readonly filesystem"); if (really_read_only) { ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); err = -EROFS; goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); if (!ext4_has_feature_journal_needs_recovery(sb)) err = jbd2_journal_wipe(journal, !really_read_only); if (!err) { char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL); __le16 orig_state; bool changed = false; if (save) memcpy(save, ((char *) es) + EXT4_S_ERR_START, EXT4_S_ERR_LEN); err = jbd2_journal_load(journal); if (save && memcmp(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN)) { memcpy(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN); changed = true; } kfree(save); orig_state = es->s_state; es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS); if (orig_state != es->s_state) changed = true; /* Write out restored error information to the superblock */ if (changed && !really_read_only) { int err2; err2 = ext4_commit_super(sb); err = err ? : err2; } } if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); goto err_out; } EXT4_SB(sb)->s_journal = journal; err = ext4_clear_journal_err(sb, es); if (err) { ext4_journal_destroy(EXT4_SB(sb), journal); return err; } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); ext4_commit_super(sb); } if (!really_read_only && journal_inum && journal_inum != le32_to_cpu(es->s_journal_inum)) { es->s_journal_inum = cpu_to_le32(journal_inum); ext4_commit_super(sb); } return 0; err_out: ext4_journal_destroy(EXT4_SB(sb), journal); return err; } /* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */ static void ext4_update_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct buffer_head *sbh = sbi->s_sbh; lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system * read/only but we need to replay the journal; at that point, * for people who are east of GMT and who make their clock * tick in localtime for Windows bug-for-bug compatibility, * the clock is set in the future, and this will cause e2fsck * to complain and force a full file system check. */ if (!sb_rdonly(sb)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1)); if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, EXT4_C2B(sbi, percpu_counter_sum_positive( &sbi->s_freeclusters_counter))); if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &sbi->s_freeinodes_counter)); /* Copy error information to the on-disk superblock */ spin_lock(&sbi->s_error_lock); if (sbi->s_add_error_count > 0) { es->s_state |= cpu_to_le16(EXT4_ERROR_FS); if (!es->s_first_error_time && !es->s_first_error_time_hi) { __ext4_update_tstamp(&es->s_first_error_time, &es->s_first_error_time_hi, sbi->s_first_error_time); strtomem_pad(es->s_first_error_func, sbi->s_first_error_func, 0); es->s_first_error_line = cpu_to_le32(sbi->s_first_error_line); es->s_first_error_ino = cpu_to_le32(sbi->s_first_error_ino); es->s_first_error_block = cpu_to_le64(sbi->s_first_error_block); es->s_first_error_errcode = ext4_errno_to_code(sbi->s_first_error_code); } __ext4_update_tstamp(&es->s_last_error_time, &es->s_last_error_time_hi, sbi->s_last_error_time); strtomem_pad(es->s_last_error_func, sbi->s_last_error_func, 0); es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line); es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino); es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block); es->s_last_error_errcode = ext4_errno_to_code(sbi->s_last_error_code); /* * Start the daily error reporting function if it hasn't been * started already and sbi->s_err_report_sec is not zero */ if (!es->s_error_count && !sbi->s_err_report_sec) mod_timer(&sbi->s_err_report, jiffies + secs_to_jiffies(sbi->s_err_report_sec)); le32_add_cpu(&es->s_error_count, sbi->s_add_error_count); sbi->s_add_error_count = 0; } spin_unlock(&sbi->s_error_lock); ext4_superblock_csum_set(sb); unlock_buffer(sbh); } static int ext4_commit_super(struct super_block *sb) { struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; if (!sbh) return -EINVAL; ext4_update_super(sb); lock_buffer(sbh); /* Buffer got discarded which means block device got invalidated */ if (!buffer_mapped(sbh)) { unlock_buffer(sbh); return -EIO; } if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the * superblock failed. This could happen because the * USB device was yanked out. Or it could happen to * be a transient write error and maybe the block will * be remapped. Nothing we can do but to retry the * write and hope for the best. */ ext4_msg(sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } /* Clear potential dirty bit if it was journalled update */ clear_buffer_dirty(sbh); bh_submit(sbh, REQ_OP_WRITE | REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0), bh_end_write); wait_on_buffer(sbh); if (buffer_write_io_error(sbh)) { ext4_msg(sb, KERN_ERR, "I/O error while writing " "superblock"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); return -EIO; } return 0; } /* * Have we just finished recovery? If so, and if we are mounting (or * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es) { int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { if (journal != NULL) { ext4_error(sb, "Journal got removed while the fs was " "mounted!"); return -EFSCORRUPTED; } return 0; } jbd2_journal_lock_updates(journal); err = jbd2_journal_flush(journal, 0); if (err < 0) goto out; if (sb_rdonly(sb) && (ext4_has_feature_journal_needs_recovery(sb) || ext4_has_feature_orphan_present(sb))) { if (!ext4_orphan_file_empty(sb)) { ext4_error(sb, "Orphan file not empty on read-only fs."); err = -EFSCORRUPTED; goto out; } ext4_clear_feature_journal_needs_recovery(sb); ext4_clear_feature_orphan_present(sb); ext4_commit_super(sb); } out: jbd2_journal_unlock_updates(journal); return err; } /* * If we are mounting (or read-write remounting) a filesystem whose journal * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; if (!ext4_has_feature_journal(sb)) { ext4_error(sb, "Journal got removed while the fs was mounted!"); return -EFSCORRUPTED; } journal = EXT4_SB(sb)->s_journal; /* * Now check for any error status which may have been recorded in the * journal by a prior ext4_error() or ext4_abort() */ j_errno = jbd2_journal_errno(journal); if (j_errno) { char nbuf[16]; errstr = ext4_decode_error(sb, j_errno, nbuf); ext4_warning(sb, "Filesystem error recorded " "from previous mount: %s", errstr); EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); j_errno = ext4_commit_super(sb); if (j_errno) return j_errno; ext4_warning(sb, "Marked fs in need of filesystem check."); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } return 0; } /* * Force the running and committing transactions to commit, * and wait on the commit. */ int ext4_force_commit(struct super_block *sb) { return ext4_journal_force_commit(EXT4_SB(sb)->s_journal); } static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; tid_t target; bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); ret = ext4_emergency_state(sb); if (unlikely(ret)) return ret; trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->rsv_conversion_wq); /* * Writeback quota in non-journalled quota case - journalled quota has * no dirty dquots */ dquot_writeback_dquots(sb, -1); /* * Data writeback is possible w/o journal transaction, so barrier must * being sent at the end of the function. But we can skip it if * transaction_commit will do it for us. */ if (sbi->s_journal) { target = jbd2_get_latest_transaction(sbi->s_journal); if (wait && sbi->s_journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(sbi->s_journal, target)) needs_barrier = true; if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) ret = jbd2_log_wait_commit(sbi->s_journal, target); } } else if (wait && test_opt(sb, BARRIER)) needs_barrier = true; if (needs_barrier) { int err; err = blkdev_issue_flush(sb->s_bdev); if (!ret) ret = err; } return ret; } /* * LVM calls this function before a (read-only) snapshot is created. This * gives us a chance to flush the journal completely and mark the fs clean. * * Note that only this function cannot bring a filesystem to be in a clean * state independently. It relies on upper layer to stop all data & metadata * modifications. */ static int ext4_freeze(struct super_block *sb) { int error = 0; journal_t *journal = EXT4_SB(sb)->s_journal; if (journal) { /* Now we set up the journal barrier. */ jbd2_journal_lock_updates(journal); /* * Don't clear the needs_recovery flag if we failed to * flush the journal. */ error = jbd2_journal_flush(journal, 0); if (error < 0) goto out; /* Journal blocked and flushed, clear needs_recovery flag. */ ext4_clear_feature_journal_needs_recovery(sb); if (ext4_orphan_file_empty(sb)) ext4_clear_feature_orphan_present(sb); } error = ext4_commit_super(sb); out: if (journal) /* we rely on upper layer to stop further updates */ jbd2_journal_unlock_updates(journal); return error; } /* * Called by LVM after the snapshot is done. We need to reset the RECOVER * flag here, even though the filesystem is not technically dirty yet. */ static int ext4_unfreeze(struct super_block *sb) { if (ext4_emergency_state(sb)) return 0; if (EXT4_SB(sb)->s_journal) { /* Reset the needs_recovery flag before the fs is unlocked. */ ext4_set_feature_journal_needs_recovery(sb); if (ext4_has_feature_orphan_file(sb)) ext4_set_feature_orphan_present(sb); } ext4_commit_super(sb); return 0; } /* * Structure to save mount options for ext4_remount's benefit */ struct ext4_mount_options { unsigned long s_mount_opt; unsigned long s_mount_opt2; kuid_t s_resuid; kgid_t s_resgid; unsigned long s_commit_interval; u32 s_min_batch_time, s_max_batch_time; #ifdef CONFIG_QUOTA int s_jquota_fmt; char *s_qf_names[EXT4_MAXQUOTAS]; #endif }; static int __ext4_remount(struct fs_context *fc, struct super_block *sb) { struct ext4_fs_context *ctx = fc->fs_private; struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long old_sb_flags; struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; char *to_free[EXT4_MAXQUOTAS]; #endif /* Store the original options */ old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; old_opts.s_mount_opt2 = sbi->s_mount_opt2; old_opts.s_resuid = sbi->s_resuid; old_opts.s_resgid = sbi->s_resgid; old_opts.s_commit_interval = sbi->s_commit_interval; old_opts.s_min_batch_time = sbi->s_min_batch_time; old_opts.s_max_batch_time = sbi->s_max_batch_time; #ifdef CONFIG_QUOTA old_opts.s_jquota_fmt = sbi->s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) if (sbi->s_qf_names[i]) { char *qf_name = get_qf_name(sb, sbi, i); old_opts.s_qf_names[i] = kstrdup(qf_name, GFP_KERNEL); if (!old_opts.s_qf_names[i]) { for (j = 0; j < i; j++) kfree(old_opts.s_qf_names[j]); return -ENOMEM; } } else old_opts.s_qf_names[i] = NULL; #endif if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO)) { if (sbi->s_journal && sbi->s_journal->j_task->io_context) ctx->journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; else ctx->journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO; } if ((ctx->spec & EXT4_SPEC_s_stripe) && ext4_is_stripe_incompatible(sb, ctx->s_stripe)) { ext4_msg(sb, KERN_WARNING, "stripe (%lu) is not aligned with cluster size (%u), " "stripe is disabled", ctx->s_stripe, sbi->s_cluster_ratio); ctx->s_stripe = 0; } /* * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause * two calls to ext4_should_dioread_nolock() to return inconsistent * values, triggering WARN_ON in ext4_add_complete_io(). we grab * here s_writepages_rwsem to avoid race between writepages ops and * remount. */ alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " "during remount not supported; ignoring"); sbi->s_mount_opt ^= EXT4_MOUNT_JOURNAL_CHECKSUM; } if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); err = -EINVAL; goto restore_opts; } if (test_opt(sb, DIOREAD_NOLOCK)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and dioread_nolock"); err = -EINVAL; goto restore_opts; } } else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) { if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit in data=ordered mode"); err = -EINVAL; goto restore_opts; } } if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) { ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount"); err = -EINVAL; goto restore_opts; } if ((old_opts.s_mount_opt & EXT4_MOUNT_DELALLOC) && !test_opt(sb, DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't disable delalloc during remount"); err = -EINVAL; goto restore_opts; } sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); es = sbi->s_es; if (sbi->s_journal) { ext4_init_journal_params(sb, sbi->s_journal); set_task_ioprio(sbi->s_journal->j_task, ctx->journal_ioprio); } /* Flush outstanding errors before changing fs state */ flush_work(&sbi->s_sb_upd_work); if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) { if (ext4_emergency_state(sb)) { err = -EROFS; goto restore_opts; } if (fc->sb_flags & SB_RDONLY) { err = sync_filesystem(sb); if (err < 0) goto restore_opts; err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; /* * First of all, the unconditional stuff we have to do * to disable replay of the journal when we next remount */ sb->s_flags |= SB_RDONLY; /* * OK, test if we are remounting a valid rw partition * readonly, and if so set the rdonly flag and then * mark the partition as valid again. */ if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) && (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); if (sbi->s_journal) { /* * We let remount-ro finish even if marking fs * as clean failed... */ ext4_mark_recovery_complete(sb, es); } } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || !ext4_feature_set_ok(sb, 0)) { err = -EROFS; goto restore_opts; } /* * Make sure the group descriptor checksums * are sane. If they aren't, refuse to remount r/w. */ for (g = 0; g < sbi->s_groups_count; g++) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, g, NULL); if (!ext4_group_desc_csum_verify(sb, g, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_remount: Checksum for group %u failed (%u!=%u)", g, le16_to_cpu(ext4_group_desc_csum(sb, g, gdp)), le16_to_cpu(gdp->bg_checksum)); err = -EFSBADCRC; goto restore_opts; } } /* * If we have an unprocessed orphan list hanging * around from a previously readonly bdev mount, * require a full umount/remount for now. */ if (es->s_last_orphan || !ext4_orphan_file_empty(sb)) { ext4_msg(sb, KERN_WARNING, "Couldn't " "remount RDWR because of unprocessed " "orphan inode list. Please " "umount/remount instead"); err = -EINVAL; goto restore_opts; } /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have * been changed by e2fsck since we originally mounted * the partition.) */ if (sbi->s_journal) { err = ext4_clear_journal_err(sb, es); if (err) goto restore_opts; } sbi->s_mount_state = (le16_to_cpu(es->s_state) & ~EXT4_FC_REPLAY); err = ext4_setup_super(sb, es, 0); if (err) goto restore_opts; sb->s_flags &= ~SB_RDONLY; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA enable_quota = 1; #endif } } /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will * succeed. */ if (test_opt(sb, BLOCK_VALIDITY) && !sbi->s_system_blks) { err = ext4_setup_system_zone(sb); if (err) goto restore_opts; } if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb); if (err) goto restore_opts; } #ifdef CONFIG_QUOTA if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); else if (ext4_has_feature_quota(sb)) { err = ext4_enable_quotas(sb); if (err) goto restore_opts; } } /* Release old quota file names */ for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); /* * Reinitialize lazy itable initialization thread based on * current settings */ if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) ext4_unregister_li_request(sb); else { ext4_group_t first_not_zeroed; first_not_zeroed = ext4_has_uninit_itable(sb); ext4_register_li_request(sb, first_not_zeroed); } if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); /* * Handle aborting the filesystem as the last thing during remount to * avoid obsure errors during remount when some option changes fail to * apply due to shutdown filesystem. */ if (test_opt2(sb, ABORT)) ext4_abort(sb, ESHUTDOWN, "Abort forced by user"); return 0; restore_opts: /* * If there was a failing r/w to ro transition, we may need to * re-enable quota */ if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; sbi->s_resuid = old_opts.s_resuid; sbi->s_resgid = old_opts.s_resgid; sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; ext4_writepages_up_write(sb, alloc_ctx); if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { to_free[i] = get_qf_name(sb, sbi, i); rcu_assign_pointer(sbi->s_qf_names[i], old_opts.s_qf_names[i]); } synchronize_rcu(); for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(to_free[i]); #endif if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); return err; } static int ext4_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int ret; bool old_ro = sb_rdonly(sb); fc->s_fs_info = EXT4_SB(sb); ret = ext4_check_opt_consistency(fc, sb); if (ret < 0) return ret; ret = __ext4_remount(fc, sb); if (ret < 0) return ret; ext4_msg(sb, KERN_INFO, "re-mounted %pU%s.", &sb->s_uuid, (old_ro != sb_rdonly(sb)) ? (sb_rdonly(sb) ? " ro" : " r/w") : ""); return 0; } #ifdef CONFIG_QUOTA static int ext4_statfs_project(struct super_block *sb, kprojid_t projid, struct kstatfs *buf) { struct kqid qid; struct dquot *dquot; u64 limit; u64 curblock; qid = make_kqid_projid(projid); dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); spin_lock(&dquot->dq_dqb_lock); limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); limit >>= sb->s_blocksize_bits; if (limit) { uint64_t remaining = 0; curblock = (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits; if (limit > curblock) remaining = limit - curblock; buf->f_blocks = min(buf->f_blocks, limit); buf->f_bfree = min(buf->f_bfree, remaining); buf->f_bavail = min(buf->f_bavail, remaining); } limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit, dquot->dq_dqb.dqb_ihardlimit); if (limit) { uint64_t remaining = 0; if (limit > dquot->dq_dqb.dqb_curinodes) remaining = limit - dquot->dq_dqb.dqb_curinodes; buf->f_files = min(buf->f_files, limit); buf->f_ffree = min(buf->f_ffree, remaining); } spin_unlock(&dquot->dq_dqb_lock); dqput(dquot); return 0; } #endif static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_fsblk_t overhead = 0, resv_blocks; s64 bfree; resv_blocks = EXT4_C2B(sbi, atomic64_read(&sbi->s_resv_clusters)); if (!test_opt(sb, MINIX_DF)) overhead = sbi->s_overhead; buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, overhead); bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); buf->f_bavail = buf->f_bfree - (ext4_r_blocks_count(es) + resv_blocks); if (buf->f_bfree < (ext4_r_blocks_count(es) + resv_blocks)) buf->f_bavail = 0; buf->f_files = le32_to_cpu(es->s_inodes_count); buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter); buf->f_namelen = EXT4_NAME_LEN; buf->f_fsid = uuid_to_fsid(es->s_uuid); #ifdef CONFIG_QUOTA if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) && sb_has_quota_limits_enabled(sb, PRJQUOTA)) ext4_statfs_project(sb, EXT4_I(dentry->d_inode)->i_projid, buf); #endif return 0; } #ifdef CONFIG_QUOTA /* * Helper functions so that transaction is started before we acquire dqio_sem * to keep correct lock ordering of transaction > dqio_sem */ static inline struct inode *dquot_to_inode(struct dquot *dquot) { return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type]; } static int ext4_write_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; struct inode *inode; inode = dquot_to_inode(dquot); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to commit dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_acquire_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_acquire(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to acquire dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static int ext4_release_dquot(struct dquot *dquot) { int ret, err; handle_t *handle; bool freeze_protected = false; /* * Trying to sb_start_intwrite() in a running transaction * can result in a deadlock. Further, running transactions * are already protected from freezing. */ if (!ext4_journal_current_handle()) { sb_start_intwrite(dquot->dq_sb); freeze_protected = true; } handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA, EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (IS_ERR(handle)) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); if (freeze_protected) sb_end_intwrite(dquot->dq_sb); return PTR_ERR(handle); } ret = dquot_release(dquot); if (ret < 0) ext4_error_err(dquot->dq_sb, -ret, "Failed to release dquot type %d", dquot->dq_id.type); err = ext4_journal_stop(handle); if (!ret) ret = err; if (freeze_protected) sb_end_intwrite(dquot->dq_sb); return ret; } static int ext4_mark_dquot_dirty(struct dquot *dquot) { struct super_block *sb = dquot->dq_sb; if (ext4_is_quota_journalled(sb)) { dquot_mark_dquot_dirty(dquot); return ext4_write_dquot(dquot); } else { return dquot_mark_dquot_dirty(dquot); } } static int ext4_write_info(struct super_block *sb, int type) { int ret, err; handle_t *handle; /* Data block + inode block */ handle = ext4_journal_start_sb(sb, EXT4_HT_QUOTA, 2); if (IS_ERR(handle)) return PTR_ERR(handle); ret = dquot_commit_info(sb, type); err = ext4_journal_stop(handle); if (!ret) ret = err; return ret; } static void lockdep_set_quota_inode(struct inode *inode, int subclass) { struct ext4_inode_info *ei = EXT4_I(inode); /* The first argument of lockdep_set_subclass has to be * *exactly* the same as the argument to init_rwsem() --- in * this case, in init_once() --- or lockdep gets unhappy * because the name of the lock is set using the * stringification of the argument to init_rwsem(). */ (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ lockdep_set_subclass(&ei->i_data_sem, subclass); } /* * Standard function to be called on quota_on */ static int ext4_quota_on(struct super_block *sb, int type, int format_id, const struct path *path) { int err; if (!test_opt(sb, QUOTA)) return -EINVAL; /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) return -EXDEV; /* Quota already enabled for this file? */ if (IS_NOQUOTA(d_inode(path->dentry))) return -EBUSY; /* Journaling quota? */ if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ if (path->dentry->d_parent != sb->s_root) ext4_msg(sb, KERN_WARNING, "Quota file not on filesystem root. " "Journaled quota will not work"); sb_dqopt(sb)->flags |= DQUOT_NOLIST_DIRTY; } else { /* * Clear the flag just in case mount options changed since * last time. */ sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY; } lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA); err = dquot_quota_on(sb, type, format_id, path); if (!err) { struct inode *inode = d_inode(path->dentry); handle_t *handle; /* * Set inode flags to prevent userspace from messing with quota * files. If this fails, we return success anyway since quotas * are already enabled and this is not a hard failure. */ inode_lock(inode); handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) goto unlock_inode; EXT4_I(inode)->i_flags |= EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL; inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, S_NOATIME | S_IMMUTABLE); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); unlock_inode: inode_unlock(inode); if (err) dquot_quota_off(sb, type); } if (err) lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_NORMAL); return err; } static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum) { switch (type) { case USRQUOTA: return qf_inum == EXT4_USR_QUOTA_INO; case GRPQUOTA: return qf_inum == EXT4_GRP_QUOTA_INO; case PRJQUOTA: return qf_inum >= EXT4_GOOD_OLD_FIRST_INO; default: BUG(); } } static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { int err; struct inode *qf_inode; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; BUG_ON(!ext4_has_feature_quota(sb)); if (!qf_inums[type]) return -EPERM; if (!ext4_check_quota_inum(type, qf_inums[type])) { ext4_error(sb, "Bad quota inum: %lu, type: %d", qf_inums[type], type); return -EUCLEAN; } qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { ext4_error(sb, "Bad quota inode: %lu, type: %d", qf_inums[type], type); return PTR_ERR(qf_inode); } /* Don't account quota for quota files to avoid recursion */ qf_inode->i_flags |= S_NOQUOTA; lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); err = dquot_load_quota_inode(qf_inode, type, format_id, flags); if (err) lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); iput(qf_inode); return err; } /* Enable usage tracking for all quota types. */ int ext4_enable_quotas(struct super_block *sb) { int type, err = 0; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; bool quota_mopt[EXT4_MAXQUOTAS] = { test_opt(sb, USRQUOTA), test_opt(sb, GRPQUOTA), test_opt(sb, PRJQUOTA), }; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; for (type = 0; type < EXT4_MAXQUOTAS; type++) { if (qf_inums[type]) { err = ext4_quota_enable(sb, type, QFMT_VFS_V1, DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { ext4_warning(sb, "Failed to enable quota tracking " "(type=%d, err=%d, ino=%lu). " "Please run e2fsck to fix.", type, err, qf_inums[type]); ext4_quotas_off(sb, type); return err; } } } return 0; } static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; handle_t *handle; int err; /* Force all delayed allocation blocks to be allocated. * Caller already holds s_umount sem */ if (test_opt(sb, DELALLOC)) sync_filesystem(sb); if (!inode || !igrab(inode)) goto out; err = dquot_quota_off(sb, type); if (err || ext4_has_feature_quota(sb)) goto out_put; /* * When the filesystem was remounted read-only first, we cannot cleanup * inode flags here. Bad luck but people should be using QUOTA feature * these days anyway. */ if (sb_rdonly(sb)) goto out_put; inode_lock(inode); /* * Update modification times of quota files when userspace can * start looking at them. If we fail, we return success anyway since * this is not a hard failure and quotas are already disabled. */ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out_unlock; } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: inode_unlock(inode); out_put: lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL); iput(inode); return err; out: return dquot_quota_off(sb, type); } /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) * we don't have to be afraid of races */ static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int offset = off & (sb->s_blocksize - 1); int tocopy; size_t toread; struct buffer_head *bh; loff_t i_size = i_size_read(inode); if (off > i_size) return 0; if (off+len > i_size) len = i_size-off; toread = len; while (toread > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread); bh = ext4_bread(NULL, inode, blk, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) /* A hole? */ memset(data, 0, tocopy); else memcpy(data, bh->b_data+offset, tocopy); brelse(bh); offset = 0; toread -= tocopy; data += tocopy; blk++; } return len; } /* Write to quotafile (we know the transaction is already started and has * enough credits) */ static ssize_t ext4_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off) { struct inode *inode = sb_dqopt(sb)->files[type]; ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb); int err = 0, err2 = 0, offset = off & (sb->s_blocksize - 1); int retries = 0; struct buffer_head *bh; handle_t *handle = journal_current_handle(); if (!handle) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because transaction is not started", (unsigned long long)off, (unsigned long long)len); return -EIO; } /* * Since we account only one data block in transaction credits, * then it is impossible to cross a block boundary. */ if (sb->s_blocksize - offset < len) { ext4_msg(sb, KERN_WARNING, "Quota write (off=%llu, len=%llu)" " cancelled because not block aligned", (unsigned long long)off, (unsigned long long)len); return -EIO; } do { bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) goto out; BUFFER_TRACE(bh, "get write access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) { brelse(bh); return err; } lock_buffer(bh); memcpy(bh->b_data+offset, data, len); flush_dcache_folio(bh->b_folio); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); out: if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; err2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(err2 && !err)) err = err2; } return err ? err : len; } #endif #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static inline void register_as_ext2(void) { int err = register_filesystem(&ext2_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext2 (%d)\n", err); } static inline void unregister_as_ext2(void) { unregister_filesystem(&ext2_fs_type); } static inline int ext2_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext2_incompat_features(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext2_ro_compat_features(sb)) return 0; return 1; } #else static inline void register_as_ext2(void) { } static inline void unregister_as_ext2(void) { } static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; } #endif static inline void register_as_ext3(void) { int err = register_filesystem(&ext3_fs_type); if (err) printk(KERN_WARNING "EXT4-fs: Unable to register as ext3 (%d)\n", err); } static inline void unregister_as_ext3(void) { unregister_filesystem(&ext3_fs_type); } static inline int ext3_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext3_incompat_features(sb)) return 0; if (!ext4_has_feature_journal(sb)) return 0; if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext3_ro_compat_features(sb)) return 0; return 1; } static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct file *bdev_file = sbi ? sbi->s_journal_bdev_file : NULL; kill_block_super(sb); if (bdev_file) bdev_fput(bdev_file); } static struct file_system_type ext4_fs_type = { .owner = THIS_MODULE, .name = "ext4", .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME | FS_LBS, }; MODULE_ALIAS_FS("ext4"); static int __init ext4_init_fs(void) { int err; ratelimit_state_init(&ext4_mount_msg_ratelimit, 30 * HZ, 64); ext4_li_info = NULL; /* Build-time check for flags consistency */ ext4_check_flag_values(); err = ext4_init_es(); if (err) return err; err = ext4_init_pending(); if (err) goto out7; err = ext4_init_post_read_processing(); if (err) goto out6; err = ext4_init_pageio(); if (err) goto out5; err = ext4_init_system_zone(); if (err) goto out4; err = ext4_init_sysfs(); if (err) goto out3; err = ext4_init_mballoc(); if (err) goto out2; err = init_inodecache(); if (err) goto out1; err = ext4_fc_init_dentry_cache(); if (err) goto out05; register_as_ext3(); register_as_ext2(); err = register_filesystem(&ext4_fs_type); if (err) goto out; return 0; out: unregister_as_ext2(); unregister_as_ext3(); ext4_fc_destroy_dentry_cache(); out05: destroy_inodecache(); out1: ext4_exit_mballoc(); out2: ext4_exit_sysfs(); out3: ext4_exit_system_zone(); out4: ext4_exit_pageio(); out5: ext4_exit_post_read_processing(); out6: ext4_exit_pending(); out7: ext4_exit_es(); return err; } static void __exit ext4_exit_fs(void) { ext4_destroy_lazyinit_thread(); unregister_as_ext2(); unregister_as_ext3(); unregister_filesystem(&ext4_fs_type); ext4_fc_destroy_dentry_cache(); destroy_inodecache(); ext4_exit_mballoc(); ext4_exit_sysfs(); ext4_exit_system_zone(); ext4_exit_pageio(); ext4_exit_post_read_processing(); ext4_exit_es(); ext4_exit_pending(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017-2018 HUAWEI, Inc. * https://www.huawei.com/ * Copyright (C) 2021, Alibaba Cloud */ #include "internal.h" #include <linux/filelock.h> #include <linux/sched/mm.h> #include <trace/events/erofs.h> void erofs_unmap_metabuf(struct erofs_buf *buf) { if (!buf->base) return; kunmap_local(buf->base); buf->base = NULL; } void erofs_put_metabuf(struct erofs_buf *buf) { if (!buf->page) return; erofs_unmap_metabuf(buf); folio_put(page_folio(buf->page)); buf->page = NULL; } void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, bool need_kmap) { pgoff_t index = (buf->off + offset) >> PAGE_SHIFT; struct folio *folio = NULL; loff_t fpos; int err; /* * Metadata access for file-backed mounts reuses page cache of backing * fs inodes (only folio data will be needed) to prevent double caching. * However, the data access range must be verified here in advance. */ if (buf->file) { fpos = (loff_t)index << PAGE_SHIFT; err = rw_verify_area(READ, buf->file, &fpos, PAGE_SIZE); if (err < 0) return ERR_PTR(err); } if (buf->page) { folio = page_folio(buf->page); if (folio_file_page(folio, index) != buf->page) erofs_unmap_metabuf(buf); } if (!folio || !folio_contains(folio, index)) { erofs_put_metabuf(buf); folio = read_mapping_folio(buf->mapping, index, buf->file); if (IS_ERR(folio)) return folio; } buf->page = folio_file_page(folio, index); if (!need_kmap) return NULL; if (!buf->base) buf->base = kmap_local_page(buf->page); return buf->base + (offset & ~PAGE_MASK); } int erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb, bool in_metabox) { struct erofs_sb_info *sbi = EROFS_SB(sb); buf->file = NULL; if (in_metabox) { if (unlikely(!sbi->metabox_inode)) return -EFSCORRUPTED; buf->mapping = sbi->metabox_inode->i_mapping; return 0; } buf->off = sbi->dif0.fsoff; if (erofs_is_fileio_mode(sbi)) { buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; return 0; } void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, erofs_off_t offset, bool in_metabox) { int err; err = erofs_init_metabuf(buf, sb, in_metabox); if (err) return ERR_PTR(err); return erofs_bread(buf, offset, true); } int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map) { struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct super_block *sb = inode->i_sb; unsigned int unit, blksz = sb->s_blocksize; struct erofs_inode *vi = EROFS_I(inode); struct erofs_inode_chunk_index *idx; erofs_blk_t startblk, addrmask; bool tailpacking; erofs_off_t pos; u64 chunknr; int err = 0; trace_erofs_map_blocks_enter(inode, map, 0); map->m_deviceid = 0; map->m_flags = 0; if (map->m_la >= inode->i_size) goto out; if (vi->datalayout != EROFS_INODE_CHUNK_BASED) { tailpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE); if (!tailpacking && vi->startblk == EROFS_NULL_ADDR) goto out; pos = erofs_pos(sb, erofs_iblks(inode) - tailpacking); map->m_flags = EROFS_MAP_MAPPED; if (map->m_la < pos) { map->m_pa = erofs_pos(sb, vi->startblk) + map->m_la; map->m_llen = pos - map->m_la; } else { map->m_pa = erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize + erofs_blkoff(sb, map->m_la); map->m_llen = inode->i_size - map->m_la; map->m_flags |= EROFS_MAP_META; } goto out; } if (vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES) unit = sizeof(*idx); /* chunk index */ else unit = EROFS_BLOCK_MAP_ENTRY_SIZE; /* block map */ chunknr = map->m_la >> vi->chunkbits; pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, unit) + unit * chunknr; idx = erofs_read_metabuf(&buf, sb, pos, erofs_inode_in_metabox(inode)); if (IS_ERR(idx)) { err = PTR_ERR(idx); goto out; } map->m_la = chunknr << vi->chunkbits; map->m_llen = min_t(erofs_off_t, 1UL << vi->chunkbits, round_up(inode->i_size - map->m_la, blksz)); if (vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES) { addrmask = (vi->chunkformat & EROFS_CHUNK_FORMAT_48BIT) ? BIT_ULL(48) - 1 : BIT_ULL(32) - 1; startblk = (((u64)le16_to_cpu(idx->startblk_hi) << 32) | le32_to_cpu(idx->startblk_lo)) & addrmask; if ((startblk ^ EROFS_NULL_ADDR) & addrmask) { map->m_deviceid = le16_to_cpu(idx->device_id) & EROFS_SB(sb)->device_id_mask; map->m_pa = erofs_pos(sb, startblk); map->m_flags = EROFS_MAP_MAPPED; } } else { startblk = le32_to_cpu(*(__le32 *)idx); if (startblk != (u32)EROFS_NULL_ADDR) { map->m_pa = erofs_pos(sb, startblk); map->m_flags = EROFS_MAP_MAPPED; } } erofs_put_metabuf(&buf); out: if (!err) { map->m_plen = map->m_llen; /* inline data should be located in the same meta block */ if ((map->m_flags & EROFS_MAP_META) && erofs_blkoff(sb, map->m_pa) + map->m_plen > blksz) { erofs_err(sb, "inline data across blocks @ nid %llu", vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } } trace_erofs_map_blocks_exit(inode, map, 0, err); return err; } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, struct super_block *sb, struct erofs_device_info *dif) { map->m_sb = sb; map->m_dif = dif; map->m_bdev = NULL; if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) { struct erofs_dev_context *devs = EROFS_SB(sb)->devs; struct erofs_device_info *dif; erofs_off_t startoff; int id; erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); if (!dif) { up_read(&devs->rwsem); return -ENODEV; } if (devs->flatdev) { map->m_pa += erofs_pos(sb, dif->uniaddr); up_read(&devs->rwsem); return 0; } erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); idr_for_each_entry(&devs->tree, dif, id) { if (!dif->uniaddr) continue; startoff = erofs_pos(sb, dif->uniaddr); if (map->m_pa >= startoff && map->m_pa < startoff + erofs_pos(sb, dif->blocks)) { map->m_pa -= startoff; erofs_fill_from_devinfo(map, sb, dif); break; } } up_read(&devs->rwsem); } return 0; } /* * bit 30: I/O error occurred on this folio * bit 29: CPU has dirty data in D-cache (needs aliasing handling); * bit 0 - 29: remaining parts to complete this folio */ #define EROFS_ONLINEFOLIO_EIO 30 #define EROFS_ONLINEFOLIO_DIRTY 29 void erofs_onlinefolio_init(struct folio *folio) { union { atomic_t o; void *v; } u = { .o = ATOMIC_INIT(1) }; folio->private = u.v; /* valid only if file-backed folio is locked */ } void erofs_onlinefolio_split(struct folio *folio) { atomic_inc((atomic_t *)&folio->private); } void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty) { int orig, v; do { orig = atomic_read((atomic_t *)&folio->private); DBG_BUGON(orig <= 0); v = dirty << EROFS_ONLINEFOLIO_DIRTY; v |= (orig - 1) | (!!err << EROFS_ONLINEFOLIO_EIO); } while (atomic_cmpxchg((atomic_t *)&folio->private, orig, v) != orig); if (v & (BIT(EROFS_ONLINEFOLIO_DIRTY) - 1)) return; folio->private = 0; if (v & BIT(EROFS_ONLINEFOLIO_DIRTY)) flush_dcache_folio(folio); folio_end_read(folio, !(v & BIT(EROFS_ONLINEFOLIO_EIO))); } struct erofs_iomap_iter_ctx { struct page *page; void *base; struct inode *realinode; }; static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap); struct erofs_iomap_iter_ctx *ctx = iter->private; struct inode *realinode = ctx ? ctx->realinode : inode; struct super_block *sb = realinode->i_sb; struct erofs_map_blocks map; struct erofs_map_dev mdev; int ret; map.m_la = offset; map.m_llen = length; ret = erofs_map_blocks(realinode, &map); if (ret < 0) return ret; iomap->offset = map.m_la; iomap->length = map.m_llen; iomap->flags = 0; iomap->addr = IOMAP_NULL_ADDR; if (!(map.m_flags & EROFS_MAP_MAPPED)) { iomap->type = IOMAP_HOLE; return 0; } if (!(map.m_flags & EROFS_MAP_META) || !erofs_inode_in_metabox(realinode)) { mdev = (struct erofs_map_dev) { .m_deviceid = map.m_deviceid, .m_pa = map.m_pa, }; ret = erofs_map_dev(sb, &mdev); if (ret) return ret; if (flags & IOMAP_DAX) iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->addr = mdev.m_dif->fsoff + mdev.m_pa; if (flags & IOMAP_DAX) iomap->addr += mdev.m_dif->dax_part_off; } if (map.m_flags & EROFS_MAP_META) { iomap->type = IOMAP_INLINE; /* read context should read the inlined data */ if (ctx) { struct erofs_buf buf = __EROFS_BUF_INITIALIZER; void *ptr; ptr = erofs_read_metabuf(&buf, sb, map.m_pa, erofs_inode_in_metabox(realinode)); if (IS_ERR(ptr)) return PTR_ERR(ptr); iomap->inline_data = ptr; ctx->page = buf.page; ctx->base = buf.base; } } else { iomap->type = IOMAP_MAPPED; } return 0; } static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned int flags, struct iomap *iomap) { struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap); struct erofs_iomap_iter_ctx *ctx = iter->private; if (ctx && ctx->base) { struct erofs_buf buf = { .page = ctx->page, .base = ctx->base, }; DBG_BUGON(iomap->type != IOMAP_INLINE); erofs_put_metabuf(&buf); ctx->base = NULL; } return written; } static const struct iomap_ops erofs_iomap_ops = { .iomap_begin = erofs_iomap_begin, .iomap_end = erofs_iomap_end, }; int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) { if (!IS_ENABLED(CONFIG_EROFS_FS_ZIP)) return -EOPNOTSUPP; return iomap_fiemap(inode, fieinfo, start, len, &z_erofs_iomap_report_ops); } return iomap_fiemap(inode, fieinfo, start, len, &erofs_iomap_ops); } /* * since we dont have write or truncate flows, so no inode * locking needs to be held at the moment. */ static int erofs_read_folio(struct file *file, struct folio *folio) { struct iomap_read_folio_ctx read_ctx = { .ops = &iomap_bio_read_ops, .cur_folio = folio, }; bool need_iput; struct erofs_iomap_iter_ctx iter_ctx = { .realinode = erofs_real_inode(folio_inode(folio), &need_iput), }; trace_erofs_read_folio(iter_ctx.realinode, folio, true); iomap_read_folio(&erofs_iomap_ops, &read_ctx, &iter_ctx); if (need_iput) iput(iter_ctx.realinode); return 0; } static void erofs_readahead(struct readahead_control *rac) { struct iomap_read_folio_ctx read_ctx = { .ops = &iomap_bio_read_ops, .rac = rac, }; bool need_iput; struct erofs_iomap_iter_ctx iter_ctx = { .realinode = erofs_real_inode(rac->mapping->host, &need_iput), }; trace_erofs_readahead(iter_ctx.realinode, readahead_index(rac), readahead_count(rac), true); iomap_readahead(&erofs_iomap_ops, &read_ctx, &iter_ctx); if (need_iput) iput(iter_ctx.realinode); } static sector_t erofs_bmap(struct address_space *mapping, sector_t block) { return iomap_bmap(mapping, block, &erofs_iomap_ops); } static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); /* no need taking (shared) inode lock since it's a ro filesystem */ if (!iov_iter_count(to)) return 0; if (IS_ENABLED(CONFIG_FS_DAX) && IS_DAX(inode)) return dax_iomap_rw(iocb, to, &erofs_iomap_ops); if ((iocb->ki_flags & IOCB_DIRECT) && inode->i_sb->s_bdev) { struct erofs_iomap_iter_ctx iter_ctx = { .realinode = inode, }; return iomap_dio_rw(iocb, to, &erofs_iomap_ops, NULL, 0, &iter_ctx, 0); } return filemap_read(iocb, to, 0); } /* for uncompressed (aligned) files and raw access for other files */ const struct address_space_operations erofs_aops = { .read_folio = erofs_read_folio, .readahead = erofs_readahead, .bmap = erofs_bmap, .direct_IO = noop_direct_IO, .release_folio = iomap_release_folio, .invalidate_folio = iomap_invalidate_folio, }; #ifdef CONFIG_FS_DAX static vm_fault_t erofs_dax_huge_fault(struct vm_fault *vmf, unsigned int order) { return dax_iomap_fault(vmf, order, NULL, NULL, &erofs_iomap_ops); } static vm_fault_t erofs_dax_fault(struct vm_fault *vmf) { return erofs_dax_huge_fault(vmf, 0); } static const struct vm_operations_struct erofs_dax_vm_ops = { .fault = erofs_dax_fault, .huge_fault = erofs_dax_huge_fault, }; static int erofs_file_mmap_prepare(struct vm_area_desc *desc) { if (!IS_DAX(file_inode(desc->file))) return generic_file_readonly_mmap_prepare(desc); if (vma_desc_test_all(desc, VMA_SHARED_BIT, VMA_MAYWRITE_BIT)) return -EINVAL; desc->vm_ops = &erofs_dax_vm_ops; vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT); return 0; } #else #define erofs_file_mmap_prepare generic_file_readonly_mmap_prepare #endif static loff_t erofs_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; const struct iomap_ops *ops = &erofs_iomap_ops; if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) { if (!IS_ENABLED(CONFIG_EROFS_FS_ZIP)) return generic_file_llseek(file, offset, whence); ops = &z_erofs_iomap_report_ops; } if (whence == SEEK_HOLE) offset = iomap_seek_hole(inode, offset, ops); else if (whence == SEEK_DATA) offset = iomap_seek_data(inode, offset, ops); else return generic_file_llseek(file, offset, whence); if (offset < 0) return offset; return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } const struct file_operations erofs_file_fops = { .llseek = erofs_file_llseek, .read_iter = erofs_file_read_iter, .unlocked_ioctl = erofs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = erofs_compat_ioctl, #endif .mmap_prepare = erofs_file_mmap_prepare, .get_unmapped_area = thp_get_unmapped_area, .splice_read = filemap_splice_read, .setlease = generic_setlease, }; |
| 4039 1288 2263 2263 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2012 Novell Inc. * Copyright (c) 2012-2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> * Copyright (c) 2012-2019 Linux Foundation * * Core driver model functions and structures that should not be * shared outside of the drivers/base/ directory. * */ #include <linux/notifier.h> /** * struct subsys_private - structure to hold the private to the driver core * portions of the bus_type/class structure. * @subsys: the struct kset that defines this subsystem * @devices_kset: the subsystem's 'devices' directory * @interfaces: list of subsystem interfaces associated * @mutex: protect the devices, and interfaces lists. * @drivers_kset: the list of drivers associated * @klist_devices: the klist to iterate over the @devices_kset * @klist_drivers: the klist to iterate over the @drivers_kset * @bus_notifier: the bus notifier list for anything that cares about things * on this bus. * @drivers_autoprobe: gate whether new devices are automatically attached to * registered drivers, or new drivers automatically attach * to existing devices. * @bus: pointer back to the struct bus_type that this structure is associated * with. * @dev_root: Default device to use as the parent. * @glue_dirs: "glue" directory to put in-between the parent device to * avoid namespace conflicts * @class: pointer back to the struct class that this structure is associated * with. * @lock_key: Lock class key for use by the lock validator * * This structure is the one that is the actual kobject allowing struct * bus_type/class to be statically allocated safely. Nothing outside of the * driver core should ever touch these fields. */ struct subsys_private { struct kset subsys; struct kset *devices_kset; struct list_head interfaces; struct mutex mutex; struct kset *drivers_kset; struct klist klist_devices; struct klist klist_drivers; struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; const struct bus_type *bus; struct device *dev_root; struct kset glue_dirs; const struct class *class; struct lock_class_key lock_key; }; #define to_subsys_private(obj) container_of_const(obj, struct subsys_private, subsys.kobj) static inline struct subsys_private *subsys_get(struct subsys_private *sp) { if (sp) kset_get(&sp->subsys); return sp; } static inline void subsys_put(struct subsys_private *sp) { if (sp) kset_put(&sp->subsys); } struct subsys_private *bus_to_subsys(const struct bus_type *bus); struct subsys_private *class_to_subsys(const struct class *class); struct driver_private { struct kobject kobj; struct klist klist_devices; struct klist_node knode_bus; struct module_kobject *mkobj; struct device_driver *driver; }; #define to_driver(obj) container_of(obj, struct driver_private, kobj) /** * struct device_private - structure to hold the private to the driver core * portions of the device structure. * @klist_children: klist containing all children of this device * @knode_parent: node in sibling list * @knode_driver: node in driver list * @knode_bus: node in bus list * @knode_class: node in class list * @deferred_probe: entry in deferred_probe_list which is used to retry the * binding of drivers which were unable to get all the * resources needed by the device; typically because it depends * on another driver getting probed first. * @async_driver: pointer to device driver awaiting probe via async_probe * @deferred_probe_reason: capture the -EPROBE_DEFER message emitted with * dev_err_probe() for later retrieval via debugfs * @device: pointer back to the struct device that this structure is * associated with. * @dead: This device is currently either in the process of or has been * removed from the system. Any asynchronous events scheduled for this * device should exit without taking any action. * * Nothing outside of the driver core should ever touch these fields. */ struct device_private { struct klist klist_children; struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; struct klist_node knode_class; struct list_head deferred_probe; const struct device_driver *async_driver; char *deferred_probe_reason; struct device *device; u8 dead:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) #define to_device_private_driver(obj) \ container_of(obj, struct device_private, knode_driver) #define to_device_private_bus(obj) \ container_of(obj, struct device_private, knode_bus) #define to_device_private_class(obj) \ container_of(obj, struct device_private, knode_class) /* initialisation functions */ int devices_init(void); int buses_init(void); int classes_init(void); int firmware_init(void); #ifdef CONFIG_SYS_HYPERVISOR int hypervisor_init(void); #else static inline int hypervisor_init(void) { return 0; } #endif int platform_bus_init(void); int faux_bus_init(void); void cpu_dev_init(void); void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS void auxiliary_bus_init(void); #else static inline void auxiliary_bus_init(void) { } #endif struct kobject *virtual_device_parent(void); int bus_add_device(struct device *dev); void bus_probe_device(struct device *dev); void bus_remove_device(struct device *dev); void bus_notify(struct device *dev, enum bus_notifier_event value); bool bus_is_registered(const struct bus_type *bus); int bus_add_driver(struct device_driver *drv); void bus_remove_driver(struct device_driver *drv); void device_release_driver_internal(struct device *dev, const struct device_driver *drv, struct device *parent); void driver_detach(const struct device_driver *drv); void driver_deferred_probe_del(struct device *dev); void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf); static inline int driver_match_device(const struct device_driver *drv, struct device *dev) { return drv->bus->match ? drv->bus->match(dev, drv) : 1; } static inline bool dev_has_sync_state(struct device *dev) { struct device_driver *drv; if (!dev) return false; drv = READ_ONCE(dev->driver); if (drv && drv->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline void dev_sync_state(struct device *dev) { if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); } int driver_add_groups(const struct device_driver *drv, const struct attribute_group *const *groups); void driver_remove_groups(const struct device_driver *drv, const struct attribute_group *const *groups); void device_driver_detach(struct device *dev); static inline void device_set_driver(struct device *dev, const struct device_driver *drv) { /* * Majority (all?) read accesses to dev->driver happens either * while holding device lock or in bus/driver code that is only * invoked when the device is bound to a driver and there is no * concern of the pointer being changed while it is being read. * However when reading device's uevent file we read driver pointer * without taking device lock (so we do not block there for * arbitrary amount of time). We use WRITE_ONCE() here to prevent * tearing so that READ_ONCE() can safely be used in uevent code. */ // FIXME - this cast should not be needed "soon" WRITE_ONCE(dev->driver, (struct device_driver *)drv); } struct devres_node; typedef void (*dr_node_release_t)(struct device *dev, struct devres_node *node); typedef void (*dr_node_free_t)(struct devres_node *node); struct devres_node { struct list_head entry; dr_node_release_t release; dr_node_free_t free_node; const char *name; size_t size; }; void devres_node_init(struct devres_node *node, dr_node_release_t release, dr_node_free_t free_node); void devres_node_add(struct device *dev, struct devres_node *node); bool devres_node_remove(struct device *dev, struct devres_node *node); void devres_set_node_dbginfo(struct devres_node *node, const char *name, size_t size); void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); int devres_release_all(struct device *dev); void device_block_probing(void); void device_unblock_probing(void); void deferred_probe_extend_timeout(void); void driver_deferred_probe_trigger(void); const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); /* /sys/devices directory */ extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) int module_add_driver(struct module *mod, const struct device_driver *drv); void module_remove_driver(const struct device_driver *drv); #else static inline int module_add_driver(struct module *mod, struct device_driver *drv) { return 0; } static inline void module_remove_driver(struct device_driver *drv) { } #endif #ifdef CONFIG_DEVTMPFS int devtmpfs_init(void); #else static inline int devtmpfs_init(void) { return 0; } #endif #ifdef CONFIG_BLOCK extern const struct class block_class; static inline bool is_blockdev(struct device *dev) { return dev->class == &block_class; } #else static inline bool is_blockdev(struct device *dev) { return false; } #endif /* Device links support */ int device_links_read_lock(void); void device_links_read_unlock(int idx); int device_links_read_lock_held(void); int device_links_check_suppliers(struct device *dev); void device_links_force_bind(struct device *dev); void device_links_driver_bound(struct device *dev); void device_links_driver_cleanup(struct device *dev); void device_links_no_driver(struct device *dev); bool device_links_busy(struct device *dev); void device_links_unbind_consumers(struct device *dev); bool device_link_flag_is_sync_state_only(u32 flags); void fw_devlink_drivers_done(void); void fw_devlink_probing_done(void); #define dev_for_each_link_to_supplier(__link, __dev) \ list_for_each_entry_srcu(__link, &(__dev)->links.suppliers, c_node, \ device_links_read_lock_held()) #define dev_for_each_link_to_consumer(__link, __dev) \ list_for_each_entry_srcu(__link, &(__dev)->links.consumers, s_node, \ device_links_read_lock_held()) /* device pm support */ void device_pm_move_to_tail(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_create_node(struct device *dev); int devtmpfs_delete_node(struct device *dev); #else static inline int devtmpfs_create_node(struct device *dev) { return 0; } static inline int devtmpfs_delete_node(struct device *dev) { return 0; } #endif void software_node_init(void); void software_node_notify(struct device *dev); void software_node_notify_remove(struct device *dev); #ifdef CONFIG_PINCTRL int pinctrl_bind_pins(struct device *dev); #else static inline int pinctrl_bind_pins(struct device *dev) { return 0; } #endif /* CONFIG_PINCTRL */ |
| 23 23 41 41 6 6 6 6 4 6 6 6 6 27 25 26 1 25 493 493 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); write_seqlock(&fs->seq); old_root = fs->root; fs->root = *path; write_sequnlock(&fs->seq); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); write_seqlock(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_sequnlock(&fs->seq); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); for_each_process_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; write_seqlock(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); while (hits--) { count++; path_get(new_root); } write_sequnlock(&fs->seq); } task_unlock(p); } read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); read_seqlock_excl(&fs->seq); tsk->fs = NULL; kill = !--fs->users; read_sequnlock_excl(&fs->seq); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; seqlock_init(&fs->seq); fs->umask = old->umask; read_seqlock_excl(&old->seq); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); read_sequnlock_excl(&old->seq); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); read_seqlock_excl(&fs->seq); kill = !--fs->users; current->fs = new_fs; read_sequnlock_excl(&fs->seq); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .seq = __SEQLOCK_UNLOCKED(init_fs.seq), .umask = 0022, }; |
| 11 4 11 18 3 13 2 3 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IP Payload Compression Protocol (IPComp) for IPv6 - RFC3173 * * Copyright (C)2003 USAGI/WIDE Project * * Author Mitsuru KANDA <mk@linux-ipv6.org> */ /* * [Memo] * * Outbound: * The compression of IP datagram MUST be done before AH/ESP processing, * fragmentation, and the addition of Hop-by-Hop/Routing header. * * Inbound: * The decompression of IP datagram MUST be done after the reassembly, * AH/ESP processing. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/module.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ipcomp.h> #include <linux/crypto.h> #include <linux/err.h> #include <linux/pfkeyv2.h> #include <linux/random.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> #include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/mutex.h> static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); __be32 spi; const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; struct ip_comp_hdr *ipcomph = (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; spi = htonl(ntohs(ipcomph->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); if (!x) return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); struct xfrm_state *t = NULL; t = xfrm_state_alloc(net); if (!t) goto out; lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPV6; t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr); if (!t->id.spi) goto error; memcpy(t->id.daddr.a6, x->id.daddr.a6, sizeof(struct in6_addr)); memcpy(&t->sel, &x->sel, sizeof(t->sel)); t->props.family = AF_INET6; t->props.mode = x->props.mode; memcpy(t->props.saddr.a6, x->props.saddr.a6, sizeof(struct in6_addr)); memcpy(&t->mark, &x->mark, sizeof(t->mark)); t->if_id = x->if_id; if (xfrm_init_state(t)) goto error; atomic_set(&t->tunnel_users, 1); out: return t; error: t->km.state = XFRM_STATE_DEAD; xfrm_state_put(t); t = NULL; goto out; } static int ipcomp6_tunnel_attach(struct xfrm_state *x) { struct net *net = xs_net(x); int err = 0; struct xfrm_state *t = NULL; __be32 spi; u32 mark = x->mark.m & x->mark.v; spi = xfrm6_tunnel_spi_lookup(net, (xfrm_address_t *)&x->props.saddr); if (spi) t = xfrm_state_lookup(net, mark, (xfrm_address_t *)&x->id.daddr, spi, IPPROTO_IPV6, AF_INET6); if (!t) { t = ipcomp6_tunnel_create(x); if (!t) { err = -EINVAL; goto out; } xfrm_state_insert(t); xfrm_state_hold(t); } x->tunnel = t; atomic_inc(&t->tunnel_users); out: return err; } static int ipcomp6_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { int err = -EINVAL; x->props.header_len = 0; switch (x->props.mode) { case XFRM_MODE_TRANSPORT: break; case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); break; default: NL_SET_ERR_MSG(extack, "Unsupported XFRM mode for IPcomp"); goto out; } err = ipcomp_init_state(x, extack); if (err) goto out; if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp6_tunnel_attach(x); if (err) { NL_SET_ERR_MSG(extack, "Kernel error: failed to initialize the associated state"); goto out; } } err = 0; out: return err; } static int ipcomp6_rcv_cb(struct sk_buff *skb, int err) { return 0; } static const struct xfrm_type ipcomp6_type = { .owner = THIS_MODULE, .proto = IPPROTO_COMP, .init_state = ipcomp6_init_state, .destructor = ipcomp_destroy, .input = ipcomp_input, .output = ipcomp_output, }; static struct xfrm6_protocol ipcomp6_protocol = { .handler = xfrm6_rcv, .input_handler = xfrm_input, .cb_handler = ipcomp6_rcv_cb, .err_handler = ipcomp6_err, .priority = 0, }; static int __init ipcomp6_init(void) { if (xfrm_register_type(&ipcomp6_type, AF_INET6) < 0) { pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (xfrm6_protocol_register(&ipcomp6_protocol, IPPROTO_COMP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp6_type, AF_INET6); return -EAGAIN; } return 0; } static void __exit ipcomp6_fini(void) { if (xfrm6_protocol_deregister(&ipcomp6_protocol, IPPROTO_COMP) < 0) pr_info("%s: can't remove protocol\n", __func__); xfrm_unregister_type(&ipcomp6_type, AF_INET6); } module_init(ipcomp6_init); module_exit(ipcomp6_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) for IPv6 - RFC3173"); MODULE_AUTHOR("Mitsuru KANDA <mk@linux-ipv6.org>"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_COMP); |
| 192 193 49 6 144 87 8 7 2 88 49 36 36 89 89 14 13 3 2 1 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2019, Tessares SA. */ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/net_namespace.h> #include <net/netns/generic.h> #include "protocol.h" #include "mib.h" #define MPTCP_SYSCTL_PATH "net/mptcp" static int mptcp_pernet_id; #ifdef CONFIG_SYSCTL static int mptcp_pm_type_max = __MPTCP_PM_TYPE_MAX; #endif struct mptcp_pernet { #ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_table_hdr; #endif unsigned int add_addr_timeout; unsigned int blackhole_timeout; unsigned int close_timeout; unsigned int stale_loss_cnt; atomic_t active_disable_times; u8 syn_retrans_before_tcp_fallback; unsigned long active_disable_stamp; u8 mptcp_enabled; u8 checksum_enabled; u8 allow_join_initial_addr_port; u8 pm_type; char scheduler[MPTCP_SCHED_NAME_MAX]; char path_manager[MPTCP_PM_NAME_MAX]; }; static struct mptcp_pernet *mptcp_get_pernet(const struct net *net) { return net_generic(net, mptcp_pernet_id); } int mptcp_is_enabled(const struct net *net) { return mptcp_get_pernet(net)->mptcp_enabled; } unsigned int mptcp_get_add_addr_timeout(const struct net *net) { return mptcp_get_pernet(net)->add_addr_timeout; } int mptcp_is_checksum_enabled(const struct net *net) { return mptcp_get_pernet(net)->checksum_enabled; } int mptcp_allow_join_id0(const struct net *net) { return mptcp_get_pernet(net)->allow_join_initial_addr_port; } unsigned int mptcp_stale_loss_cnt(const struct net *net) { return mptcp_get_pernet(net)->stale_loss_cnt; } unsigned int mptcp_close_timeout(const struct sock *sk) { if (sock_flag(sk, SOCK_DEAD)) return TCP_TIMEWAIT_LEN; return mptcp_get_pernet(sock_net(sk))->close_timeout; } int mptcp_get_pm_type(const struct net *net) { return mptcp_get_pernet(net)->pm_type; } const char *mptcp_get_path_manager(const struct net *net) { return mptcp_get_pernet(net)->path_manager; } const char *mptcp_get_scheduler(const struct net *net) { return mptcp_get_pernet(net)->scheduler; } static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; pernet->blackhole_timeout = 3600; pernet->syn_retrans_before_tcp_fallback = 2; atomic_set(&pernet->active_disable_times, 0); pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; pernet->allow_join_initial_addr_port = 1; pernet->stale_loss_cnt = 4; pernet->pm_type = MPTCP_PM_TYPE_KERNEL; strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler)); strscpy(pernet->path_manager, "kernel", sizeof(pernet->path_manager)); } #ifdef CONFIG_SYSCTL static int mptcp_set_scheduler(char *scheduler, const char *name) { struct mptcp_sched_ops *sched; int ret = 0; rcu_read_lock(); sched = mptcp_sched_find(name); if (sched) strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); return ret; } static int proc_scheduler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data; char val[MPTCP_SCHED_NAME_MAX]; struct ctl_table tbl = { .data = val, .maxlen = MPTCP_SCHED_NAME_MAX, }; int ret; strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = mptcp_set_scheduler(*scheduler, val); return ret; } static int proc_available_schedulers(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = MPTCP_SCHED_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; mptcp_get_available_schedulers(tbl.data, MPTCP_SCHED_BUF_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct mptcp_pernet *pernet = container_of(table->data, struct mptcp_pernet, blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) atomic_set(&pernet->active_disable_times, 0); return ret; } static int mptcp_set_path_manager(char *path_manager, const char *name) { struct mptcp_pm_ops *pm_ops; int ret = 0; rcu_read_lock(); pm_ops = mptcp_pm_find(name); if (pm_ops) strscpy(path_manager, name, MPTCP_PM_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); return ret; } static int proc_path_manager(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct mptcp_pernet *pernet = container_of(ctl->data, struct mptcp_pernet, path_manager); char (*path_manager)[MPTCP_PM_NAME_MAX] = ctl->data; char pm_name[MPTCP_PM_NAME_MAX]; const struct ctl_table tbl = { .data = pm_name, .maxlen = MPTCP_PM_NAME_MAX, }; int ret; strscpy(pm_name, *path_manager, MPTCP_PM_NAME_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { ret = mptcp_set_path_manager(*path_manager, pm_name); if (ret == 0) { u8 pm_type = __MPTCP_PM_TYPE_NR; if (strncmp(pm_name, "kernel", MPTCP_PM_NAME_MAX) == 0) pm_type = MPTCP_PM_TYPE_KERNEL; else if (strncmp(pm_name, "userspace", MPTCP_PM_NAME_MAX) == 0) pm_type = MPTCP_PM_TYPE_USERSPACE; pernet->pm_type = pm_type; } } return ret; } static int proc_pm_type(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct mptcp_pernet *pernet = container_of(ctl->data, struct mptcp_pernet, pm_type); int ret; ret = proc_dou8vec_minmax(ctl, write, buffer, lenp, ppos); if (write && ret == 0) { u8 pm_type = READ_ONCE(*(u8 *)ctl->data); char *pm_name = ""; if (pm_type == MPTCP_PM_TYPE_KERNEL) pm_name = "kernel"; else if (pm_type == MPTCP_PM_TYPE_USERSPACE) pm_name = "userspace"; mptcp_set_path_manager(pernet->path_manager, pm_name); } return ret; } static int proc_available_path_managers(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = MPTCP_PM_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; mptcp_pm_get_available(tbl.data, MPTCP_PM_BUF_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", .maxlen = sizeof(u8), .mode = 0644, /* users with CAP_NET_ADMIN or root (not and) can change this * value, same as other sysctl or the 'net' tree. */ .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "add_addr_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "checksum_enabled", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "allow_join_initial_addr_port", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "stale_loss_cnt", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, }, { .procname = "pm_type", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_pm_type, .extra1 = SYSCTL_ZERO, .extra2 = &mptcp_pm_type_max }, { .procname = "scheduler", .maxlen = MPTCP_SCHED_NAME_MAX, .mode = 0644, .proc_handler = proc_scheduler, }, { .procname = "available_schedulers", .maxlen = MPTCP_SCHED_BUF_MAX, .mode = 0444, .proc_handler = proc_available_schedulers, }, { .procname = "close_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "blackhole_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_blackhole_detect_timeout, .extra1 = SYSCTL_ZERO, }, { .procname = "syn_retrans_before_tcp_fallback", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "path_manager", .maxlen = MPTCP_PM_NAME_MAX, .mode = 0644, .proc_handler = proc_path_manager, }, { .procname = "available_path_managers", .maxlen = MPTCP_PM_BUF_MAX, .mode = 0444, .proc_handler = proc_available_path_managers, }, }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) { struct ctl_table_header *hdr; struct ctl_table *table; table = mptcp_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(mptcp_sysctl_table), GFP_KERNEL); if (!table) goto err_alloc; } table[0].data = &pernet->mptcp_enabled; table[1].data = &pernet->add_addr_timeout; table[2].data = &pernet->checksum_enabled; table[3].data = &pernet->allow_join_initial_addr_port; table[4].data = &pernet->stale_loss_cnt; table[5].data = &pernet->pm_type; table[6].data = &pernet->scheduler; /* table[7] is for available_schedulers which is read-only info */ table[8].data = &pernet->close_timeout; table[9].data = &pernet->blackhole_timeout; table[10].data = &pernet->syn_retrans_before_tcp_fallback; table[11].data = &pernet->path_manager; /* table[12] is for available_path_managers which is read-only info */ hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); if (!hdr) goto err_reg; pernet->ctl_table_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) { const struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg; unregister_net_sysctl_table(pernet->ctl_table_hdr); kfree(table); } #else static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) { return 0; } static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {} #endif /* CONFIG_SYSCTL */ /* The following code block is to deal with middle box issues with MPTCP, * similar to what is done with TFO. * The proposed solution is to disable active MPTCP globally when SYN+MPC are * dropped, while SYN without MPC aren't. In this case, active side MPTCP is * disabled globally for 1hr at first. Then if it happens again, it is disabled * for 2h, then 4h, 8h, ... * The timeout is reset back to 1hr when a successful active MPTCP connection is * fully established. */ /* Disable active MPTCP and record current jiffies and active_disable_times */ void mptcp_active_disable(struct sock *sk) { struct net *net = sock_net(sk); struct mptcp_pernet *pernet; pernet = mptcp_get_pernet(net); if (!READ_ONCE(pernet->blackhole_timeout)) return; /* Paired with READ_ONCE() in mptcp_active_should_disable() */ WRITE_ONCE(pernet->active_disable_stamp, jiffies); /* Paired with smp_rmb() in mptcp_active_should_disable(). * We want pernet->active_disable_stamp to be updated first. */ smp_mb__before_atomic(); atomic_inc(&pernet->active_disable_times); MPTCP_INC_STATS(net, MPTCP_MIB_BLACKHOLE); } /* Calculate timeout for MPTCP active disable * Return true if we are still in the active MPTCP disable period * Return false if timeout already expired and we should use active MPTCP */ bool mptcp_active_should_disable(struct sock *ssk) { struct net *net = sock_net(ssk); unsigned int blackhole_timeout; struct mptcp_pernet *pernet; unsigned long timeout; int disable_times; int multiplier; pernet = mptcp_get_pernet(net); blackhole_timeout = READ_ONCE(pernet->blackhole_timeout); if (!blackhole_timeout) return false; disable_times = atomic_read(&pernet->active_disable_times); if (!disable_times) return false; /* Paired with smp_mb__before_atomic() in mptcp_active_disable() */ smp_rmb(); /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(disable_times - 1, 6); /* Paired with the WRITE_ONCE() in mptcp_active_disable(). */ timeout = READ_ONCE(pernet->active_disable_stamp) + multiplier * blackhole_timeout * HZ; return time_before(jiffies, timeout); } /* Enable active MPTCP and reset active_disable_times if needed */ void mptcp_active_enable(struct sock *sk) { struct mptcp_pernet *pernet = mptcp_get_pernet(sock_net(sk)); if (atomic_read(&pernet->active_disable_times)) { struct net_device *dev; struct dst_entry *dst; rcu_read_lock(); dst = __sk_dst_get(sk); dev = dst ? dst_dev_rcu(dst) : NULL; if (!(dev && (dev->flags & IFF_LOOPBACK))) atomic_set(&pernet->active_disable_times, 0); rcu_read_unlock(); } } /* Check the number of retransmissions, and fallback to TCP if needed */ void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) { struct mptcp_subflow_context *subflow; u8 timeouts, to_max; struct net *net; /* Only check MPTCP SYN ... */ if (likely(!sk_is_mptcp(ssk) || ssk->sk_state != TCP_SYN_SENT)) return; subflow = mptcp_subflow_ctx(ssk); /* ... + MP_CAPABLE */ if (!subflow->request_mptcp) { /* Mark as blackhole iif the 1st non-MPTCP SYN is accepted */ subflow->mpc_drop = 0; return; } net = sock_net(ssk); timeouts = inet_csk(ssk)->icsk_retransmits; to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback; if (timeouts == to_max || (timeouts < to_max && expired)) { subflow->mpc_drop = 1; mptcp_early_fallback(mptcp_sk(subflow->conn), subflow, MPTCP_MIB_MPCAPABLEACTIVEDROP); } } static int __net_init mptcp_net_init(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); mptcp_pernet_set_defaults(pernet); return mptcp_pernet_new_table(net, pernet); } /* Note: the callback will only be called per extra netns */ static void __net_exit mptcp_net_exit(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); mptcp_pernet_del_table(pernet); } static struct pernet_operations mptcp_pernet_ops = { .init = mptcp_net_init, .exit = mptcp_net_exit, .id = &mptcp_pernet_id, .size = sizeof(struct mptcp_pernet), }; void __init mptcp_init(void) { mptcp_join_cookie_init(); mptcp_proto_init(); if (register_pernet_subsys(&mptcp_pernet_ops) < 0) panic("Failed to register MPTCP pernet subsystem.\n"); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) int __init mptcpv6_init(void) { int err; err = mptcp_proto_v6_init(); return err; } #endif |
| 703 96 264 703 3 127 2 499 379 227 369 163 10 23 12 3 4 171 171 1 166 179 133 51 30 147 8 24 7 7 203 7 15 181 1 207 197 5 8 200 3 3 200 1 35 88 1 84 240 240 1 177 22 538 541 3 477 172 3 146 101 43 68 5 88 88 1 81 89 3 1 85 16 68 89 87 3 3 12 7 3 7 73 1 114 2 65 110 72 1 71 71 116 16 1 103 100 199 193 3 188 2 70 117 62 56 81 35 26 9 2 11 12 24 7 28 19 22 4 16 26 17 22 2 19 19 2 18 6 15 7 26 35 18 19 34 24 16 21 16 7 21 27 28 2 16 16 28 12 15 18 18 18 26 20 21 3 21 21 56 11 45 1 21 21 24 17 12 28 16 9 5 10 621 617 545 147 139 126 573 75 565 928 1 339 517 59 485 486 31 37 485 576 556 4 29 168 4 74 155 166 1 9 9 70 69 17 144 144 18 2 8 6 2 5 1 5 60 3 3 45 48 55 54 47 47 10 55 55 508 508 508 5 5 1367 1238 128 1369 109 109 8 99 108 22 21 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 | // SPDX-License-Identifier: GPL-2.0-only /* File: fs/xattr.c Extended attribute handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com> Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/fs.h> #include <linux/filelock.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/xattr.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fsnotify.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <linux/posix_acl_xattr.h> #include <linux/rhashtable.h> #include <linux/uaccess.h> #include "internal.h" struct sx_key { const struct list_head *parent; const char *name; }; static const char * strcmp_prefix(const char *a, const char *a_prefix) { while (*a_prefix && *a == *a_prefix) { a++; a_prefix++; } return *a_prefix ? NULL : a; } /* * In order to implement different sets of xattr operations for each xattr * prefix, a filesystem should create a null-terminated array of struct * xattr_handler (one for each prefix) and hang a pointer to it off of the * s_xattr field of the superblock. */ #define for_each_xattr_handler(handlers, handler) \ if (handlers) \ for ((handler) = *(handlers)++; \ (handler) != NULL; \ (handler) = *(handlers)++) /* * Find the xattr_handler with the matching prefix. */ static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return ERR_PTR(-EIO); return ERR_PTR(-EOPNOTSUPP); } for_each_xattr_handler(handlers, handler) { const char *n; n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { if (!handler->prefix ^ !*n) { if (*n) continue; return ERR_PTR(-EINVAL); } *name = n; return handler; } } return ERR_PTR(-EOPNOTSUPP); } /** * may_write_xattr - check whether inode allows writing xattr * @idmap: idmap of the mount the inode was found from * @inode: the inode on which to set an xattr * * Check whether the inode allows writing xattrs. Specifically, we can never * set or remove an extended attribute on a read-only filesystem or on an * immutable / append-only inode. * * We also need to ensure that the inode has a mapping in the mount to * not risk writing back invalid i_{g,u}id values. * * Return: On success zero is returned. On error a negative errno is returned. */ int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode) { if (IS_IMMUTABLE(inode)) return -EPERM; if (IS_APPEND(inode)) return -EPERM; if (HAS_UNMAPPED_ID(idmap, inode)) return -EPERM; return 0; } static inline int xattr_permission_error(int mask) { if (mask & MAY_WRITE) return -EPERM; return -ENODATA; } /* * Check permissions for extended attribute access. This is a bit complicated * because different namespaces have very different rules. */ static int xattr_permission(struct mnt_idmap *idmap, struct inode *inode, const char *name, int mask) { if (mask & MAY_WRITE) { int ret; ret = may_write_xattr(idmap, inode); if (ret) return ret; } /* * No restriction for security.* and system.* from the VFS. Decision * on these is left to the underlying filesystem / security module. */ if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return 0; /* * The trusted.* namespace can only be accessed by privileged users. */ if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { if (!capable(CAP_SYS_ADMIN)) return xattr_permission_error(mask); return 0; } /* * In the user.* namespace, only regular files and directories can have * extended attributes. For sticky directories, only the owner and * privileged users can write attributes. */ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { switch (inode->i_mode & S_IFMT) { case S_IFREG: break; case S_IFDIR: if (!(inode->i_mode & S_ISVTX)) break; if (!(mask & MAY_WRITE)) break; if (inode_owner_or_capable(idmap, inode)) break; return -EPERM; case S_IFSOCK: break; default: return xattr_permission_error(mask); } } return inode_permission(idmap, inode, mask); } /* * Look for any handler that deals with the specified namespace. */ int xattr_supports_user_prefix(struct inode *inode) { const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return -EIO; return -EOPNOTSUPP; } for_each_xattr_handler(handlers, handler) { if (!strncmp(xattr_prefix(handler), XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) return 0; } return -EOPNOTSUPP; } EXPORT_SYMBOL(xattr_supports_user_prefix); int __vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ return handler->set(handler, idmap, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); /** * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * * @idmap: idmap of the mount the inode was found from * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * * returns the result of the internal setxattr or setsecurity operations. * * This function requires the caller to lock the inode's i_rwsem before it * is executed. It also assumes that the caller will make the appropriate * permission checks. */ int __vfs_setxattr_noperm(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { error = __vfs_setxattr(idmap, dentry, inode, name, value, size, flags); if (!error) { fsnotify_xattr(dentry); security_inode_post_setxattr(dentry, name, value, size, flags); } } else { if (unlikely(is_bad_inode(inode))) return -EIO; } if (error == -EAGAIN) { error = -EOPNOTSUPP; if (issec) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; error = security_inode_setsecurity(inode, suffix, value, size, flags); if (!error) fsnotify_xattr(dentry); } } return error; } /** * __vfs_setxattr_locked - set an extended attribute while holding the inode * lock * * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags, struct delegated_inode *delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; error = security_inode_setxattr(idmap, dentry, name, value, size, flags); if (error) goto out; error = try_break_deleg(inode, 0, delegated_inode); if (error) goto out; error = __vfs_setxattr_noperm(idmap, dentry, name, value, size, flags); out: return error; } EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; struct delegated_inode delegated_inode = { }; const void *orig_value = value; int error; if (size && strcmp(name, XATTR_NAME_CAPS) == 0) { error = cap_convert_nscap(idmap, dentry, &value, size); if (error < 0) return error; size = error; } retry_deleg: inode_lock(inode); error = __vfs_setxattr_locked(idmap, dentry, name, value, size, flags, &delegated_inode); inode_unlock(inode); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } if (value != orig_value) kfree(value); return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); static ssize_t xattr_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { len = security_inode_getsecurity(idmap, inode, name, &buffer, false); goto out_noalloc; } len = security_inode_getsecurity(idmap, inode, name, &buffer, true); if (len < 0) return len; if (size < len) { len = -ERANGE; goto out; } memcpy(value, buffer, len); out: kfree(buffer); out_noalloc: return len; } /* * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr * * Allocate memory, if not already allocated, or re-allocate correct size, * before retrieving the extended attribute. The xattr value buffer should * always be freed by the caller, even on error. * * Returns the result of alloc, if failed, or the getxattr operation. */ int vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, char **xattr_value, size_t xattr_size, gfp_t flags) { const struct xattr_handler *handler; struct inode *inode = dentry->d_inode; char *value = *xattr_value; int error; error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; error = handler->get(handler, dentry, inode, name, NULL, 0); if (error < 0) return error; if (!value || (error > xattr_size)) { value = krealloc(*xattr_value, error + 1, flags); if (!value) return -ENOMEM; memset(value, 0, error + 1); } error = handler->get(handler, dentry, inode, name, value, error); *xattr_value = value; return error; } ssize_t __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; return handler->get(handler, dentry, inode, name, value, size); } EXPORT_SYMBOL(__vfs_getxattr); ssize_t vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_READ); if (error) return error; error = security_inode_getxattr(dentry, name); if (error) return error; if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; int ret = xattr_getsecurity(idmap, inode, suffix, value, size); /* * Only overwrite the return value if a security module * is actually active. */ if (ret == -EOPNOTSUPP) goto nolsm; return ret; } nolsm: return __vfs_getxattr(dentry, inode, name, value, size); } EXPORT_SYMBOL_GPL(vfs_getxattr); /** * vfs_listxattr - retrieve \0 separated list of xattr names * @dentry: the dentry from whose inode the xattr names are retrieved * @list: buffer to store xattr names into * @size: size of the buffer * * This function returns the names of all xattrs associated with the * inode of @dentry. * * Note, for legacy reasons the vfs_listxattr() function lists POSIX * ACLs as well. Since POSIX ACLs are decoupled from IOP_XATTR the * vfs_listxattr() function doesn't check for this flag since a * filesystem could implement POSIX ACLs without implementing any other * xattrs. * * However, since all codepaths that remove IOP_XATTR also assign of * inode operations that either don't implement or implement a stub * ->listxattr() operation. * * Return: On success, the size of the buffer that was used. On error a * negative error code. */ ssize_t vfs_listxattr(struct dentry *dentry, char *list, size_t size) { struct inode *inode = d_inode(dentry); ssize_t error; error = security_inode_listxattr(dentry); if (error) return error; if (inode->i_op->listxattr) { error = inode->i_op->listxattr(dentry, list, size); } else { error = security_inode_listsecurity(inode, list, size); if (size && error > size) error = -ERANGE; } return error; } EXPORT_SYMBOL_GPL(vfs_listxattr); int __vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = d_inode(dentry); const struct xattr_handler *handler; if (is_posix_acl_xattr(name)) return -EOPNOTSUPP; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; return handler->set(handler, idmap, dentry, inode, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); /** * __vfs_removexattr_locked - set an extended attribute while holding the inode * lock * * @idmap: idmap of the mount of the target inode * @dentry: object to perform setxattr on * @name: name of xattr to remove * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_removexattr_locked(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, struct delegated_inode *delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(idmap, inode, name, MAY_WRITE); if (error) return error; error = security_inode_removexattr(idmap, dentry, name); if (error) goto out; error = try_break_deleg(inode, 0, delegated_inode); if (error) goto out; error = __vfs_removexattr(idmap, dentry, name); if (error) return error; fsnotify_xattr(dentry); security_inode_post_removexattr(dentry, name); out: return error; } EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; struct delegated_inode delegated_inode = { }; int error; retry_deleg: inode_lock(inode); error = __vfs_removexattr_locked(idmap, dentry, name, &delegated_inode); inode_unlock(inode); if (is_delegated(&delegated_inode)) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); int import_xattr_name(struct xattr_name *kname, const char __user *name) { int error = strncpy_from_user(kname->name, name, sizeof(kname->name)); if (error == 0 || error == sizeof(kname->name)) return -ERANGE; if (error < 0) return error; return 0; } /* * Extended attribute SET operations */ int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx) { int error; if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; error = import_xattr_name(ctx->kname, name); if (error) return error; if (ctx->size) { if (ctx->size > XATTR_SIZE_MAX) return -E2BIG; ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size); if (IS_ERR(ctx->kvalue)) { error = PTR_ERR(ctx->kvalue); ctx->kvalue = NULL; } } return error; } static int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, struct kernel_xattr_ctx *ctx) { if (is_posix_acl_xattr(ctx->kname->name)) return do_set_acl(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size); return vfs_setxattr(idmap, dentry, ctx->kname->name, ctx->kvalue, ctx->size, ctx->flags); } int file_setxattr(struct file *f, struct kernel_xattr_ctx *ctx) { int error = mnt_want_write_file(f); if (!error) { audit_file(f); error = do_setxattr(file_mnt_idmap(f), f->f_path.dentry, ctx); mnt_drop_write_file(f); } return error; } int filename_setxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx) { struct path path; int error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = do_setxattr(mnt_idmap(path.mnt), path.dentry, ctx); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } static int path_setxattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name, const void __user *value, size_t size, int flags) { struct xattr_name kname; struct kernel_xattr_ctx ctx = { .cvalue = value, .kvalue = NULL, .size = size, .kname = &kname, .flags = flags, }; unsigned int lookup_flags = 0; int error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags = LOOKUP_FOLLOW; error = setxattr_copy(name, &ctx); if (error) return error; CLASS(filename_maybe_null, filename)(pathname, at_flags); if (!filename && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) error = -EBADF; else error = file_setxattr(fd_file(f), &ctx); } else { error = filename_setxattr(dfd, filename, lookup_flags, &ctx); } kvfree(ctx.kvalue); return error; } SYSCALL_DEFINE6(setxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name, const struct xattr_args __user *, uargs, size_t, usize) { struct xattr_args args = {}; int error; BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0); BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST); if (unlikely(usize < XATTR_ARGS_SIZE_VER0)) return -EINVAL; if (usize > PAGE_SIZE) return -E2BIG; error = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (error) return error; return path_setxattrat(dfd, pathname, at_flags, name, u64_to_user_ptr(args.value), args.size, args.flags); } SYSCALL_DEFINE5(setxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattrat(AT_FDCWD, pathname, 0, name, value, size, flags); } SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name, value, size, flags); } SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { return path_setxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size, flags); } /* * Extended attribute GET operations */ static ssize_t do_getxattr(struct mnt_idmap *idmap, struct dentry *d, struct kernel_xattr_ctx *ctx) { ssize_t error; char *kname = ctx->kname->name; void *kvalue = NULL; if (ctx->size) { if (ctx->size > XATTR_SIZE_MAX) ctx->size = XATTR_SIZE_MAX; kvalue = kvzalloc(ctx->size, GFP_KERNEL); if (!kvalue) return -ENOMEM; } if (is_posix_acl_xattr(kname)) error = do_get_acl(idmap, d, kname, kvalue, ctx->size); else error = vfs_getxattr(idmap, d, kname, kvalue, ctx->size); if (error > 0) { if (ctx->size && copy_to_user(ctx->value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(kvalue); return error; } ssize_t file_getxattr(struct file *f, struct kernel_xattr_ctx *ctx) { audit_file(f); return do_getxattr(file_mnt_idmap(f), f->f_path.dentry, ctx); } ssize_t filename_getxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx) { struct path path; ssize_t error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) return error; error = do_getxattr(mnt_idmap(path.mnt), path.dentry, ctx); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } static ssize_t path_getxattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name, void __user *value, size_t size) { struct xattr_name kname; struct kernel_xattr_ctx ctx = { .value = value, .size = size, .kname = &kname, .flags = 0, }; ssize_t error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; error = import_xattr_name(&kname, name); if (error) return error; CLASS(filename_maybe_null, filename)(pathname, at_flags); if (!filename && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_getxattr(fd_file(f), &ctx); } else { int lookup_flags = 0; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags = LOOKUP_FOLLOW; return filename_getxattr(dfd, filename, lookup_flags, &ctx); } } SYSCALL_DEFINE6(getxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name, struct xattr_args __user *, uargs, size_t, usize) { struct xattr_args args = {}; int error; BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0); BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST); if (unlikely(usize < XATTR_ARGS_SIZE_VER0)) return -EINVAL; if (usize > PAGE_SIZE) return -E2BIG; error = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (error) return error; if (args.flags != 0) return -EINVAL; return path_getxattrat(dfd, pathname, at_flags, name, u64_to_user_ptr(args.value), args.size); } SYSCALL_DEFINE4(getxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(AT_FDCWD, pathname, 0, name, value, size); } SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name, value, size); } SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { return path_getxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size); } /* * Extended attribute LIST operations */ static ssize_t listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kvmalloc(size, GFP_KERNEL); if (!klist) return -ENOMEM; } error = vfs_listxattr(d, klist, size); if (error > 0) { if (size && copy_to_user(list, klist, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { /* The file system tried to returned a list bigger than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(klist); return error; } static ssize_t file_listxattr(struct file *f, char __user *list, size_t size) { audit_file(f); return listxattr(f->f_path.dentry, list, size); } static ssize_t filename_listxattr(int dfd, struct filename *filename, unsigned int lookup_flags, char __user *list, size_t size) { struct path path; ssize_t error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) return error; error = listxattr(path.dentry, list, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } static ssize_t path_listxattrat(int dfd, const char __user *pathname, unsigned int at_flags, char __user *list, size_t size) { int lookup_flags; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; CLASS(filename_maybe_null, filename)(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_listxattr(fd_file(f), list, size); } lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; return filename_listxattr(dfd, filename, lookup_flags, list, size); } SYSCALL_DEFINE5(listxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, char __user *, list, size_t, size) { return path_listxattrat(dfd, pathname, at_flags, list, size); } SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattrat(AT_FDCWD, pathname, 0, list, size); } SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, list, size); } SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { return path_listxattrat(fd, NULL, AT_EMPTY_PATH, list, size); } /* * Extended attribute REMOVE operations */ static long removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name) { if (is_posix_acl_xattr(name)) return vfs_remove_acl(idmap, d, name); return vfs_removexattr(idmap, d, name); } static int file_removexattr(struct file *f, struct xattr_name *kname) { int error = mnt_want_write_file(f); if (!error) { audit_file(f); error = removexattr(file_mnt_idmap(f), f->f_path.dentry, kname->name); mnt_drop_write_file(f); } return error; } static int filename_removexattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct xattr_name *kname) { struct path path; int error; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = removexattr(mnt_idmap(path.mnt), path.dentry, kname->name); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } static int path_removexattrat(int dfd, const char __user *pathname, unsigned int at_flags, const char __user *name) { struct xattr_name kname; unsigned int lookup_flags; int error; if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; error = import_xattr_name(&kname, name); if (error) return error; CLASS(filename_maybe_null, filename)(pathname, at_flags); if (!filename) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; return file_removexattr(fd_file(f), &kname); } lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; return filename_removexattr(dfd, filename, lookup_flags, &kname); } SYSCALL_DEFINE4(removexattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags, const char __user *, name) { return path_removexattrat(dfd, pathname, at_flags, name); } SYSCALL_DEFINE2(removexattr, const char __user *, pathname, const char __user *, name) { return path_removexattrat(AT_FDCWD, pathname, 0, name); } SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, const char __user *, name) { return path_removexattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name); } SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { return path_removexattrat(fd, NULL, AT_EMPTY_PATH, name); } int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) { size_t len; len = strlen(name) + 1; if (*buffer) { if (*remaining_size < len) return -ERANGE; memcpy(*buffer, name, len); *buffer += len; } *remaining_size -= len; return 0; } /** * generic_listxattr - run through a dentry's xattr list() operations * @dentry: dentry to list the xattrs * @buffer: result buffer * @buffer_size: size of @buffer * * Combine the results of the list() operation from every xattr_handler in the * xattr_handler stack. * * Note that this will not include the entries for POSIX ACLs. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr; ssize_t remaining_size = buffer_size; for_each_xattr_handler(handlers, handler) { int err; if (!handler->name || (handler->list && !handler->list(dentry))) continue; err = xattr_list_one(&buffer, &remaining_size, handler->name); if (err) return err; } return buffer_size - remaining_size; } EXPORT_SYMBOL(generic_listxattr); /** * xattr_full_name - Compute full attribute name from suffix * * @handler: handler of the xattr_handler operation * @name: name passed to the xattr_handler operation * * The get and set xattr handler operations are called with the remainder of * the attribute name after skipping the handler's prefix: for example, "foo" * is passed to the get operation of a handler with prefix "user." to get * attribute "user.foo". The full name is still "there" in the name though. * * Note: the list xattr handler operation when called from the vfs is passed a * NULL name; some file systems use this operation internally, with varying * semantics. */ const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } EXPORT_SYMBOL(xattr_full_name); /** * simple_xattr_space - estimate the memory used by a simple xattr * @name: the full name of the xattr * @size: the size of its value * * This takes no account of how much larger the two slab objects actually are: * that would depend on the slab implementation, when what is required is a * deterministic number, which grows with name length and size and quantity. * * Return: The approximate number of bytes of memory used by such an xattr. */ size_t simple_xattr_space(const char *name, size_t size) { /* * Use "40" instead of sizeof(struct simple_xattr), to return the * same result on 32-bit and 64-bit, and even if simple_xattr grows. */ return 40 + size + strlen(name); } /** * simple_xattr_free - free an xattr object * @xattr: the xattr object * * Free the xattr object. Can handle @xattr being NULL. */ void simple_xattr_free(struct simple_xattr *xattr) { if (xattr) kfree(xattr->name); kvfree(xattr); } static void simple_xattr_rcu_free(struct rcu_head *head) { struct simple_xattr *xattr = container_of(head, struct simple_xattr, rcu); simple_xattr_free(xattr); } /** * simple_xattr_free_rcu - free an xattr object with RCU delay * @xattr: the xattr object * * Free the xattr object after an RCU grace period. This must be used when * the xattr was removed from a data structure that concurrent RCU readers * may still be traversing. Can handle @xattr being NULL. */ void simple_xattr_free_rcu(struct simple_xattr *xattr) { if (xattr) call_rcu(&xattr->rcu, simple_xattr_rcu_free); } /** * simple_xattr_alloc - allocate new xattr object * @value: value of the xattr object * @size: size of @value * * Allocate a new xattr object and initialize respective members. The caller is * responsible for handling the name of the xattr. * * Return: New xattr object on success, NULL if @value is NULL, ERR_PTR on * failure. */ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) { struct simple_xattr *new_xattr; size_t len; if (!value) return NULL; /* wrap around? */ len = sizeof(*new_xattr) + size; if (len < sizeof(*new_xattr)) return ERR_PTR(-ENOMEM); new_xattr = kvmalloc(len, GFP_KERNEL_ACCOUNT); if (!new_xattr) return ERR_PTR(-ENOMEM); new_xattr->size = size; memcpy(new_xattr->value, value, size); return new_xattr; } static u32 sx_hashfn(const char *name, const struct list_head *parent, u32 seed) { return jhash(name, strlen(name), jhash(&parent, sizeof(parent), seed)); } static u32 simple_xattr_hashfn(const void *data, u32 len, u32 seed) { const struct sx_key *key = data; return sx_hashfn(key->name, key->parent, seed); } static u32 simple_xattr_obj_hashfn(const void *obj, u32 len, u32 seed) { const struct simple_xattr *xattr = obj; return sx_hashfn(xattr->name, xattr->parent, seed); } static int simple_xattr_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) { const struct simple_xattr *xattr = obj; const struct sx_key *key = arg->key; return xattr->parent != key->parent || strcmp(xattr->name, key->name); } static const struct rhashtable_params simple_xattr_params = { .head_offset = offsetof(struct simple_xattr, hash_node), .hashfn = simple_xattr_hashfn, .obj_hashfn = simple_xattr_obj_hashfn, .obj_cmpfn = simple_xattr_obj_cmpfn, .automatic_shrinking = true, }; /** * simple_xattr_get - get an xattr object * @cache: anchor for the hash table * @xattrs: the header of the xattr object * @name: the name of the xattr to retrieve * @buffer: the buffer to store the value into * @size: the size of @buffer * * Try to find and retrieve the xattr object associated with @name. * If @buffer is provided store the value of @xattr in @buffer * otherwise just return the length. The size of @buffer is limited * to XATTR_SIZE_MAX which currently is 65536. * * Return: On success the length of the xattr value is returned. On error a * negative error code is returned. */ int simple_xattr_get(struct simple_xattr_cache *cache, struct list_head *xattrs, const char *name, void *buffer, size_t size) { struct simple_xattr *xattr; struct sx_key key = { .parent = xattrs, .name = name }; struct rhashtable *ht = READ_ONCE(cache->ht); int ret = -ENODATA; if (!ht) return ret; guard(rcu)(); xattr = rhashtable_lookup(ht, &key, simple_xattr_params); if (xattr) { ret = xattr->size; if (buffer) { if (size < xattr->size) ret = -ERANGE; else memcpy(buffer, xattr->value, xattr->size); } } return ret; } static struct rhashtable *simple_xattrs_lazy_alloc(struct simple_xattr_cache *cache, const void *value, int flags) { struct rhashtable *oldht, *ht = READ_ONCE(cache->ht); int err; if (unlikely(!ht)) { if (!value) return (flags & XATTR_REPLACE) ? ERR_PTR(-ENODATA) : NULL; ht = kzalloc_obj(*ht); if (!ht) return ERR_PTR(-ENOMEM); err = rhashtable_init(ht, &simple_xattr_params); if (err) { kfree(ht); return ERR_PTR(err); } /* * Provides release semantics on success, so that use of a * non-NULL READ_ONCE(cache->ht) will be ordered relative to the * above initialization, due to implicit address dependency. */ oldht = cmpxchg_release(&cache->ht, NULL, ht); if (oldht) { /* Race lost */ rhashtable_destroy(ht); kfree(ht); ht = oldht; } } return ht; } /** * simple_xattr_set - set an xattr object * @cache: anchor for the hash table * @xattrs: the header of the xattr object * @name: the name of the xattr to retrieve * @value: the value to store along the xattr * @size: the size of @value * @flags: the flags determining how to set the xattr * * Set a new xattr object. * If @value is passed a new xattr object will be allocated. If XATTR_REPLACE * is specified in @flags a matching xattr object for @name must already exist. * If it does it will be replaced with the new xattr object. If it doesn't we * fail. If XATTR_CREATE is specified and a matching xattr does already exist * we fail. If it doesn't we create a new xattr. If @flags is zero we simply * insert the new xattr replacing any existing one. * * If @value is empty and a matching xattr object is found we delete it if * XATTR_REPLACE is specified in @flags or @flags is zero. * * If @value is empty and no matching xattr object for @name is found we do * nothing if XATTR_CREATE is specified in @flags or @flags is zero. For * XATTR_REPLACE we fail as mentioned above. * * Note: Callers must externally serialize writes. All current callers hold * the inode lock for write operations. The lookup->replace/remove sequence * is not atomic with respect to the rhashtable's per-bucket locking, but * is safe because writes are serialized by the caller. * * Return: On success, the removed or replaced xattr is returned, to be freed * by the caller; or NULL if none. On failure a negative error code is returned. */ struct simple_xattr *simple_xattr_set(struct simple_xattr_cache *cache, struct list_head *xattrs, const char *name, const void *value, size_t size, int flags) { struct sx_key key = { .parent = xattrs, .name = name }; struct simple_xattr *old_xattr = NULL; struct rhashtable *ht; int err; ht = simple_xattrs_lazy_alloc(cache, value, flags); if (IS_ERR_OR_NULL(ht)) return ERR_CAST(ht); CLASS(simple_xattr, new_xattr)(value, size); if (IS_ERR(new_xattr)) return new_xattr; if (new_xattr) { new_xattr->parent = xattrs; new_xattr->name = kstrdup(name, GFP_KERNEL_ACCOUNT); if (!new_xattr->name) return ERR_PTR(-ENOMEM); } /* * Hash table lookup/replace/remove will grab RCU read lock themselves. * This makes sure that hash table lookup is safe against concurrent * modification on another inode. */ old_xattr = rhashtable_lookup_fast(ht, &key, simple_xattr_params); if (old_xattr) { /* Fail if XATTR_CREATE is requested and the xattr exists. */ if (flags & XATTR_CREATE) return ERR_PTR(-EEXIST); if (new_xattr) { err = rhashtable_replace_fast(ht, &old_xattr->hash_node, &new_xattr->hash_node, simple_xattr_params); if (err) return ERR_PTR(err); list_replace_rcu(&old_xattr->node, &new_xattr->node); } else { err = rhashtable_remove_fast(ht, &old_xattr->hash_node, simple_xattr_params); if (err) return ERR_PTR(err); list_del_rcu(&old_xattr->node); } } else { /* Fail if XATTR_REPLACE is requested but no xattr is found. */ if (flags & XATTR_REPLACE) return ERR_PTR(-ENODATA); /* * If XATTR_CREATE or no flags are specified together with a * new value simply insert it. */ if (new_xattr) { err = rhashtable_insert_fast(ht, &new_xattr->hash_node, simple_xattr_params); if (err) return ERR_PTR(err); list_add_tail_rcu(&new_xattr->node, xattrs); } /* * If XATTR_CREATE or no flags are specified and neither an * old or new xattr exist then we don't need to do anything. */ } retain_and_null_ptr(new_xattr); return old_xattr; } static inline void simple_xattr_limits_dec(struct simple_xattr_limits *limits, size_t size) { atomic_sub(size, &limits->xattr_size); atomic_dec(&limits->nr_xattrs); } static inline int simple_xattr_limits_inc(struct simple_xattr_limits *limits, |